Predicting clinically significant prostate cancer with a deep learning approach: a multicentre retrospective study.

Litao ZhaoJie BaoXiaomeng QiaoPengfei JinYanting JiZhenkai LiJi ZhangYueting SuLibiao JiJunkang ShenYueyue ZhangLei NiuWanfang XieChunhong HuHailin ShenXiming WangJiangang LiuZhenyu Zhang

Published in: European journal of nuclear medicine and molecular imaging (2022)

Our proposed DL models can be a potential non-invasive auxiliary tool for predicting csPCa. Furthermore, PIDL-CS greatly increased the specificity of csPCa detection compared with PI-RADS assessment by expert radiologists, greatly reducing unnecessary biopsies and helping radiologists achieve a precise diagnosis of csPCa.

Keyphrases

prostate cancer
artificial intelligence
deep learning
radical prostatectomy
machine learning
clinical trial
loop mediated isothermal amplification
convolutional neural network
clinical practice
real time pcr
ultrasound guided
human health
structural basis
quantum dots