No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Can deep learning effectively diagnose cardiac amyloidosis with 99mTc-PYP scintigraphy?
Abstract
This study investigates the effectiveness of deep learning models in diagnosing cardiac amyloidosis using 99mTc-PYP scintigraphy. We evaluated more than 40 deep learning models, including both convolutional neural networks (CNNs) and Vision Transformer (ViT) models. The highest-performing model achieved 89.80% accuracy. The study highlights the potential of deep learning methods to improve diagnostic accuracy and reduce patient wait times. These results demonstrate the clinical value of deep learning models in early and accurate cardiac amyloidosis diagnosis, contributing to better patient outcomes and timely interventions.
... However, classical CNN ignores the small and boundary region in several applications 29 . The ViT (Vision Transformer) and attention-based models that handle these challenges have been tested in medical domains and achieved satisfactory results [30][31][32] . In the proposed study, we design lightweight, explainable sequential CNN with label-guided attention (LWENet) for the mouth and oral cancer diagnosis. ...
Oral cavity cancer exhibits high morbidity and mortality rates. Therefore, it is essential to diagnose the disease at an early stage. Machine learning and convolution neural networks (CNN) are powerful tools for diagnosing mouth and oral cancer. In this study, we design a lightweight explainable network (LWENet) with label-guided attention (LGA) to provide a second opinion to the expert. The LWENet contains depth-wise separable convolution layers to reduce the computation costs. Moreover, the LGA module provides label consistency to the neighbor pixel and improves the spatial features. Furthermore, AMSA (axial multi-head self-attention) based ViT encoder incorporated in the model to provide global attention. Our ViT (vision transformer) encoder is computationally efficient compared to the classical ViT encoder. We tested LWRNet performance on the MOD (mouth and oral disease) and OCI (oral cancer image) datasets, and results are compared with the other CNN and ViT (vision transformer) based methods. The LWENet achieved a precision and F1-scores of 96.97% and 98.90% on the MOD dataset, and 99.48% and 98.23% on the OCI dataset, respectively. By incorporating Grad-CAM, we visualize the decision-making process, enhancing model interpretability. This work demonstrates the potential of LWENet with LGA in facilitating early oral cancer detection.
... To address these limitations, deep learning, a subset of artificial intelligence, has emerged as a transformative paradigm 21 . Unlike traditional machine learning methods, deep learning employs multilayered neural networks to autonomously extract patterns and features from raw data, resulting in significantly enhanced diagnostic accuracy [22][23][24] . This approach has shown exceptional promise in the field of medical imaging and cancer detection, with notable success in identifying cancers such as lung, breast, and skin, as well as in analyzing imaging modalities like MRI, CT, and histopathology data 25 . ...
Skin cancer represents a significant global health concern, where early and precise diagnosis plays a pivotal role in improving treatment efficacy and patient survival rates. Nonetheless, the inherent visual similarities between benign and malignant lesions pose substantial challenges to accurate classification. To overcome these obstacles, this study proposes an innovative hybrid deep learning model that combines ConvNeXtV2 blocks and separable self-attention mechanisms, tailored to enhance feature extraction and optimize classification performance. The inclusion of ConvNeXtV2 blocks in the initial two stages is driven by their ability to effectively capture fine-grained local features and subtle patterns, which are critical for distinguishing between visually similar lesion types. Meanwhile, the adoption of separable self-attention in the later stages allows the model to selectively prioritize diagnostically relevant regions while minimizing computational complexity, addressing the inefficiencies often associated with traditional self-attention mechanisms. The model was comprehensively trained and validated on the ISIC 2019 dataset, which includes eight distinct skin lesion categories. Advanced methodologies such as data augmentation and transfer learning were employed to further enhance model robustness and reliability. The proposed architecture achieved exceptional performance metrics, with 93.48% accuracy, 93.24% precision, 90.70% recall, and a 91.82% F1-score, outperforming over ten Convolutional Neural Network (CNN) based and over ten Vision Transformer (ViT) based models tested under comparable conditions. Despite its robust performance, the model maintains a compact design with only 21.92 million parameters, making it highly efficient and suitable for model deployment. The Proposed Model demonstrates exceptional accuracy and generalizability across diverse skin lesion classes, establishing a reliable framework for early and accurate skin cancer diagnosis in clinical practice.
Oral carcinoma (OC) is a toxic illness among the most general malignant cancers globally, and it has developed a gradually significant public health concern in emerging and low-to-middle-income states. Late diagnosis, high incidence, and inadequate treatment strategies remain substantial challenges. Analysis at an initial phase is significant for good treatment, prediction, and existence. Despite the current growth in the perception of molecular devices, late analysis and methods near precision medicine for OC patients remain a challenge. A machine learning (ML) model was employed to improve early detection in medicine, aiming to reduce cancer-specific mortality and disease progression. Recent advancements in this approach have significantly enhanced the extraction and diagnosis of critical information from medical images. This paper presents a Deep Structured Learning with Vision Intelligence for Oral Carcinoma Lesion Segmentation and Classification (DSLVI-OCLSC) model for medical imaging. Using medical imaging, the DSLVI-OCLSC model aims to enhance OC’s classification and recognition outcomes. To accomplish this, the DSLVI-OCLSC model utilizes wiener filtering (WF) as a pre-processing technique to eliminate the noise. In addition, the ShuffleNetV2 method is used for the group of higher-level deep features from an input image. The convolutional bidirectional long short-term memory network with a multi-head attention mechanism (MA-CNN‐BiLSTM) approach is utilized for oral carcinoma recognition and identification. Moreover, the Unet3 + is employed to segment abnormal regions from the classified images. Finally, the sine cosine algorithm (SCA) approach is utilized to hyperparameter-tune the DL model. A wide range of simulations is implemented to ensure the enhanced performance of the DSLVI-OCLSC method under the OC images dataset. The experimental analysis of the DSLVI-OCLSC method portrayed a superior accuracy value of 98.47% over recent approaches.
The emergence of the coronavirus disease 2019 (COVID-19) pandemic has caused great fear and panic around the world. In order to fight the COVID-19 virus, countries have had to develop some vaccines and drugs. Unfortunately, the effectiveness of these vaccines and drugs has diminished significantly due to the frequent mutations of the COVID-19 virus. Therefore, if future mutations on the Spike (S) protein of the COVID-19 virus can be predicted, vaccines and drugs can be developed faster and the fight against the COVID-19 virus can be easier. As in every field, artificial intelligence (AI)-based approaches also offer promising results in COVID-19 mutation prediction. However, finding the best hyperparameter value to improve the performance of each AI-based approach is quite difficult. In this study, we propose a robust StackGridCov model to predict future mutations on the COVID-19 virus. We utilize GridSearchCV hyperparameter tuning algorithm to improve the performance of the proposed StackGridCov model. Our main aim is to predict future mutations on the COVID-19 virus using the proposed StackGridCov model. In addition, to evaluate the performance of the proposed StackGridCov model, we carry out mutation prediction on the previously emerged influenza A/H1N1 HA virus dataset. The experimental results show that the proposed StackGridCov model outperforms 0.6623 accuracy, 0.6723 F1-score and 0.3273 MCC both the literature and other models. The results indicate that the proposed StackGridCov model can make a reliable contribution to predict mutations in both COVID-19 virus datasets and influenza A/H1N1 HA virus dataset.
Skin cancer (SC) is an important medical condition that necessitates prompt identification to ensure timely treatment. Although visual evaluation by dermatologists is considered the most reliable method, its efficacy is subjective and laborious. Deep learning-based computer-aided diagnostic (CAD) platforms have become valuable tools for supporting dermatologists. Nevertheless, current CAD tools frequently depend on Convolutional Neural Networks (CNNs) with huge amounts of deep layers and hyperparameters, single CNN model methodologies, large feature space, and exclusively utilise spatial image information, which restricts their effectiveness. This study presents SCaLiNG, an innovative CAD tool specifically developed to address and surpass these constraints. SCaLiNG leverages a collection of three compact CNNs and Gabor Wavelets (GW) to acquire a comprehensive feature vector consisting of spatial–textural–frequency attributes. SCaLiNG gathers a wide range of image details by breaking down these photos into multiple directional sub-bands using GW, and then learning several CNNs using those sub-bands and the original picture. SCaLiNG also combines attributes taken from various CNNs trained with the actual images and subbands derived from GW. This fusion process correspondingly improves diagnostic accuracy due to the thorough representation of attributes. Furthermore, SCaLiNG applies a feature selection approach which further enhances the model’s performance by choosing the most distinguishing features. Experimental findings indicate that SCaLiNG maintains a classification accuracy of 0.9170 in categorising SC subcategories, surpassing conventional single-CNN models. The outstanding performance of SCaLiNG underlines its ability to aid dermatologists in swiftly and precisely recognising and classifying SC, thereby enhancing patient outcomes.
Skin cancer is one of the most frequently occurring cancers worldwide, and early detection is crucial for effective treatment. Dermatologists often face challenges such as heavy data demands, potential human errors, and strict time limits, which can negatively affect diagnostic outcomes. Deep learning–based diagnostic systems offer quick, accurate testing and enhanced research capabilities, providing significant support to dermatologists. In this study, we enhanced the Swin Transformer architecture by implementing the hybrid shifted window-based multi-head self-attention (HSW-MSA) in place of the conventional shifted window-based multi-head self-attention (SW-MSA). This adjustment enables the model to more efficiently process areas of skin cancer overlap, capture finer details, and manage long-range dependencies, while maintaining memory usage and computational efficiency during training. Additionally, the study replaces the standard multi-layer perceptron (MLP) in the Swin Transformer with a SwiGLU-based MLP, an upgraded version of the gated linear unit (GLU) module, to achieve higher accuracy, faster training speeds, and better parameter efficiency. The modified Swin model-base was evaluated using the publicly accessible ISIC 2019 skin dataset with eight classes and was compared against popular convolutional neural networks (CNNs) and cutting-edge vision transformer (ViT) models. In an exhaustive assessment on the unseen test dataset, the proposed Swin-Base model demonstrated exceptional performance, achieving an accuracy of 89.36%, a recall of 85.13%, a precision of 88.22%, and an F1-score of 86.65%, surpassing all previously reported research and deep learning models documented in the literature.
Cardiac amyloidosis (CA) is an underdiagnosed form of infiltrative cardiomyopathy caused by abnormal amyloid fibrils deposited extracellularly in the myocardium and cardiac structures. There can be high variability in its clinical manifestations, and diagnosing CA requires expertise and often thorough evaluation; as such, the diagnosis of CA can be challenging and is often delayed. The application of artificial intelligence (AI) to different diagnostic modalities is rapidly expanding and transforming cardiovascular medicine. Advanced AI methods such as deep-learning convolutional neural networks (CNNs) may enhance the diagnostic process for CA by identifying patients at higher risk and potentially expediting the diagnosis of CA. In this review, we summarize the current state of AI applications to different diagnostic modalities used for the evaluation of CA, including their diagnostic and prognostic potential, and current challenges and limitations.
Plant diseases cause significant agricultural losses, demanding accurate detection methods. Traditional approaches relying on expert knowledge may be biased, but advancements in computing, particularly deep learning, offer non-experts effective tools. This study focuses on fine-tuning cutting-edge pre-trained CNN and vision transformer models to classify grape leaves and diagnose grape leaf diseases through digital images. Our research examined a PlantVillage dataset, which comprises 4062 leaf images distributed across four categories. Additionally, we utilized the Grapevine dataset, consisting of 500 leaf images. This dataset is organized into five distinct groups, with each group containing 100 images corresponding to one of the five grape types. The PlantVillage dataset focuses on four classes related to grape diseases, namely Black Rot, Leaf Blight, Healthy, and Esca leaves. On the other hand, the Grapevine dataset includes five classes for leaf recognition, specifically Ak, Alaidris, Buzgulu, Dimnit, and Nazli. In experiments with 14 CNN and 17 vision transformer models, deep learning demonstrated high accuracy in distinguishing grape diseases and recognizing leaves. Notably, four models achieved 100% accuracy on PlantVillage and Grapevine datasets, with Swinv2-Base standing out. This approach holds promise for enhancing crop productivity through early disease detection and providing insights into grape variety characterization in agriculture.
Background The diagnosis of cardiac amyloidosis can be established non-invasively by scintigraphy using bone-avid tracers, but visual assessment is subjective and can lead to misdiagnosis. We aimed to develop and validate an artificial intelligence (AI) system for standardised and reliable screening of cardiac amyloidosis-suggestive uptake and assess its prognostic value, using a multinational database of ⁹⁹ m Tc-scintigraphy data across multiple tracers and scanners.
Serious consequences due to brain tumors necessitate a timely and accurate diagnosis. However, obstacles such as suboptimal imaging quality, issues with data integrity, varying tumor types and stages, and potential errors in interpretation hinder the achievement of precise and prompt diagnoses. The rapid identification of brain tumors plays a pivotal role in ensuring patient safety. Deep learning-based systems hold promise in aiding radiologists to make diagnoses swiftly and accurately. In this study, we present an advanced deep learning approach based on the Swin Transformer. The proposed method introduces a novel Hybrid Shifted Windows Multi-Head Self-Attention module (HSW-MSA) along with a rescaled model. This enhancement aims to improve classification accuracy, reduce memory usage, and simplify training complexity. The Residual-based MLP (ResMLP) replaces the traditional MLP in the Swin Transformer, thereby improving accuracy, training speed, and parameter efficiency. We evaluate the Proposed-Swin model on a publicly available brain MRI dataset with four classes, using only test data. Model performance is enhanced through the application of transfer learning and data augmentation techniques for efficient and robust training. The Proposed-Swin model achieves a remarkable accuracy of 99.92%, surpassing previous research and deep learning models. This underscores the effectiveness of the Swin Transformer with HSW-MSA and ResMLP improvements in brain tumor diagnosis. This method introduces an innovative diagnostic approach using HSW-MSA and ResMLP in the Swin Transformer, offering potential support to radiologists in timely and accurate brain tumor diagnosis, ultimately improving patient outcomes and reducing risks.
Introduction
Cardiac amyloidosis (CA) shares similar clinical and imaging characteristics (e.g., hypertrophic phenotype) with aortic stenosis (AS), but its prognosis is generally worse than severe AS alone. Recent studies suggest that the presence of CA is frequent (1 out of 8 patients) in patients with severe AS. The coexistence of the two diseases complicates the prognosis and therapeutic management of both conditions. Thus, there is an urgent need to standardize and optimize the diagnostic process of CA and AS. The aim of this study is to develop a robust and reliable radiomics-based pipeline to differentiate the two pathologies.
Methods
Thirty patients were included in the study, equally divided between CA and AS. For each patient, a cardiac computed tomography (CCT) was analyzed by extracting 107 radiomics features from the LV wall. Feature robustness was evaluated by means of geometrical transformations to the ROIs and intra-class correlation coefficient (ICC) computation. Various correlation thresholds (0.80, 0.85, 0.90, 0.95, 1), feature selection methods [ p -value, least absolute shrinkage and selection operator (LASSO), semi-supervised LASSO, principal component analysis (PCA), semi-supervised PCA, sequential forwards selection] and machine learning classifiers (k-nearest neighbors, support vector machine, decision tree, logistic regression and gradient boosting) were assessed using a leave-one-out cross-validation. Data augmentation was performed using the synthetic minority oversampling technique. Finally, explainability analysis was performed by using the SHapley Additive exPlanations (SHAP) method.
Results
Ninety-two radiomic features were selected as robust and used in the further steps. Best performances of classification were obtained using a correlation threshold of 0.95, PCA (keeping 95% of the variance, corresponding to 9 PCs) and support vector machine classifier reaching an accuracy, sensitivity and specificity of 0.93. Four PCs were found to be mainly dependent on textural features, two on first-order statistics and three on shape and size features.
Conclusion
These preliminary results show that radiomics might be used as non-invasive tool able to differentiate CA from AS using clinical routine available images.
Background : Cardiac uptake on technetium-99m whole-body scintigraphy (WBS) is almost pathognomonic of transthyretin cardiac amyloidosis. The rare false positives are often related to light-chain cardiac amyloidosis. However, this scintigraphic feature remains largely unknown, leading to misdiagnosis despite characteristic images. A retrospective review of all WBSs in a hospital database to detect those with cardiac uptake may allow the identification of undiagnosed patients.
Objectives : The authors sought to develop and validate a deep learning–based model that automatically detects significant cardiac uptake (≥Perugini grade 2) on WBS from large hospital databases in order to retrieve patients at risk of cardiac amyloidosis.
Methods : The model is based on a convolutional neural network with image-level labels. The performance evaluation was performed with C-statistics using a 5-fold cross-validation scheme stratified so that the proportion of positive and negative WBSs remained constant across folds and using an external validation data set.
Results : The training data set consisted of 3,048 images: 281 positives (≥Perugini 2) and 2,767 negatives. The external validation data set consisted of 1,633 images: 102 positives and 1,531 negatives. The performance of the 5-fold cross-validation and external validation was as follows: 98.9% (± 1.0) and 96.1% for sensitivity, 99.5% (± 0.4) and 99.5% for specificity, and 0.999 (SD = 0.000) and 0.999 for the area under the curve of the receiver-operating characteristic curves. Sex, age <90 years, body mass index, injection-acquisition delay, radionuclides, and the indication of WBS only slightly affected performances.
Conclusions : The authors’ detection model is effective at identifying patients with cardiac uptake ≥Perugini 2 on WBS and may help in the diagnosis of patients with cardiac amyloidosis.
Cardiac amyloidosis is an uncommon restrictive cardiomyopathy featuring an unregulated amyloid protein deposition that impairs organic function. Early cardiac amyloidosis diagnosis is generally delayed by indistinguishable clinical findings of more frequent hypertrophic diseases. Furthermore, amyloidosis is divided into various groups, according to a generally accepted taxonomy, based on the proteins that make up the amyloid deposits; a careful differentiation between the various forms of amyloidosis is necessary to undertake an adequate therapeutic treatment. Thus, cardiac amyloidosis is thought to be underdiagnosed, which delays necessary therapeutic procedures, diminishing quality of life and impairing clinical prognosis. The diagnostic work-up for cardiac amyloidosis begins with the identification of clinical features, electrocardiographic and imaging findings suggestive or compatible with cardiac amyloidosis, and often requires the histological demonstration of amyloid deposition. One approach to overcome the difficulty of an early diagnosis is the use of automated diagnostic algorithms. Machine learning enables the automatic extraction of salient information from “raw data” without the need for pre-processing methods based on the a priori knowledge of the human operator. This review attempts to assess the various diagnostic approaches and artificial intelligence computational techniques in the detection of cardiac amyloidosis.
The aim of this work was to compare the classification of cardiac MR-images of AL versus ATTR amyloidosis by neural networks and by experienced human readers. Cine-MR images and late gadolinium enhancement (LGE) images of 120 patients were studied (70 AL and 50 TTR). A VGG16 convolutional neural network (CNN) was trained with a 5-fold cross validation process, taking care to strictly distribute images of a given patient in either the training group or the test group. The analysis was performed at the patient level by averaging the predictions obtained for each image. The classification accuracy obtained between AL and ATTR amyloidosis was 0.750 for cine-CNN, 0.611 for Gado-CNN and between 0.617 and 0.675 for human readers. The corresponding AUC of the ROC curve was 0.839 for cine-CNN, 0.679 for gado-CNN (p < 0.004 vs. cine) and 0.714 for the best human reader (p < 0.007 vs. cine). Logistic regression with cine-CNN and gado-CNN, as well as analysis focused on the specific orientation plane, did not change the overall results. We conclude that cine-CNN leads to significantly better discrimination between AL and ATTR amyloidosis as compared to gado-CNN or human readers, but with lower performance than reported in studies where visual diagnosis is easy, and is currently suboptimal for clinical practice.
Background
Transthyretin amyloidosis (ATTR) is a progressive disease which can be diagnosed non-invasively using bone avid [99mTc]-labeled radiotracers. Thus, ATTR is also an occasional incidental finding on bone scintigraphy. In this study, we trained convolutional neural networks (CNN) to automatically detect and classify ATTR from scintigraphy images. The study population consisted of 1334 patients who underwent [99mTc]-labeled hydroxymethylene diphosphonate (HMDP) scintigraphy and were visually graded using Perugini grades (grades 0–3). A total of 47 patients had visual grade ≥ 2 which was considered positive for ATTR. Two custom-made CNN architectures were trained to discriminate between the four Perugini grades of cardiac uptake. The classification performance was compared to four state-of-the-art CNN models.
Results
Our CNN models performed better than, or equally well as, the state-of-the-art models in detection and classification of cardiac uptake. Both models achieved area under the curve (AUC) ≥ 0.85 in the four-class Perugini grade classification. Accuracy was good in detection of negative vs. positive ATTR patients (grade < 2 vs grade ≥ 2, AUC > 0.88) and high-grade cardiac uptake vs. other patients (grade < 3 vs. grade 3, AUC = 0.94). Maximum activation maps demonstrated that the automated deep learning models were focused on detecting the myocardium and not extracardiac features.
Conclusion
Automated convolutional neural networks can accurately detect and classify different grades of cardiac uptake on bone scintigraphy. The CNN models are focused on clinically relevant image features. Automated screening of bone scintigraphy images using CNN could improve the early diagnosis of ATTR.
Background: Diagnosing cardiac amyloidosis (CA) from cine-CMR (cardiac magnetic resonance) alone is not reliable. In this study, we tested if a convolutional neural network (CNN) could outperform the visual diagnosis of experienced operators. Method: 119 patients with cardiac amyloidosis and 122 patients with left ventricular hypertrophy (LVH) of other origins were retrospectively selected. Diastolic and systolic cine-CMR images were preprocessed and labeled. A dual-input visual geometry group (VGG ) model was used for binary image classification. All images belonging to the same patient were distributed in the same set. Accuracy and area under the curve (AUC) were calculated per frame and per patient from a 40% held-out test set. Results were compared to a visual analysis assessed by three experienced operators. Results: frame-based comparisons between humans and a CNN provided an accuracy of 0.605 vs. 0.746 (p < 0.0008) and an AUC of 0.630 vs. 0.824 (p < 0.0001). Patient-based comparisons provided an accuracy of 0.660 vs. 0.825 (p < 0.008) and an AUC of 0.727 vs. 0.895 (p < 0.002). Conclusion: based on cine-CMR images alone, a CNN is able to discriminate cardiac amyloidosis from LVH of other origins better than experienced human operators (15 to 20 points more in absolute value for accuracy and AUC), demonstrating a unique capability to identify what the eyes cannot see through classical radiological analysis.
Aims: We tested the hypothesis that artificial intelligence (AI)-powered algorithms applied to cardiac magnetic resonance (CMR) images could be able to detect the potential patterns of cardiac amyloidosis (CA). Readers in CMR centers with a low volume of referrals for the detection of myocardial storage diseases or a low volume of CMRs, in general, may overlook CA. In light of the growing prevalence of the disease and emerging therapeutic options, there is an urgent need to avoid misdiagnoses. Methods and Results: Using CMR data from 502 patients (CA: n = 82), we trained convolutional neural networks (CNNs) to automatically diagnose patients with CA. We compared the diagnostic accuracy of different state-of-the-art deep learning techniques on common CMR imaging protocols in detecting imaging patterns associated with CA. As a result of a 10-fold cross-validated evaluation, the best-performing fine-tuned CNN achieved an average ROC AUC score of 0.96, resulting in a diagnostic accuracy of 94% sensitivity and 90% specificity. Conclusions: Applying AI to CMR to diagnose CA may set a remarkable milestone in an attempt to establish a fully computational diagnostic path for the diagnosis of CA, in order to support the complex diagnostic work-up requiring a profound knowledge of experts from different disciplines.
Patients with rare conditions such as cardiac amyloidosis (CA) are difficult to identify, given the similarity of disease manifestations to more prevalent disorders. The deployment of approved therapies for CA has been limited by delayed diagnosis of this disease. Artificial intelligence (AI) could enable detection of rare diseases. Here we present a pipeline for CA detection using AI models with electrocardiograms (ECG) or echocardiograms as inputs. These models, trained and validated on 3 and 5 academic medical centers (AMC) respectively, detect CA with C-statistics of 0.85–0.91 for ECG and 0.89–1.00 for echocardiography. Simulating deployment on 2 AMCs indicated a positive predictive value (PPV) for the ECG model of 3–4% at 52–71% recall. Pre-screening with ECG enhance the echocardiography model performance at 67% recall from PPV of 33% to PPV of 74–77%. In conclusion, we developed an automated strategy to augment CA detection, which should be generalizable to other rare cardiac diseases.
The objective of the present work was to evaluate the potential of deep learning tools for characterizing the presence of cardiac amyloidosis from early acquired PET images, i.e. 15 min after [18F]-Florbetaben tracer injection. 47 subjects were included in the study: 13 patients with transthyretin-related amyloidosis cardiac amyloidosis (ATTR-CA), 15 patients with immunoglobulin light-chain amyloidosis (AL-CA), and 19 control-patients (CTRL). [18F]-Florbetaben PET/CT images were acquired in list mode and data was sorted into a sinogram, covering a time interval of 5 min starting 15 min after the injection. The resulting sinogram was reconstructed using OSEM iterative algorithm. A deep convolutional neural network (CAclassNet) was designed and implemented, consisting of five 2D convolutional layers, three fully connected layers and a final classifier returning AL, ATTR and CTRL scores. A total of 1107 2D images (375 from AL-subtype patients, 312 from ATTR-subtype, and 420 from Controls) have been considered in the study and used to train, validate and test the proposed network. CAclassNet cross-validation resulted with train error mean ± sd of 2.001% ± 0.96%, validation error of 4.5% ± 2.26%, and net accuracy of 95.49% ± 2.26%. Network test error resulted in a mean ± sd values of 10.73% ± 0.76%. Sensitivity, specificity, and accuracy evaluated on the test dataset were respectively for AL-CA sub-type: 1, 0.912, 0.936; for ATTR-CA: 0.935, 0.897, 0.972; for control subjects: 0.809, 0.971, 0.909. In conclusion, the proposed CAclassNet model seems very promising as an aid for the clinician in the diagnosis of CA from cardiac [18F]-Florbetaben PET images acquired a few minutes after the injection.
Background
Cardiovascular magnetic resonance (CMR) is part of the diagnostic work-up for cardiac amyloidosis (CA). Deep learning (DL) is an application of artificial intelligence that may allow to automatically analyze CMR findings and establish the likelihood of CA.
Methods
1.5 T CMR was performed in 206 subjects with suspected CA (n = 100, 49% with unexplained left ventricular (LV) hypertrophy; n = 106, 51% with blood dyscrasia and suspected light-chain amyloidosis). Patients were randomly assigned to the training (n = 134, 65%), validation (n = 30, 15%), and testing subgroups (n = 42, 20%). Short axis, 2-chamber, 4-chamber late gadolinium enhancement (LGE) images were evaluated by 3 networks (DL algorithms). The tags “amyloidosis present” or “absent” were attributed when the average probability of CA from the 3 networks was ≥ 50% or < 50%, respectively. The DL strategy was compared to a machine learning (ML) algorithm considering all manually extracted features (LV volumes, mass and function, LGE pattern, early blood-pool darkening, pericardial and pleural effusion, etc.), to reproduce exam reading by an experienced operator.
Results
The DL strategy displayed good diagnostic accuracy (88%), with an area under the curve (AUC) of 0.982. The precision (positive predictive value), recall score (sensitivity), and F1 score (a measure of test accuracy) were 83%, 95%, and 89% respectively. A ML algorithm considering all CMR features had a similar diagnostic yield to DL strategy (AUC 0.952 vs. 0.982; p = 0.39).
Conclusions
A DL approach evaluating LGE acquisitions displayed a similar diagnostic performance for CA to a ML-based approach, which simulates CMR reading by experienced operators.
Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to consistent performance gains on a wide range of applications. However, most existing methods represent the multi-scale features in a layer-wise manner. In this paper, we propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The proposed Res2Net block can be plugged into the state-of-the-art backbone CNN models, e.g., ResNet, ResNeXt, and DLA. We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e.g., CIFAR-100 and ImageNet. Further ablation studies and experimental results on representative computer vision tasks, i.e., object detection, class activation mapping, and salient object detection, further verify the superiority of the Res2Net over the state-of-the-art baseline methods. The source code and trained models are available on https://mmcheng.net/res2net/.
Systemic amyloidosis comprises an uncommon group of disorders caused by the extracellular deposition of misfolded proteins in various organs. Cardiac amyloid deposition, causing an infiltrative/restrictive cardiomyopathy, is a frequent feature of amyloidosis and a major determinant of survival. It may be the presenting feature of the disease or may be identified while investigating a patient presenting with other organ involvement. The need for a high index of suspicion and the critical importance of precise biochemical typing of the amyloid deposits is paramount in light of recent therapeutic advances that can significantly improve prognosis. Most cases of cardiac amyloidosis are of either transthyretin type, which may be acquired in older individuals or inherited in younger patients, or acquired monoclonal immunoglobulin light chain (AL) type. This article aims to review recent developments in diagnosis and management of cardiac amyloidosis.
Gas turbines are widely used for power generation globally, and their greenhouse gas emissions have increasingly drawn public attention. Compliance with environmental regulations necessitates sophisticated emission measurement techniques and tools. Traditional sensors used for monitoring emission gases can provide inaccurate data due to malfunction or miscalibration. Accurate estimation of gas turbine emissions, such as particulate matter, carbon monoxide, and nitrogen oxides, is crucial for assessing the environmental impact of industrial activities and power generation. This study used 5 different machine learning models to predict emissions from gas turbines, including adaboost, xgboost, k-nearest neighbor, linear and random forest models. Random search optimization was used to set the regression parameters. The findings indicate that the adaboost regressor model provides superior prediction accuracy for emissions compared to other models, with an accuracy of 99.97% and a mean squared error of 2.17 on training data. This research offers a practical modeling approach for forecasting gas turbine emissions, contributing to the reduction of air pollution in industrial applications.
Background
Recent studies suggest that cardiac amyloidosis (CA) is significantly underdiagnosed. For rare diseases like CA, the optimal selection of cases and controls for artificial intelligence model training is unknown and can significantly impact model performance.
Objectives
This study evaluates the performance of electrocardiogram (ECG) waveform-based artificial intelligence models for CA screening and assesses impact of different criteria for defining cases and controls.
Methods
Using a primary cohort of ∼1.3 million ECGs from 341,989 patients, models were trained using different case and control definitions. Case definitions included ECGs from patients with an amyloidosis diagnosis by International Classification of Diseases-9/10 code, patients with CA, and patients seen in CA clinic. Models were then tested on test cohorts with identical selection criteria as well as a Cedars-Sinai general patient population cohort.
Results
In matched held-out test data sets, different model AUCs ranged from 0.660 (95% CI: 0.642-0.736) to 0.898 (95% CI: 0.868-0.924). However, algorithms exhibited variable generalizability when tested on a Cedars-Sinai general patient population cohort, with AUCs dropping to 0.467 (95% CI: 0.443-0.491) to 0.898 (95% CI: 0.870-0.923). Models trained on more well-curated patient cases resulted in higher AUCs on similarly constructed test cohorts. However, all models performed similarly in the overall Cedars-Sinai general patient population cohort. A model trained with International Classification of Diseases 9/10 cases and population controls matched for age and sex resulted in the best screening performance.
Conclusions
Models performed similarly in population screening, regardless of stringency of cases used during training, showing that institutions without dedicated amyloid clinics can train meaningful models on less curated CA cases. Additionally, AUC or other metrics alone are insufficient in evaluating deep learning algorithm performance. Instead, evaluation in the most clinically meaningful population is key.
Electric motors are increasingly used in various products, including turbines and electric vehicles. Precise temperature measurement is essential for the safe operation of a Permanent Magnet Synchronous Motor. Direct temperature detection of the permanent magnet and stator involves significant costs and hardware requirements. To overcome these challenges, Machine Learning models can eliminate the need for specialized sensors. This study used four diverse regression algorithms: Linear, K-Nearest Neighbor, XGBoost, and AdaBoost. The objective of this study is to model a Permanent Magnet Synchronous Motor used in electric vehicles and predict the temperatures of some of its parameters. The K-Nearest Neighbor Regressor outperformed the other algorithms, achieving a training accuracy of 99.65%, test accuracy of 98.72%, root-mean-square error of 2.16, R2 score of 98.72, and Cross-Validation R2 of 97.77%. These results enable low-cost, real-time temperature monitoring of electrical machinery, enhancing power density, safety, and efficiency.
Coronavirus disease 2019 (COVID-19), caused by Severe Acute Respiratory Syndrome Coronavirus 2, is an emerging and rapidly spreading type of coronavirus. One of the most important reasons for the rapid spread of the COVID-19 virus are the frequent mutations of the COVID-19 virus. One of the most important methods to overcome mutations of the COVID-19 virus is to predict these mutations before they occur. In this study, we propose a robust HyperMixer and long short-term memory based model with attention mechanisms, HyperAttCov, for COVID-19 virus mutation prediction. The proposed HyperAttCov model outperforms several state-of-the-art methods. Experimental results have showed that the proposed HyperAttCov model reached accuracy 70.0%, precision 92.0%, MCC 46.5% on the COVID-19 testing dataset. Similarly, the proposed HyperAttCov model reached accuracy 70.2%, precision 90.4%, MCC 46.2% on the COVID-19 testing dataset with an average of 10 random trail. Besides, When the proposed HyperAttCov model with 10 random trail has been compared with compared to the study in the literature, the average of performance values has been increased by accuracy 7.18%, precision 37.39%, MCC 49.51% on the testing dataset. As a result, the proposed HyperAttCov can successfully predict mutations occurring on the COVID-19 dataset in the 2022 year.
Acute lymphoblastic leukemia (ALL) is considered the most fatal form of leukemia (also known as blood cancer). It propagates quickly among adults and children and could lead to their death. Early detection of ALL and ALL subtypes is the key factor in selecting effective treatment types and improving survival rates. However, routine diagnostic approaches have several drawbacks. Computer-assisted diagnosis (CAD) is the perfect solution to avoid these challenges and achieve a fast and accurate diagnosis. Current CAD models require enhancement/segmentation processing. Besides, they are either dependent on deep learning (DL) models or handcrafted features along with machine learning. Those CADs that employed DL approaches relied solely on spatial information during the training procedure. However, learning them with spectral temporal and temporal representations could improve performance. Furthermore, integrating deep features from DL models along with handcrafted features can increase the discrimination ability of attributes in medical image classification. This study aims to propose a novel CAD for ALL detection and subtype classification without pre-segmentation or enhancement steps. The proposed CAD extends the conventional DL models of convolutional neural networks by introducing an additional wavelet pooling, accompanied by a dense layer or a long-short-term memory (LSTM) layer, and then a SoftMax layer, acquiring spectral-temporal information along with temporal information. To further improve the framework's ability to discriminate, the introduced CAD then combines the wavelet-based deep features of every CNN with numerous handcrafted attributes. Afterward, a feature selection methodology is utilized to create a model with limited features and improved accuracy. The performance results show that the novel CAD is capable of achieving 100% ALL detection accuracy, as well as 100% ALL-subtype classification accuracy with just 88 and 146 features. Thus, this CAD can be employed to assist pathologists in the rapid and precise ALL identification and subcategories recognition.
A Vision Transformer (ViT) is a simple neural architecture amenable to serve several computer vision tasks. It has limited built-in architectural priors, in contrast to more recent architectures that incorporate priors either about the input data or of specific tasks. Recent works show that ViTs benefit from self-supervised pre-training, in particular BerT-like pre-training like BeiT.In this paper, we revisit the supervised training of ViTs. Our procedure builds upon and simplifies a recipe introduced for training ResNet-50. It includes a new simple data-augmentation procedure with only 3 augmentations, closer to the practice in self-supervised learning. Our evaluations on Image classification (ImageNet-1k with and without pre-training on ImageNet-21k), transfer learning and semantic segmentation show that our procedure outperforms by a large margin previous fully supervised training recipes for ViT. It also reveals that the performance of our ViT trained with supervision is comparable to that of more recent architectures. Our results could serve as better baselines for recent self-supervised approaches demonstrated on ViT.
Systemic amyloidosis encompasses a debilitating, under-diagnosed but increasingly recognized group of disorders characterized by the extracellular deposition of misfolded proteins in one or more organs. Cardiac amyloid deposition leads to an infiltrative or restrictive cardiomyopathy and is the major contributor to poor prognosis in patients with systemic amyloidosis. In total, >30 proteins can form amyloid fibrils, but the two main types of amyloid that can infiltrate the heart are monoclonal immunoglobulin light-chain amyloid and transthyretin amyloid. Cardiac amyloidosis can be acquired in older individuals or inherited from birth. Given the nonspecific symptoms of these disorders, a high index of suspicion is paramount in making the correct diagnosis, which can involve the use of non-invasive imaging methods such as echocardiography, bone scintigraphy and cardiovascular MRI. In the past decade, the use of cardiovascular MRI with tissue characterization and bone scintigraphy to diagnose cardiac amyloidosis has revolutionized our understanding of the disease, leading to changes in patient care. However, a need remains for improved awareness and expertise, and greater clinical suspicion, because the initial clues provided by electrocardiography and echocardiography might not be typical. With specific treatments now available, timely diagnosis of cardiac amyloidosis is more important than ever. In this Review, we discuss the current and novel approaches for the diagnostic imaging of cardiac amyloidosis.
The amyloidoses are a group of systemic diseases characterized by organ deposition of misfolded protein fragments of diverse origins. The natural history of the disease, involvement of other organs, and treatment options vary significantly based on the protein of origin. In AL amyloidosis, amyloid protein is derived from immunoglobulin light chains, and most often involves the kidneys and the heart. ATTR amyloidosis is categorized as mutant or wild-type depending on the genetic sequence of the transthyretin (TTR) protein produced by the liver. Wild-type ATTR amyloidosis mainly involves the heart, although the reported occurrence of bilateral carpal tunnel syndrome, spinal stenosis and biceps tendon rupture in these patients speaks to more generalized protein deposition. Mutant TTR is marked by cardiac and/or peripheral nervous system involvement. Cardiac involvement is associated with symptoms of heart failure, and dictates the clinical course of the disease. Cardiac amyloidosis can be diagnosed noninvasively by echocardiography, cardiac MRI, or nuclear scintigraphy. Endomyocardial biopsy may be needed in the case of equivocal imaging findings or discordant data. Treatment is aimed at relieving congestive symptoms and targeting the underlying amyloidogenic process. This includes anti-plasma cell therapy in AL amyloidosis, and stabilization of the TTR tetramer or inhibition of TTR protein production in ATTR amyloidosis. Cardiac transplantation can be considered in highly selected patients in tandem with therapy aimed at suppressing the amyloidogenic process, and appears associated with durable long term survival.
Gaining knowledge and actionable insights from complex, high-dimensional and heterogeneous biomedical data remains a key challenge in transforming health care. Various types of data have been emerging in modern biomedical research, including electronic health records, imaging, -omics, sensor data and text, which are complex, heterogeneous, poorly annotated and generally unstructured. Traditional data mining and statistical learning approaches typically need to first perform feature engineering to obtain effective and more robust features from those data, and then build prediction or clustering models on top of them. There are lots of challenges on both steps in a scenario of complicated data and lacking of sufficient domain knowledge. The latest advances in deep learning technologies provide new effective paradigms to obtain end-to-end learning models from complex data. In this article, we review the recent literature on applying deep learning technologies to advance the health care domain. Based on the analyzed work, we suggest that deep learning approaches could be the vehicle for translating big biomedical data into improved human health. However, we also note limitations and needs for improved methods development and applications, especially in terms of ease-of-understanding for domain experts and citizen scientists. We discuss such challenges and suggest developing holistic and meaningful interpretable architectures to bridge deep learning models and human interpretability.
Cardiac amyloidosis occurs as a result of abnormal protein (amyloid) deposition in the cardiac tissue. Even with advanced diagnostic techniques and treatments, the prognosis of amyloidosis remains poor. The diagnosis of cardiac amyloidosis particularly needs to be in the differential in patients presenting with heart failure with preserved ejection fraction. This entity remains underdiagnosed due to lack of suspicion on the part of many clinicians. Involvement is cardiac tissue is the utmost determinant factor for available treatment options and prognosis. Many cases of cardiac amyloidosis usually remain undiagnosed or diagnosed only in advanced stages when treatment options are limited and associated with poor survival. Hence, early recognition of cardiac amyloidosis is indispensable in halting the disease process before irreversible changes occurs. The purpose of this review is to summarize the recent updates in the evaluation and management of cardiac amyloidosis and discuss potential future treatments options.
Very deep convolutional networks have been central to the largest advances in image recognition performance in recent years. One example is the Inception architecture that has been shown to achieve very good performance at relatively low computational cost. Recently, the introduction of residual connections in conjunction with a more traditional architecture has yielded state-of-the-art performance in the 2015 ILSVRC challenge; its performance was similar to the latest generation Inception-v3 network. This raises the question of whether there are any benefit in combining the Inception architecture with residual connections. Here we give clear empirical evidence that training with residual connections accelerates the training of Inception networks significantly. There is also some evidence of residual Inception networks outperforming similarly expensive Inception networks without residual connections by a thin margin. We also present several new streamlined architectures for both residual and non-residual Inception networks. These variations improve the single-frame recognition performance on the ILSVRC 2012 classification task significantly. We further demonstrate how proper activation scaling stabilizes the training of very wide residual Inception networks. With an ensemble of three residual and one Inception-v4, we achieve 3.08 percent top-5 error on the test set of the ImageNet classification (CLS) challenge
Amyloidosis is an increasingly recognized cause of heart disease, caused by the deposition of misfolded protein within the heart. These proteins may deposit systemically and include the heart or deposit only within the heart muscle itself. In either case, cardiac symptoms may be the primary manifestation. The diagnosis is usually made by the pathologist identifying amyloid within a tissue sample. The diagnosis, however, does not end with such visual recognition of the presence of amyloid. Newer generation pharmacotherapeutic agents that are protein specific necessitate a closer evaluation to determine the type of protein being deposited and accurately conveying this to the treating clinician. Herein, the gross and histopathologic features of cardiac amyloidosis are reviewed along with a review of amyloid typing strategies (both direct and indirect) that may be employed in the diagnostic workup as well as the nomenclature standards for reporting.
Systemic amyloidosis is generally considered to be rare, but the heart is frequently involved and is a major determinant of prognosis. New diagnostic imaging methods have recently been developed with the capacity to enhance the accuracy of diagnosis, which will be ever more important with the variety of new treatments on the near horizon. Most cases of cardiac amyloidosis are of either monoclonal immunoglobulin light chain (AL) type, which can occur at any age from young adulthood onwards, or transthyretin (ATTR) type, which can be acquired in elderly individuals or inherited at a younger age. Cardiac involvement is the most serious manifestation of AL amyloidosis, and serum cardiac biomarkers have proved to be of great value in staging disease severity and response to an ever increasing array of chemotherapy agents. Cardiac involvement is the dominant manifestation of nonhereditary ATTR amyloidosis, also known as senile cardiac amyloidosis, the prevalence of which is not known but is probably much greater than currently recognized. A genetic variant in the gene for transthyretin (TTR), which is present in 3-4% of African Americans and probably a similar proportion of black individuals of African descent generally, appears to be associated with increased susceptibility to developing cardiac ATTR amyloidosis in older age. Several novel therapies are in the advanced stages of development for ATTR amyloidosis including TTR protein stabilizers and RNA inhibitors that greatly diminish TTR production. Here, we will review recent developments in the diagnosis and management of cardiac amyloidosis.
© 2015 The Association for the Publication of the Journal of Internal Medicine.
Amyloidosis is a severe systemic disease. Cardiac involvement may occur in the three main types of amyloidosis (acquired monoclonal light-chain, hereditary transthyretin and senile amyloidosis) and has a major impact on prognosis. Imaging the heart to characterize and detect early cardiac involvement is one of the major aims in the assessment of this disease. Electrocardiography and transthoracic echocardiography are important diagnostic and prognostic tools in patients with cardiac involvement. Cardiac magnetic resonance imaging better characterizes myocardial involvement, functional abnormalities and amyloid deposition due to its high spatial resolution. Nuclear imaging has a role in the diagnosis of transthyretin amyloid cardiomyopathy. Cardiac biomarkers are now used for risk stratification and staging of patients with light-chain systemic amyloidosis. Different types of cardiac complications may occur, including diastolic followed by systolic heart failure, atrial and/or ventricular arrhythmias, conduction disturbances, embolic events and sometimes sudden death. Senile amyloid and hereditary transthyretin amyloid cardiomyopathy have better prognoses than light-chain amyloidosis. Cardiac treatment of heart failure is usually ineffective and is often poorly tolerated because of its hypotensive and bradycardiac effects. The three main types of amyloid disease, despite their similar cardiac appearance, have specific new aetiological treatments that may change the prognosis of this disease. Cardiologists should be aware of this disease to allow early treatment.
Cardiac amyloidosis describes clinically significant involvement of the heart by amyloid deposition, which may or may not be associated with involvement of other organs. The purpose of this review is to summarize the current state of evidence for the effective evaluation and management of cardiac amyloidosis. Acquired systemic amyloidosis occurs in more than 10 per million person-years in the U.S. population. Although no single noninvasive test or abnormality is pathognomonic of cardiac amyloid, case-control studies indicate that echocardiographic evidence of left ventricular wall thickening, biatrial enlargement, and increased echogenicity in conjunction with reduced electrocardiographic voltages is strongly suggestive of cardiac amyloidosis. Furthermore, newer echocardiographic techniques such as strain and strain rate imaging can demonstrate impairment in longitudinal function before ejection fraction becomes abnormal. Recent observational studies also suggest that cardiovascular magnetic resonance imaging yields characteristic findings in amyloidosis, offering promise for the early detection of cardiac involvement, and the presence of detectable cardiac troponin and elevated B-type natriuretic peptide in serum of affected patients portends an adverse prognosis. Management strategies for cardiac amyloid are largely based on nonrandomized single-center studies. One of the few published randomized studies shows the superiority of oral prednisolone and melphalan compared with colchicine in systemic AL amyloidosis. Intermediate-dose infusional chemotherapy regimes (such as vincristine, adriamycin, and dexamethasone) and high-dose chemotherapy with peripheral stem cell rescue have been used widely, but treatment-related mortality remains substantial with chemotherapy. Recent studies also indicate promising strategies to stabilize the native structures of amyloidogenic proteins; inhibit fibril formation; and disrupt established deposits using antibodies, synthetic peptides, and small-molecule drugs.
Updates in cardiac amyloidosis: a review
- S M Banypersad
- J C Moon
- C Whelan
- P N Hawkins
- A D Wechalekar
- SM Banypersad
Banypersad SM, Moon JC, Whelan C, Hawkins PN, Wechalekar
AD (2012) Updates in cardiac amyloidosis: a review. J Am Heart
Assoc. https:// doi. org/ 10. 1161/ JAHA. 111. 000364/ ASSET/ 2FB02
EDB-FAAF-498A-A62A-CA2D4 0085F 31/ ASSETS/ IMAGES/
LARGE/ JAH316-FIG-0006. JPG
Do vision transformers see like convolutional neural networks?
- M Raghu
- T Unterthiner
- S Kornblith
- C Zhang
- A Dosovitskiy
Raghu M, Unterthiner T, Kornblith S, Zhang C, Dosovitskiy
A (2021) Do vision transformers see like convolutional neural
networks?
An image is worth 16x16 words: Transformers for image recognition at scale
- A Dosovitskiy
- L Beyer
- A Kolesnikov
- D Weissenborn
- X Zhai
- T Unterthiner
Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X,
Unterthiner T, et al (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv Preprint https://
arxiv. org/ abs/ 2010. 11929
FastViT: a fast hybrid vision transformer using structural reparameterization
- Pka Vasu
- J Gabriel
- J Zhu
- O Tuzel
- A Ranjan
Vasu PKA, Gabriel J, Zhu J, Tuzel O, Ranjan A (2023) FastViT: a
fast hybrid vision transformer using structural reparameterization
Enhancing Efficient-Netv2 with global and efficient channel attention mechanisms for accurate MRI-Based brain tumor classification
- I Pacal
- O Celik
- B Bayram
- A Cunha
Pacal I, Celik O, Bayram B, Cunha A (2024) Enhancing Efficient-Netv2 with global and efficient channel attention mechanisms for
accurate MRI-Based brain tumor classification. Cluster Comput
27:11187-11212. https:// doi. org/ 10. 1007/ S10586-024-04532-1/
TABLES/4
Artificial intelligence as a tool for diagnosis of cardiac amyloidosis: a systematic review
- A Ahmadi-Hadad
- De Rosa
- Di Serafino
- L Esposito
Ahmadi-Hadad A, De Rosa E, Di Serafino L, Esposito G (2024)
Artificial intelligence as a tool for diagnosis of cardiac amyloidosis: a systematic review. J Med Biol Eng 44:499-513. https:// doi.
org/ 10. 1007/ S40846-024-00893-5/ TABLES/2
Diagnosis of cardiac amyloidosis: a systematic review on the role of imaging and biomarkers
- P Kyriakou
- D Mouselimis
- A Tsarouchas
- A Rigopoulos
- C Bakogiannis
- M Noutsias
Kyriakou P, Mouselimis D, Tsarouchas A, Rigopoulos A, Bakogiannis C, Noutsias M et al (2018) Diagnosis of cardiac amyloidosis: a systematic review on the role of imaging and biomarkers. BMC Cardiovasc Disord 18:1-11. https:// doi. org/ 10. 1186/
S12872-018-0952-8/ FIGUR ES/4
Cardiac amyloidosis: the great pretender
- C Rapezzi
- M Lorenzini
- S Longhi
- A Milandri
- C Gagliardi
Rapezzi C, Lorenzini M, Longhi S, Milandri A, Gagliardi C, Bartolomei I et al (2015) Cardiac amyloidosis: the great pretender.
Heart Fail Rev 20:117-124. https:// doi. org/ 10. 1007/ S10741-015-9480-0/ TABLES/4
TfrAdmCov: a robust transformer encoder based model with Adam optimizer algorithm for COVID-19 mutation prediction
- M Burukanli
- N Yumuşak
Burukanli M, Yumuşak N (2024) TfrAdmCov: a robust transformer encoder based model with Adam optimizer algorithm for
COVID-19 mutation prediction. Conn Sci 36:2365334. https:// doi.
org/ 10. 1080/ 09540 091. 2024. 23653 34/ ASSET/ 63F4F 138-0658-4D2F-A063-2099F 6D5EF EE/ ASSETS/ GRAPH IC/ CCOS_A_
23653 34_ F0017_ OC. JPG