Computer-aided diagnosis of prostate cancer on magnetic resonance imaging using a convolutional neural network algorithm

BJU International
Junichiro IshiokaYasuhisa Fujii

Abstract

To develop a computer-aided diagnosis (CAD) algorithm with a deep learning architecture for detecting prostate cancer on magnetic resonance imaging (MRI) to promote global standardisation and diminish variation in the interpretation of prostate MRI. We retrospectively reviewed data from 335 patients with a prostate-specific antigen level of <20 ng/mL who underwent MRI and extended systematic prostate biopsy with or without MRI-targeted biopsy. The data were divided into a training data set (n = 301), which was used to develop the CAD algorithm, and two evaluation data sets (n = 34). A deep convolutional neural network (CNN) was trained using MR images labelled as 'cancer' or 'no cancer' confirmed by the above-mentioned biopsy. Using the CAD algorithm that showed the best diagnostic accuracy with the two evaluation data sets, the data set not used for evaluation was analysed, and receiver operating curve analysis was performed. Graphics processing unit computing required 5.5 h to learn to analyse 2 million images. The time required for the CAD algorithm to evaluate a new image was 30 ms/image. The two algorithms showed area under the curve values of 0.645 and 0.636, respectively, in the validation data sets. The number of patien...Continue Reading

References

Apr 16, 2014·BJU International·Hideki TakeshitaKazunori Kihara
Feb 25, 2015·JAMA : the Journal of the American Medical Association·Howard L McLeod
May 29, 2015·Nature·Yann LeCunGeoffrey Hinton
Oct 3, 2015·European Urology·Jeffrey C WeinrebSadna Verma
Nov 30, 2016·JAMA : the Journal of the American Medical Association·Varun GulshanDale R Webster
Mar 4, 2017·Computer Methods and Programs in Biomedicine·Shuchao PangMehmet A Orgun

❮ Previous
Next ❯

Citations

Nov 14, 2018·Minerva urologica e nefrologica = The Italian journal of urology and nephrology·Zisis KratirasProkar Dasgupta
Dec 6, 2019·Der Radiologe·Charlie Alexander HammTobias Penzkofer
Feb 28, 2020·Medicina·Vlad Cristian MunteanuIoan Coman
Jul 31, 2020·International Journal of Urology : Official Journal of the Japanese Urological Association·Makoto SumitomoRyoichi Shiroki
Sep 18, 2020·Current Opinion in Urology·Sharif HoseinQuoc-Dien Trinh
Aug 24, 2018·International Journal of Urology : Official Journal of the Japanese Urological Association·Takahiko SomaYasuhisa Fujii
Dec 14, 2018·Physics in Medicine and Biology·Anjali BalagopalSteve Jiang
Apr 9, 2019·Biomedical Engineering Letters·Rahul HoodaSanjeev Sofat
Mar 8, 2020·Journal of Translational Medicine·Yuxin LinBairong Shen
Aug 9, 2019·European Radiology Experimental·Renato CuocoloMassimo Imbriaco
Apr 7, 2021·Arkhiv patologii·G V PopovV A Varshavsky
Nov 22, 2020·The Urologic Clinics of North America·Timothy C ChangJoseph C Liao
Sep 4, 2020·Current Opinion in Urology·Enrico CheccucciUNKNOWN Uro-technology and SoMe Working Group of the Young Academic Urologists Working Party of the European Association of Urology
Jan 20, 2020·The American Journal of Medicine·Joseph M Norris, Asif Raza
Jan 20, 2020·The American Journal of Medicine·Vida Abedi, Ramin Zand
Jun 3, 2021·Sensors·Islam R AbdelmaksoudAyman El-Baz
Dec 4, 2021·The British Journal of Radiology·Baris Turkbey, Masoom A Haider

❮ Previous
Next ❯

Related Concepts

Related Feeds

Cancer Imaging

Imaging techniques, including CT and MR, have become essential to tumor detection, diagnosis, and monitoring. Here is the latest research on cancer imaging.