Multi-phase contrast-enhanced magnetic resonance image-based radiomics-combined machine learning reveals microscopic ultra-early hepatocellular carcinoma lesions

Abstract

Purpose This study aimed to investigate whether models built from radiomics features based on multiphase contrast-enhanced MRI can identify microscopic pre-hepatocellular carcinoma lesions. Methods We retrospectively studied 54 small hepatocellular carcinoma (SHCC, diameter < 2 cm) patients and 70 patients with hepatocellular cysts or haemangiomas from September 2018 to June 2021. For the former, two MRI scans were collected within 12 months of each other; the 2nd scan was used to confirm the diagnosis. The volumes of interest (VOIs), including SHCCs and normal liver tissues, were delineated on the 2nd scans, mapped to the 1st scans via image registration, and enrolled into the SHCC and internal-control cohorts, respectively, while those of normal liver tissues from patients with hepatocellular cysts or haemangioma were enrolled in the external-control cohort. We extracted 1132 radiomics features from each VOI and analysed their discriminability between the SHCC and internal-control cohorts for intra-group classification and the SHCC and external-control cohorts for inter-group classification. Five radial basis-function, kernel-based support vector machine (SVM) models (four corresponding single-phase models and one integrated from the four-phase MR images) were established. Results Among the 124 subjects, the multiphase models yielded better performance on the testing set for intra-group and inter-group classification, with areas under the receiver operating characteristic curves of 0.93 (95% CI, 0.85–1.00) and 0.97 (95% CI, 0.92–1.00), accuracies of 86.67% and 94.12%, sensitivities of 87.50% and 94.12%, and specificities of 85.71% and 94.12%, respectively. Conclusion The combined multiphase MRI-based radiomics feature model revealed microscopic pre-hepatocellular carcinoma lesions.

CT-based radiomics nomogram for differentiation of adrenal hyperplasia from lipid-poor adenoma: an exploratory study

“…Briefly, features of first-order and texture (GLCM, GLSZM, etc.) features reflected tumor heterogeneity and microenvironment, which is consistent with other studies [ 33 – 35 ].…”

Predictive value of ultrasonic artificial intelligence in placental characteristics of early pregnancy for gestational diabetes mellitus

“…Predicting GDM risk in pregnant women by identifying early pregnancy placental features through radiomics and deep learning methods could enable interventions and lifestyle changes to prevent GDM development ( 35 ). This approach also provides clinicians with sufficient time to formulate appropriate therapeutic strategies, reducing the harm associated with GDM or preventing its occurrence.…”

Machine learning methods for accurately predicting survival and guiding treatment in stage I and II hepatocellular carcinoma

“…ML algorithms have increasingly conspicuous applications within health care, with applications in HCC including the prediction of tumor characteristics by biochemical and clinical indicators, [ 26 , 27 ] prediction of postoperative adverse events by preoperative features, [ 28 , 29 ] and diagnosis by imaging, [ 30 – 32 ] among others. Since standard survival analysis is limited by the assumption of a linear combination of covariates, ML is proposed as a novel method for survival analysis.…”