A Deep Learning-Aided Decision-Support Tool for Precise Prediction of Lymph Node Metastasis in Patients with Prostate Cancer

Background: Accurate identification of pelvic lymph node metastasis (PLNM) in patients with prostate cancer (PCa) is crucial for determining appropriate treatment options. However, there is no clear consensus on the integration of clinicopathological and inaging findings available to predict PLNM. Therefore, we built a Prostate Cancer Risk (PRISK) tool to obtain a precisely informed decision about whether to perform extended pelvic lymph node dissection (ePLND) . Methods: PRISK provides a novel precise risk assessment tool to reduce unnecessary ePLNDs while controlling PLNM missing rate. It was developed in 281 patients and verified in 71 patients by integrating a set of radiologists’ interpretations, clinicopathological factors and newly refined imaging indicators from MR images with radiomics machine-learning and deep learning algorithms. Its clinical applicability was compared with Briganti and Memorial Sloan Kettering Cancer Center (MSKCC) nomograms. Findings: PRISK yielded the best diagnostic performance with areas under the receiver operating characteristic curve (AUC) of 0.935 (95% CI, 0.899-0.961) and 0.935 (95% CI: 0.850-0.980) and in the training/validation and test cohort. PRISK significantly improved risk prediction for prediction of PLNM at threshold probabilities of ePLND ≤ 90% compared to Briganti and MSKCC nomograms. Prospective use of PRISK can help to spare more ePLNDs (63.6% vs 57.7%) at lower cost of missing PLNMs (2.2% vs 3.4%) than Briganti and MSKCC nomograms. Interpretation: PRISK offers a noninvasive clinical biomarker to predict PLNM for patients with PCa. It shows improved accuracy of diagnosis support and reduced overtreatment burdens for patients with findings suggested of PCa. Funding: Contract grant sponsor: Key research and development program of Jiangsu Province; contract grant number: BE2017756 (to Y.D.Z.); Contract grant sponsor: Key Project of the National Natural Science Foundation of China; contract grant number: 61731009 (to G.Y.); Contract grant sponsor: Microscale Magnetic Resonance Platform of East China Normal University and Open Project from Shanghai Key Laboratory of Magnetic Resonance; contract grant number: N2019001 (to G.Y.). Declaration of Interests: The authors who have taken part in this study declared that they do not have anything to disclose regarding funding or conflict of interest with respect to this manuscript. Ethics Approval Statement: This retrospective study involved standard care performed at a single medical institution. Ethics committee approval was granted by the local institutional ethics review board (protocol 2019-SR-396), and the requirement of written informed consent was waived. All procedures involving human participants were performed in accordance with the 1975 Helsinki declaration and its later amendments.