3D-Vision-Transformer Stacking Ensemble for Assessing Prostate Cancer Aggressiveness from T2w Images

Author:

Pachetti Eva12ORCID,Colantonio Sara1ORCID

Affiliation:

1. “Alessandro Faedo” Institute of Information Science and Technologies (ISTI), National Research Council of Italy (CNR), 56127 Pisa, Italy

2. Department of Information Engineering (DII), University of Pisa, 56122 Pisa, Italy

Abstract

Vision transformers represent the cutting-edge topic in computer vision and are usually employed on two-dimensional data following a transfer learning approach. In this work, we propose a trained-from-scratch stacking ensemble of 3D-vision transformers to assess prostate cancer aggressiveness from T2-weighted images to help radiologists diagnose this disease without performing a biopsy. We trained 18 3D-vision transformers on T2-weighted axial acquisitions and combined them into two- and three-model stacking ensembles. We defined two metrics for measuring model prediction confidence, and we trained all the ensemble combinations according to a five-fold cross-validation, evaluating their accuracy, confidence in predictions, and calibration. In addition, we optimized the 18 base ViTs and compared the best-performing base and ensemble models by re-training them on a 100-sample bootstrapped training set and evaluating each model on the hold-out test set. We compared the two distributions by calculating the median and the 95% confidence interval and performing a Wilcoxon signed-rank test. The best-performing 3D-vision-transformer stacking ensemble provided state-of-the-art results in terms of area under the receiving operating curve (0.89 [0.61–1]) and exceeded the area under the precision–recall curve of the base model of 22% (p < 0.001). However, it resulted to be less confident in classifying the positive class.

Funder

European Union’s Horizon 2020 research and innovation program

Regional Project PAR FAS Tuscany—NAVIGATOR

Publisher

MDPI AG

Subject

Bioengineering

Reference49 articles.

1. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries;Sung;CA Cancer J. Clin.,2021

2. Leslie, S.W., Soon-Sutton, T.L., Sajjad, H., and Siref, L.E. (2022). Prostate Cancer, StatPearls Publishing.

3. Ng, M., and Baradhi, K.M. (2022). Benign Prostatic Hyperplasia, StatPearls Publishing.

4. Prostate Imaging Reporting and Data System Version 2.1: 2019 Update of Prostate Imaging Reporting and Data System Version 2;Turkbey;Eur. Urol.,2019

5. International Society of Urological Pathology (ISUP) grading of prostate cancer—An ISUP consensus on contemporary grading;Egevad;APMIS Acta Pathol. Microbiol. Immunol. Scand.,2016

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3