ProsDectNet: Bridging the Gap in Prostate Cancer Detection via Transrectal B-mode Ultrasound Imaging
This work addresses the need for improved prostate cancer targeting in biopsies, which can miss up to 52% of cancers, by developing a computer-aided diagnosis system for use with widely available ultrasound imaging.
The paper tackled the problem of low sensitivity and accuracy in prostate cancer detection using B-mode ultrasound images by proposing ProsDectNet, a multi-task deep learning model that achieved a patient-level ROC-AUC of 82%, sensitivity of 74%, and specificity of 67%, outperforming average expert clinicians.
Interpreting traditional B-mode ultrasound images can be challenging due to image artifacts (e.g., shadowing, speckle), leading to low sensitivity and limited diagnostic accuracy. While Magnetic Resonance Imaging (MRI) has been proposed as a solution, it is expensive and not widely available. Furthermore, most biopsies are guided by Transrectal Ultrasound (TRUS) alone and can miss up to 52% cancers, highlighting the need for improved targeting. To address this issue, we propose ProsDectNet, a multi-task deep learning approach that localizes prostate cancer on B-mode ultrasound. Our model is pre-trained using radiologist-labeled data and fine-tuned using biopsy-confirmed labels. ProsDectNet includes a lesion detection and patch classification head, with uncertainty minimization using entropy to improve model performance and reduce false positive predictions. We trained and validated ProsDectNet using a cohort of 289 patients who underwent MRI-TRUS fusion targeted biopsy. We then tested our approach on a group of 41 patients and found that ProsDectNet outperformed the average expert clinician in detecting prostate cancer on B-mode ultrasound images, achieving a patient-level ROC-AUC of 82%, a sensitivity of 74%, and a specificity of 67%. Our results demonstrate that ProsDectNet has the potential to be used as a computer-aided diagnosis system to improve targeted biopsy and treatment planning.