Clinical evaluation of novel deep learning‐based auto‐segmentation software: Utility and potential pitfalls

Abstract

Abstract Background Accurate contouring of target volumes and organs at risk is critical in radiotherapy. While deep learning (DL) models offer automated contouring, their clinical applicability to real‐world cases containing anatomical variations and artifacts requires rigorous validation. Purpose To evaluate the clinical accuracy and potential vulnerabilities of RatoGuide, novel DL‐based auto‐segmentation software, using a dataset including atypical cases derived from routine clinical practice. Methods This single‐center retrospective study included 69 thoracic and male pelvic cases. The cohort was intentionally selected to encompass diverse anatomies and artifacts (e.g., pacemakers, SpaceOAR implants, artificial femoral head replacements, and unilateral atelectasis). Auto‐contours generated by RatoGuide were compared with expert‐approved manual contours. Performance was evaluated quantitatively using the Dice Similarity Coefficient (DSC) and 95th percentile Hausdorff Distance (HD95), and qualitatively via a 5‐point visual assessment scale by four independent reviewers. Statistical comparisons between cohorts were performed using the Mann‐Whitney U test. Additionally, a dosimetric evaluation was conducted for male pelvic cases to assess clinical impact. Results In typical cases, the software maintained high segmentation accuracy (thorax: mean DSC 0.856, mean HD95 6.89 mm; male pelvis: mean DSC 0.874, mean HD95 4.11 mm). However, performance declined in atypical cohorts (thorax: mean DSC 0.808, p = 0.0457, mean HD95 12.22 mm, p = 0.0002; male pelvis: mean DSC 0.828, p = 0.1620, mean HD95 6.16 mm, p = 0.0075). Notable decreases in accuracy were observed in challenging scenarios, such as artificial femoral head replacements (DSC: 0.754) and unilateral atelectasis (DSC: 0.784). Qualitative assessment revealed that errors were primarily due to anatomical factors and artifacts. Furthermore, the dosimetric evaluation identified one critical false‐negative error where a dose constraint violation was overlooked when the DL contour was used. Conclusions RatoGuide demonstrated favorable performance in typical cases, but accuracy declined in atypical cases with artifacts or altered anatomy. For clinical implementation, rigorous visual verification and manual review by experts are essential, particularly for atypical cases and organs in high‐dose gradient regions.