10 December 2024 in medRxiv
Objectives: Current study aimed to investigate radiomics features derived from two-center diffusion-MRI to differentiate benign and hepatocellular carcinoma (HCC) liver nodules. Methods: A total of 328 patients with 517 LI-RADS 2-5 nodules were included. MR images were retrospectively collected from 3T and 1.5T MRI vendors. Lesions were categorized into 242 benign and 275 HCC based on follow-up imaging for LR-2,3 and pathology results for LR4,5 nodules, and randomly divided into training (80%) and test (20%) sets. Preprocessing included resampling and normalization. Radiomics features were extracted from lesion volume-of-interest (VOI) on diffusion Images. Scanner variability was corrected using ComBat harmonization method followed by High-correlation filter, PCA filter, and LASSO to select important features. Best classifier model was selected by 10-fold cross-validation, and accuracy was assessed on the test dataset. Results: 1,434 features were extracted, and subsequent classifiers were constructed based on the 16 most important selected features. Notably, support-vector machine (SVM) demonstrated better performance in the test dataset in distinguishing between benign and HCC nodules, achieving an accuracy of 0.92, sensitivity of 0.94, and specificity of 0.86. Conclusions: Utilizing diffusion-MRI radiomics, our study highlights the performance of SVM, trained on lesions’ diffusivity characteristics, in distinguishing benign and HCC nodules, ensuring clinical potential. It is suggested that further evaluations be conducted on multi-center datasets to address harmonization challenges. Advances in knowledge: Integration of diffusion radiomics, for monitoring water restriction patterns as tumor histopathological index, with machine learning models demonstrates potential for achieving a reliable noninvasive method to improve the current diagnosis criteria.
26 May 2025 in British Journal of Radiology
Objectives: Current study aimed to investigate radiomics features derived from 2-centre diffusion-MRI to differentiate benign and hepatocellular carcinoma (HCC) liver nodules. Methods: A total of 328 patients with 517 Liver Imaging Reporting and Data System (LI-RADS) 2-5 nodules were included. MR images were retrospectively collected from 3 T and 1.5 T MRI vendors. Lesions were categorized into 242 benign and 275 HCC based on follow-up imaging for LR-2,3 and pathology results for LR-4,5 nodules and randomly divided into training (80%) and test (20%) sets. Preprocessing included resampling and normalization. Radiomics features were extracted from lesion volume-of-interest (VOI) on diffusion images. Scanner variability was corrected using ComBat harmonization method followed by high-correlation filter, PCA filter, and LASSO to select important features. The best classifier model was selected by 10-fold cross-validation, and accuracy was assessed on the test dataset. Results: In total, 1434 features were extracted, and subsequent classifiers were constructed based on the 16 most important selected features. Notably, support-vector machine (SVM) demonstrated better performance in the test dataset in distinguishing between benign and HCC nodules, achieving an accuracy of 0.92, sensitivity of 0.94, and specificity of 0.86. Conclusions: Utilizing diffusion-MRI radiomics, our study highlights the performance of SVM, trained on lesions’ diffusivity characteristics, in distinguishing benign and HCC nodules, ensuring clinical potential. It is suggested that further evaluations be conducted on multicentre datasets to address harmonization challenges. Advances in knowledge: Integration of diffusion radiomics for monitoring water restriction patterns as tumour histopathological index, with machine learning models demonstrates potential for achieving a reliable noninvasive method to improve the current diagnostic criteria.