Panzeri Davide, Laohawetwanit Thiyaphat, Akpinar Reha, De Carlo Camilla, Belsito Vincenzo, Terracciano Luigi, Aghemo Alessio, Pugliese Nicola, Chirico Giuseppe, Inverso Donato, Calderaro Julien, Sironi Laura, Di Tommaso Luca
Department of Physics, University of Milano-Bicocca, Milan, Italy.
Division of Pathology, Chulabhorn International College of Medicine, Thammasat University, Pathum Thani, Thailand.
Hepatol Commun. 2025 Apr 30;9(5). doi: 10.1097/HC9.0000000000000695. eCollection 2025 May 1.
Large language models like ChatGPT have demonstrated potential in medical image interpretation, but their efficacy in liver histopathological analysis remains largely unexplored. This study aims to assess ChatGPT-4-vision's diagnostic accuracy, compared to liver pathologists' performance, in evaluating liver fibrosis (stage) in metabolic dysfunction-associated steatohepatitis.
Digitized Sirius Red-stained images for 59 metabolic dysfunction-associated steatohepatitis tissue biopsy specimens were evaluated by ChatGPT-4 and 4 pathologists using the NASH-CRN staging system. Fields of view at increasing magnification levels, extracted by a senior pathologist or randomly selected, were shown to ChatGPT-4, asking for fibrosis staging. The diagnostic accuracy of ChatGPT-4 was compared with pathologists' evaluations and correlated to the collagen proportionate area for additional insights. All cases were further analyzed by an in-context learning approach, where the model learns from exemplary images provided during prompting.
ChatGPT-4's diagnostic accuracy was 81% when using images selected by a pathologist, while it decreased to 54% with randomly cropped fields of view. By employing an in-context learning approach, the accuracy increased to 88% and 77% for selected and random fields of view, respectively. This method enabled the model to fully and correctly identify the tissue structures characteristic of F4 stages, previously misclassified. The study also highlighted a moderate to strong correlation between ChatGPT-4's fibrosis staging and collagen proportionate area.
ChatGPT-4 showed remarkable results with a diagnostic accuracy overlapping those of expert liver pathologists. The in-context learning analysis, applied here for the first time to assess fibrosis deposition in metabolic dysfunction-associated steatohepatitis samples, was crucial in accurately identifying the key features of F4 cases, critical for early therapeutic decision-making. These findings suggest the potential for integrating large language models as supportive tools in diagnostic pathology.
像ChatGPT这样的大语言模型已在医学图像解读中展现出潜力，但其在肝脏组织病理学分析中的功效仍很大程度上未被探索。本研究旨在评估ChatGPT-4-vision在评估代谢功能障碍相关脂肪性肝炎中的肝纤维化（阶段）时，与肝脏病理学家的表现相比，其诊断准确性。
59份代谢功能障碍相关脂肪性肝炎组织活检标本的数字化天狼星红染色图像由ChatGPT-4和4名病理学家使用NASH-CRN分期系统进行评估。由一名资深病理学家提取或随机选择的不同放大倍数水平的视野展示给ChatGPT-4，要求其进行纤维化分期。将ChatGPT-4的诊断准确性与病理学家的评估进行比较，并与胶原比例面积相关联以获得更多见解。所有病例均通过上下文学习方法进一步分析，即模型从提示过程中提供的示例图像中学习。
当使用病理学家选择的图像时，ChatGPT-4的诊断准确性为81%，而随机裁剪的视野使其降至54%。通过采用上下文学习方法，对于选择的和随机的视野，准确性分别提高到88%和77%。这种方法使模型能够完全且正确地识别先前被错误分类的F4阶段的组织结构特征。该研究还强调了ChatGPT-4的纤维化分期与胶原比例面积之间存在中度至强相关性。
ChatGPT-4显示出显著结果，其诊断准确性与肝脏病理专家相当。本文首次应用的上下文学习分析对于准确识别F4病例的关键特征至关重要，这对早期治疗决策至关重要，这些发现表明将大语言模型整合为诊断病理学辅助工具的潜力。
