arXiv 2307.055192023-07-07q-bio.QMcs.AIcs.CVeess.IV

用于稳健人工智能辅助癌症诊断的数字病理扫描仪物理颜色校准

Physical Color Calibration of Digital Pathology Scanners for Robust Artificial Intelligence Assisted Cancer Diagnosis

Karolinska Institutet（卡罗林斯卡学院）；FFEI Ltd（FFEI有限公司）；University of Turku（图尔库大学）；Stavanger University Hospital（斯塔万格大学医院）；University of Stavanger（斯塔万格大学）；Aarhus University Hospital（奥胡斯大学医院）；Aarhus University（奥胡斯大学）；Tampere University（坦佩雷大学）

Xiaoyi Ji, Richard Salmon, Nita Mulliqi, Umair Khan, Yinxi Wang, Anders Blilie, Henrik Olsson, Bodil Ginnerup Pedersen, Karina Dalsgaard Sørensen, Benedicte Par… 展开作者

Xiaoyi Ji, Richard Salmon, Nita Mulliqi, Umair Khan, Yinxi Wang, Anders Blilie, Henrik Olsson, Bodil Ginnerup Pedersen, Karina Dalsgaard Sørensen, Benedicte Parm Ulhøi, Svein R Kjosavik, Emilius AM Janssen, Mattias Rantalainen, Lars Egevad, Pekka Ruusuvuori, Martin Eklund, Kimmo Kartasalo

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对多站点数字病理图像颜色差异影响AI诊断的问题，本文在四实验室、1161张WSI上验证扫描仪物理颜色校准，可改善模型校准与Gleason分级。

摘要：

人工智能（AI）在数字病理学中的潜力受到全切片图像（WSIs）制作过程中技术不一致性的限制，这会导致AI性能下降，并给广泛临床应用带来挑战，因为针对每个新站点微调算法并不现实。成像工作流程的变化还可能导致诊断受损和患者安全风险。我们评估了扫描仪的物理颜色校准是否能够标准化WSI外观并实现稳健的AI性能。我们在四个不同实验室使用了颜色校准载玻片，并在1,161张WSIs上评估了其对前列腺癌诊断AI系统性能的影响。颜色标准化持续改善了AI模型校准，并显著提升了Gleason分级性能。该研究表明，物理颜色校准为不同扫描仪引入的差异提供了一种潜在解决方案，使基于AI的癌症诊断在临床环境中更加可靠和适用。

英文摘要：

The potential of artificial intelligence (AI) in digital pathology is limited by technical inconsistencies in the production of whole slide images (WSIs), leading to degraded AI performance and posing a challenge for widespread clinical application as fine-tuning algorithms for each new site is impractical. Changes in the imaging workflow can also lead to compromised diagnoses and patient safety risks. We evaluated whether physical color calibration of scanners can standardize WSI appearance and enable robust AI performance. We employed a color calibration slide in four different laboratories and evaluated its impact on the performance of an AI system for prostate cancer diagnosis on 1,161 WSIs. Color standardization resulted in consistently improved AI model calibration and significant improvements in Gleason grading performance. The study demonstrates that physical color calibration provides a potential solution to the variation introduced by different scanners, making AI-based cancer diagnostics more reliable and applicable in clinical settings.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。