Evaluating Automatic Segmentation for Swallowing-Related Organs for Head and Neck Cancer.

Purpose: To evaluate the accuracy of deep-learning-based auto-segmentation of the superior constrictor, middle constrictor, inferior constrictor, and larynx in comparison with a traditional multi-atlas-based method. Methods and Materials: One hundred and five computed tomography image datasets from 83 head and neck cancer patients were retrospectively collected and the superior constrictor, middle constrictor, inferior constrictor, and larynx were analyzed for deep-learning versus multi-atlas-based segmentation. Eighty-three computed tomography images (40 diagnostic computed tomography and 43 planning computed tomography) were used for training the convolutional neural network, and for atlas-based model training. The remaining 22 computed tomography datasets were used for validation of the atlas-based auto-segmentation versus deep-learning-based auto-segmentation contours, both of which were compared with the corresponding manual contours. Quantitative measures included Dice similarity coefficient, recall, precision, Hausdorff distance, 95th percentile of Hausdorff distance, and mean surface distance. Dosimetric differences between the auto-generated contours and manual contours were evaluated. Subjective evaluation was obtained from 3 clinical observers to blindly score the autosegmented structures based on the percentage of slices that require manual modification. Results: The deep-learning-based auto-segmentation versus atlas-based auto-segmentation results were compared for the superior constrictor, middle constrictor, inferior constrictor, and larynx. The mean Dice similarity coefficient values for the 4 structures were 0.67, 0.60, 0.65, and 0.84 for deep-learning-based auto-segmentation, whereas atlas-based auto-segmentation has Dice similarity coefficient results at 0.45, 0.36, 0.50, and 0.70, respectively. The mean 95th percentile of Hausdorff distance (cm) for the 4 structures were 0.41, 0.57, 0.59, and 0.54 for deep-learning-based auto-segmentation, but 0.78, 0.95, 0.96, and 1.23 for atlas-based auto-segmentation results, respectively. Similar mean dose differences were obtained from the 2 sets of autosegmented contours compared to manual contours. The dose-volume discrepancies and the average modification rates were higher with the atlas-based auto-segmentation contours. Conclusion: Swallowing-related structures are more accurately generated with DL-based versus atlas-based segmentation when compared with manual contours.

MRI Radiomics for Prediction of Tumor Response and Downstaging in Rectal Cancer Patients after Preoperative Chemoradiation.

PURPOSE: This study aimed to investigate radiomic features extracted from magnetic resonance imaging (MRI) scans performed before and after neoadjuvant chemoradiotherapy (nCRT) in predicting response of locally advanced rectal cancer (LARC). METHODS AND MATERIALS: Thirty-nine patients who underwent nCRT for LARC were included, with 294 radiomic features extracted from MRI that was performed before (pre-CRT) and 6 to 8 weeks after completing nCRT (post-CRT). Based on tumor regression grade (TRG), 26 patients were classified as having a histopathologic good response (GR; TRG 0-1) and 13 as non-GR (TRG 2-3). Tumor downstaging (T-downstaging) occurred in 25 patients. Univariate analyses were performed to assess potential radiomic and delta-radiomic predictors for TRG in pathologic complete response (pCR) versus non-pCR, GR versus non-GR, and T-downstaging. The support vector machine-based multivariate model was used to select the best predictors for TRG and T-downstaging. RESULTS: We identified 13 predictive features for pCR versus non-pCR, 14 for GR versus non-GR, and 16 for T-downstaging. Pre-CRT gray-level run length matrix nonuniformity, pre-CRT neighborhood intensity difference matrix (NIDM) texture strength, and post-CRT NIDM busyness predicted all 3 treatment responses. The best predictor for GR versus non-GR was pre-CRT global minimum combined with clinical N stage in the multivariate analysis. The best predictor for T-downstaging was the combination of pre-CRT gray-level co-occurrence matrix correlation, NIDM-texture strength, and gray-level co-occurrence matrix variance. The pre-CRT, post-CRT, and delta radiomic-based models had no significant difference in predicting all 3 responses. CONCLUSIONS: Pre-CRT MRI, post-CRT MRI, and delta radiomic-based models have the potential to predict tumor response after nCRT in LARC. These data, if validated in larger cohorts, can provide important predictive information to aid in clinical decision making.

Effect and Safety of Radiation Therapy Boost to Extramesorectal Lymph Nodes in Rectal Cancer.

PURPOSE: In rectal cancer, the presence of extramesorectal/lateral pelvic lymph node (LPN) is associated with higher risk of locoregional and distant recurrences. LPNs are not typically resected during a standard total mesorectal excision (TME) procedure, and the optimal management for these patients is controversial. We assessed the safety and efficacy of adding a radiation therapy boost to clinically positive LPN during neoadjuvant chemoradiation therapy for rectal cancer. METHODS AND MATERIALS: We analyzed nonmetastatic, lymph node positive rectal adenocarcinoma patients treated with neoadjuvant chemoradiation therapy followed by TME between May 2011 and February 2018. Patients without LPN involvement received external beam radiation therapy (45 Gy in 25 fractions) to the primary tumor and regional draining lymph node basins followed by a boost (5.4 Gy in 3 fractions) to gross disease. Patients with clinically positive LPN that would not be removed during TME received an additional boost (up to a total dose between 54.0 and 59.4 Gy) to the involved LPNs. We compared locoregional control, overall survival, progression-free survival, and treatment-related toxicity between these 2 groups. RESULTS: Fifty-three patients were included in this analysis with median follow-up of 30.6 months for the LPN- group (n = 41) and 19.9 months for the LPN+ group (n = 12). There was no difference in 3-year overall survival (90.04% vs 83.33%, P = .890) and progression-free survival (80.12% vs 80.21%, P = .529) between the 2 groups. We did not observe any LPN recurrences. There were no differences in rates of acute grade 3+ or chronic toxicities. CONCLUSIONS: Despite the well-documented negative prognostic effect of LPN metastasis, we observed promising outcomes for LPN+ patients treated with an additional radiation boost. Our results suggest that radiation therapy boost to clinically involved, unresected LPN is an effective treatment approach with limited toxicity. Additional studies are needed to optimize treatment strategies for this unique patient subset.