近日，美国密歇根大学Todd Hollon团队研发了快速、无标记检测胶质瘤浸润的基础模型。这一研究成果于2024年11月13日发表在国际顶尖学术期刊《自然》上。

据了解，胶质瘤治疗的一个关键挑战是在手术中检测肿瘤浸润，以实现安全的最大切除。不幸的是，在大多数胶质瘤术后患者中发现了可安全切除的残留肿瘤，导致早期复发和生存率降低。

该团队提出了FastGlioma，一个快速（<10s）和准确检测新鲜，未经处理的手术组织中胶质瘤浸润的视觉基础模型。FastGlioma进行大规模自我监督预训练(约4百万张图像)在快速，无标签的光学显微镜，并微调输出一个标准化的分数，表明肿瘤浸润的程度在整个玻片光学图像。

在一项前瞻性、多中心、国际的鉴别性胶质瘤患者检测队列（n = 220）中，FastGlioma能够检测并量化肿瘤浸润程度，其在受试者工作特征曲线下的平均面积为92.1±0.9%。在一项头部对头部的前瞻性研究中，FastGlioma在手术期间检测肿瘤浸润方面表现，优于图像引导和荧光引导辅助手段（n=129）。

FastGlioma的性能在不同的患者群体、医疗中心，以及世界卫生组织定义的弥漫性胶质瘤分子亚型中保持了高水平。FastGlioma对其他成人和儿童脑肿瘤的诊断显示出零样本学习泛化能力，表明该基础模型有可能成为指导脑肿瘤手术的通用辅助工具。这些发现代表了医学基础模型，在释放人工智能在癌症患者护理中的作用方面的变革潜力。

附：英文原文

Title: Foundation models for fast, label-free detection of glioma infiltration

Author: Kondepudi, Akhil, Pekmezci, Melike, Hou, Xinhai, Scotford, Katie, Jiang, Cheng, Rao, Akshay, Harake, Edward S., Chowdury, Asadur, Al-Holou, Wajd, Wang, Lin, Pandey, Aditya, Lowenstein, Pedro R., Castro, Maria G., Koerner, Lisa Irina, Roetzer-Pejrimovsky, Thomas, Widhalm, Georg, Camelo-Piragua, Sandra, Movahed-Ezazi, Misha, Orringer, Daniel A., Lee, Honglak, Freudiger, Christian, Berger, Mitchel, Hervey-Jumper, Shawn, Hollon, Todd

Issue&Volume: 2024-11-13

Abstract: A critical challenge in glioma treatment is detecting tumour infiltration during surgery to achieve safe maximal resection1,2,3. Unfortunately, safely resectable residual tumour is found in the majority of patients with glioma after surgery, causing early recurrence and decreased survival4,5,6. Here we present FastGlioma, a visual foundation model for fast (<10s) and accurate detection of glioma infiltration in fresh, unprocessed surgical tissue. FastGlioma was pretrained using large-scale self-supervision (around 4million images) on rapid, label-free optical microscopy, and fine-tuned to output a normalized score that indicates the degree of tumour infiltration within whole-slide optical images. In a prospective, multicentre, international testing cohort of patients with diffuse glioma (n=220), FastGlioma was able to detect and quantify the degree of tumour infiltration with an average area under the receiver operating characteristic curve of 92.1±0.9%. FastGlioma outperformed image-guided and fluorescence-guided adjuncts for detecting tumour infiltration during surgery by a wide margin in a head-to-head, prospective study (n=129). The performance of FastGlioma remained high across diverse patient demographics, medical centres and diffuse glioma molecular subtypes as defined by the World Health Organization. FastGlioma shows zero-shot generalization to other adult and paediatric brain tumour diagnoses, demonstrating the potential for our foundation model to be used as a general-purpose adjunct for guiding brain tumour surgeries. These findings represent the transformative potential of medical foundation models to unlock the role of artificial intelligence in the care of patients with cancer.

DOI: 10.1038/s41586-024-08169-3

Source: https://www.nature.com/articles/s41586-024-08169-3