Evaluation of different algorithms for automatic segmentation of head-and-neck lymph nodes on CT images.

PURPOSE: To investigate the performance of 4 atlas-based (multi-ABAS) and 2 deep learning (DL) solutions for head-and-neck (HN) elective nodes (CTVn) automatic segmentation (AS) on CT images. MATERIAL AND METHODS: Bilateral CTVn levels of 69 HN cancer patients were delineated on contrast-enhanced planning CT. Ten and 49 patients were used for atlas library and for training a mono-centric DL model, respectively. The remaining 20 patients were used for testing. Additionally, three commercial multi-ABAS methods and one commercial multi-centric DL solution were investigated. Quantitative evaluation was assessed using volumetric Dice Similarity Coefficient (DSC) and 95-percentile Hausdorff distance (HD95%). Blind evaluation was performed for 3 solutions by 4 physicians. One recorded the time needed for manual corrections. A dosimetric study was finally conducted using automated planning. RESULTS: Overall DL solutions had better DSC and HD95% results than multi-ABAS methods. No statistically significant difference was found between the 2 DL solutions. However, the contours provided by multi-centric DL solution were preferred by all physicians and were also faster to correct (1.1 min vs 4.17 min, on average). Manual corrections for multi-ABAS contours took on average 6.52 min Overall, decreased contour accuracy was observed from CTVn2 to CTVn3 and to CTVn4. Using the AS contours in treatment planning resulted in underdosage of the elective target volume. CONCLUSION: Among all methods, the multi-centric DL method showed the highest delineation accuracy and was better rated by experts. Manual corrections remain necessary to avoid elective target underdosage. Finally, AS contours help reducing the workload of manual delineation task.

Comparison of atlas-based and deep learning methods for organs at risk delineation on head-and-neck CT images using an automated treatment planning system.

BACKGROUND AND PURPOSE: To investigate the performance of head-and-neck (HN) organs-at-risk (OAR) automatic segmentation (AS) using four atlas-based (ABAS) and two deep learning (DL) solutions. MATERIAL AND METHODS: All patients underwent iodine contrast-enhanced planning CT. Fourteen OAR were manually delineated. DL.1 and DL.2 solutions were trained with 63 mono-centric patients and > 1000 multi-centric patients, respectively. Ten and 15 patients with varied anatomies were selected for the atlas library and for testing, respectively. The evaluation was based on geometric indices (DICE coefficient and 95th percentile-Hausdorff Distance (HD95%)), time needed for manual corrections and clinical dosimetric endpoints obtained using automated treatment planning. RESULTS: Both DICE and HD95% results indicated that DL algorithms generally performed better compared with ABAS algorithms for automatic segmentation of HN OAR. However, the hybrid-ABAS (ABAS.3) algorithm sometimes provided the highest agreement to the reference contours compared with the 2 DL. Compared with DL.2 and ABAS.3, DL.1 contours were the fastest to correct. For the 3 solutions, the differences in dose distributions obtained using AS contours and AS + manually corrected contours were not statistically significant. High dose differences could be observed when OAR contours were at short distances to the targets. However, this was not always interrelated. CONCLUSION: DL methods generally showed higher delineation accuracy compared with ABAS methods for AS segmentation of HN OAR. Most ABAS contours had high conformity to the reference but were more time consuming than DL algorithms, especially when considering the computing time and the time spent on manual corrections.

Evaluation of fully automated a priori MCO treatment planning in VMAT for head-and-neck cancer.

PURPOSE: Automated planning techniques aim to reduce manual planning time and inter-operator variability without compromising the plan quality which is particularly challenging for head-and-neck (HN) cancer radiotherapy. The objective of this study was to evaluate the performance of an a priori-multicriteria plan optimization algorithm on a cohort of HN patients. METHODS: A total of 14 nasopharyngeal carcinoma (upper-HN) and 14 "middle-lower indications" (lower-HN) previously treated in our institution were enrolled in this study. Automatically generated plans (autoVMAT) were compared to manual VMAT or Helical Tomotherapy planning (manVMAT-HT) by assessing differences in dose delivered to targets and organs at risk (OARs), calculating plan quality indexes (PQIs) and performing blinded comparisons by clinicians. Quality control of the plans and measurements of the delivery times were also performed. RESULTS: For the 14 lower-HN patients, with equivalent planning target volume (PTV) dosimetric criteria and dose homogeneity, significant decrease in the mean doses to the oral cavity, esophagus, trachea and larynx were observed for autoVMAT compared to manVMAT-HT. Regarding the 14 upper-HN cases, the PTV coverage was generally significantly superior for autoVMAT which was also confirmed with higher calculated PQIs on PTVs for 13 out of 14 patients, whereas PQIs calculated on OARs were generally equivalent. Number of MUs and total delivery time were significantly higher for autoVMAT compared to manVMAT. All plans were considered clinically acceptable by clinicians. CONCLUSIONS: Overall superiority of autoVMAT compared to manVMAT-HT plans was demonstrated for HN cancer. The obtained plans were operator-independent and required no post-optimization or manual intervention.