深度学习区分胰腺癌组织与非癌胰腺组织：一项具有跨种族外部验证的回顾性研究。

Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation.

机构信息

Department of Medical Imaging, National Taiwan University Cancer Center, Taipei, Taiwan; Department of Medical Imaging, National Taiwan University Hospital, National Taiwan University College of Medicine, Taipei, Taiwan.

Institute of Applied Mathematical Sciences, National Taiwan University, Taipei, Taiwan.

出版信息

Lancet Digit Health. 2020 Jun;2(6):e303-e313. doi: 10.1016/S2589-7500(20)30078-9.

DOI:10.1016/S2589-7500(20)30078-9

PMID:33328124

Abstract

BACKGROUND

The diagnostic performance of CT for pancreatic cancer is interpreter-dependent, and approximately 40% of tumours smaller than 2 cm evade detection. Convolutional neural networks (CNNs) have shown promise in image analysis, but the networks' potential for pancreatic cancer detection and diagnosis is unclear. We aimed to investigate whether CNN could distinguish individuals with and without pancreatic cancer on CT, compared with radiologist interpretation.

METHODS

In this retrospective, diagnostic study, contrast-enhanced CT images of 370 patients with pancreatic cancer and 320 controls from a Taiwanese centre were manually labelled and randomly divided for training and validation (295 patients with pancreatic cancer and 256 controls) and testing (75 patients with pancreatic cancer and 64 controls; local test set 1). Images were preprocessed into patches, and a CNN was trained to classify patches as cancerous or non-cancerous. Individuals were classified as with or without pancreatic cancer on the basis of the proportion of patches diagnosed as cancerous by the CNN, using a cutoff determined using the training and validation set. The CNN was further tested with another local test set (101 patients with pancreatic cancers and 88 controls; local test set 2) and a US dataset (281 pancreatic cancers and 82 controls). Radiologist reports of pancreatic cancer images in the local test sets were retrieved for comparison.

FINDINGS

Between Jan 1, 2006, and Dec 31, 2018, we obtained CT images. In local test set 1, CNN-based analysis had a sensitivity of 0·973, specificity of 1·000, and accuracy of 0·986 (area under the curve [AUC] 0·997 (95% CI 0·992-1·000). In local test set 2, CNN-based analysis had a sensitivity of 0·990, specificity of 0·989, and accuracy of 0·989 (AUC 0·999 [0·998-1·000]). In the US test set, CNN-based analysis had a sensitivity of 0·790, specificity of 0·976, and accuracy of 0·832 (AUC 0·920 [0·891-0·948)]. CNN-based analysis achieved higher sensitivity than radiologists did (0·983 vs 0·929, difference 0·054 [95% CI 0·011-0·098]; p=0·014) in the two local test sets combined. CNN missed three (1·7%) of 176 pancreatic cancers (1·1-1·2 cm). Radiologists missed 12 (7%) of 168 pancreatic cancers (1·0-3·3 cm), of which 11 (92%) were correctly classified using CNN. The sensitivity of CNN for tumours smaller than 2 cm was 92·1% in the local test sets and 63·1% in the US test set.

INTERPRETATION

CNN could accurately distinguish pancreatic cancer on CT, with acceptable generalisability to images of patients from various races and ethnicities. CNN could supplement radiologist interpretation.

FUNDING

Taiwan Ministry of Science and Technology.

摘要

背景

CT 对胰腺癌的诊断性能依赖于影像科医生的判读能力，大约有 40%直径小于 2 厘米的肿瘤会被漏诊。卷积神经网络（CNN）在图像分析方面表现出了一定的潜力，但它们在胰腺癌检测和诊断方面的潜力尚不清楚。我们旨在研究与影像科医生判读相比，CNN 是否能在 CT 上区分患有和不患有胰腺癌的个体。

方法

在这项回顾性的、诊断性研究中，我们对来自台湾一个中心的 370 名胰腺癌患者和 320 名对照者的增强 CT 图像进行了手动标注，并将其随机分为训练和验证集（295 名胰腺癌患者和 256 名对照者）和测试集（75 名胰腺癌患者和 64 名对照者；本地测试集 1）。我们将图像预处理成补丁，然后使用一个 CNN 对这些补丁进行分类，判断其是否为癌症。根据 CNN 诊断为癌症的补丁比例，个体被分为患有或不患有胰腺癌。在本地测试集 1 中，基于 CNN 的分析的敏感性为 0.973，特异性为 1.000，准确性为 0.986（曲线下面积[AUC]为 0.997[0.992-1.000]）。在本地测试集 2 中，基于 CNN 的分析的敏感性为 0.990，特异性为 0.989，准确性为 0.989（AUC 为 0.999[0.998-1.000]）。在 US 测试集中，基于 CNN 的分析的敏感性为 0.790，特异性为 0.976，准确性为 0.832（AUC 为 0.920[0.891-0.948]）。在两个本地测试集合并的情况下，基于 CNN 的分析的敏感性（0.983 比 0.929，差异 0.054[95%CI 0.011-0.098]；p=0.014）高于影像科医生的判读。CNN 漏诊了 176 例（1.7%）胰腺癌（直径为 1.1-1.2 厘米）。影像科医生漏诊了 168 例（1.0-3.3 厘米）胰腺癌，其中 11 例（92%）使用 CNN 进行了正确分类。在本地测试集和 US 测试集中，CNN 对直径小于 2 厘米的肿瘤的敏感性分别为 92.1%和 63.1%。