MicroSegNet: A Deep Learning Approach for Prostate Segmentation on Micro-Ultrasound Images

TL;DR

MicroSegNet is a novel transformer-based UNet model that improves prostate segmentation accuracy on high-resolution micro-ultrasound images by focusing on challenging regions during training, outperforming existing methods and human annotators.

Contribution

The paper introduces MicroSegNet, a multi-scale annotation-guided transformer UNet with a novel AG-BCE loss for improved prostate segmentation on micro-US images.

Findings

Achieved a Dice coefficient of 0.939, surpassing state-of-the-art methods.

Reduced Hausdorff distance to 2.02 mm, indicating precise boundary delineation.

Outperformed human annotators with varying experience levels.

Abstract

Micro-ultrasound (micro-US) is a novel 29-MHz ultrasound technique that provides 3-4 times higher resolution than traditional ultrasound, potentially enabling low-cost, accurate diagnosis of prostate cancer. Accurate prostate segmentation is crucial for prostate volume measurement, cancer diagnosis, prostate biopsy, and treatment planning. However, prostate segmentation on micro-US is challenging due to artifacts and indistinct borders between the prostate, bladder, and urethra in the midline. This paper presents MicroSegNet, a multi-scale annotation-guided transformer UNet model designed specifically to tackle these challenges. During the training process, MicroSegNet focuses more on regions that are hard to segment (hard regions), characterized by discrepancies between expert and non-expert annotations. We achieve this by proposing an annotation-guided binary cross entropy (AG-BCE) loss that assigns a larger weight to prediction errors in hard regions and a lower weight to prediction errors in easy regions. The AG-BCE loss was seamlessly integrated into the training process through the utilization of multi-scale deep supervision, enabling MicroSegNet to capture global contextual dependencies and local information at various scales. We trained our model using micro-US images from 55 patients, followed by evaluation on 20 patients. Our MicroSegNet model achieved a Dice coefficient of 0.939 and a Hausdorff distance of 2.02 mm, outperforming several state-of-the-art segmentation methods, as well as three human annotators with different experience levels. Our code is publicly available at https://github.com/mirthAI/MicroSegNet and our dataset is publicly available at https://zenodo.org/records/10475293.