The dosimetric impact of deep learning-based auto-segmentation of organs at risk on nasopharyngeal and rectal cancer

• Published in: Radiation oncology (London, England) Vol. 16; no. 1; pp. 113 - 14
• Main Authors: Guo, Hongbo, Wang, Jiazhou, Xia, Xiang, Zhong, Yang, Peng, Jiayuan, Zhang, Zhen, Hu, Weigang
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 23.06.2021; BioMed Central; BMC
• Subjects: Auto-segmentation; Bladder; Cancer; Colorectal cancer; Complications and side effects; Correlation analysis; Deep Learning; Dose-response relationship (Biochemistry); Dosimetric; Dosimetry; Eye lens; Femur; Health risk assessment; Humans; Image Processing, Computer-Assisted - methods; Larynx; Machine learning; Metric space; Nasopharyngeal cancer; Nasopharyngeal carcinoma; Nasopharyngeal Neoplasms - diagnostic imaging; Nasopharyngeal Neoplasms - pathology; Nasopharyngeal Neoplasms - radiotherapy; Nerves; Optimization; Oral cavity; Organs; Organs at Risk - radiation effects; Patients; Planning; Prognosis; Radiation therapy; Radiotherapy Dosage; Radiotherapy Planning, Computer-Assisted - methods; Radiotherapy, Intensity-Modulated - methods; Rectal Neoplasms - diagnostic imaging; Rectal Neoplasms - pathology; Rectal Neoplasms - radiotherapy; Rectum; Segmentation; Technology application; Temporal lobe; Testing; Tomography, X-Ray Computed - methods; Treatment planning; China; United States > US; Deep learning; Dosimetric; Auto-segmentation; Treatment planning
• DOI: 10.1186/s13014-021-01837-y
• ISSN: 1748-717X

To investigate the dosimetric impact of deep learning-based auto-segmentation of organs at risk (OARs) on nasopharyngeal and rectal cancer. Twenty patients, including ten nasopharyngeal carcinoma (NPC) patients and ten rectal cancer patients, who received radiotherapy in our department were enrolled in this study. Two deep learning-based auto-segmentation systems, including an in-house developed system (FD) and a commercial product (UIH), were used to generate two auto-segmented OARs sets (OAR_FD and OAR_UIH). Treatment plans based on auto-segmented OARs and following our clinical requirements were generated for each patient on each OARs sets (Plan_FD and Plan_UIH). Geometric metrics (Hausdorff distance (HD), mean distance to agreement (MDA), the Dice similarity coefficient (DICE) and the Jaccard index) were calculated for geometric evaluation. The dosimetric impact was evaluated by comparing Plan_FD and Plan_UIH to original clinically approved plans (Plan_Manual) with dose-volume metrics and 3D gamma analysis. Spearman's correlation analysis was performed to investigate the correlation between dosimetric difference and geometric metrics. FD and UIH could provide similar geometric performance in parotids, temporal lobes, lens, and eyes (DICE, p > 0.05). OAR_FD had better geometric performance in the optic nerves, oral cavity, larynx, and femoral heads (DICE, p < 0.05). OAR_UIH had better geometric performance in the bladder (DICE, p < 0.05). In dosimetric analysis, both Plan_FD and Plan_UIH had nonsignificant dosimetric differences compared to Plan_Manual for most PTV and OARs dose-volume metrics. The only significant dosimetric difference was the max dose of the left temporal lobe for Plan_FD vs. Plan_Manual (p = 0.05). Only one significant correlation was found between the mean dose of the femoral head and its HD index (R = 0.4, p = 0.01), there is no OARs showed strong correlation between its dosimetric difference and all of four geometric metrics. Deep learning-based OARs auto-segmentation for NPC and rectal cancer has a nonsignificant impact on most PTV and OARs dose-volume metrics. Correlations between the auto-segmentation geometric metric and dosimetric difference were not observed for most OARs.