Clinical evaluation of deep learning-based automatic clinical target volume segmentation: a single-institution multi-site tumor experience.

PURPOSE: The large variability in tumor appearance and shape makes manual delineation of the clinical target volume (CTV) time-consuming, and the results depend on the oncologists' experience. Whereas deep learning techniques have allowed oncologists to automate the CTV delineation, multi-site tumor analysis is often lacking in the literature. This study aimed to evaluate the deep learning models that automatically contour CTVs of tumors at various sites on computed tomography (CT) images from objective and subjective perspectives. METHODS AND MATERIALS: 577 patients were selected for the present study, including nasopharyngeal (n = 34), esophageal (n = 40), breast-conserving surgery (BCS) (left-sided, n = 71; right-sided, n = 71), breast-radical mastectomy (BRM) (left-sided, n = 43; right-sided, n = 37), cervical (radical radiotherapy, n = 45; postoperative, n = 85), prostate (n = 42), and rectal (n = 109) carcinomas. Manually delineated CTV contours by radiation oncologists are served as ground truth. Four models were evaluated: Flexnet, Unet, Vnet, and Segresnet, which are commercially available in the medical product "AccuLearning AI model training platform". The data were divided into the training, validation, and testing set at a ratio of 5:1:4. The geometric metrics, including Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD), were calculated for objective evaluation. For subjective assessment, oncologists rated the segmentation contours of the testing set visually. RESULTS: High correlations were observed between automatic and manual contours. Based on the results of the independent test group, most of the patients achieved satisfactory quantitative results (DSC > 0.8), except for patients with esophageal carcinoma (DSC: 0.62-0.64). The subjective review indicated that 82.65% of predicted CTVs scored either as clinically accepting (8.68%) or requiring minor revision (73.97%), and no patients were scored as rejected. CONCLUSION: This experimental work demonstrated that auto-generated contours could serve as an initial template to help oncologists save time in CTV delineation. The deep learning-based auto-segmentations achieve acceptable accuracy and show the potential to improve clinical efficiency for radiotherapy of a variety of cancer.

A deep learning model for translating CT to ventilation imaging: analysis of accuracy and impact on functional avoidance radiotherapy planning.

PURPOSE: Radiotherapy planning incorporating functional lung images has the potential to reduce pulmonary toxicity. Free-breathing 4DCT-derived ventilation image (CTVI) may help quantify lung function. This study introduces a novel deep-learning model directly translating planning CT images into CTVI. We investigated the accuracy of generated images and the impact on functional avoidance planning. MATERIALS AND METHODS: Paired planning CT and 4DCT scans from 48 patients with NSCLC were randomized to training (n = 41) and testing (n = 7) data sets. The ventilation maps were generated from 4DCT using a Jacobian-based algorithm to provide ground truth labels (CTVI4DCT). A 3D U-Net-based model was trained to map CT to synthetic CTVI (CTVISyn) and validated using fivefold cross-validation. The highest-performing model was applied to the testing set. Spearman's correlation (rs) and Dice similarity coefficient (DSC) determined voxel-wise and functional-wise concordance between CTVI4DCT and CTVISyn. Three plans were designed per patient in the testing set: one clinical plan without CTVI and two functional avoidance plans combined with CTVI4DCT or CTVISyn, aimed at sparing high-functional lungs defined as the top 50% of the percentile ventilation ranges. Dose-volume (DVH) parameters regarding the planning target volume (PTV) and organs at risk (OARs) were recorded. Radiation pneumonitis (RP) risk was estimated using a dose-function (DFH)-based normal tissue complication probability (NTCP) model. RESULTS: CTVISyn showed a mean rs value of 0.65 ± 0.04 compared to CTVI4DCT. Mean DSC values over the top 50% and 60% of ventilation ranges were 0.41 ± 0.07 and 0.52 ± 0.10, respectively. In the test set (n = 7), all patients' RP-risk benefited from CTVI4DCT-guided plans (Riskmean_4DCT_vs_Clinical: 29.24% vs. 49.12%, P = 0.016), and six patients benefited from CTVISyn-guided plans (Riskmean_Syn_vs_Clinical: 31.13% vs. 49.12%, P = 0.022). There were no significant differences in DVH and DFH metrics between CTVISyn and CTVI4DCT-guided plan (P > 0.05). CONCLUSION: Using deep-learning techniques, CTVISyn generated from planning CT exhibited a moderate-to-high correlation with CTVI4DCT. The CTVISyn-guided plans were comparable to the CTVI4DCT-guided plans, effectively reducing pulmonary toxicity in patients while maintaining acceptable plan quality. Further prospective trials are needed to validate these findings.

CT ventilation image-guided helical Tomotherapy at sparing functional lungs for locally advanced lung cancer: analysis of dose-function metrics and the impact on pulmonary toxicity.

PURPOSE: CT ventilation image (CTVI)-guided radiotherapy that selectively avoids irradiating highly-functional lung regions has potential to reduce pulmonary toxicity. Considering Helical TomoTherapy (HT) has higher modulation capabilities, we investigated the capability and characteristic of HT at sparing functional lungs for locally advanced lung cancer. METHODS AND MATERIALS: Pretreatment 4DCT scans were carried out for 17 patients. Local lung volume expansion (or contraction) during inspiration is related to the volume change at a given lung voxel and is used as a surrogate for ventilation. The ventilation maps were generated from two sets of CT images (peak-exhale and peak-inhale) by deformable registration and a Jacobian-based algorithm. Each ventilation map was normalized to percentile images. Six plans were designed for each patient: one anatomical plan without ventilation map and five functional plans incorporating ventilation map which designed to spare varying degrees of high-functional lungs that were defined as the top 10%, 20%, 30%, 40%, and 50% of the percentile ventilation ranges, respectively. The dosimetric and evaluation factors were recorded regarding planning target volume (PTV) and other organs at risk (OARs), with particular attention to the dose delivered to total lung and functional lungs. An established dose-function-based normal tissue complication probability (NTCP) model was used to estimate risk of radiation pneumonitis (RP) for each scenario. RESULTS: Patients were divided into a benefit group (8 patients) and a non-benefit group (9 patients) based on whether the RP-risk of functional plan was lower than that of anatomical plan. The distance between high-ventilated region and PTV, as well as tumor volume had significant differences between the two groups (P < 0.05). For patients in the benefit group, the mean value of fV5, fV10, fV20, and fMLD (functional V5, V10, V20, and mean lung dose, respectively) were significantly lower starting from top 30% functional plan than in anatomical plan (P < 0.05). With expand of avoidance region in functional plans, the dose coverage of PTV is not sacrificed (P > 0.05) but at the cost of increased dose received by OARs. CONCLUSION: Ventilation image-guided HT plans can reduce the dose received by highly-functional lung regions with a range up to top 50% ventilated area. The spatial distribution of ventilation and tumor size were critical factors to better select patients who could benefit from the functional plan.