Machine Learning Models for Prediction of Posttreatment Recurrence in Early-Stage Hepatocellular Carcinoma Using Pretreatment Clinical and MRI Features: A Proof-of-Concept Study

Background: The aim was to investigate the role of pre-ablation tumor radiomics in predicting pathologic treatment response in patients with early-stage hepatocellular carcinoma (HCC) who underwent liver transplant. Methods: Using data collected from 2005–2015, we included adult patients who (1) had a contrast-enhanced MRI within 3 months prior to ablation therapy and (2) underwent liver transplantation. Demographics were obtained for each patient. The treated hepatic tumor volume was manually segmented on the arterial phase T1 MRI images. A vector with 112 radiomic features (shape, first-order, and texture) was extracted from each tumor. Feature selection was employed through minimum redundancy and maximum relevance using a training set. A random forest model was developed based on top radiomic and demographic features. Model performance was evaluated by ROC analysis. SHAP plots were constructed in order to visualize feature importance in model predictions. Results: Ninety-seven patients (117 tumors, 31 (32%) microwave ablation, 66 (68%) radiofrequency ablation) were included. The mean model for end-stage liver disease (MELD) score was 10.5 ± 3. The mean follow-up time was 336.2 ± 179 days. Complete response on pathology review was achieved in 62% of patients at the time of transplant. Incomplete pathologic response was associated with four features: two first-order and two GLRM features using univariate logistic regression analysis (p < 0.05). The random forest model included two radiomic features (diagnostics maximum and first-order maximum) and four clinical features (pre-procedure creatinine, pre-procedure albumin, age, and gender) achieving an AUC of 0.83, a sensitivity of 82%, a specificity of 67%, a PPV of 69%, and an NPV of 80%. Conclusions: Pre-ablation MRI radiomics could act as a valuable imaging biomarker for the prediction of tumor pathologic response in patients with HCC.

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Machine Learning-Based Radiomic Features on Pre-Ablation MRI as Predictors of Pathologic Response in Patients with Hepatocellular Carcinoma Who Underwent Hepatic Transplant

Tabari

D'Amore

Cox

et al. 2023

“…AI tools developed for specific, narrow tasks, such as case assignment, lesion detection, and segmentation of regions of interest, are critical for oncological imaging. Reconstruction of images using DL algorithms has shown remarkable improvements in image contrast and SNR for CT [19,47,48] and MRI [49][50][51]. As mentioned above, manually segmenting longitudinal tumor volume is laborious, time-consuming, and difficult to perform accurately.…”

Section: Specific-narrow Tasks Developed Using Ai For Radiological Wo...mentioning

confidence: 99%

“…Previously developed auto-segmentation methods were sensitive to changes in scanning parameters, resolution, and image quality, which limited their clinical value [52]. AI-based algorithms have been successful at tumor segmentation and have shown better accuracy and robustness to imaging acquisition differences [49][50][51]. In parallel, new AI tools have been developed for the quantification of image features from both radiomics and lesion classification [16,53,54].…”

Section: Specific-narrow Tasks Developed Using Ai For Radiological Wo...mentioning

confidence: 99%

Artificial Intelligence in CT and MR Imaging for Oncological Applications

Paudyal

Shah

Akın

et al. 2023

Cancer care increasingly relies on imaging for patient management. The two most common cross-sectional imaging modalities in oncology are computed tomography (CT) and magnetic resonance imaging (MRI), which provide high-resolution anatomic and physiological imaging. Herewith is a summary of recent applications of rapidly advancing artificial intelligence (AI) in CT and MRI oncological imaging that addresses the benefits and challenges of the resultant opportunities with examples. Major challenges remain, such as how best to integrate AI developments into clinical radiology practice, the vigorous assessment of quantitative CT and MR imaging data accuracy, and reliability for clinical utility and research integrity in oncology. Such challenges necessitate an evaluation of the robustness of imaging biomarkers to be included in AI developments, a culture of data sharing, and the cooperation of knowledgeable academics with vendor scientists and companies operating in radiology and oncology fields. Herein, we will illustrate a few challenges and solutions of these efforts using novel methods for synthesizing different contrast modality images, auto-segmentation, and image reconstruction with examples from lung CT as well as abdome, pelvis, and head and neck MRI. The imaging community must embrace the need for quantitative CT and MRI metrics beyond lesion size measurement. AI methods for the extraction and longitudinal tracking of imaging metrics from registered lesions and understanding the tumor environment will be invaluable for interpreting disease status and treatment efficacy. This is an exciting time to work together to move the imaging field forward with narrow AI-specific tasks. New AI developments using CT and MRI datasets will be used to improve the personalized management of cancer patients.

“…They found better risk prediction of HCC recurrence after transplantation when the Milan criteria was added to AFP and DCP biomarkers. Iseke et al used MR imaging features and three ML models to predict posttreatment HCC recurrence in 120 patients with early-stage HCC who were initially eligible for liver transplant and had undergone treatment by resection, thermal ablation, or transplant [73]. They found that the ML model that incorporated imaging features was better than the ML that incorporated clinical features (AUC: 0.76 vs. 0.68, respectively; p = 0.03), but there was no significant difference between the clinical model and the combined model with both imaging and clinical data (AUC: 0.76 vs. 0.76, respectively, p > 0.05).…”

Section: The Role Of Ai In Facilitating Biomarkers To Predict the Rec...mentioning

confidence: 99%

The Role of Artificial Intelligence in the Detection and Implementation of Biomarkers for Hepatocellular Carcinoma: Outlook and Opportunities

Mansur

Vrionis

Charles

et al. 2023

Liver cancer is a leading cause of cancer-related death worldwide, and its early detection and treatment are crucial for improving morbidity and mortality. Biomarkers have the potential to facilitate the early diagnosis and management of liver cancer, but identifying and implementing effective biomarkers remains a major challenge. In recent years, artificial intelligence has emerged as a promising tool in the cancer sphere, and recent literature suggests that it is very promising in facilitating biomarker use in liver cancer. This review provides an overview of the status of AI-based biomarker research in liver cancer, with a focus on the detection and implementation of biomarkers for risk prediction, diagnosis, staging, prognostication, prediction of treatment response, and recurrence of liver cancers.