Ohad Kott1, Drew Linsley2, Ali Amin3, Andreas Karagounis2, Carleen Jeffers2, Dragan Golijanin4, Thomas Serre2, Boris Gershman5. 1. Minimally Invasive Urology Institute, The Miriam Hospital, Providence, RI, USA. 2. Carney Institute for Brain Science, Department of Cognitive, Linguistic & Psychological Sciences, Brown University, Providence, RI, USA. 3. Department of Pathology and Laboratory Medicine, The Miriam Hospital, Providence, RI, USA; Warren Alpert Medical School of Brown University, Providence, RI, USA. 4. Minimally Invasive Urology Institute, The Miriam Hospital, Providence, RI, USA; Warren Alpert Medical School of Brown University, Providence, RI, USA; Division of Urology, Rhode Island Hospital and The Miriam Hospital, Providence, RI, USA. 5. Division of Urologic Surgery, Beth Israel Deaconess Medical Center, Boston, MA, USA. Electronic address: bgershma@bidmc.harvard.edu.
Abstract
BACKGROUND: The pathologic diagnosis and Gleason grading of prostate cancer are time-consuming, error-prone, and subject to interobserver variability. Machine learning offers opportunities to improve the diagnosis, risk stratification, and prognostication of prostate cancer. OBJECTIVE: To develop a state-of-the-art deep learning algorithm for the histopathologic diagnosis and Gleason grading of prostate biopsy specimens. DESIGN, SETTING, AND PARTICIPANTS: A total of 85 prostate core biopsy specimens from 25 patients were digitized at 20× magnification and annotated for Gleason 3, 4, and 5 prostate adenocarcinoma by a urologic pathologist. From these virtual slides, we sampled 14803 image patches of 256×256 pixels, approximately balanced for malignancy. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: We trained and tested a deep residual convolutional neural network to classify each patch at two levels: (1) coarse (benign vs malignant) and (2) fine (benign vs Gleason 3 vs 4 vs 5). Model performance was evaluated using fivefold cross-validation. Randomization tests were used for hypothesis testing of model performance versus chance. RESULTS AND LIMITATIONS: The model demonstrated 91.5% accuracy (p<0.001) at coarse-level classification of image patches as benign versus malignant (0.93 sensitivity, 0.90 specificity, and 0.95 average precision). The model demonstrated 85.4% accuracy (p<0.001) at fine-level classification of image patches as benign versus Gleason 3 versus Gleason 4 versus Gleason 5 (0.83 sensitivity, 0.94 specificity, and 0.83 average precision), with the greatest number of confusions in distinguishing between Gleason 3 and 4, and between Gleason 4 and 5. Limitations include the small sample size and the need for external validation. CONCLUSIONS: In this study, a deep learning-based computer vision algorithm demonstrated excellent performance for the histopathologic diagnosis and Gleason grading of prostate cancer. PATIENT SUMMARY: We developed a deep learning algorithm that demonstrated excellent performance for the diagnosis and grading of prostate cancer.
BACKGROUND: The pathologic diagnosis and Gleason grading of prostate cancer are time-consuming, error-prone, and subject to interobserver variability. Machine learning offers opportunities to improve the diagnosis, risk stratification, and prognostication of prostate cancer. OBJECTIVE: To develop a state-of-the-art deep learning algorithm for the histopathologic diagnosis and Gleason grading of prostate biopsy specimens. DESIGN, SETTING, AND PARTICIPANTS: A total of 85 prostate core biopsy specimens from 25 patients were digitized at 20× magnification and annotated for Gleason 3, 4, and 5 prostate adenocarcinoma by a urologic pathologist. From these virtual slides, we sampled 14803 image patches of 256×256 pixels, approximately balanced for malignancy. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: We trained and tested a deep residual convolutional neural network to classify each patch at two levels: (1) coarse (benign vs malignant) and (2) fine (benign vs Gleason 3 vs 4 vs 5). Model performance was evaluated using fivefold cross-validation. Randomization tests were used for hypothesis testing of model performance versus chance. RESULTS AND LIMITATIONS: The model demonstrated 91.5% accuracy (p<0.001) at coarse-level classification of image patches as benign versus malignant (0.93 sensitivity, 0.90 specificity, and 0.95 average precision). The model demonstrated 85.4% accuracy (p<0.001) at fine-level classification of image patches as benign versus Gleason 3 versus Gleason 4 versus Gleason 5 (0.83 sensitivity, 0.94 specificity, and 0.83 average precision), with the greatest number of confusions in distinguishing between Gleason 3 and 4, and between Gleason 4 and 5. Limitations include the small sample size and the need for external validation. CONCLUSIONS: In this study, a deep learning-based computer vision algorithm demonstrated excellent performance for the histopathologic diagnosis and Gleason grading of prostate cancer. PATIENT SUMMARY: We developed a deep learning algorithm that demonstrated excellent performance for the diagnosis and grading of prostate cancer.
Authors: Babak Ehteshami Bejnordi; Mitko Veta; Paul Johannes van Diest; Bram van Ginneken; Nico Karssemeijer; Geert Litjens; Jeroen A W M van der Laak; Meyke Hermsen; Quirine F Manson; Maschenka Balkenhol; Oscar Geessink; Nikolaos Stathonikos; Marcory Crf van Dijk; Peter Bult; Francisco Beca; Andrew H Beck; Dayong Wang; Aditya Khosla; Rishab Gargeya; Humayun Irshad; Aoxiao Zhong; Qi Dou; Quanzheng Li; Hao Chen; Huang-Jing Lin; Pheng-Ann Heng; Christian Haß; Elia Bruni; Quincy Wong; Ugur Halici; Mustafa Ümit Öner; Rengul Cetin-Atalay; Matt Berseth; Vitali Khvatkov; Alexei Vylegzhanin; Oren Kraus; Muhammad Shaban; Nasir Rajpoot; Ruqayya Awan; Korsuk Sirinukunwattana; Talha Qaiser; Yee-Wah Tsang; David Tellez; Jonas Annuscheit; Peter Hufnagl; Mira Valkonen; Kimmo Kartasalo; Leena Latonen; Pekka Ruusuvuori; Kaisa Liimatainen; Shadi Albarqouni; Bharti Mungal; Ami George; Stefanie Demirci; Nassir Navab; Seiryo Watanabe; Shigeto Seno; Yoichi Takenaka; Hideo Matsuda; Hady Ahmady Phoulady; Vassili Kovalev; Alexander Kalinovsky; Vitali Liauchuk; Gloria Bueno; M Milagro Fernandez-Carrobles; Ismael Serrano; Oscar Deniz; Daniel Racoceanu; Rui Venâncio Journal: JAMA Date: 2017-12-12 Impact factor: 56.272
Authors: Jonathan I Epstein; Lars Egevad; Mahul B Amin; Brett Delahunt; John R Srigley; Peter A Humphrey Journal: Am J Surg Pathol Date: 2016-02 Impact factor: 6.394
Authors: Guy Nir; Soheil Hor; Davood Karimi; Ladan Fazli; Brian F Skinnider; Peyman Tavassoli; Dmitry Turbin; Carlos F Villamil; Gang Wang; R Storey Wilson; Kenneth A Iczkowski; M Scott Lucia; Peter C Black; Purang Abolmaesumi; S Larry Goldenberg; Septimiu E Salcudean Journal: Med Image Anal Date: 2018-09-24 Impact factor: 8.545
Authors: Guido Sauter; Stefan Steurer; Till Sebastian Clauditz; Till Krech; Corinna Wittmer; Florian Lutz; Maximilian Lennartz; Tim Janssen; Nayira Hakimi; Ronald Simon; Mareike von Petersdorff-Campen; Frank Jacobsen; Katharina von Loga; Waldemar Wilczak; Sarah Minner; Maria Christina Tsourlakis; Viktoria Chirico; Alexander Haese; Hans Heinzer; Burkhard Beyer; Markus Graefen; Uwe Michl; Georg Salomon; Thomas Steuber; Lars Henrik Budäus; Elena Hekeler; Julia Malsy-Mink; Sven Kutzera; Christoph Fraune; Cosima Göbel; Hartwig Huland; Thorsten Schlomm Journal: Eur Urol Date: 2015-11-02 Impact factor: 20.096
Authors: Guy Nir; Davood Karimi; S Larry Goldenberg; Ladan Fazli; Brian F Skinnider; Peyman Tavassoli; Dmitry Turbin; Carlos F Villamil; Gang Wang; Darby J S Thompson; Peter C Black; Septimiu E Salcudean Journal: JAMA Netw Open Date: 2019-03-01
Authors: Kunal Nagpal; Davis Foote; Yun Liu; Po-Hsuan Cameron Chen; Ellery Wulczyn; Fraser Tan; Niels Olson; Jenny L Smith; Arash Mohtashamian; James H Wren; Greg S Corrado; Robert MacDonald; Lily H Peng; Mahul B Amin; Andrew J Evans; Ankur R Sangoi; Craig H Mermel; Jason D Hipp; Martin C Stumpe Journal: NPJ Digit Med Date: 2019-06-07
Authors: Petronio Augusto de Souza Melo; Carmen Liane Neubarth Estivallet; Miguel Srougi; William Carlos Nahas; Katia Ramos Moreira Leite Journal: Clinics (Sao Paulo) Date: 2021-10-29 Impact factor: 2.365
Authors: Indrani Bhattacharya; Yash S Khandwala; Sulaiman Vesal; Wei Shao; Qianye Yang; Simon J C Soerensen; Richard E Fan; Pejman Ghanouni; Christian A Kunder; James D Brooks; Yipeng Hu; Mirabela Rusu; Geoffrey A Sonn Journal: Ther Adv Urol Date: 2022-10-10