ProstAttention-Net: A deep attention model for prostate cancer segmentation by aggressiveness in MRI scans

ProstAttention-Net: a deep attention model for prostate cancer segmentation by aggressiveness in MRI scans

Audrey Duran (1) , Gaspard Dussert (1) , Olivier Rouvière (2) , Tristan Jaouen (2) , Pierre-Marc Jodoin (3) , Carole Lartizien (1)

1 MYRIAD - Modeling & analysis for medical imaging and Diagnosis
2 Department of Urinary and Vascular Radiology
3 UdeS - Université de Sherbrooke

Multiparametric magnetic resonance imaging (mp-MRI) has shown excellent results in the detection of prostate cancer (PCa). However, characterizing prostate lesions aggressiveness in mp-MRI sequences is impossible in clinical practice, and biopsy remains the reference to determine the Gleason score (GS). In this work, we propose a novel end-to-end multi-class network that jointly segments the prostate gland and cancer lesions with GS group grading. After encoding the information on a latent space, the network is separated in two branches: 1) the first branch performs prostate segmentation 2) the second branch uses this zonal prior as an attention gate for the detection and grading of prostate lesions. The model was trained and validated with a 5-fold cross-validation on an heterogeneous series of 219 MRI exams acquired on three different scanners prior prostatectomy. In the free-response receiver operating characteristics (FROC) analysis for clinically significant lesions (defined as GS > 6) detection, our model achieves 69.0% ±14.5% sensitivity at 2.9 false positive per patient on the whole prostate and 70.8% ±14.4% sensitivity at 1.5 false positive when considering the peripheral zone (PZ) only. Regarding the automatic GS group

Mots clés: Deep Learning; Semantic segmentation; Attention models; Computer-aided detection; Prostate cancer; Magnetic Resonance Imaging

Domaines: Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]; Traitement du signal et de l'image [eess.SP]; Imagerie médicale

Audrey Duran, Gaspard Dussert, Olivier Rouvière, Tristan Jaouen, Pierre-Marc Jodoin, et al.. ProstAttention-Net: A deep attention model for prostate cancer segmentation by aggressiveness in MRI scans. Medical Image Analysis, 2022, 77, pp.102347. ⟨10.1016/j.media.2021.102347⟩. ⟨hal-03704155⟩