Value of perfusion parameters from golden-angle radial sparse parallel dynamic contrast-enhanced magnetic resonance imaging in predicting pathological complete response after neoadjuvant chemoradiotherapy for locally advanced rectal cancer.

PURPOSE: Non-invasive methods for predicting pathological complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT) can provide distinct leverage in the management of patients with locally advanced rectal cancer (LARC). This study aimed to investigate whether including the golden-angle radial sparse parallel (GRASP) dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) perfusion parameter (Ktrans), in addition to tumor regression grading (TRG) and apparent diffusion coefficient (ADC) values, can improve the predictive ability for pCR. METHODS: Patients with LARC who underwent nCRT and subsequent surgery were included. The imaging parameters were compared between patients with and without pCR. Receiver operating characteristic (ROC) curve analysis was used to evaluate the predictive ability of these parameters for pCR. RESULTS: A total of 111 patients were included in the study. A pCR was obtained in 32 patients (28.8%). MRI-based TRG (mrTRG) showed a negative correlation with pCR (r = -0.61, P < 0.001), and the average ADC value showed a positive correlation with pCR (r = 0.62, P < 0.001). Before nCRT, Ktrans in the pCR group was significantly higher than in the non-pCR group (1.30 ± 0.24 vs. 0.88 ± 0.34, P < 0.001), but no difference was identified after nCRT. Following ROC curve analysis, the area under the curve (AUC) of mrTRG (level 1-2), average ADC value, and Ktrans value for predicting pCR were 0.738 [95% confidence interval (CI): 0.65-0.82], 0.78 (95% CI: 0.69-0.86), and 0.84 (95% CI: 0.77-0.92), respectively. The model combining the three parameters had significantly higher predictive ability for pCR (AUC: 0.94, 95% CI: 0.88-0.98). CONCLUSION: The use of a combination of the GRASP DCE-MRI Ktrans with mrTRG and ADC can lead to a better pCR predictive performance.

Preoperative prediction of macrotrabecular-massive hepatocellular carcinoma through dynamic contrast-enhanced magnetic resonance imaging-based radiomics.

BACKGROUND: Macrotrabecular-massive hepatocellular carcinoma (MTM-HCC) is closely related to aggressive phenotype, gene mutation, carcinogenic pathway, and immunohistochemical markers and is a strong independent predictor of early recurrence and poor prognosis. With the development of imaging technology, successful applications of contrast-enhanced magnetic resonance imaging (MRI) have been reported in identifying the MTM-HCC subtype. Radiomics, as an objective and beneficial method for tumour evaluation, is used to convert medical images into high-throughput quantification features that greatly push the development of precision medicine. AIM: To establish and verify a nomogram for preoperatively identifying MTM-HCC by comparing different machine learning algorithms. METHODS: This retrospective study enrolled 232 (training set, 162; test set, 70) hepatocellular carcinoma patients from April 2018 to September 2021. A total of 3111 radiomics features were extracted from dynamic contrast-enhanced MRI, followed by dimension reduction of these features. Logistic regression (LR), K-nearest neighbour (KNN), Bayes, Tree, and support vector machine (SVM) algorithms were used to select the best radiomics signature. We used the relative standard deviation (RSD) and bootstrap methods to quantify the stability of these five algorithms. The algorithm with the lowest RSD represented the best stability, and it was used to construct the best radiomics model. Multivariable logistic analysis was used to select the useful clinical and radiological features, and different predictive models were established. Finally, the predictive performances of the different models were assessed by evaluating the area under the curve (AUC). RESULTS: The RSD values based on LR, KNN, Bayes, Tree, and SVM were 3.8%, 8.6%, 4.3%, 17.7%, and 17.4%, respectively. Therefore, the LR machine learning algorithm was selected to construct the best radiomics signature, which performed well with AUCs of 0.766 and 0.739 in the training and test sets, respectively. In the multivariable analysis, age [odds ratio (OR) = 0.956, P = 0.034], alpha-fetoprotein (OR = 10.066, P < 0.001), tumour size (OR = 3.316, P = 0.002), tumour-to-liver apparent diffusion coefficient (ADC) ratio (OR = 0.156, P = 0.037), and radiomics score (OR = 2.923, P < 0.001) were independent predictors of MTM-HCC. Among the different models, the predictive performances of the clinical-radiomics model and radiological-radiomics model were significantly improved compared to those of the clinical model (AUCs: 0.888 vs 0.836, P = 0.046) and radiological model (AUCs: 0.796 vs 0.688, P = 0.012), respectively, in the training set, highlighting the improved predictive performance of radiomics. The nomogram performed best, with AUCs of 0.896 and 0.805 in the training and test sets, respectively. CONCLUSION: The nomogram containing radiomics, age, alpha-fetoprotein, tumour size, and tumour-to-liver ADC ratio revealed excellent predictive ability in preoperatively identifying the MTM-HCC subtype.

Deep Learning Analysis Using 18F-FDG PET/CT to Predict Occult Lymph Node Metastasis in Patients With Clinical N0 Lung Adenocarcinoma.

Introduction: The aim of this work was to determine the feasibility of using a deep learning approach to predict occult lymph node metastasis (OLM) based on preoperative FDG-PET/CT images in patients with clinical node-negative (cN0) lung adenocarcinoma. Materials and Methods: Dataset 1 (for training and internal validation) included 376 consecutive patients with cN0 lung adenocarcinoma from our hospital between May 2012 and May 2021. Dataset 2 (for prospective test) used 58 consecutive patients with cN0 lung adenocarcinoma from June 2021 to February 2022 at the same center. Three deep learning models: PET alone, CT alone, and combined model, were developed for the prediction of OLM. The performance of the models was evaluated on internal validation and prospective test in terms of accuracy, sensitivity, specificity, and areas under the receiver operating characteristic curve (AUCs). Results: The combined model incorporating PET and CT showed the best performance, achieved an AUC of 0.81 [95% confidence interval (CI): 0.61, 1.00] in the prediction of OLM in internal validation set (n = 60) and an AUC of 0.87 (95% CI: 0.75, 0.99) in the prospective test set (n = 58). The model achieved 87.50% sensitivity, 80.00% specificity, and 81.00% accuracy in the internal validation set and achieved 75.00% sensitivity, 88.46% specificity, and 86.60% accuracy in the prospective test set. Conclusion: This study presented a deep learning approach to enable the prediction of occult nodal involvement based on the PET/CT images before surgery in cN0 lung adenocarcinoma, which would help clinicians select patients who would be suitable for sublobar resection.

A nomogram diagnostic prediction model of pancreatic metastases of small cell lung carcinoma based on clinical characteristics, radiological features and biomarkers.

Objective: To investigate clinical characteristics, radiological features and biomarkers of pancreatic metastases of small cell lung carcinoma (PM-SCLC), and establish a convenient nomogram diagnostic predictive model to differentiate PM-SCLC from pancreatic ductal adenocarcinomas (PDAC) preoperatively. Methods: A total of 299 patients with meeting the criteria (PM-SCLC n=93; PDAC n=206) from January 2016 to March 2022 were retrospectively analyzed, including 249 patients from hospital 1 (training/internal validation cohort) and 50 patients from hospital 2 (external validation cohort). We searched for meaningful clinical characteristics, radiological features and biomarkers and determined the predictors through multivariable logistic regression analysis. Three models: clinical model, CT imaging model, and combined model, were developed for the diagnosis and prediction of PM-SCLC. Nomogram was constructed based on independent predictors. The receiver operating curve was undertaken to estimate the discrimination. Results: Six independent predictors for PM-SCLC diagnosis in multivariate logistic regression analysis, including clinical symptoms, CA199, tumor size, parenchymal atrophy, vascular involvement and enhancement type. The nomogram diagnostic predictive model based on these six independent predictors showed the best performance, achieved the AUCs of the training cohort (n = 174), internal validation cohort (n = 75) and external validation cohort (n = 50) were 0.950 (95%CI, 0.917-0.976), 0.928 (95%CI, 0.873-0.971) and 0.976 (95%CI, 0.944-1.00) respectively. The model achieved 94.50% sensitivity, 83.20% specificity, 86.80% accuracy in the training cohort and 100.00% sensitivity, 80.40% specificity, 86.70% accuracy in the internal validation cohort and 100.00% sensitivity, 88.90% specificity, 87.50% accuracy in the external validation cohort. Conclusion: We proposed a noninvasive and convenient nomogram diagnostic predictive model based on clinical characteristics, radiological features and biomarkers to preoperatively differentiate PM-SCLC from PDAC.