Dataset for Prostate Cancer Screening Enhanced: Multi-Class Semantic Segmentation and Grading Score with the DARUN Model

Prostate cancer is a major global health challenge, emphasizing the need for better diagnostic methods. This study addresses this need through early detection and advanced multi-class semantic segmentation, specifically focusing on differentiating Gleason patterns 3 and 4 in prostate adenocarcinoma tissues. We utilize innovative data science techniques to potentially improve patient survival rates and address gaps in current cancer diagnosis and treatment. We introduce our publicly available dataset of 100 digitized whole-slide images, segmented into training, validation, and testing sets. To combat class imbalance, techniques like pixel expansion and computed class weights were applied. Our proposed DARUN model architecture incorporates dilated attention and residual convolutional U-Net, enhancing feature map contextual understanding. Extensive hyperparameter fine-tuning optimized training efficiency. Model performance was evaluated using ensemble methods and a Paired t-test. The DARUN models achieved an average Dice coefficient of 0.66 and an accuracy of 0.82 on unseen testing data. Additionally, we performed adenocarcinoma segmentation and grade scoring at the slide level, with pathologist-verified segmented prediction results. An ablation study confirmed the model's generalization and robustness, achieving high Jaccard and Dice coefficients on a separate testing set. Based on a limited dataset, this study suggests the potential of the proposed methodologies and DARUN models as a promising tool for early prostate cancer screening within existing clinical practice.