小柯机器人

德国德累斯顿工业大学Jakob Nikolas Kather和亥姆霍兹慕尼黑-德国环境与健康研究中心Tingying Peng共同合作，近期取得重要工作进展。他们发起了基于Transformer的结直肠癌组织学生物标志物预测：一项大规模多中心研究。相关研究成果2023年8月30日在线发表于《癌细胞》上。

据介绍，深度学习（DL）可以加速从结直肠癌（CRC）的常规病理切片中预测预后生物标志物。然而，目前的方法依赖于卷积神经网络（CNN），并且大多在小型患者群体中得到了验证。

研究人员开发了一种新的基于转换器的管道，通过将预先训练的转换器编码器与用于补丁聚合的转换器网络相结合，从病理切片中进行端到端生物标志物预测。与当前最先进的算法相比，这一基于转换器的方法大大提高了性能、可推广性、数据效率和可解释性。在对来自16个癌症大肠癌队列的13000多名患者的大型多中心群体进行培训和评估后，研究人员对外科切除标本上微卫星不稳定性（MSI）的预测达到了0.99的敏感性和超过0.99的阴性预测值。

总之，这一研究证明，仅切除标本的训练在内镜活检组织上达到了临床级的性能，解决了一个长期存在的诊断问题。

附：英文原文

Title: Transformer-based biomarker prediction from colorectal cancer histology: A large-scale multicentric study

Author: Sophia J. Wagner, Daniel Reisenbüchler, Nicholas P. West, Jan Moritz Niehues, Jiefu Zhu, Sebastian Foersch, Gregory Patrick Veldhuizen, Philip Quirke, Heike I. Grabsch, Piet A. van den Brandt, Gordon G.A. Hutchins, Susan D. Richman, Tanwei Yuan, Rupert Langer, Josien C.A. Jenniskens, Kelly Offermans, Wolfram Mueller, Richard Gray, Stephen B. Gruber, Joel K. Greenson, Gad Rennert, Joseph D. Bonner, Daniel Schmolze, Jitendra Jonnagaddala, Nicholas J. Hawkins, Robyn L. Ward, Dion Morton, Matthew Seymour, Laura Magill, Marta Nowak, Jennifer Hay, Viktor H. Koelzer, David N. Church, David Church, Enric Domingo, Joanne Edwards, Bengt Glimelius, Ismail Gogenur, Andrea Harkin, Jen Hay, Timothy Iveson, Emma Jaeger, Caroline Kelly, Rachel Kerr, Noori Maka, Hannah Morgan, Karin Oien, Clare Orange, Claire Palles, Campbell Roxburgh, Owen Sansom, Mark Saunders, Ian Tomlinson, Christian Matek, Carol Geppert, Chaolong Peng, Cheng Zhi, Xiaoming Ouyang, Jacqueline A. James, Maurice B. Loughrey, Manuel Salto-Tellez, Hermann Brenner, Michael Hoffmeister, Daniel Truhn, Julia A. Schnabel, Melanie Boxberg, Tingying Peng, Jakob Nikolas Kather

Issue&Volume: 2023-08-30

Abstract: Deep learning (DL) can accelerate the prediction of prognostic biomarkers from routine pathology slides in colorectal cancer (CRC). However, current approaches rely on convolutional neural networks (CNNs) and have mostly been validated on small patient cohorts. Here, we develop a new transformer-based pipeline for end-to-end biomarker prediction from pathology slides by combining a pre-trained transformer encoder with a transformer network for patch aggregation. Our transformer-based approach substantially improves the performance, generalizability, data efficiency, and interpretability as compared with current state-of-the-art algorithms. After training and evaluating on a large multicenter cohort of over 13,000 patients from 16 colorectal cancer cohorts, we achieve a sensitivity of 0.99 with a negative predictive value of over 0.99 for prediction of microsatellite instability (MSI) on surgical resection specimens. We demonstrate that resection specimen-only training reaches clinical-grade performance on endoscopic biopsy tissue, solving a long-standing diagnostic problem.

DOI: 10.1016/j.ccell.2023.08.002

Source: https://www.cell.com/cancer-cell/fulltext/S1535-6108(23)00278-7

Cancer Cell：《癌细胞》，创刊于2002年。隶属于细胞出版社，最新IF：38.585
官方网址：https://www.cell.com/cancer-cell/home
投稿链接：https://www.editorialmanager.com/cancer-cell/default.aspx