Artificial intelligence-based autosegmentation for radiotherapy

Background and Purpose In the field of medicine, artificial intelligence (AI) is emerging as a promising tool. In this paper, we present our experience with the integration of commercially available AI-based software into our radiotherapy contouring workflow. We also analyzed the accuracy of the automated segmentation system. Methods and Materials We analyzed contours of 19 anatomical regions from 24 patients. Comparisons between AI-generated and human-generated contours were made based on volume, Dice coefficients, and contour center of mass shifts. Results The data indicate that there are minimal differences between AI-generated and human-generated contours, such as those of the lungs. The volume differences are relatively minor <1 cm3 (P > 0.05). Nevertheless, for certain organs, such as the small intestine, there can be considerable discrepancies, as the AI delineates the entire organ, in contrast to the RTT. Variations of volumes (bowels) > 300 cm3. The AI completes the contouring process in approximately 2 min, whereas human experts take up to 1 h to create the structures for a given region. Conclusion The workflow can be highly automated and standardised, resulting in significant time savings. A consistent level of quality can be maintained, regardless of RTT experience. The results are comparable to those reported by Doolan et al.