Assessing the performance of deep learning-based models for prostate cancer segmentation using uncertainty scores
This work addresses prostate cancer diagnosis by providing incremental improvements in segmentation accuracy and uncertainty estimation for medical imaging.
This study compared deep learning models for prostate segmentation from MRI to improve cancer detection workflows, finding that Attention R2U-Net achieved a mean IoU of 76.3% and Dice score of 85% with the lowest uncertainty scores.
This study focuses on comparing deep learning methods for the segmentation and quantification of uncertainty in prostate segmentation from MRI images. The aim is to improve the workflow of prostate cancer detection and diagnosis. Seven different U-Net-based architectures, augmented with Monte-Carlo dropout, are evaluated for automatic segmentation of the central zone, peripheral zone, transition zone, and tumor, with uncertainty estimation. The top-performing model in this study is the Attention R2U-Net, achieving a mean Intersection over Union (IoU) of 76.3% and Dice Similarity Coefficient (DSC) of 85% for segmenting all zones. Additionally, Attention R2U-Net exhibits the lowest uncertainty values, particularly in the boundaries of the transition zone and tumor, when compared to the other models.