Multimodal Large Language Model for Zero-Shot L3 Body Composition Segmentation on CT: Improved Accuracy via Automated Candidate Selection [0.03%]
多模态大型语言模型在CT图像中进行零样本L3身体组成分割的自动候选选择改进准确度研究
Haruto Sugawara,Akiyo Takada,Shimpei Kato
Haruto Sugawara
The purpose of the study is to evaluate zero-shot L3 body composition segmentation on computed tomography (CT) using a general-purpose multimodal large language model (MLLM) and to assess whether automated candidate selection improves segme...
Scalable Left Ventricular ROI Annotation for Stress Perfusion Cardiac MRI using Deep Learning with Visual Refinement [0.03%]
基于深度学习的心肌灌注MRI的左心室感兴趣区域标注及视觉优化方法
Mahsa Pourhossein Kalashami,Mohamed Elshibly,Simran Shergill et al.
Mahsa Pourhossein Kalashami et al.
Accurate extraction of the left ventricular (LV)-centred region of interest (ROI) in stress perfusion cardiovascular magnetic resonance (CMR) remains challenging due to low signal-to-noise ratio (SNR), motion artefacts, high-dimensional ima...
RE-LIG: A Faithfulness-Driven Layer Integrated Gradients Framework for Explainable Medical Visual Question Answering [0.03%]
基于信仰驱动的层集成梯度框架的解释性医学视觉问答研究
Esra Balık,İrfan Aygün,Mehmet Kaya
Esra Balık
Medical Visual Question Answering (Med-VQA) systems have the potential to support medical image interpretation and clinical decision-making processes. However, the "black-box" nature of existing systems and low-resolution constraints limit ...
Bridging Parallel Disciplines: An Integrated Workshop for Clinical and Imaging Informatics Training [0.03%]
融合学科壁垒：临床与影像信息学培训综合研讨会
James Whitfill,Kayla Berigan,Ankit A Modi et al.
James Whitfill et al.
Medical informatics training consists of two types of fellowship programs: clinical informatics (CI) and imaging informatics (II). Historically, there has been little collaborative learning between these fellowships despite significant over...
CRAF-Net: A Fine-Grained Cross-Channel Attention Network for Preoperative Microvascular Invasion Grading in Hepatocellular Carcinoma via DCE-MRI [0.03%]
基于DCE-MRI的肝细胞癌术前微血管侵犯分级的细粒度跨通道注意力网络(CRAF-Net)
Zebang Zhong,Xiao Luo,Daoying Geng et al.
Zebang Zhong et al.
To address the clinical challenge of preoperative microvascular invasion (MVI) grading in hepatocellular carcinoma (HCC), this paper proposes a cross-channel attention fine-grained Network (CRAF-Net) using dynamic contrast-enhanced magnetic...
Reasoning Model-Assisted Second-Reader Quality Control of Chinese-Language Ultrasound Reports: A Retrospective Imaging Informatics Study [0.03%]
基于推理模型的中国超声报告二级质控研究性影像信息学研究
Zhenqi Zhang,Zirui Jiang,Yihan Qi et al.
Zhenqi Zhang et al.
The purpose of this study is to evaluate whether the reasoning model DeepSeek-R1 can function as a second-reader quality control (QC) tool for Chinese-language ultrasound reports. In this retrospective diagnostic-accuracy study with a paral...
Elizabeth A Krupinski,Marly van Assen,Carlo N De Cecco et al.
Elizabeth A Krupinski et al.
The purpose was to examine how variations in AI output design affect radiologists' performance in interpreting chest X-rays. Eight readers interpreted 80 COVID-19 chest images under five AI conditions in this retrospective study: no feedbac...
How is Bias Learned in Medical Image Analysis Models? An Exploration of the Encoding of Demographic Information in Deep Learning Models Trained to Detect Abnormalities on Chest X-Rays [0.03%]
医学影像分析模型中的偏见是如何产生的？深度学习模型中人口统计信息编码的探索：基于胸部X光片异常检测模型
Nikhil Cherian Kurian,Phoenix Williams,Sahar Abdulrahman et al.
Nikhil Cherian Kurian et al.
Deep learning models achieve strong diagnostic performance in medical imaging, yet often exhibit systematic performance disparities across demographic subgroups. Although prior work has shown that attributes such as age, sex and race are en...
AI-Based Opportunistic CT Risk Assessment Using TotalSegmentator in Osteoporotic Vertebral Fractures [0.03%]
基于人工智能的机会主义CT风险评估在骨质疏松性椎体骨折中的应用_totalSegmentator的应用
Magdalena Seng,Jakob Wasserthal,Michael Bach et al.
Magdalena Seng et al.
Osteoporotic vertebral fractures impair quality of life and increase both morbidity and mortality, yet they are largely preventable. Routine CT examinations offer an opportunity for early risk stratification. This study aimed to evaluate wh...
A Computationally Efficient and Improved Brain Tumor Recognition System by MRI-Segmentation Integrated Classification Network [0.03%]
一种计算高效的改进的脑肿瘤识别系统基于MRI分割集成分类网络
Namya Musthafa,Qurban Memon,Mohammad Masud
Namya Musthafa
Brain tumors present a major global health concern, and a precise diagnosis is essential for proper treatment. Many existing MRI-based machine learning approaches focus solely on segmentation or classification, rather than addressing both t...