Literature DB >> 33328124

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

Kao-Lang Liu1, Tinghui Wu2, Po-Ting Chen3, Yuhsiang M Tsai2, Holger Roth4, Ming-Shiang Wu5, Wei-Chih Liao6, Weichung Wang7.   

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.
Copyright © 2020 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved.

Entities:  

Year:  2020        PMID: 33328124     DOI: 10.1016/S2589-7500(20)30078-9

Source DB:  PubMed          Journal:  Lancet Digit Health        ISSN: 2589-7500


  22 in total

Review 1.  Artificial intelligence: a critical review of current applications in pancreatic imaging.

Authors:  Maxime Barat; Guillaume Chassagnon; Anthony Dohan; Sébastien Gaujoux; Romain Coriat; Christine Hoeffel; Christophe Cassinotto; Philippe Soyer
Journal:  Jpn J Radiol       Date:  2021-02-06       Impact factor: 2.374

2.  A new magnetic resonance imaging tumour response grading scheme for locally advanced rectal cancer.

Authors:  Xiaolin Pang; Peiyi Xie; Li Yu; Haiyang Chen; Jian Zheng; Xiaochun Meng; Xiangbo Wan
Journal:  Br J Cancer       Date:  2022-04-06       Impact factor: 9.075

Review 3.  Artificial intelligence and imaging for risk prediction of pancreatic cancer: a narrative review.

Authors:  Touseef Ahmad Qureshi; Sehrish Javed; Tabasom Sarmadi; Stephen Jacob Pandol; Debiao Li
Journal:  Chin Clin Oncol       Date:  2022-02-09

4.  An Overview of Artificial Intelligence Applications in Liver and Pancreatic Imaging.

Authors:  Nicolò Cardobi; Alessandro Dal Palù; Federica Pedrini; Alessandro Beleù; Riccardo Nocini; Riccardo De Robertis; Andrea Ruzzenente; Roberto Salvia; Stefania Montemezzi; Mirko D'Onofrio
Journal:  Cancers (Basel)       Date:  2021-04-30       Impact factor: 6.639

5.  System for quantitative evaluation of DAB&H-stained breast cancer biopsy digital images (CHISEL).

Authors:  Lukasz Roszkowiak; Anna Korzynska; Krzysztof Siemion; Jakub Zak; Dorota Pijanowska; Ramon Bosch; Marylene Lejeune; Carlos Lopez
Journal:  Sci Rep       Date:  2021-04-29       Impact factor: 4.379

6.  Deep learning-based pancreas volume assessment in individuals with type 1 diabetes.

Authors:  Raphael Roger; Melissa A Hilmes; Jonathan M Williams; Daniel J Moore; Alvin C Powers; R Cameron Craddock; John Virostko
Journal:  BMC Med Imaging       Date:  2022-01-05       Impact factor: 1.930

7.  Radiomic Features at CT Can Distinguish Pancreatic Cancer from Noncancerous Pancreas.

Authors:  Po-Ting Chen; Dawei Chang; Huihsuan Yen; Kao-Lang Liu; Su-Yun Huang; Holger Roth; Ming-Shiang Wu; Wei-Chih Liao; Weichung Wang
Journal:  Radiol Imaging Cancer       Date:  2021-07

8.  Deep Learning in Pancreatic Tissue: Identification of Anatomical Structures, Pancreatic Intraepithelial Neoplasia, and Ductal Adenocarcinoma.

Authors:  Mark Kriegsmann; Katharina Kriegsmann; Georg Steinbuss; Christiane Zgorzelski; Anne Kraft; Matthias M Gaida
Journal:  Int J Mol Sci       Date:  2021-05-20       Impact factor: 5.923

9.  Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography.

Authors:  Natália Alves; Megan Schuurmans; Geke Litjens; Joeran S Bosma; John Hermans; Henkjan Huisman
Journal:  Cancers (Basel)       Date:  2022-01-13       Impact factor: 6.639

10.  Deep Learning on Enhanced CT Images Can Predict the Muscular Invasiveness of Bladder Cancer.

Authors:  Gumuyang Zhang; Zhe Wu; Lili Xu; Xiaoxiao Zhang; Daming Zhang; Li Mao; Xiuli Li; Yu Xiao; Jun Guo; Zhigang Ji; Hao Sun; Zhengyu Jin
Journal:  Front Oncol       Date:  2021-06-11       Impact factor: 6.244

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.