RESUMEN
RATIONALE AND OBJECTIVES: To preoperatively predict lymph node metastasis (LNM) in patients with cervical nonsquamous cell carcinoma (non-SCC) based on magnetic resonance imaging (MRI) texture analysis. MATERIALS AND METHODS: This retrospective study included 104 consecutive patients (mean age of 47.2 ± 11.3 years) with stage IB-IIA cervical non-SCC. According to the ratio of 7:3, 72, and 32 patients were randomly divided into the training and testing cohorts. A total of 272 original features were extracted. In the process of feature selection, features with intraclass correlation coefficients (ICCs) less than 0.8 were eliminated. The Pearson correlation coefficient (PCC) and analysis of variance (ANOVA) were applied to reduce redundancy, overfitting, and selection biases. Further, a support vector machine (SVM) with linear kernel function was applied to select the optimal feature set with a high discrimination power. RESULTS: The T2WI + DWI-based, T2WI + DWI + CE-T1WI-based and T2WI + DWI + LNS-MRI (LN status on MRI)-based SVM models yielded an AUC and accuracy of 0.78 and 0.79; 0.79 and 0.69; 0.79 and 0.81 for predicting LNM in the training cohort, and 0.82 and 0.78; 0.82 and 0.69; 0.79 and 0.72 in the testing cohort. The T2WI + DWI-based, T2WI + DWI + CE-T1WI-based and T2WI + DWI + LNS-MRI-based SVM models performed better than morphologic criteria of LNS-MRI and yield similar discrimination abilities in predicting LNM in the training and testing cohorts (all p-value > 0.05). In addition, the T2WI + DWI-based and T2WI + DWI + LNS-MRI-based SVM models showed robust performance in the AC and ASC subgroups (all p-value > 0.05). CONCLUSION: The T2WI + DWI-based, T2WI + DWI + CE-T1WI-based and T2WI+DWI+LNS-MRI-based SVM models showed similar good discrimination ability and performed better than the morphologic criteria of LNS-MRI in predicting LNM in patients with cervical non-SCC. The inclusion of the CE-T1WI sequence and morphologic criteria of LNS-MRI did not significantly improve the performance of the T2WI + DWI-based model. The T2WI + DWI-based and T2WI + DWI + LNS-MRI-based SVM models showed robust performance in the subgroup analysis.
RESUMEN
OBJECTIVES: To develop and validate a deep learning-based overall survival (OS) prediction model in patients with hepatocellular carcinoma (HCC) treated with transarterial chemoembolization (TACE) plus sorafenib. METHODS: This retrospective multicenter study consisted of 201 patients with treatment-naïve, unresectable HCC who were treated with TACE plus sorafenib. Data from 120 patients were used as the training set for model development. A deep learning signature was constructed using the deep image features from preoperative contrast-enhanced computed tomography images. An integrated nomogram was built using Cox regression by combining the deep learning signature and clinical features. The deep learning signature and nomograms were also externally validated in an independent validation set of 81 patients. C-index was used to evaluate the performance of OS prediction. RESULTS: The median OS of the entire set was 19.2 months and no significant difference was found between the training and validation cohort (18.6 months vs. 19.5 months, P = 0.45). The deep learning signature achieved good prediction performance with a C-index of 0.717 in the training set and 0.714 in the validation set. The integrated nomogram showed significantly better prediction performance than the clinical nomogram in the training set (0.739 vs. 0.664, P = 0.002) and validation set (0.730 vs. 0.679, P = 0.023). CONCLUSION: The deep learning signature provided significant added value to clinical features in the development of an integrated nomogram which may act as a potential tool for individual prognosis prediction and identifying HCC patients who may benefit from the combination therapy of TACE plus sorafenib.
RESUMEN
Objectives: To establish a radiomic algorithm based on grayscale ultrasound images and to make preoperative predictions of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) patients. Methods: In this retrospective study, 322 cases of histopathologically confirmed HCC lesions were included. The classifications based on preoperative grayscale ultrasound images were performed in two stages: (1) classifier #1, MVI-negative and MVI-positive cases; (2) classifier #2, MVI-positive cases were further classified as M1 or M2 cases. The gross-tumoral region (GTR) and peri-tumoral region (PTR) signatures were combined to generate gross- and peri-tumoral region (GPTR) radiomic signatures. The optimal radiomic signatures were further incorporated with vital clinical information. Multivariable logistic regression was used to build radiomic models. Results: Finally, 1,595 radiomic features were extracted from each HCC lesion. At the classifier #1 stage, the radiomic signatures based on features of GTR, PTR, and GPTR showed area under the curve (AUC) values of 0.708 (95% CI, 0.603-0.812), 0.710 (95% CI, 0.609-0.811), and 0.726 (95% CI, 0.625-0.827), respectively. Upon incorporation of vital clinical information, the AUC of the GPTR radiomic algorithm was 0.744 (95% CI, 0.646-0.841). At the classifier #2 stage, the AUC of the GTR radiomic signature was 0.806 (95% CI, 0.667-0.944). Conclusions: Our radiomic algorithm based on grayscale ultrasound images has potential value to facilitate preoperative prediction of MVI in HCC patients. The GTR radiomic signature may be helpful for further discriminating between M1 and M2 levels among MVI-positive patients.
