Using an Artificial Intelligence System “Limbus AI” for Automatic Segmentation of OAR's in Radiotherapy: Evaluation of Effectiveness and Dosimetric Impact

Abstract

Accurate definition of organs at risk and target volumes is a critically important step in the radiotherapy workflow prior to therapy delivery. This activity is time-consuming for the operator, who performs it manually. Self-contouring software based on deep learning has been developed to improve efficiency; in this study, we examined the commercial software Limbus Contour (LC), version 1.5.0 (Limbus AI Inc., Regina, SK, Canada), which exploits deep convolutional neural networks, evaluating its impact on the radiotherapy workflow in three specific pathological sites: head-neck, left breast, and prostate. We compared manual versus automated segmentation on selected organs at risk associated with specific types of treatment, evaluating geometric performance (volume change, Dice Index), dosimetric impact (differences in DVHs), and timing of the two contouring modes. The average Dice Index value obtained was 84%; in particular, the best results were recorded for the lungs, but equally good results were obtained for the bladder, femoral heads, and heart. The greatest time saving, on the other hand, was recorded in head-neck tumors, with a saving of about 80 minutes. Evaluating DVHs, the greatest dosimetric difference was found for prostate cancer in patient 1, where the penile bulb showed an average dose difference, in the two contouring modes, of 73%. The contours and data generated by AI were compared and validated by oncologists in our department, who confirmed that the use of Limbus Contour  helped reduce the inter-operator discrepancies typical of manual contouring. The introduction of this self-contouring software brought an improvement of workflow in Rieti radiotherapy department by significantly reducing procedure time, maintaining high quality of treatments, and reducing variability between operators.