Correlation between gastric volume and organs at risk dose in adjuvant radiotherapy for left breast cancer.

BACKGROUND: The role of the gastric volume on the dose-effect relationship for these organs has not been investigated. The aim of the study was to evaluate the correlation between gastric volume and dose-volume histogram (DVH) parameters of the heart, left lung and stomach during left breast cancer radiotherapy (RT). MATERIALS AND METHODS: Ninety-nine left breast cancer patients who got adjuvant radiotherapy were included. Study was classified into two groups based on treatment field arrangements: 1) breast tangential fields only (T) and 2) breast tangential and supraclavicular fields (TS). Organs DVHs were extracted. Descriptive statistics, Pearson correlation, linear regression analyses, and receiver operating characteristic (ROC) analyses were performed. RESULTS: There is a direct but not significant correlation between the gastric volume and doses to the stomach and left lung. For a 100-cc increase in the gastric volume, the stomach maximum dose and the V50 increased by 3 Gy and 4%, respectively. For the left lung, V4 and V5 increased by 1% for TS cases. Considering ROC analysis results, one can make a decision for about 74% of patients due to their left lung DVH parameters, using gastric volume as a known input data. The correlation between gastric volume and heart dose was not significant. CONCLUSIONS: The gastric volume of about 170 cc or less can result in lower dose to the stomach and ipsilateral lung during left breast cancer radiotherapy, especially for TS cases. To reach this gastric volume threshold, patients should be fast for 2 hours before the procedure of CT simulation and treatment.

Differential privacy preserved federated learning for prognostic modeling in COVID-19 patients using large multi-institutional chest CT dataset.

BACKGROUND: Notwithstanding the encouraging results of previous studies reporting on the efficiency of deep learning (DL) in COVID-19 prognostication, clinical adoption of the developed methodology still needs to be improved. To overcome this limitation, we set out to predict the prognosis of a large multi-institutional cohort of patients with COVID-19 using a DL-based model. PURPOSE: This study aimed to evaluate the performance of deep privacy-preserving federated learning (DPFL) in predicting COVID-19 outcomes using chest CT images. METHODS: After applying inclusion and exclusion criteria, 3055 patients from 19 centers, including 1599 alive and 1456 deceased, were enrolled in this study. Data from all centers were split (randomly with stratification respective to each center and class) into a training/validation set (70%/10%) and a hold-out test set (20%). For the DL model, feature extraction was performed on 2D slices, and averaging was performed at the final layer to construct a 3D model for each scan. The DensNet model was used for feature extraction. The model was developed using centralized and FL approaches. For FL, we employed DPFL approaches. Membership inference attack was also evaluated in the FL strategy. For model evaluation, different metrics were reported in the hold-out test sets. In addition, models trained in two scenarios, centralized and FL, were compared using the DeLong test for statistical differences. RESULTS: The centralized model achieved an accuracy of 0.76, while the DPFL model had an accuracy of 0.75. Both the centralized and DPFL models achieved a specificity of 0.77. The centralized model achieved a sensitivity of 0.74, while the DPFL model had a sensitivity of 0.73. A mean AUC of 0.82 and 0.81 with 95% confidence intervals of (95% CI: 0.79-0.85) and (95% CI: 0.77-0.84) were achieved by the centralized model and the DPFL model, respectively. The DeLong test did not prove statistically significant differences between the two models (p-value = 0.98). The AUC values for the inference attacks fluctuate between 0.49 and 0.51, with an average of 0.50 ± 0.003 and 95% CI for the mean AUC of 0.500 to 0.501. CONCLUSION: The performance of the proposed model was comparable to centralized models while operating on large and heterogeneous multi-institutional datasets. In addition, the model was resistant to inference attacks, ensuring the privacy of shared data during the training process.

COVID-19 prognostic modeling using CT radiomic features and machine learning algorithms: Analysis of a multi-institutional dataset of 14,339 patients.

BACKGROUND: We aimed to analyze the prognostic power of CT-based radiomics models using data of 14,339 COVID-19 patients. METHODS: Whole lung segmentations were performed automatically using a deep learning-based model to extract 107 intensity and texture radiomics features. We used four feature selection algorithms and seven classifiers. We evaluated the models using ten different splitting and cross-validation strategies, including non-harmonized and ComBat-harmonized datasets. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were reported. RESULTS: In the test dataset (4,301) consisting of CT and/or RT-PCR positive cases, AUC, sensitivity, and specificity of 0.83 ± 0.01 (CI95%: 0.81-0.85), 0.81, and 0.72, respectively, were obtained by ANOVA feature selector + Random Forest (RF) classifier. Similar results were achieved in RT-PCR-only positive test sets (3,644). In ComBat harmonized dataset, Relief feature selector + RF classifier resulted in the highest performance of AUC, reaching 0.83 ± 0.01 (CI95%: 0.81-0.85), with a sensitivity and specificity of 0.77 and 0.74, respectively. ComBat harmonization did not depict statistically significant improvement compared to a non-harmonized dataset. In leave-one-center-out, the combination of ANOVA feature selector and RF classifier resulted in the highest performance. CONCLUSION: Lung CT radiomics features can be used for robust prognostic modeling of COVID-19. The predictive power of the proposed CT radiomics model is more reliable when using a large multicentric heterogeneous dataset, and may be used prospectively in clinical setting to manage COVID-19 patients.

Radiotherapy based management during Covid-19 pandemic - A systematic review of presented consensus and guidelines.

Treatment management of cancer patients in the radiation oncology departments during the current COVID-19 pandemic is challenging. A systematic review of published consensus/guidelines on the role of radiotherapy prioritization, suggested treatment protocols, and set up management was undertaken based on the PRISMA protocol and through PubMed/PMC, Scopus, Google Scholar, Web of Science databases until 01/20/2021. One hundred and sixty-eight publications or regional consensus were included. Summary of recommendations contained: (1) using hypo-fractionated (Hypo-F) regimens for therapeutic/palliative indications, (2) delaying radiotherapy for several weeks or until pandemic over, (3) omitting radiotherapy by replacement of alternative therapies or active surveillance, (4) applying safer patients' setup and preparation protocols, (5) developing telemedicine/telehealth service. To conclude, it is essential to carefully weigh the risk of exposure to COVID-19 infection and the benefit of treating cancer patients during the pandemic. Trying to have a global guideline facing this or any other probable crisis is crucial for health care service.