Advancing Kidney, Kidney Tumor, Cyst Segmentation: A Multi-Planner U-Net Approach for the KiTS23 Challenge

Accurate segmentation of kidney tumors in medical images is crucial for effective treatment planning and patient outcomes prediction. The Kidney and Kidney Tumor Segmentation challenge (KiTS23) serves as a platform for evaluating advanced segmentation methods. In this study, we present our approach utilizing a Multi-Planner U-Net for kidney tumor segmentation. Our method combines the U-Net architecture with multiple image planes to enhance spatial information and improve segmentation accuracy. We employed a 3-fold cross-validation technique on the KiTS23 dataset, evaluating Mean Dice Score, precision, and recall metrics. Results indicate promising performance in segmenting Kidney + Tumor + Cyst and Tumor-only classes, while challenges persist in segmenting Tumor + Cyst cases. Our approach demonstrates potential in kidney tumor segmentation, with room for further refinement to address complex coexisting structures.