Afzaal Usman, Su Ziyu, Sajjad Usama, Stack Thomas, Lu Hao, Niu Shuo, Akbar Abdul Rehman, Gurcan Metin Nafi, Niazi Muhammad Khalid Khan
Department of Pathology, College of Medicine, The Ohio State University Wexner Medical Center, Columbus, OH, USA.
Edward Via College of Osteopathic Medicine, Blacksburg, VA, USA.
Patterns (N Y). 2025 May 30;6(8):101284. doi: 10.1016/j.patter.2025.101284. eCollection 2025 Aug 8.
Artificial intelligence (AI) has the potential to greatly enhance diagnostic pathology, including the analysis of tissue samples to detect diseases such as colorectal cancer. This study explores how large language models (LLMs) and multimodal LLMs (MLLMs) can improve histopathological analysis by using medical data to aid diagnostics. However, challenges such as data quality and availability limit their effectiveness. To address these challenges, we introduce HistoChat, an AI-powered assistant designed to assist in colorectal cancer histopathology. It uses advanced techniques to improve data quality, such as generating image combinations and question-answer (QA) pairs to boost its learning. Despite working with limited data, HistoChat has significantly improved key metrics, including BLEU, ROUGE-L, and BERTScore, with an overall accuracy of 69.1% in human evaluation. These results suggest that HistoChat is a promising tool for enhancing diagnostic accuracy, especially in cases where data are scarce.
人工智能（AI）有潜力极大地提升诊断病理学水平，包括对组织样本进行分析以检测诸如结直肠癌等疾病。本研究探讨了大语言模型（LLMs）和多模态大语言模型（MLLMs）如何通过利用医学数据辅助诊断来改善组织病理学分析。然而，数据质量和可用性等挑战限制了它们的有效性。为应对这些挑战，我们引入了HistoChat，这是一款旨在辅助结直肠癌组织病理学诊断的人工智能助手。它采用先进技术来提高数据质量，例如生成图像组合和问答（QA）对以促进其学习。尽管使用的数据有限，但HistoChat显著改善了关键指标，包括BLEU、ROUGE-L和BERTScore，在人工评估中的总体准确率达到了69.1%。这些结果表明，HistoChat是提高诊断准确性的一个有前景的工具，特别是在数据稀缺的情况下。
Zotero 插件
