Pretreatment information-aided automatic segmentation for online magnetic resonance imaging-guided prostate radiotherapy.

BACKGROUND: It is necessary to contour regions of interest (ROIs) for online magnetic resonance imaging (MRI)-guided adaptive radiotherapy (MRIgART). These updated contours are used for online replanning to obtain maximum dosimetric benefits. Contouring can be accomplished using deformable image registration (DIR) and deep learning (DL)-based autosegmentation methods. However, these methods may require considerable manual editing and thus prolong treatment time. PURPOSE: The present study aimed to improve autosegmentation performance by integrating patients' pretreatment information in a DL-based segmentation algorithm. It is expected to improve the efficiency of current MRIgART process. METHODS: Forty patients with prostate cancer were enrolled retrospectively. The online adaptive MR images, patient-specific planning computed tomography (CT), and contours in CT were used for segmentation. The deformable registration of planning CT and MR images was performed first to obtain a deformable CT and corresponding contours. A novel DL network, which can integrate such patient-specific information (deformable CT and corresponding contours) into the segmentation task of MR images was designed. We performed a four-fold cross-validation for the DL models. The proposed method was compared with DIR and DL methods on segmentation of prostate cancer. The ROIs included the clinical target volume (CTV), bladder, rectum, left femur head, and right femur head. Dosimetric parameters of automatically generated ROIs were evaluated using a clinical treatment planning system. RESULTS: The proposed method enhanced the segmentation accuracy of conventional procedures. Its mean value of the dice similarity coefficient (93.5%) over the five ROIs was higher than both DIR (87.5%) and DL (87.2%). The number of patients (n = 40) that required major editing using DIR, DL, and our method were 12, 18, and 7 (CTV); 17, 4, and 1 (bladder); 8, 11, and 5 (rectum); 2, 4, and 1 (left femur head); and 3, 7, and 1 (right femur head), respectively. The Spearman rank correlation coefficient of dosimetry parameters between the proposed method and ground truth was 0.972 ± 0.040, higher than that of DIR (0.897 ± 0.098) and DL (0.871 ± 0.134). CONCLUSION: This study proposed a novel method that integrates patient-specific pretreatment information into DL-based segmentation algorithm. It outperformed baseline methods, thereby improving the efficiency and segmentation accuracy in adaptive radiotherapy.

Efficient segmentation using domain adaptation for MRI-guided and CBCT-guided online adaptive radiotherapy.

BACKGROUND: Delineation of regions of interest (ROIs) is important for adaptive radiotherapy (ART) but it is also time consuming and labor intensive. AIM: This study aims to develop efficient segmentation methods for magnetic resonance imaging-guided ART (MRIgART) and cone-beam computed tomography-guided ART (CBCTgART). MATERIALS AND METHODS: MRIgART and CBCTgART studies enrolled 242 prostate cancer patients and 530 nasopharyngeal carcinoma patients, respectively. A public dataset of CBCT from 35 pancreatic cancer patients was adopted to test the framework. We designed two domain adaption methods to learn and adapt the features from planning computed tomography (pCT) to MRI or CBCT modalities. The pCT was transformed to synthetic MRI (sMRI) for MRIgART, while CBCT was transformed to synthetic CT (sCT) for CBCTgART. Generalized segmentation models were trained with large popular data in which the inputs were sMRI for MRIgART and pCT for CBCTgART. Finally, the personalized models for each patient were established by fine-tuning the generalized model with the contours on pCT of that patient. The proposed method was compared with deformable image registration (DIR), a regular deep learning (DL) model trained on the same modality (DL-regular), and a generalized model in our framework (DL-generalized). RESULTS: The proposed method achieved better or comparable performance. For MRIgART of the prostate cancer patients, the mean dice similarity coefficient (DSC) of four ROIs was 87.2%, 83.75%, 85.36%, and 92.20% for the DIR, DL-regular, DL-generalized, and proposed method, respectively. For CBCTgART of the nasopharyngeal carcinoma patients, the mean DSC of two target volumes were 90.81% and 91.18%, 75.17% and 58.30%, for the DIR, DL-regular, DL-generalized, and the proposed method, respectively. For CBCTgART of the pancreatic cancer patients, the mean DSC of two ROIs were 61.94% and 61.44%, 63.94% and 81.56%, for the DIR, DL-regular, DL-generalized, and the proposed method, respectively. CONCLUSION: The proposed method utilizing personalized modeling improved the segmentation accuracy of ART.

Improving accelerated 3D imaging in MRI-guided radiotherapy for prostate cancer using a deep learning method.

PURPOSE: This study was to improve image quality for high-speed MR imaging using a deep learning method for online adaptive radiotherapy in prostate cancer. We then evaluated its benefits on image registration. METHODS: Sixty pairs of 1.5 T MR images acquired with an MR-linac were enrolled. The data included low-speed, high-quality (LSHQ), and high-speed low-quality (HSLQ) MR images. We proposed a CycleGAN, which is based on the data augmentation technique, to learn the mapping between the HSLQ and LSHQ images and then generate synthetic LSHQ (synLSHQ) images from the HSLQ images. Five-fold cross-validation was employed to test the CycleGAN model. The normalized mean absolute error (nMAE), peak signal-to-noise ratio (PSNR), structural similarity index measurement (SSIM), and edge keeping index (EKI) were calculated to determine image quality. The Jacobian determinant value (JDV), Dice similarity coefficient (DSC), and mean distance to agreement (MDA) were used to analyze deformable registration. RESULTS: Compared with the LSHQ, the proposed synLSHQ achieved comparable image quality and reduced imaging time by ~ 66%. Compared with the HSLQ, the synLSHQ had better image quality with improvement of 57%, 3.4%, 26.9%, and 3.6% for nMAE, SSIM, PSNR, and EKI, respectively. Furthermore, the synLSHQ enhanced registration accuracy with a superior mean JDV (6%) and preferable DSC and MDA values compared with HSLQ. CONCLUSION: The proposed method can generate high-quality images from high-speed scanning sequences. As a result, it shows potential to shorten the scan time while ensuring the accuracy of radiotherapy.

Deep learning framework to improve the quality of cone-beam computed tomography for radiotherapy scenarios.

BACKGROUND: The application of cone-beam computed tomography (CBCT) in image-guided radiotherapy and adaptive radiotherapy remains limited due to its poor image quality. PURPOSE: In this study, we aim to develop a deep learning framework to generate high-quality CBCT images for therapeutic applications. METHODS: The synthetic CT (sCT) generation from the CBCT was proposed using a transformer-based network with a hybrid loss function. The network was trained and validated using the data from 176 patients to produce a general model that can be extensively applied to enhance CBCT images. After the first therapy, each patient can receive paired CBCT/planning CT (pCT) scans, and the obtained data were used to fine-tune the general model for further improvement. For subsequent treatment, a patient-specific, personalized model was made available. In total, 34 patients were examined for general model testing, and another six patients who underwent rescanned pCT scan were used for personalized model training and testing. RESULTS: The general model decreased the mean absolute error (MAE) from 135 HU to 59 HU as compared to the CBCT. The hybrid loss function demonstrated superior performance in CT number correction and noise/artifacts reduction. The proposed transformer-based network also showed superior power in CT number correction compared to the classical convolutional neural network. The personalized model showed improvement based on the general model in some details, and the MAE was reduced from 59 HU (for the general model) to 57 HU (p < 0.05 Wilcoxon signed-rank test). CONCLUSION: We established a deep learning framework based on transformer for clinical needs. The deep learning model demonstrated potential for continuous improvement with the help of a suggested personalized training strategy compatible with the clinical workflow.

Association of current hepatitis B virus infection with mortality in adults with sepsis.

This study aimed to determine the impact of current hepatitis B virus (HBV) infection on patients hospitalised with sepsis. This was a retrospective cohort study. Patients from three medical centres in Suzhou from 10 January 2016 to 23 July 2022 participated in this study. Demographic characteristics and clinical characteristics were collected. A total of 945 adult patients with sepsis were included. The median age was 66.0 years, 68.6% were male, 13.1% presented with current HBV infection, and 34.9% of all patients died. In the multivariable-adjusted Cox model, patients with current HBV infection had significantly higher mortality than those without (hazard ratio (HR) 1.50, 95% confidence interval (CI) 1.11-2.02). A subgroup analysis showed that being infected with HBV significantly increased in-hospital mortality in patients younger than 65 years old (HR 1.74, 95% CI 1.16-2.63), whereas no significant impact was observed in patients ≥65 years. The propensity score-matched case-control analysis showed that the rate of septic shock (91.4% vs. 62.1%, P < 0.001) and in-hospital mortality (48.3% vs. 35.3%, P = 0.045) were much higher in the propensity score-matched HBV infection group compared with the control group. In conclusion, current HBV infection was associated with mortality in adults with sepsis.

A projection-domain correction method in CBCT reconstruction for head and neck radiotherapy using cycle-GAN and nonlocal means filter.

BACKGROUND: In radiation treatments for head and neck tumors, cone-beam computed tomography (CBCT) is employed for patient positioning and dose calculation of adaptive radiotherapy. However, the quality of CBCT is degraded by the scatter and noise, majorly impacting the accuracy of patient positioning and dose calculation. PURPOSE: To improve the quality of CBCT for patients with head and neck cancer, a projection-domain CBCT correction method was proposed using a cycle-consistent generative adversarial network (cycle-GAN) and a nonlocal means filter (NLMF) based on a reference digitally reconstructed radiograph (DRR). METHODS: A cycle-GAN was initially trained to learn mapping from CBCT projections to a DRR using the data obtained from 30 patients. For each patient, 671 CBCT projections were measured for CBCT reconstruction. Moreover, 360 Digital Reconstructed Radiographs (DRR) were computed from each patient's planning computed tomography (CT), whose projection angles ranged from 0° to 359° with an interval of 1°. By applying the trained generator of the cycle-GAN to the unseen CBCT projection, a synthetic DRR with considerably less scatter was obtained. However, annular artifacts were observed in the CBCT reconstructed with synthetic DRR. To address this issue, a NLMF based on reference DRR was used to further correct the synthetic DRR, which corrected the synthetic DRR using the calculated DRR as a reference image. Finally, the CBCT with no annular artifact and little noise was reconstructed with the corrected synthetic DRR. The proposed method was tested using the data of six patients. The corrected synthetic DRR and CBCT were compared with the corresponding real DRR and CT images. The structural preservation ability of the proposed method was evaluated using the Dice coefficients of the automatically extracted nasal cavity. Moreover, the image quality of CBCT corrected with the proposed method was objectively assessed with an five-point human scoring system and compared with CT, original CBCT and CBCT corrected with other strategies. RESULTS: The mean absolute value (MAE) of the relative error between the corrected synthetic and real DRR was <8%. The MAE between the corrected CBCT and corresponding CT was <30 HU. Moreover, the Dice coefficient of nasal cavity between the corrected CBCT image and the original image exceeded 98.8 for all the patients. Last but not least, the objective assessment of image quality showed the proposed method had an average score of 4.2 in overall image quality, which was higher than that of the original CBCT, CBCT reconstructed with synthetic DRR, and CBCT reconstructed with projections filtered with NLMF only. CONCLUSIONS: The proposed method can considerably improve the CBCT image quality with little anatomical distortion, improving the accuracy of radiotherapy for head and neck patients.

Combining distance and anatomical information for deep-learning based dose distribution predictions for nasopharyngeal cancer radiotherapy planning.

Purpose: Deep-learning effectively predicts dose distributions in knowledge-based radiotherapy planning. Using anatomical information that includes a structure map and computed tomography (CT) data as input has been proven to work well. The minimum distance from each voxel in normal structures to planning target volume (DPTV) closely affects each voxel's dose. In this study, we combined DPTV and anatomical information as input for a deep-learning-based dose-prediction network to improve performance. Materials and methods: One hundred patients who underwent volumetric-modulated arc therapy for nasopharyngeal cancer were selected in this study. The prediction model based on a residual network had DPTV maps, structure maps, and CT as inputs and the corresponding dose distribution maps as outputs. The performances of the combined distance and anatomical information (COM) model and the traditional anatomical (ANAT) model with two-channel inputs (structure maps and CT) were compared. A 10-fold cross validation was performed to separately train and test the COM and ANAT models. The voxel-based mean error (ME), mean absolute error (MAE), dosimetric parameters, and dice similarity coefficient (DSC) of isodose volumes were used for modeling evaluation. Results: The mean MAE of the body volume of the COM model were 4.89 ± 1.35%, highly significantly lower than those for the ANAT model of 5.07 ± 1.37% (p<0.001). The ME values of the body for the 2-type models were similar (p >0.05). The mean DSC values of the isodose volumes in the range of 60 Gy were all better in the COM model (p<0.05), and there were highly significant differences between 10 Gy and 55 Gy (p<0.001). For most organs at risk, the ME, MAE, and dosimetric parameters predicted by both models were concurrent with the ground truth values except the MAE values of the pituitary and optic chiasm in the ANAT model and the average mean dose of the right parotid in the ANAT model. Conclusions: The COM model outperformed the ANAT model and could improve automated planning with statistically highly significant differences.

T4b Sinonasal Squamous Cell Carcinoma: Surgery Plus Radiotherapy May Contribute to Prolonged Survival.

PURPOSE: To determine oncologic outcomes for patients with T4b sinonasal squamous cell carcinoma (SNSCC) treated with either surgery plus radiotherapy or definitive radiotherapy. MATERIALS AND METHODS: Between January 1999 and December 2016, 85 patients with T4b SNSCC were analyzed retrospectively, there were 54 who received surgery plus radiotherapy (S + RT group) ± chemotherapy and 31 with definitive radiotherapy (RT group) ± chemotherapy. A 1: 2 propensity score matching (PSM) was performed to balance clinical factors and match patients. Kaplan-Meier method and Cox proportional hazard model were used to determine risk factors on survival outcomes. RESULTS: The median follow-up time was 76.7 months. The cumulative rates of locoregional control (LRC), distant metastasis-free survival (DMFS), cancer-specific survival (CSS), and overall survival (OS) at 5 years for entire cohort were 44.6%, 33.1%, 38.8%, and 33.9% respectively. After PSM, a total of 50 patients in S + RT group and 25 patients in RT group were analyzed. The 5-year LRC, DMFS, CSS, and OS between S + RT and RT group were 58.6% versus 27.5% (p = 0.035), 42.8% versus 20.0% (p = 0.006), 50.3% versus 22.0% (p = 0.005), 44.5% veruss 20.0% (p = 0.004). The 5-year survival rates with orbital retention between groups were 32.7% and 15.0%, p = 0.080. Multivariate Cox analysis revealed non-surgical therapy (HR = 3.678, 95%CI 1.951-6.933) and invasion of cranial nerves (other than maxillary division of trigeminal nerves) (HR = 2.596, 95%CI 1.217-5.535) were associated with decreased OS. CONCLUSION: The inclusion of surgery in the multimodal management of T4b SNSCC might confer a survival benefit. Further prospective studies comparing the oncologic outcomes of S + RT with RT are warranted. LEVEL OF EVIDENCE: 3 Laryngoscope, 133:2222-2231, 2023.

A more effective CT synthesizer using transformers for cone-beam CT-guided adaptive radiotherapy.

Purpose: The challenge of cone-beam computed tomography (CBCT) is its low image quality, which limits its application for adaptive radiotherapy (ART). Despite recent substantial improvement in CBCT imaging using the deep learning method, the image quality still needs to be improved for effective ART application. Spurred by the advantages of transformers, which employs multi-head attention mechanisms to capture long-range contextual relations between image pixels, we proposed a novel transformer-based network (called TransCBCT) to generate synthetic CT (sCT) from CBCT. This study aimed to further improve the accuracy and efficiency of ART. Materials and methods: In this study, 91 patients diagnosed with prostate cancer were enrolled. We constructed a transformer-based hierarchical encoder-decoder structure with skip connection, called TransCBCT. The network also employed several convolutional layers to capture local context. The proposed TransCBCT was trained and validated on 6,144 paired CBCT/deformed CT images from 76 patients and tested on 1,026 paired images from 15 patients. The performance of the proposed TransCBCT was compared with a widely recognized style transferring deep learning method, the cycle-consistent adversarial network (CycleGAN). We evaluated the image quality and clinical value (application in auto-segmentation and dose calculation) for ART need. Results: TransCBCT had superior performance in generating sCT from CBCT. The mean absolute error of TransCBCT was 28.8 ± 16.7 HU, compared to 66.5 ± 13.2 for raw CBCT, and 34.3 ± 17.3 for CycleGAN. It can preserve the structure of raw CBCT and reduce artifacts. When applied in auto-segmentation, the Dice similarity coefficients of bladder and rectum between auto-segmentation and oncologist manual contours were 0.92 and 0.84 for TransCBCT, respectively, compared to 0.90 and 0.83 for CycleGAN. When applied in dose calculation, the gamma passing rate (1%/1 mm criterion) was 97.5% ± 1.1% for TransCBCT, compared to 96.9% ± 1.8% for CycleGAN. Conclusions: The proposed TransCBCT can effectively generate sCT for CBCT. It has the potential to improve radiotherapy accuracy.

A two-step method to improve image quality of CBCT with phantom-based supervised and patient-based unsupervised learning strategies.

Objective.In this study, we aimed to develop deep learning framework to improve cone-beam computed tomography (CBCT) image quality for adaptive radiation therapy (ART) applications.Approach.Paired CBCT and planning CT images of 2 pelvic phantoms and 91 patients (15 patients for testing) diagnosed with prostate cancer were included in this study. First, well-matched images of rigid phantoms were used to train a U-net, which is the supervised learning strategy to reduce serious artifacts. Second, the phantom-trained U-net generated intermediate CT images from the patient CBCT images. Finally, a cycle-consistent generative adversarial network (CycleGAN) was trained with intermediate CT images and deformed planning CT images, which is the unsupervised learning strategy to learn the style of the patient images for further improvement. When testing or applying the trained model on patient CBCT images, the intermediate CT images were generated from the original CBCT image by U-net, and then the synthetic CT images were generated by the generator of CycleGAN with intermediate CT images as input. The performance was compared with conventional methods (U-net/CycleGAN alone trained with patient images) on the test set.Results.The proposed two-step method effectively improved the CBCT image quality to the level of CT scans. It outperformed conventional methods for region-of-interest contouring and HU calibration, which are important to ART applications. Compared with the U-net alone, it maintained the structure of CBCT. Compared with CycleGAN alone, our method improved the accuracy of CT number and effectively reduced the artifacts, making it more helpful for identifying the clinical target volume.Significance.This novel two-step method improves CBCT image quality by combining phantom-based supervised and patient-based unsupervised learning strategies. It has immense potential to be integrated into the ART workflow to improve radiotherapy accuracy.

Deep learning improves image quality and radiomics reproducibility for high-speed four-dimensional computed tomography reconstruction.

BACKGROUND AND PURPOSE: Hybrid iterative reconstruction (HIR) is the most commonly used algorithm for four-dimensional computed tomography (4DCT) reconstruction due to its high speed. However, the image quality is worse than that of model-based iterative reconstruction (MIR). Different reconstruction methods affect the stability of radiomics features. Herein, we developed a deep learning method to improve the quality and radiomics reproducibility of the high-speed reconstruction. MATERIALS AND METHODS: The 4DCT images of 70 patients were reconstructed using both the HIR and MIR algorithms. A cycle-consistent adversarial network was adopted to learn the mapping from HIR to MIR, and then generate synthetic MIR (sMIR) images from HIR. The performance was evaluated using the testing set (10 patients). RESULTS: The total reconstruction times for the HIR, MIR, and proposed sMIR images were approximately 2.5, 15, and 3.1 mins, respectively. The quality of sMIR images was close to that of MIR and was superior to that of HIR images, with noise reduced by 45-77% and contrast-to-noise ratio improved by 91-296%. The concordance correlation coefficients (CCC) of radiomic features improved from 0.89 ± 0.15 for HIR to 0.97 ± 0.07 for the proposed sMIR. The percentage of reproducible features (CCC ≥ 0.85) increased from 76.08% for HIR to 95.86% for sMIR, with an improvement of 19.78%. CONCLUSION: Compared to existing HIR algorithm, the proposed method improves the image quality and radiomics reproducibility of 4DCT images under high-speed reconstruction. It is computationally efficient and has potential to be integrated into any CT system.

A feasible method to evaluate deformable image registration with deep learning-based segmentation.

PURPOSE: We have developed a feasible method to evaluate deformable image registration using deep learning (DL)-based segmentation. METHODS: Eighty patients with nasopharyngeal carcinoma were enrolled in this study. Two sets of fixed and moving computed tomography images acquired from each patient were input into the DL segmentation model to generate nine anatomic regions of interest (ROIs) separately and automatically. The ROIs generated in moving images were transferred to the fixed images using the registration transformation metric. The registration evaluation indexes, including the Dice similarity coefficient, derived from 60 well-registrated cases were then used to develop criteria for decision making. A double-blind study was performed to test the proposed method on quality assurance (QA) for image registration on a new test data set of 20 cases. RESULTS: The values of evaluation indexes generated by our automated evaluation method were quite consistent with those from the manual method; however, the proposed method could save about 116 min per patient on average. The QA method achieved promising image registration error detection, with the following metrics for the nine ROIs: balanced accuracy, 0.946 ± 0.029; sensitivity, 0.959 ± 0.021; and specificity, 0.933 ± 0.050. CONCLUSIONS: The proposed method could potentially evaluate the deformable registration accuracy of specific areas. The preliminary NPC result shows that it has consistent performance with the conventional evaluation method with higher efficiency.

A deep-learning method for generating synthetic kV-CT and improving tumor segmentation for helical tomotherapy of nasopharyngeal carcinoma.

Objective:Megavoltage computed tomography (MV-CT) is used for setup verification and adaptive radiotherapy in tomotherapy. However, its low contrast and high noise lead to poor image quality. This study aimed to develop a deep-learning-based method to generate synthetic kilovoltage CT (skV-CT) and then evaluate its ability to improve image quality and tumor segmentation.Approach:The planning kV-CT and MV-CT images of 270 patients with nasopharyngeal carcinoma (NPC) treated on an Accuray TomoHD system were used. An improved cycle-consistent adversarial network which used residual blocks as its generator was adopted to learn the mapping between MV-CT and kV-CT and then generate skV-CT from MV-CT. A Catphan 700 phantom and 30 patients with NPC were used to evaluate image quality. The quantitative indices included contrast-to-noise ratio (CNR), uniformity and signal-to-noise ratio (SNR) for the phantom and the structural similarity index measure (SSIM), mean absolute error (MAE), and peak signal-to-noise ratio (PSNR) for patients. Next, we trained three models for segmentation of the clinical target volume (CTV): MV-CT, skV-CT, and MV-CT combined with skV-CT. The segmentation accuracy was compared with indices of the dice similarity coefficient (DSC) and mean distance agreement (MDA).Mainresults:Compared with MV-CT, skV-CT showed significant improvement in CNR (184.0%), image uniformity (34.7%), and SNR (199.0%) in the phantom study and improved SSIM (1.7%), MAE (24.7%), and PSNR (7.5%) in the patient study. For CTV segmentation with only MV-CT, only skV-CT, and MV-CT combined with skV-CT, the DSCs were 0.75 ± 0.04, 0.78 ± 0.04, and 0.79 ± 0.03, respectively, and the MDAs (in mm) were 3.69 ± 0.81, 3.14 ± 0.80, and 2.90 ± 0.62, respectively.Significance:The proposed method improved the image quality of MV-CT and thus tumor segmentation in helical tomotherapy. The method potentially can benefit adaptive radiotherapy.

DVHnet: A deep learning-based prediction of patient-specific dose volume histograms for radiotherapy planning.

PURPOSE: To develop a deep learning method to predict patient-specific dose volume histograms (DVHs) for radiotherapy planning. METHODS: Patient data included 180 cases with nasopharyngeal cancer, of which 153 cases were used for training and 27 for testing. A network (named "DVHnet") based on a convolutional neural network (CNN) was designed for directly predicting DVHs of organs at risk (OARs). Two-channel images with contoured structures were generated as the inputs for training the model. A one-dimensional array consisting of 256 continuous volume percentages on a DVH curve for each slice was calculated as the corresponding output. The combined DVH was then calculated. Sixteen OARs were modeled in the study. Prediction accuracy was evaluated against the corresponding DVH curve of ground truth (GT) plans. A global DVH analysis and critical dosimetry metrics for each OAR were calculated for quantitative evaluation. The performance of DVHnet also was evaluated against two baselines: DosemapNet (developed by our research group) and commercial RapidPlan software. RESULTS: The predicted mean difference in average dose of all OARs using DVHnet was 0.30 ± 0.95 Gy. And the predicted differences in D2% and D50 can be control within 2.32 and 0.69 Gy. For most OARs, there were no obvious differences between the dosimetric metrics of the predicted and GT values for both DVHnet and DosemapNet (P ≥ 0.05). Only the predicted D2% of the optic organs for DVHnet, and of brain stem PRV for DosemapNet displayed statistically significant differences. Except for the optic organs, DVHnet performs better than or comparably with RapidPlan. The mean difference in proportion of points of interest was 3.59% ± 7.78%. CONCLUSIONS: A deep learning network model was developed to automatically extract useful features for accurate prediction of patient-specific DVH curves directly. The performance of DVHnet was comparable to DosemapNet and RapidPlan.

Automatic segmentation of three clinical target volumes in radiotherapy using lifelong learning.

BACKGROUND AND PURPOSE: Convolutional neural networks (CNNs) have comparable human level performance in automatic segmentation. An important challenge that CNNs face in segmentation is catastrophic forgetting. They lose performance on tasks that were previously learned when trained on task. In this study, we propose a lifelong learning method to learn multiple segmentation tasks continuously without forgetting previous tasks. MATERIALS AND METHODS: The cohort included three tumors, 800 patients of which had nasopharyngeal cancer (NPC), 800 patients had breast cancer, and 800 patients had rectal cancer. The tasks included segmentation of the clinical target volume (CTV) of these three cancers. The proposed lifelong learning network adopted dilation adapter to learn three segmentation tasks one by one. Only the newly added dilation adapter (seven layers) was fine tuning for incoming new task, whereas all the other learned layers were frozen. RESULTS: Compared with single-task, multi-task or transfer learning, the proposed lifelong learning can achieve better or comparable segmentation accuracy with a DSC of 0.86 for NPC, 0.89 for breast cancer, and 0.87 for rectal cancer. Lifelong learning can avoid forgetting in sequential learning and yield good performance with less training data. Furthermore, it is more efficient than single-task or transfer learning, which reduced the number of parameters, size of model, and training time by ~58.8%, ~55.6%, and ~25.0%, respectively. CONCLUSION: The proposed method preserved the knowledge of previous tasks while learning a new one using a dilation adapter. It could yield comparable performance with much less training data, model parameters, and training time.

Continual improvement of nasopharyngeal carcinoma segmentation with less labeling effort.

PURPOSE: Convolutional neural networks (CNNs) offer a promising approach to automated segmentation. However, labeling contours on a large scale is laborious. Here we propose a method to improve segmentation continually with less labeling effort. METHODS: The cohort included 600 patients with nasopharyngeal carcinoma. The proposed method was comprised of four steps. First, an initial CNN model was trained from scratch to perform segmentation of the clinical target volume. Second, a binary classifier was trained using a secondary CNN to identify samples for which the initial model gave a dice similarity coefficient (DSC) < 0.85. Third, the classifier was used to select such samples from the new coming data. Forth, the final model was fine-tuned from the initial model, using only selected samples. RESULTS: The classifier can detect poor segmentation of the model with an accuracy of 92%. The proposed segmentation method improved the DSC from 0.82 to 0.86 while reducing the labeling effort by 45%. CONCLUSIONS: The proposed method reduces the amount of labeled training data and improves segmentation by continually acquiring, fine-tuning, and transferring knowledge over long time spans.

Evaluation of Automatic Segmentation Model With Dosimetric Metrics for Radiotherapy of Esophageal Cancer.

Background and Purpose: Automatic segmentation model is proven to be efficient in delineation of organs at risk (OARs) in radiotherapy; its performance is usually evaluated with geometric differences between automatic and manual delineations. However, dosimetric differences attract more interests than geometric differences in the clinic. Therefore, this study aimed to evaluate the performance of automatic segmentation with dosimetric metrics for volumetric modulated arc therapy of esophageal cancer patients. Methods: Nineteen esophageal cancer cases were included in this study. Clinicians manually delineated the target volumes and the OARs for each case. Another set of OARs was automatically generated using convolutional neural network models. The radiotherapy plans were optimized with the manually delineated targets and the automatically delineated OARs separately. Segmentation accuracy was evaluated by Dice similarity coefficient (DSC) and mean distance to agreement (MDA). Dosimetric metrics of manually and automatically delineated OARs were obtained and compared. The clinically acceptable dose difference and volume difference of OARs between manual and automatic delineations are supposed to be within 1 Gy and 1%, respectively. Results: Average DSC values were greater than 0.92 except for the spinal cord (0.82), and average MDA values were <0.90 mm except for the heart (1.74 mm). Eleven of the 20 dosimetric metrics of the OARs were not significant (P > 0.05). Although there were significant differences (P < 0.05) for the spinal cord (D2%), left lung (V10, V20, V30, and mean dose), and bilateral lung (V10, V20, V30, and mean dose), their absolute differences were small and acceptable for the clinic. The maximum dosimetric metrics differences of OARs between manual and automatic delineations were ΔD2% = 0.35 Gy for the spinal cord and ΔV30 = 0.4% for the bilateral lung, which were within the clinical criteria in this study. Conclusion: Dosimetric metrics were proposed to evaluate the automatic delineation in radiotherapy planning of esophageal cancer. Consequently, the automatic delineation could substitute the manual delineation for esophageal cancer radiotherapy planning based on the dosimetric evaluation in this study.

Anticancer effect of SZC017, a novel derivative of oleanolic acid, on human gastric cancer cells.

Oleanolic acid (OA) and its several derivatives possess chemopreventive and chemotherapeutic functions against a series of cancer types. Many chemotherapeutic compounds are effective in improving the quality of life and prolonging the survival of patients with gastric cancer, therefore progress in the treatment of gastric cancer, especially the anticancer effects of OA derivatives must be achieved. The inhibitory effect of SZC017, a newly synthesized derivative of OA, on cell viability was determined by MTT assay. Furthermore, flow cytometry, transmission electron microscopy, and western blot analysis revealed that the inhibition of cell viability by OA was mediated by triggering the intrinsic apoptosis of gastric cancer cells, and inducing S phase arrest of SGC7901 cells. Mechanistically, SZC017 was effective against gastric cancer cells via inhibiting Akt/NF­κB signaling and topoisomerase I and IIα proteins. Taken together, our data indicate that SZC017 may be a potential chemotherapeutic agent against gastric cancer cells.