Anatomically guided self-adapting deep neural network for clinically significant prostate cancer detection on bi-parametric MRI: a multi-center study

Abstract

Objective To evaluate the effectiveness of a self-adapting deep network, trained on large-scale bi-parametric MRI data, in detecting clinically significant prostate cancer (csPCa) in external multi-center data from men of diverse demographics; to investigate the advantages of transfer learning. Methods We used two samples: (i) Publicly available multi-center and multi-vendor Prostate Imaging: Cancer AI (PI-CAI) training data, consisting of 1500 bi-parametric MRI scans, along with its unseen validation and testing samples; (ii) In-house multi-center testing and transfer learning data, comprising 1036 and 200 bi-parametric MRI scans. We trained a self-adapting 3D nnU-Net model using probabilistic prostate masks on the PI-CAI data and evaluated its performance on the hidden validation and testing samples and the in-house data with and without transfer learning. We used the area under the receiver operating characteristic (AUROC) curve to evaluate patient-level performance in detecting csPCa. Results The PI-CAI training data had 425 scans with csPCa, while the in-house testing and fine-tuning data had 288 and 50 scans with csPCa, respectively. The nnU-Net model achieved an AUROC of 0.888 and 0.889 on the hidden validation and testing data. The model performed with an AUROC of 0.886 on the in-house testing data, with a slight decrease in performance to 0.870 using transfer learning. Conclusions The state-of-the-art deep learning method using prostate masks trained on large-scale bi-parametric MRI data provides high performance in detecting csPCa in internal and external testing data with different characteristics, demonstrating the robustness and generalizability of deep learning within and across datasets. Clinical relevance statement A self-adapting deep network, utilizing prostate masks and trained on large-scale bi-parametric MRI data, is effective in accurately detecting clinically significant prostate cancer across diverse datasets, highlighting the potential of deep learning methods for improving prostate cancer detection in clinical practice. Graphical Abstract

Development and Validation of a Deep Learning Model to Reduce the Interference of Rectal Artifacts in MRI-based Prostate Cancer Diagnosis

“…In our study, the TPAS model achieved similar or better performance than most DL models published in previous studies ( 12 , 27 – 33 ), which mainly focused on improving model diagnostic performance by modifying the DL structure or increasing the sample size of the training dataset ( 21 ). A systematic review of state-of-the-art DL models for the diagnosis and localization of csPCa using MRI between 2019 and 2022 ( 34 ) reported an average AUC of 0.82 (range: 0.76–0.86) for DL systems in diagnosing csPCa at the patient level.…”

“…Sun et al ( 35 ) proposed a cascade 3D U-Net–based model to detect and localize visible csPCa, demonstrating a patient-level AUC of 0.88. Karagoz et al ( 21 ) trained a self-adapting 3D nnU-Net model with an AUC of 0.89 using the Prostate Imaging: Cancer AI Challenge data ( 13 ). However, these models exclude cases with poor image quality or severe artifacts.…”

“…Categorical variables are presented as percentages and were compared using the χ 2 test. True-positive lesions were predictions that shared a minimum overlap of 0.10 in 3D space with the ground-truth annotation following the challenge and earlier studies ( 13 , 21 ). The interreader agreement of rectal artifact evaluation was assessed using Cohen weighted κ.…”

An Automated Prostate-cancer Prediction System (APPS) Based on Advanced DFO-ConGA2L Model using MRI Imaging Technique

“…It is divided into two areas: the base, which is located adjacent to the bladder, and the apex, which is located adjacent to the ureteral sphincter. Prostate cancer [3] can be diagnosed in a number of methods such as digital rectal examination, PSA test, biopsy, transrectal ultrasound, MRI, genomic tests, CT scan, or bone scan. Screening tests are used for symptoms of urinary tract cancer; however, most men are experiencing persistent inflammation after the test.…”