CT radiomics based on different machine learning models for classifying gross tumor volume and normal liver tissue in hepatocellular carcinoma.

BACKGROUND & AIMS: The present study utilized extracted computed tomography radiomics features to classify the gross tumor volume and normal liver tissue in hepatocellular carcinoma by mainstream machine learning methods, aiming to establish an automatic classification model. METHODS: We recruited 104 pathologically confirmed hepatocellular carcinoma patients for this study. GTV and normal liver tissue samples were manually segmented into regions of interest and randomly divided into five-fold cross-validation groups. Dimensionality reduction using LASSO regression. Radiomics models were constructed via logistic regression, support vector machine (SVM), random forest, Xgboost, and Adaboost algorithms. The diagnostic efficacy, discrimination, and calibration of algorithms were verified using area under the receiver operating characteristic curve (AUC) analyses and calibration plot comparison. RESULTS: Seven screened radiomics features excelled at distinguishing the gross tumor area. The Xgboost machine learning algorithm had the best discrimination and comprehensive diagnostic performance with an AUC of 0.9975 [95% confidence interval (CI): 0.9973-0.9978] and mean MCC of 0.9369. SVM had the second best discrimination and diagnostic performance with an AUC of 0.9846 (95% CI: 0.9835- 0.9857), mean Matthews correlation coefficient (MCC)of 0.9105, and a better calibration. All other algorithms showed an excellent ability to distinguish between gross tumor area and normal liver tissue (mean AUC 0.9825, 0.9861,0.9727,0.9644 for Adaboost, random forest, logistic regression, naivem Bayes algorithm respectively). CONCLUSION: CT radiomics based on machine learning algorithms can accurately classify GTV and normal liver tissue, while the Xgboost and SVM algorithms served as the best complementary algorithms.

Dosimetric comparison of helical tomotherapy and volumetric modulated arc therapy in hippocampal avoidance whole-brain radiotherapy.

OBJECTIVE: This study aimed to discuss the dosimetric advantages of helical tomotherapy (HT) and volumetric modulated arc therapy (VMAT) technology in hippocampal avoidance whole-brain radiotherapy and provide references for clinical selection of ideal radiotherapy technology. METHODS: A total of 20 patients with hippocampal avoidance whole-brain radiotherapy were chosen randomly. Computed tomography (CT) and MRI scanning images were input into the treatment planning system (TPS). After the CT and enhanced magnetic resonance T1 weighted images were fused and registered, the same radiation therapy physician was invited to outline the tumor target volume. PTV-HS refers to the whole brain subtracted by 5 mm outward expansion of the hippocampus (HP). The prescribed dose was 30 Gy/10 fractions. HT and VMAT plans were designed for each patient in accordance with PTV. Under the premise that the 95% isodose curve covers the PTV, dose-volume histogram was applied to evaluate the PTV, conformal index (CI), heterogeneity index (HI), maximum dose (Dmax), mean dose (Dmean), minimum dose (Dmin) and absorbed doses of organs at risk (OARs) in HT and VMAT plans. Paired t-test was performed to compare the differences between two radiation therapy plans, and p  <  0.05 was considered statistically significant. RESULTS: These two plans had no significant difference in PTV-HS (max, min, and mean). However, the HI and CI of the HT plan were significantly better than those of the VMAT plan, showing statistically significant difference (p < 0.05). The HT plan was significantly superior to the VMAT plan in terms of the Dmax, Dmin, and Dmean of HP, left and right eye lens, left and right eye, and spinal cord, showing statistically significant difference (p < 0.05). The HT plan was also better than the VMAT plan in terms of the Dmax of the left optic nerve. However, the two plans showed no obvious differences in terms of the absorbed doses of the right optic nerve and brainstem, without statistical significance. CONCLUSIONS: Compared with the VMAT plan of hippocampal avoidance, HT technology has significant dosimetric advantages. HT plans significantly decreased the radiation dose and radiation volume of OARs surrounding the target area (e.g., surrounding eye lens and eye, especially hippocampal avoidance area) while increasing the CI and HI of PTV dose in whole brain radiotherapy (WBRT) greatly, thus enabling the decrease in the incidence rate of radioactive nerve function impairment.

Reducing Target Volumes of Intensity Modulated Radiation Therapy After Induction Chemotherapy in Locoregionally Advanced Nasopharyngeal Carcinoma: Long-Term Results of a Prospective, Multicenter, Randomized Trial.

PURPOSE: The objective of this study was to estimate the long-term survival, late toxicity profile, and quality of life of patients with locoregionally advanced nasopharyngeal carcinoma (NPC) treated with combined induction chemotherapy (IC) and concurrent chemoradiotherapy from a clinical trial focused on reducing the target volume of intensity modulated radiation therapy (IMRT). METHODS AND MATERIALS: This prospective, randomized clinical trial was conducted across 6 Chinese hospitals and included 212 patients with stage III-IVB NPC who were randomly allocated to a pre-IC or post-IC group. Eligible patients were treated with 2 cycles of IC + CCRT. All patients underwent radical IMRT. Gross tumor volumes of the nasopharynx were delineated according to pre-IC and post-IC tumor extent in the pre-IC and post-IC groups, respectively. RESULTS: After a median follow-up of 98.4 months, 32 of 97 (32.9%) and 33 of 115 (28.7%) patients experienced treatment failure or died in the pre-IC and post-IC groups, respectively. None of the patients developed grade 4 late toxicity. Late radiation-induced toxicity predominantly manifested as grade 1 to 2 subcutaneous fibrosis, hearing loss, tinnitus, and xerostomia, whereas grade 3 late toxicity included xerostomia and hearing loss. The 5-year estimated overall, progression-free, locoregional recurrence-free, and distant metastasis-free survival rates in the pre-IC and post-IC groups were 78.2% versus 83.3%, 72.0% versus 78.1%, 90.2% versus 93.5%, and 78.1% versus 82.1%, respectively. The pre-IC group had a significantly higher incidence of xerostomia and hearing damage than the post-IC group. In terms of quality of life, compared with the pre-IC group, the post-IC group showed significant improvement in cognitive function (P = .045) and symptoms including dry mouth (P = .004), sticky saliva (P = .047), and feeling ill (P = .041). CONCLUSIONS: After long-term follow-up, we confirmed that reducing the target volumes of IMRT after IC in locoregionally advanced NPC showed no inferiority in terms of the risk of locoregional relapse and potentially improved quality of life and alleviated late toxicity.

Dose prediction of organs at risk in patients with cervical cancer receiving brachytherapy using needle insertion based on a neural network method.

OBJECTIVE: A neural network method was employed to establish a dose prediction model for organs at risk (OAR) in patients with cervical cancer receiving brachytherapy using needle insertion. METHODS: A total of 218 CT-based needle-insertion brachytherapy fraction plans for loco-regionally advanced cervical cancer treatment were analyzed in 59 patients. The sub-organ of OAR was automatically generated by self-written MATLAB, and the volume of the sub-organ was read. Correlations between D2cm3 of each OAR and volume of each sub-organ-as well as high-risk clinical target volume for bladder, rectum, and sigmoid colon-were analyzed. We then established a neural network predictive model of D2cm3 of OAR using the matrix laboratory neural net. Of these plans, 70% were selected as the training set, 15% as the validation set, and 15% as the test set. The regression R value and mean squared error were subsequently used to evaluate the predictive model. RESULTS: The D2cm3/D90 of each OAR was related to volume of each respective sub-organ. The R values for bladder, rectum, and sigmoid colon in the training set for the predictive model were 0.80513, 0.93421, and 0.95978, respectively. The ∆D2cm3/D90 for bladder, rectum, and sigmoid colon in all sets was 0.052 ± 0.044, 0.040 ± 0.032, and 0.041 ± 0.037, respectively. The MSE for bladder, rectum, and sigmoid colon in the training set for the predictive model was 4.779 × 10-3, 1.967 × 10-3 and 1.574 × 10-3, respectively. CONCLUSION: The neural network method based on a dose-prediction model of OAR in brachytherapy using needle insertion was simple and reliable. In addition, it only addressed volumes of sub-organs to predict the dose of OAR, which we believe is worthy of further promotion and application.

Effect of 3-Dimensional Interstitial High-Dose-Rate Brachytherapy With Regional Metastatic Lymph Node Intensity-Modulated Radiation Therapy in Locally Advanced Peripheral Non-Small Cell Lung Cancer: 5-Year Follow-up of a Phase 2 Clinical Trial.

PURPOSE: We aimed to reveal the 5-year clinical outcomes of 3-dimensional (3D) interstitial high-dose-rate (HDR) brachytherapy with regional metastatic lymph node intensity modulated radiation therapy (IMRT) for locally advanced peripheral non-small cell lung cancer (NSCLC), which has been shown to have low toxicity and improved 2-year survival rates in patients with this disease. METHODS AND MATERIALS: In this phase 2, single-arm, open-label clinical trial, 83 patients with locally advanced peripheral NSCLC were enrolled (median follow-up [range], 53.7 [4.3-120.4] months). All eligible patients received 3D interstitial HDR brachytherapy with regional metastatic lymph node IMRT. The primary endpoint was overall survival (OS). Secondary endpoints were local recurrence-free survival, regional recurrence-free survival, progression-free survival, distant metastasis-free survival, toxicities, and quality of life. RESULTS: The final analysis included 75 patients (19 [25.3%] females, 56 [74.7%] males; median [range] age, 64 [44-80] years; stage IIIA, 34 [45.3%]; stage IIIB, 41 [54.7%]). At the latest follow-up, 32 (42.7%) patients had survived. The median OS was 38.0 months (5-year OS, 44.5%; 95% confidence interval [CI], 33.8%-58.6%). Local recurrence-free survival, recurrence-free survival, and distant metastasis-free survival at 5 years were 79.2% (95% CI, 68.5%-91.5%), 73.6% (95% CI, 61.5%-88.1%), and 50.3% (95% CI, 38.3%-66.1%), respectively. The dominant failure pattern was distant disease, corresponding to 40% (30 of 75) of patients and 65.2% (30 of 46) of all failures. Two (2.7%) patients developed grade 1 acute pneumonitis. Grade 2 and 3 acute esophagitis occurred in 11 (14.7%) and 4 (5.3%) patients, respectively. No late radiation-related grade ≥2 late adverse events were observed. CONCLUSIONS: 3D interstitial HDR brachytherapy with regional metastatic lymph node IMRT for locally advanced peripheral NSCLC shows significant OS and has a low toxicity rate. Additional evaluation in a phase 3 trial is recommended to substantiate these findings.

Positron Emission Tomography-Based Short-Term Efficacy Evaluation and Prediction in Patients With Non-Small Cell Lung Cancer Treated With Hypo-Fractionated Radiotherapy.

BACKGROUND: Positron emission tomography is known to provide more accurate estimates than computed tomography when staging non-small cell lung cancer. The aims of this prospective study were to contrast the short-term efficacy of the two imaging methods while evaluating the effects of hypo-fractionated radiotherapy in non-small cell lung cancer, and to establish a short-term efficacy prediction model based on the radiomics features of positron emission tomography. METHODS: This nonrandomized-controlled trial was conducted from March 2015 to June 2019. Thirty-one lesions of 30 patients underwent the delineation of the regions of interest on positron emission tomography and computed tomography 1 month before, and 3 months after hypo-fractionated radiotherapy. Each patient was evaluated for the differences in local objective response rate between the two images. The Kaplan Meier method was used to analyze the local objective response and subsequent survival duration of the two imaging methods. The 3D Slicer was used to extract the radiomics features based on positron emission tomography. Least absolute shrinkage and selection operator regression was used to eliminate redundant features, and logistic regression analysis was used to develop the curative-effect-predicting model, which was displayed through a radiomics nomogram. Receiver operating characteristic curve and decision curve were used to evaluate the accuracy and clinical usefulness of the prediction model. RESULTS: Positron emission tomography-based local objective response rate was significantly higher than that based on computed tomography [70.97% (22/31) and 12.90% (4/31), respectively (p<0.001)]. The mean survival time of responders and non-responders assessed by positron emission tomography was 28.6 months vs. 11.4 months (p=0.29), whereas that assessed by computed tomography was 24.5 months vs. 26 months (p=0.66), respectively. Three radiomics features were screened to establish a personalized prediction nomogram with high area under curve (0.94, 95% CI 0.85-0.99, p<0.001). The decision curve showed a high clinical value of the radiomics nomogram. CONCLUSIONS: We recommend positron emission tomography for evaluating the short-term efficacy of hypo-fractionated radiotherapy in non-small cell lung cancer, and that the radiomics nomogram could be an important technique for the prediction of short-term efficacy, which might enable an improved and precise treatment. REGISTRATION NUMBER/URL: ChiCTR1900027768/http://www.chictr.org.cn/showprojen.aspx?proj=46057.

Nutritional outcomes after radiotherapy target volume reduction for nasopharyngeal cancer: a Phase III trial.

Aim: This study aimed to assess the nutritional status of patients with locoregionally advanced nasopharyngeal cancer, for whom intensity-modulated radiotherapy (IMRT) was planned using their pre- or post-induction chemotherapy (IC) nasopharyngeal gross tumor volume. Materials & methods: 212 cases of stage III-IVb nasopharyngeal cancer were randomized into groups A (n = 97) and B (n = 115). IMRT was planned for groups A and B using pre-IC and post-IC images, respectively. Results: There was a significant decrease in the nutritional parameters of group B compared with those of group A during radiotherapy. Multivariate analysis indicated that the T stage and nasopharyngeal gross tumor volume IMRT-planning protocol were prognostic factors of poor nutritional status. Conclusion: Decreasing the IMRT target volume through IC can improve nutritional status.

Comparison of different images in gross target volume delineating on VX2 nasopharyngeal transplantation tumor models.

Background: To determine the optimum conditions for diagnosis of nasopharyngeal carcinoma, we established VX2 rabbit model to delineate gross target volume (GTV) in different imaging methods. Methods: The orthotopic nasopharyngeal carcinoma (NPC) was established in sixteen New Zealand rabbits. After 7-days inoculation, the rabbits were examined by CT scanning and then sacrificed for pathological examination. To achieve the best delineation, different GTVs of CT, MRI, 18F-FDG PET/CT, and 18F-FLT PET/CT images were correlated with pathological GTV (GTVp). Results: We found 45% and 60% of the maximum standardized uptake value (SUVmax) as the optimal SUV threshold for the target volume of NPC in 18F-FDG PET/CT and 18F-FLT PET/CT images, respectively (GTVFDG45% and GTVFLT60%). Moreover, the GTVMRI and GTVCT were significantly higher than the GTVp (P ≤ 0.05), while the GTVFDG45% and especially GTVFLT60% were similar to the GTVp (R = 0.892 and R = 0.902, respectively; P ≤ 0.001). Conclusions: Notably, the results suggested that 18F-FLT PET/CT could reflect the tumor boundaries more accurately than 18F-FDG PET/CT, MRI and CT, which makes 18F-FLT PET-CT more advantageous for the clinical delineation of the target volume in NPC.

Template-assisted 192Ir-based stereotactic ablative brachytherapy as a neoadjuvant treatment for operable peripheral non-small cell lung cancer: a phase I clinical trial.

PURPOSE: To evaluate safety, feasibility, and efficacy of template-assisted 192Ir-based stereotactic ablative brachytherapy (SABT), combined with surgery for peripheral non-small cell lung cancer (NSCLC). MATERIAL AND METHODS: Patients with pathologically confirmed operable peripheral NSCLC, who underwent template-assisted SABT (30 Gy delivered in one fraction) and were scheduled for tumor resection 4-6 weeks after SABT were included in this study. The perioperative adverse reactions of SABT were recorded to evaluate safety and feasibility of SABT for neoadjuvant therapy. Dosimetric data from both simulated and actual plans were collected and compared. Imaging with 18F-fluorodeoxyglucose-positron emission tomography/computed tomography (18F-FDG-PET/CT) and dynamic contrast-enhanced computed tomography were scheduled before SABT and surgery to evaluate the efficacy of the neoadjuvant therapy with SABT. RESULTS: Patients did not experience any serious adverse events. None of the patients had a delay in receiving surgery. After 4-6 weeks, the indicators for the efficacy of neoadjuvant therapy significantly decreased in all patients: gross tumor volume (p < 0.001), maximum standardized uptake value (p < 0.001), tumor blood volume (p < 0.001), and tumor blood flow (p = 0.008). Dosimetric parameters in the delivered SABT plan slightly changed from the preoperative simulation, but the difference was not statistically significant (p > 0.05). CONCLUSIONS: The efficacy of template-assisted SABT for neoadjuvant therapy was significant in operable peripheral NSCLC. Moreover, no serious adverse reactions were observed; when the coplanar template guidance technique was applied, dosimetric parameters were in good agreement between the actual SABT plan and the preoperative simulated plan.

Computed Tomography-Guided Interstitial High-Dose-Rate Brachytherapy in Combination With Regional Positive Lymph Node Intensity-Modulated Radiation Therapy in Locally Advanced Peripheral Non-Small Cell Lung Cancer: A Phase 1 Clinical Trial.

PURPOSE: To assess the technical safety, adverse events, and efficacy of computed tomography (CT)-guided interstitial high-dose-rate (HDR) brachytherapy in combination with regional positive lymph node intensity modulated radiation therapy in patients with locally advanced peripheral non-small cell lung cancer (NSCLC). METHODS AND MATERIALS: Twenty-six patients with histologically confirmed NSCLC were enrolled in a prospective, officially approved phase 1 trial. Primary tumors were treated with HDR brachytherapy. A single 30-Gy dose was delivered to the 90% isodose line of the gross lung tumor volume. A total dose of at least 70 Gy was administered to the 95% isodose line of the planning target volume of malignant lymph nodes using 6-MV X-rays. The patients received concurrent or sequential chemotherapy. We assessed treatment efficacy, adverse events, and radiation toxicity. RESULTS: The median follow-up time was 28 months (range, 7-44 months). There were 3 cases of mild pneumothorax but no cases of hemothorax, dyspnea, or pyothorax after the procedure. Grade 3 or 4 acute hematologic toxicity was observed in 5 patients. During follow-up, mild fibrosis around the puncture point was observed on the CT scans of 2 patients, but both patients were asymptomatic. The overall response rates (complete and partial) for the primary mass and positive lymph nodes were 100% and 92.3%, respectively. The 1-year and 2-year overall survival (OS) rates were 90.9% and 67%, respectively, with a median OS of 22.5 months. CONCLUSION: Our findings suggest that HDR brachytherapy is safe and feasible for peripheral locally advanced NSCLC, justifying a phase 2 clinical trial.