Pinle Qin's research while affiliated with North University of China and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (25)
Spine segmentation is necessary for the clinical quantitative analysis of computed tomography (CT) images and plays an important role in the early diagnosis and treatment of spine diseases. However, because of the different fields of view of sagittal CT, these images show different shapes and sizes of vertebrae, unclear vertebral boundaries, and di...
Compared to computed tomography (CT), magnetic resonance imaging (MRI) is more sensitive to acute ischemic stroke lesion. However, MRI is time-consuming, expensive, and susceptible to interference from metal implants. Generating MRI images from CT images can address the limitations of MRI. The key problem in the process is obtaining lesion informat...
Many brain tissue segmentation methods generally utilize one-level fusion
to explore complementary discrepancies among different modalities. However, this one-level fusion manner cannot fully explore potential characteristics of multi-modality images. To this end, we propose a multi-level fusion segmentation transformer framework (dubbed SF-SeForme...
Objective
This work aimed to develop a radiomics nomogram to predict 3-year overall survival of esophageal cancer patients after chemoradiotherapy.
Methods
A total of 109 esophageal cancer patients, diagnosed from November 2012 to February 2015, were enrolled in this retrospective study. They were randomly divided into training set (77 cases) and...
The low accuracy of MR image segmentation is often caused by blurred glioma region boundaries and intensity inhomogeneity as well as class-imbalance problems, which greatly influences glioma quantitative analysis. To resolve these problems, we propose a Deep Multiple Guidances based Glioma Segmentation Network (DMGSN), which is designed according t...
Multimodal medical image fusion technology can assist doctors diagnose diseases accurately and efficiently. However the multi-scale decomposition based image fusion methods exhibit low contrast and energy loss. And the sparse representation based fusion methods exist weak expression ability caused by the single dictionary and the spatial inconsiste...
Objectives:
To evaluate the utility of radiomics features in differentiating central lung cancers and atelectasis on contrast-enhanced computed tomography (CT) images. This study is retrospective.
Materials and methods:
In this study, 36 patients with central pulmonary cancer and atelectasis between July 2013 and June 2018 were identified. A tot...
This two volume set (CCIS 1451 and 1452) constitutes the refereed proceedings of the 7th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2021 held in Taiyuan, China, in September 2021.
The 81 papers presented in these two volumes were carefully reviewed and selected from 256 submissions. The papers are o...
This two volume set (CCIS 1451 and 1452) constitutes the refereed proceedings of the 7th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2021 held in Taiyuan, China, in September 2021.
The 81 papers presented in these two volumes were carefully reviewed and selected from 256 submissions. The papers are o...
This study aims at analyzing the separability of acute cerebral infarction lesions which were invisible in CT. 38 patients, who were diagnosed with acute cerebral infarction and performed both CT and MRI, and 18 patients, who had no positive finding in either CT or MRI, were enrolled. Comparative studies were performed on lesion and symmetrical reg...
We propose a novel indoor head detection network using dual-stream information and multi-attention that can be used for indoor crowd counting. To solve the problem of object scale diversity in indoor human head detection, especially the problem of small-scale human head, we propose a dual-stream information flow structure to enrich the positioning...
In this paper, we propose a triple intersecting U-Nets (TIU-Nets) for brain glioma segmentation. First, the proposed TIU-Nets is composed of binary-class segmentation U-Net (BU-Net) and multi-class segmentation U-Net (MU-Net), in which MU-Net reuses multi-resolution features from BU-Net. Second, we introduce a segmentation soft-mask predicted by BU...
Approximate Bayesian Computation (ABC) is a popular approach for Bayesian modeling, when these models exhibit an intractable likelihood. However, during each proposal of ABC, a great number of simulators are required and each simulation is always time-consuming. The overall goal of this work is to avoid inefficient computational cost of ABC. A pre-...
This two volume set (CCIS 1257 and 1258) constitutes the refereed proceedings of the 6th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2020 held in Taiyuan, China, in September 2020.
The 98 papers presented in these two volumes were carefully reviewed and selected from 392 submissions. The papers are o...
Ultrasonography is one of the main imaging methods for diagnosing thyroid nodules. Automatic differentiation between benign and malignant nodules in ultrasound images can great assist inexperienced clinicians in their diagnosis. The core of problem is the effective utilization of the features of ultrasound images. In this study, we propose a method...
The magnetic resonance (MR) brain tumor image segmentation can quantitatively analyze the tumor size and provide a large number of brain functional and anatomical information, which to a certain degree can guide the brain disease diagnosis and treatment planning. In this paper, we proposed a framework for brain tumor MR image segmentation combining...
Aiming at the problem of insufficient detail retention in multimodal medical image fusion (MMIF) based on sparse representation (SR), an MMIF method based on density peak clustering and convolution sparse representation (CSR-DPC) is proposed. First, the base layer is obtained based on the registered input image by the averaging filter, and the orig...
To solve the low detection accuracy of SSD for the small size object, this paper proposed an improved algorithm of SSD object detection based on the feature pyramid (FP-SSD). In the deep convolutional neural network, the high-level features contain well semantic information but are not sensitive to the translations. The low-level features have high...
With a widespread use of digital imaging data in hospitals, the size of medical image repositories is increasing rapidly. This causes difficulty in managing and querying these large databases leading to the need of content based medical image retrieval (CBMIR) systems. A major challenge in CBMIR systems is the “semantic gap” that exists between the...
Histopathology image analysis is a gold standard for cancer recognition and diagnosis. But typical problems with histopathology images that hamper automatic analysis include complex clinical features, insufficient training data, and large size of a single image (always up to gigapixels). In this paper, an image semantic segmentation algorithm based...
In order to colorize the grayscale images efficiently, an image colorization method based on deep residual neural network is proposed. This method combines the classified information and features of the image, uses the whole image as the input of the network and forms a non-linear mapping from grayscale images to the colorful images through the dee...
Aimed at the problems of small gradient, low learning rate, slow convergence error when the DBN using back-propagation process to fix the network connection weight and bias, proposing a new algorithm that combines with multi-innovation theory to improve standard DBN algorithm, that is the multi-innovation DBN(MI-DBN). It sets up a new model of back...
Moving objects tracking is an active problem in computer vision and has a wide variety of applications. The Kalman Filter algorithm has been commonly used for estimation and prediction of the target position in target tracking domain, of which the algorithm is adaptive to linear system, but the error of Kalman Filter will become large or even diver...
Citations
... These different types of MR modalities provide complementary information which can be utilized for diagnostic purposes and for registration to different brain atlases. Eleven papers [18][19][20][21][22][23][24][25][26][27][28] studied MRI synthesis from CT which demonstrates a knowledge gap in this area. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/1006321734270977-1616937206354_Q64/Eryan-Feng.jpg)
... The lightweight characteristic of transformer architecture makes it suitable for working with large medical image datasets. This has led to its application in solving tasks like Brain Tissue Image segmentation [17], myocardial fibrosis tissue detection [18] to name a few. Additionally, new models have also been proposed specifically for medical image analysis, by combining the transformer's encoding capabilities with Unet architecture, such as TransUNet [19], Mix Transformer-Unet [20]. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/11431281081207878-1661602696303_Q64/Jinjing-Zhang-8.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/11431281122416646-1677333790936_Q64/Lijun-Zhao-9.jpg)
... It represents the probability of belonging to a certain class. The cross-entropy loss [21] function is used in the training. The formula is shown in (3). ...
... In MRI images, brain tumors can be categorized in many ways [10][11][12][13][14]. One of the most prominent ones is fuzzy clustering means (FCM), support vector machine (SVM), artificial neural network (ANN), knowledge-based techniques, and the expectation-maximization (EM) algorithm methodology [14,[17][18][19]. ...
... The main goal of image decomposition methods is to separate an image into high-frequency and low-frequency components. There are several methods that are commonly used for image decomposition, including the discrete wavelet transform (DWT), stationary wavelet transform (SWT) [4,5], Laplacian Pyramid (LP) [6][7][8], , and NSST [12][13][14][15][16][17][18]. Other techniques can be employed to decompose images, including sparse representation (SR) [19][20][21][22][23][24], spectral total variation (STV) [25,26], two-scale image decomposition [19,27], and hybrid 1 − 0 layer decomposition [28]. ...
... --Arab A. [26] 2020 Ret ro spec tive CNNs with deep su per vi sion (CNN-DS) 10 45 Neuhaus A. [27] 2020 Ret ro spec tive Brainomix e-AS PECTS 178 -Shinohara Y. [28] 2020 Ret ro spec tive Xception 22 -Kral J. [29] 2020 Pro spec tive Brainomix 45 -Guan Y. [30] 2020 [35] 2020 Ret ro spec tive Sup port vec tor ma chine 1832 -Ko H. [36] 2020 Ret ro spec tive CNN-LSTM; Xception 727392 4516842 Iron side N. [37] 2019 Ret ro spec tive An a lyze 12.0 40 260 Amukotuwa SA. [38] 2019 Ret ro spec tive RAPID 4.9.1 969 -Kuang H. [39] 2019 Ret ro spec tive Ran dom For est 100 157 Seker F. [40] 2019 Ret ro spec tive Brainomix e-AS PECTS 43 -Vargas J. [41] 2018 Ret ro spec tive CNN 40 356 Albers GW. [42] 2019 Ret ro spec tive RAPID AS PECTS 65 -Austein F. [43] 2019 Ret ro spec tive Brainomix e-AS PECTS, iSchema View RAPID AS PECTS 52 -Li L. [44] 2020 Ret ro spec tive Fron tier AS PECTS 55 -Sales Barros R. [45] 2020 Ret ro spec tive CNN 396 630 You J. [46] 2020 Ret ro spec tive XGBoost 100 200 Wen X. [47] 2020 Ret ro spec tive Multivariate lo gis tic re gres sion model 39 87 Guberina N. [48] 2018 Ret ro spec tive Brainomix e-AS PECTS 117 -Amukotuwa SA. [49] 2019 Ret ro spec tive RAPID CTA 477 -Copelan AZ. [50] 2020 Ret ro spec tive RAPID 38 -Heit JJ. [51] 2021 Ret ro spec tive RAPID ICH 308 -Stib MT. [52] 2020 Ret ro spec tive DenseNet-121 116 424 Prevedello LM. [53] 2017 Ret ro spec tive GoogLeNet 50 264 Schultheiss M. [54] 2020 Ret ro spec tive U-net 186 369 Lo CM. [55] 2021 Ret ro spec tive AlexNet 325 1254 Wang C. [56] 2021 Ret ro spec tive 3D CNN 194 259 Herweh C. [57] 2016 Ret ro spec tive Brainomix e-AS PECTS 34 -Nagel S. [58] 2017 Ret ro spec tive Brainomix e-AS PECTS 132 -Goebel J. [59] 2018 Ret ro spec tive Brainomix, Fron tier AS PECTS 150 -Wu G. [60] 2021 Ret ro spec tive U-net, ResNet, MAP 128 149 intracerebral hem or rhage, 4 stud ies as sessed large ves sel oc clu sion and ischemic core vol ume, and 1 study as sessed intracranial hem or rhage and intracerebral hem or rhage. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/318819069825025-1453023797739_Q64/Yanfeng-Meng.jpg)
... A The differentiation of brain tumors from normal tumors causes difficulty in brain tumor segmentation and also consists of a high degree in shape, patient extension, and area. To capture the spatial information from far away at different resolutions, a multi-scale 3 Dimensional (3D) U-Nets architecture is used and the 3D depth-wise separable convolution is involved in it to reduce the cost of computation [6]. The image was captured to evaluate the information that existed in it but while capturing the data a lot of noise like pepper noise, salt & speckle noise, and Gaussian noise are reduced by using a modified iterative median filter technique and for input MRI a homomorphic wavelet filter is used [7,8]. ...
... The convolutional neural network-based detection model (Yu et al., 2020a;Yu et al., 2020b;Shen et al., 2019) has significantly improved the target detection task. A salient feature of the deep learning models, regarding the ability to generalize, is the quality and quantity of the dataset, and the abundant high-quality data can enhance the robustness and generalization of the model. ...
... Zhang et al. [85] used a random forest model for the differential diagnosis of thyroid nodules based on conventional ultrasound and realtime UE. Qin et al. [86] proposed a method based on a CNN that combined the characteristics of conventional ultrasound and ultrasound elasticity images to form a hybrid feature space for the classification of benign and malignant thyroid nodules. Zhao et al. [87] used a machine learning model that incorporated radiomic features extracted from ultrasound and SWE images to develop ML-assisted radiomics approaches. ...
... The review of related literature is as follows. [48][49][50][51], CSR combined with PCNN (CSR-PCNN) [28,38,[52][53][54], multi-component CSR [55][56][57][58], modified CSR model [59][60][61][62], CSR combined with deep learning [63,64], CSR combined with clustering [65] Advantages: robust to misregistration and noise, preserves details (compared to SR and MST); simple model and easy to implement. Disadvantages: insufficient feature extraction capability; high computational cost and low efficiency. ...
