Prostate Segmentation from Ultrasound Images using Residual Fully Convolutional Network
This provides a faster and more straightforward segmentation method for medical professionals in prostate cancer diagnosis, though it appears incremental as it builds on existing network architectures.
The study tackled prostate segmentation in transrectal ultrasound images for cancer diagnosis by proposing a residual fully convolutional network, achieving around 86% Dice Similarity accuracy with minimal datasets and no pre-processing.
Medical imaging based prostate cancer diagnosis procedure uses intra-operative transrectal ultrasound (TRUS) imaging to visualize the prostate shape and location to collect tissue samples. Correct tissue sampling from prostate requires accurate prostate segmentation in TRUS images. To achieve this, this study uses a novel residual connection based fully convolutional network. The advantage of this segmentation technique is that it requires no pre-processing of TRUS images to perform the segmentation. Thus, it offers a faster and straightforward prostate segmentation from TRUS images. Results show that the proposed technique can achieve around 86% Dice Similarity accuracy using only few TRUS datasets.