Osamu Abe

Verified

Osamu verified their affiliation via an institutional email.

Learn more

Verified

Osamu verified their affiliation via an institutional email.

Learn more

• MD, PhD
• Professor at The University of Tokyo

Purpose This study aimed to compare three publicly available deep learning models (TotalSegmentator, TotalVibeSegmentator, and PanSegNet) for automated pancreatic segmentation on magnetic resonance images and to evaluate their performance against human annotations in terms of segmentation accuracy, volumetric measurement, and intrapancreatic fat fr...

Uterine sarcoma is a rare disease whose association with body composition parameters is poorly understood. This study explored the impact of body composition parameters on overall survival with uterine sarcoma. This multicenter study included 52 patients with uterine sarcomas treated at three Japanese hospitals between 2007 and 2023. A semi-automat...

Objectives Appropriate categorization based on magnetic resonance imaging (MRI) findings is important for managing intraductal papillary mucinous neoplasms (IPMNs). In this study, a large language model (LLM) that classifies IPMNs based on MRI findings was developed, and its performance was compared with that of less experienced human readers. Met...

The purpose of the study is to investigate the degree and performance in the differential diagnosis of bronchiectasis/airspace enlargement in an iodine map obtainable from CT pulmonary angiography compared with monochromatic images. This retrospective study included 62 patients with a lung nodule who underwent CT pulmonary angiography. The iodine m...

Purpose This study aimed to develop an automated early warning system using a large language model (LLM) to identify acute to subacute brain infarction from free-text computed tomography (CT) or magnetic resonance imaging (MRI) radiology reports. Methods In this retrospective study, 5,573, 1,883, and 834 patients were included in the training (mea...

Syphilis displays a wide array of clinical and radiologic features resembling infectious, inflammatory, and neoplastic disorders, requiring recognition of its many possible imaging manifestations for precise diagnosis.

Purpose Postmortem computed tomography (PMCT) typically reveals blood clots and sedimentation in cardiac and vascular structures. We examined the associations between these postmortem findings and antemortem clinical and laboratory parameters in in-hospital death. Material and methods This prospective study included 114 non-traumatic in-hospital d...

Objective/Background : Multiple sclerosis (MS) shows a gradient of periventricular white matter damage, especially close to the ventricles. Although evaluating this gradient has demonstrated its usefulness in understanding microstructural changes in MS, assessments have primarily used nonspecific imaging techniques, such as two-dimensional magnetiz...

Introduction: This study evaluates the diagnostic performance of a large language model (LLM) in determining causes of death by comparing three different information sources. Methods: A total of 150 consecutive adult in-hospital cadavers underwent postmortem CT and pathological autopsy (2009-2013). The diagnostic accuracy of Claude 3.5 Sonnet (Anth...

Super-resolution deep learning reconstruction (SR-DLR) is a promising tool for improving image quality by enhancing spatial resolution compared to conventional deep learning reconstruction (DLR). This study aimed to evaluate whether SR-DLR improves microbleed detection and visualization in brain magnetic resonance imaging (MRI) compared to DLR. Thi...

Background Medical image segmentation is crucial for diagnosis and treatment planning in radiology, but it traditionally requires extensive manual effort and specialized training data. With its novel video tracking capabilities, the Segment Anything Model 2 (SAM 2) presents a potential solution for automated 3D medical image segmentation without th...

Prediction of severe disease (SVD) in patients with coronavirus disease (COVID-19) pneumonia at an early stage could allow for more appropriate triage and improve patient prognosis. Moreover, the visualization of the topological properties of COVID-19 pneumonia could help clinical physicians describe the reasons for their decisions. We aimed to con...

Purpose These guidelines aim to support magnetic resonance imaging (MRI) diagnosis in patients receiving anti-amyloid β (Aβ) antibody treatment without restricting treatment eligibility. Materials and methods These guidelines were collaboratively established by Japan Radiological Society, The Japanese Society of Neuroradiology, and Japanese Societ...

Purpose To investigate whether super-resolution deep learning reconstruction (SR-DLR) of MR myelography-aided evaluations of lumbar spinal stenosis. Material and methods In this retrospective study, lumbar MR myelography of 40 patients (16 males and 24 females; mean age, 59.4 ± 31.8 years) were analyzed. Using the MR imaging data, MR myelography w...

Research on biomarkers for predicting psychiatric disorders from resting-state functional connectivity (FC) is advancing. While the focus has primarily been on the discriminative performance of biomarkers by machine learning, identification of abnormal FCs in psychiatric disorders has often been treated as a secondary goal. However, it is crucial t...

Within the cortico-basal ganglia network, the volume and functional connectivity (FC) of the globus pallidus (GP) are altered in schizophrenia-spectrum disorders, with GP enlargement being relatively specific to schizophrenia compared to other disorders. However, little is known about alterations in its two major segments, externus (GPe) and intern...

Purpose: These guidelines aim to support MRI diagnosis in patients receiving anti-amyloid β (Aβ) antibody treatment without restricting treatment eligibility. Materials and Methods: These guidelines were collaboratively established by Japan Radiological Society, The Japanese Society of Neuroradiology, and Japanese Society for Magnetic Resonance in...

The Alzheimer’s disease (AD) continuum is characterized by amyloid and tau protein deposition, which is partly attributable to the dysfunction of the brain clearance system. However, the specific phase in the AD continuum wherein aberrant clearance is present remains unclear. This study aimed to assess noninvasive magnetic resonance imaging (MRI) i...

This study presents a novel two stage deep learning algorithm for automated detection of mucus plugs in CT scans of patients with respiratory diseases. Despite the clinical significance of mucus plugs in COPD and asthma where they indicate hypoxemia, reduced exercise tolerance, and poorer outcomes, they remain under evaluated in clinical practice d...

Objective: This study aims to evaluate and compare the performance of two Japanese language models-conventional Bidirectional Encoder Representations from Transformers (BERT) and the newer ModernBERT-in classifying findings from chest CT reports, with a focus on tokenization efficiency, processing time, and classification performance. Methods: We c...

One of the challenges in diagnosing psychiatric disorders is that the results of biological and neuroscience research are not reflected in the diagnostic criteria. Thus, data‐driven analyses incorporating biological and cross‐disease perspectives, regardless of the diagnostic category, have recently been proposed. A data‐driven clustering study bas...

Background To evaluate the efficacy of computed tomography (CT) lymphangiography after direct mesenteric lymph node injection for thoracic duct (TD) visualization in mice. Methods Twelve female BALB/c mice were injected with 35 μL of iodinated contrast medium (iomeprol 350 mgI/mL) into the mesenteric (mesenteric group) or popliteal (popliteal grou...

Background and purpose: Intracranial solitary fibrous tumors (SFTs) and meningiomas are CNS tumors that share similar imaging manifestations but exhibit different clinical behaviors. This study aimed to compare ADC values and conventional imaging features, particularly pre-contrast T1-weighted signal intensity, between intracranial SFTs and mening...

Large language models (LLMs) show promise in radiological diagnosis, but their performance may be affected by the context of the cases presented. Our purpose is to investigate how providing information about prior probabilities influences the diagnostic performance of an LLM in radiological quiz cases. We analyzed 322 consecutive cases from Radiolo...

Accurate CT protocol assignment is crucial for optimizing medical imaging procedures. The integration of large language models (LLMs) may be helpful, but its efficacy as a clinical decision support system for protocoling tasks remains unknown. This study aimed to develop and evaluate fine-tuned LLM specifically designed for CT protocoling, as well...

This study aimed to investigate the performance of a fine-tuned large language model (LLM) in extracting patients on pretreatment for lung cancer from picture archiving and communication systems (PACS) and comparing it with that of radiologists. Patients whose radiological reports contained the term lung cancer (3111 for training, 124 for validatio...

To characterize the radiological findings of desmoid-type fibromatosis (DF). This two-institution retrospective study included 152 patients with pathologically confirmed DF who underwent computed tomography (CT), magnetic resonance imaging (MRI), or 18F-fluorodeoxyglucose-positron emission tomography (FDG-PET)/CT between January 2001 and February 2...

Anorexia nervosa (AN) is a severe eating disorder characterized by intense fear of weight gain, distorted body image, and extreme food restriction. This research employed advanced diffusion MRI techniques including single-shell 3-tissue constrained spherical deconvolution, anatomically constrained tractography, and spherical deconvolution informed...

Background The application of natural language processing in medicine has increased significantly, including tasks such as information extraction and classification. Natural language processing plays a crucial role in structuring free-form radiology reports, facilitating the interpretation of textual content, and enhancing data utility through clus...

Objectives This study aimed to investigate the impact of changing inspiratory depth from end- to mid-inspiratory level on the iodine concentration of lung parenchyma and main pulmonary artery in dual-energy CT pulmonary angiography. Methods This retrospective study included patients who underwent dual-energy CT pulmonary angiography from July 2020...

Background Alzheimer’s disease (AD) progression is often characterized by the accumulation of amyloid and tau proteins, which can be linked to impaired brain clearance mechanisms, including the glymphatic system. Our research evaluates noninvasive MRI‐based indicators of brain clearance functionality, such as choroid plexus volume (CPV), lateral ve...

Purpose: The prevalence of type 2 diabetes mellitus (T2DM) has been steadily increasing over the years. We aim to predict the occurrence of T2DM using mammography images within 5 years using two different methods and compare their performance. Approach: We examined 312 samples, including 110 positive cases (developed T2DM after 5 years) and 202...

Background: Recent advances in large language models highlight the need for high-quality multilingual medical datasets. While Japan leads globally in CT scanner deployment and utilization, the lack of large-scale Japanese radiology datasets has hindered the development of specialized language models for medical imaging analysis. Objective: To devel...

This study aimed to develop a large multimodality model (LMM) that can detect breast and esophageal carcinomas on chest contrast-enhanced CT. In this retrospective study, CT images of 401 (age, 62.9 ± 12.9 years; 169 males), 51 (age, 65.5 ± 11.6 years; 23 males), and 120 (age, 64.6 ± 14.2 years; 60 males) patients were used in the training, validat...

The aim of this study is to develop a fine-tuned large language model that classifies interventional radiology reports into technique categories and to compare its performance with readers. This retrospective study included 3198 patients (1758 males and 1440 females; age, 62.8 ± 16.8 years) who underwent interventional radiology from January 2018 t...

A general-purpose method of emphasizing abnormal lesions in chest radiographs, named EGGPALE (Extrapolative, Generative and General-Purpose Abnormal Lesion Emphasizer), is presented. The proposed EGGPALE method is composed of a flow-based generative model and L-infinity-distance-based extrapolation in a latent space. The flow-based model is trained...

Purpose The aim of this study is to investigate the capability of generative pre-trained transformer 4 (GPT-4) and GPT-4o in identifying chest radiography reports requiring further assessment. Materials and methods This retrospective study included 100 cases from the National Institutes of Health chest radiography dataset, including 50 abnormal and...

Objective: To comprehensively evaluate the effects of contrast-medium administration and measurement level (L3 and L1) on computed tomography (CT) derived body composition parameters, promising prognostic factors for various diseases. Methods: 203 dynamic contrast-enhanced CT examinations, including unenhanced (phase 0) and early arterial, late art...

Large Language Models (LLMs) show promise in medical diagnosis, but their performance varies with prompting. Recent studies suggest that modifying prompts may enhance diagnostic capabilities. This study aimed to test whether a prompting approach that aligns with general clinical reasoning methodology—specifically, using a standardized template to f...

Purpose: To investigate the effects of deep learning reconstruction on depicting arteries and providing suitable images for the evaluation of hemorrhages with abdominopelvic contrast-enhanced computed tomography (CT) compared with hybrid iterative reconstruction. Methods: This retrospective study included 16 patients (mean age: 54.2 ± 22.1 years...

Purpose Large language models (LLMs) are neural network models that are trained on large amounts of textual data, showing promising performance in various fields. In radiology, studies have demonstrated the strong performance of LLMs in diagnostic imaging quiz cases. However, the inherent differences in prior probabilities of a final diagnosis betw...

Purpose Transarterial radioembolization (TARE) is effective for unresectable hepatocellular carcinoma; however, it awaits approval in Japan. This study aimed to simulate the cost-effectiveness of TARE over chemoembolization when TARE is approved in Japan and identify the requirements for cost-effectiveness. Materials and methods A Markov model was...

Purpose Large language models (LLMs) are neural network models trained on vast amounts of textual data, showing promising performance in various fields. In radiology, studies have demonstrated the strong performance of LLMs in diagnostic imaging quiz cases. However, the inherent differences of prior probabilities of a final diagnosis between clinic...

Epidermoid cyst in intrapancreatic accessory spleen (ECIPAS) is a rare benign condition that occasionally mimic malignant pancreatic neoplasms. We present a case of ECIPAS in a 53-year-old asymptomatic male, initially discovered incidentally during imaging for a suspected hepatic hemangioma. The lesion, located in the pancreatic tail, demonstrated...

To release medical images that can be freely used in downstream processes while maintaining their utility, it is necessary to remove personal features from the images while preserving the lesion structures. Unlike previous studies that focused on removing lesion structures while preserving the individuality of medical images, this study proposes an...

Background: Large Language Models (LLMs) show promise in medical diagnosis, but their performance varies with prompting. Recent studies suggest that modifying prompts may enhance diagnostic capabilities. Objective: This study aimed to test whether a prompting approach that aligns with general clinical reasoning methodology, specifically, separating...

Changing a window width (WW) alters appearance of noise and contrast of CT images. The aim of this study was to investigate the impact of adjusted WW for deep learning reconstruction (DLR) in detecting hepatocellular carcinomas (HCCs) on CT with DLR. This retrospective study included thirty-five patients who underwent abdominal dynamic contrast-enh...

Background Bleeding from the puncture tract after percutaneous transhepatic portal vein intervention can become life-threatening. To date, studies about tract embolization with gelatin sponge after percutaneous transhepatic portal vein intervention are only with small numbers of patients, or non-consecutive or pediatric patients with a relatively s...

Background Large language models (LLMs) show promise in radiological diagnosis, but their performance may be affected by the context of the cases presented. Purpose To investigate how providing information about prior probabilities influences the diagnostic performance of an LLM in radiological quiz cases. Materials and Methods We analyzed 322 cons...

Early detection of patients with impending bone metastasis is crucial for prognosis improvement. This study aimed to investigate the feasibility of a fine-tuned, locally run large language model (LLM) in extracting patients with bone metastasis in unstructured Japanese radiology report and to compare its performance with manual annotation. This ret...

Introduction: This study evaluates the diagnostic performance of the latest large language models (LLMs), GPT-4o (OpenAI, San Francisco, CA, USA) and Claude 3 Opus (Anthropic, San Francisco, CA, USA), in determining causes of death from medical histories and postmortem CT findings. Methods: We included 100 adult cases whose postmortem CT scans were...

This study aimed to compare the image quality and detection performance of pancreatic cystic lesions between computed tomography (CT) images reconstructed by deep learning reconstruction (DLR) and filtered back projection (FBP). This retrospective study included 54 patients (mean age: 67.7 ± 13.1) who underwent contrast-enhanced CT from May 2023 to...

Purpose: This study aimed to evaluate the zero-shot performance of Segment Anything Model 2 (SAM 2) in 3D segmentation of abdominal organs in CT scans, leveraging its video tracking capabilities for volumetric medical imaging. Materials and Methods: Using a subset of the TotalSegmentator CT dataset (n=123) from 8 different institutions, we assessed...

Trabectedin is an antineoplastic drug used to treat soft tissue sarcomas. Trabectedin is mainly infused from the central venous port (CVP) because trabectedin leakage causes serious skin and soft tissue complications. Characteristic sterile inflammation has recently been reported after infusion of trabectedin from the CVP. Here, we report a case of...

The diagnostic performance of large language artificial intelligence (AI) models when utilizing radiological images has yet to be investigated. We employed Claude 3 Opus (released on March 4, 2024) and Claude 3.5 Sonnet (released on June 21, 2024) to investigate their diagnostic performances in response to the Radiology’s Diagnosis Please quiz ques...

Purpose The quality and bias of annotations by annotators (e.g., radiologists) affect the performance changes in computer-aided detection (CAD) software using machine learning. We hypothesized that the difference in the years of experience in image interpretation among radiologists contributes to annotation variability. In this study, we focused on...

Purpose This retrospective study aimed to investigate the radiological features of pancreatic desmoid-type fibromatosis (PDF) and systematically review the previous publications and two new cases. Methods We searched PubMed, Cochrane Library, and Web of Science Core Collection and included 31 patients with pathologically proven PDFs with analyzabl...

Aggressive systemic mastocytosis (ASM) is an advanced subtype of systemic mastocytosis characterized by organ involvement. In this article, we report a case with ASM in a 54-year-old woman with characteristic findings on computed tomography (CT) and fluorine-18-fluorodeoxyglucose positron emission tomography (¹⁸F-FDG PET)/CT. Contrast-enhanced CT o...

Purpose Many large radiographic datasets of lung nodules are available, but the small and hard-to-detect nodules are rarely validated by computed tomography. Such difficult nodules are crucial for training nodule detection methods. This lack of difficult nodules for training can be addressed by artificial nodule synthesis algorithms, which can crea...

Purpose This study aimed to investigate the efficacy of fine-tuned large language models (LLM) in classifying brain MRI reports into pretreatment, posttreatment, and nontumor cases. Methods This retrospective study included 759, 284, and 164 brain MRI reports for training, validation, and test dataset. Radiologists stratified the reports into thre...

Background This study aimed to evaluate if combining low muscle mass with additional body composition abnormalities, such as myosteatosis or adiposity, could improve survival prediction accuracy in a large cohort of gastrointestinal and genitourinary malignancies. Methods In total, 2015 patients with surgically‐treated gastrointestinal or genitour...

Large language models (LLMs) are rapidly advancing and demonstrating high performance in understanding textual information, suggesting potential applications in interpreting patient histories and documented imaging findings. As LLMs continue to improve, their diagnostic abilities are expected to be enhanced further. However, there is a lack of comp...

The aim of this study was to investigate the effect of iterative motion correction (IMC) on reducing artifacts in brain magnetic resonance imaging (MRI) with deep learning reconstruction (DLR). The study included 10 volunteers (between September 2023 and December 2023) and 30 patients (between June 2022 and July 2022) for quantitative and qualitati...

Peliosis hepatis (PH) is a rare benign vascular condition characterized by sinusoidal dilatation and the presence of blood-filled spaces within the liver. PH is often clinically asymptomatic and is discovered incidentally. It presents a clinical challenge as its imaging findings frequently mimic other pathologies, including primary or secondary mal...

Purpose: To verify the usefulness of a deep learning model for determining the presence or absence of contrast-enhanced myocardium in late gadolinium-enhancement images in cardiac MRI. Methods: We used 174 late gadolinium-enhancement myocardial short-axis images obtained from contrast-enhanced cardiac MRI performed using a 3.0T MRI system at the Un...

Germinomas frequently cause hydrocephalus, and ventriculoperitoneal shunts (VPS) have been commonly used for their management. Although VPS can potentially serve as a route for peritoneal dissemination of germinomas, the abdominal imaging characteristics of this rare yet important complication remain unknown. In this article, we report the computed...

Background and study aims Pancreatitis is a potentially lethal adverse event of endoscopic transpapillary placement of a self-expandable metal stent (SEMS) for malignant biliary obstruction (MBO). Deep learning-based image recognition has not been investigated in predicting pancreatitis in this setting. Patients and methods We included 70 patients...

This study aimed to establish the diagnostic criteria for upper gastrointestinal bleeding (UGIB) using postmortem computed tomography (PMCT). This case-control study enrolled 27 consecutive patients with autopsy-proven UGIB and 170 of the 566 patients without UGIB who died in a university hospital in Japan after treatment and underwent both noncont...

Cytokines are small secreted proteins that have specific effects on cellular interactions and are crucial for functioning of the immune system. Cytokines are involved in almost all diseases, but as microscopic chemical compounds they cannot be visualized at imaging for obvious reasons. Several imaging manifestations have been well recognized owing...

Backgrounds Large language models (LLMs) are rapidly advancing and demonstrating high performance in understanding textual information, suggesting potential applications in interpreting patient histories and documented imaging findings. LLMs are advancing rapidly and an improvement in their diagnostic ability is expected. Furthermore, there has bee...

We describe the usefulness of n-butyl-cyanoacrylate (nBCA)-assisted retrograde transvenous obliteration (NARTO) for gastric varices in 3 consecutive patients. In all patients, balloon catheters were inserted into the gastrorenal shunt via the left renal vein. After injecting sclerosant into the gastric varix under balloon occlusion, nBCA was inject...

Background Cortical neurodegenerative processes may precede the emergence of disease symptoms in patients with Alzheimer’s disease (AD) by many years. No study has evaluated the free water of patients with AD using gray matter-based spatial statistics. Objective The aim of this study was to explore cortical microstructural changes within the gray...

To assess the performance of GPT-4 Turbo with Vision (GPT-4TV), OpenAI’s latest multimodal large language model, by comparing its ability to process both text and image inputs with that of the text-only GPT-4 Turbo (GPT-4 T) in the context of the Japan Diagnostic Radiology Board Examination (JDRBE). The dataset comprised questions from JDRBE 2021 a...

To compare computed tomography (CT) pulmonary angiography and unenhanced CT to determine the effect of rapid iodine contrast agent infusion on tracheal diameter and lung volume. This retrospective study included 101 patients who underwent CT pulmonary angiography and unenhanced CT, for which the time interval between them was within 365 days. CT pu...