小柯机器人

荷兰分子医学中心J. de Ridder和荷兰马克西玛公主儿科肿瘤中心B. B. J. Tops共同合作，近期取得重要工作进展。他们研究提出了术中超快速深度学习中枢神经系统肿瘤分类的方法。相关研究成果2023年10月11日在线发表于《自然》杂志上。

据介绍，中枢神经系统肿瘤是最致命的癌症类型之一，尤其是在儿童中。主要治疗包括肿瘤的神经外科切除，必须在最大限度地扩大切除范围和最大限度地减少神经损伤和合并症的风险之间取得微妙的平衡。然而，外科医生在手术前对确切的肿瘤类型了解有限。目前的标准做法依赖于术前成像和术中组织学分析，但这些并不总是决定性的，偶尔也会出错。使用快速纳米孔测序，可以在手术过程中获得稀疏的甲基化图谱。

研究人员开发了Sturgeon，一种与患者无关的迁移学习神经网络，以实现基于这种稀疏图谱的中枢神经系统肿瘤的分子亚类化。在50个回顾性测序样本中的45个样本开始测序后40分钟内，Sturgeon给出了准确的诊断(放弃对其他5个样本的诊断)。

此外，研究人员在25次手术中实时证明了其适用性，实现了小于90分钟的诊断周转时间。其中，18例（72%）诊断正确，7例未达到所需的置信阈值。

总之，研究人员表明，基于低成本术中测序的机器学习诊断可以帮助神经外科决策，潜在地预防神经合并症并避免额外的手术。

附：英文原文

Title: Ultra-fast deep-learned CNS tumour classification during surgery

Author: Vermeulen, C., Pags-Gallego, M., Kester, L., Kranendonk, M. E. G., Wesseling, P., Verburg, N., de Witt Hamer, P., Kooi, E. J., Dankmeijer, L., van der Lugt, J., van Baarsen, K., Hoving, E. W., Tops, B. B. J., de Ridder, J.

Issue&Volume: 2023-10-11

Abstract: Central nervous system tumours represent one of the most lethal cancer types, particularly among children1. Primary treatment includes neurosurgical resection of the tumour, in which a delicate balance must be struck between maximizing the extent of resection and minimizing risk of neurological damage and comorbidity2,3. However, surgeons have limited knowledge of the precise tumour type prior to surgery. Current standard practice relies on preoperative imaging and intraoperative histological analysis, but these are not always conclusive and occasionally wrong. Using rapid nanopore sequencing, a sparse methylation profile can be obtained during surgery4. Here we developed Sturgeon, a patient-agnostic transfer-learned neural network, to enable molecular subclassification of central nervous system tumours based on such sparse profiles. Sturgeon delivered an accurate diagnosis within 40minutes after starting sequencing in 45 out of 50 retrospectively sequenced samples (abstaining from diagnosis of the other 5 samples). Furthermore, we demonstrated its applicability in real time during 25 surgeries, achieving a diagnostic turnaround time of less than 90min. Of these, 18 (72%) diagnoses were correct and 7 did not reach the required confidence threshold. We conclude that machine-learned diagnosis based on low-cost intraoperative sequencing can assist neurosurgical decision-making, potentially preventing neurological comorbidity and avoiding additional surgeries.

DOI: 10.1038/s41586-023-06615-2

Source: https://www.nature.com/articles/s41586-023-06615-2

Nature：《自然》，创刊于1869年。隶属于施普林格·自然出版集团，最新IF：69.504
官方网址：http://www.nature.com/
投稿链接：http://www.nature.com/authors/submit_manuscript.html