Abstract
PURPOSE: Thermal ablation is a minimally invasive therapy used for the treatment of small renal cell carcinoma tumors. Treatment success is evaluated on postablation computed tomography (CT) to determine if the ablation zone covered the tumor with an adequate treatment margin (often 5 to 10 mm). Incorrect margin identification can lead to treatment misassessment, resulting in unnecessary additional ablation. Therefore, segmentation of the renal ablation zone (RAZ) is crucial for treatment evaluation. We aim to develop and assess an accurate deep learning workflow for delineating the RAZ from surrounding tissues in kidney CT images. APPROACH: We present an advanced deep learning method using the attention-based U-Net architecture to segment the RAZ. The workflow leverages the strengths of U-Net, enhanced with attention mechanisms, to improve the network's focus on the most relevant parts of the images, resulting in an accurate segmentation. RESULTS: Our model was trained and evaluated on a dataset comprising 76 patients' annotated RAZs in CT images. Analysis demonstrated that the proposed workflow achieved an accuracy = 0.97 ± 0.02 , precision = 0.74 ± 0.23 , recall = 0.73 ± 0.25 , DSC = 0.70 ± 0.22 , Jaccard = 0.58 ± 0.22 , specificity = 0.99 ± 0.01 , Hausdorff distance = 6.70 ± 4.44 mm , and mean absolute boundary distance = 2.67 ± 2.22 mm . CONCLUSIONS: We used 3D CT images with RAZs and, for the first time, addressed deep-learning-based RAZ segmentation using parallel CT images. Our framework can effectively segment RAZs, allowing clinicians to automatically determine the ablation margin, making our tool ready for clinical use. Prediction time is ∼ 1 s per patient, enabling clinicians to perform quick reviews, especially in time-constrained settings.