Tumor response prediction in 90Y radioembolization with PET-based radiomics features and absorbed dose metrics

Abstract

Purpose To evaluate whether lesion radiomics features and absorbed dose metrics extracted from post-therapy 90Y PET can be integrated to better predict outcomes in microsphere radioembolization of liver malignancies Methods Given the noisy nature of 90Y PET, first, a liver phantom study with repeated acquisitions and varying reconstruction parameters was used to identify a subset of robust radiomics features for the patient analysis. In 36 radioembolization procedures, 90Y PET/CT was performed within a couple of hours to extract 46 radiomics features and estimate absorbed dose in 105 primary and metastatic liver lesions. Robust radiomics modeling was based on bootstrapped multivariate logistic regression with shrinkage regularization (LASSO) and Cox regression with LASSO. Nested cross-validation and bootstrap resampling were used for optimal parameter/feature selection and for guarding against overfitting risks. Spearman rank correlation was used to analyze feature associations. Area under the receiver-operating characteristics curve (AUC) was used for lesion response (at first follow-up) analysis while Kaplan-Meier plots and c-index were used to assess progression model performance. Models with absorbed dose only, radiomics only, and combined models were developed to predict lesion outcome. Results The phantom study identified 15/46 reproducible and robust radiomics features that were subsequently used in the patient models. A lesion response model with zone percentage (ZP) and mean absorbed dose achieved an AUC of 0.729 (95% CI 0.702–0.758), and a progression model with zone size nonuniformity (ZSN) and absorbed dose achieved a c-index of 0.803 (95% CI 0.790–0.815) on nested cross-validation (CV). Although the combined models outperformed the radiomics only and absorbed dose only models, statistical significance was not achieved with the current limited data set to establish expected superiority. Conclusion We have developed new lesion-level response and progression models using textural radiomics features, derived from 90Y PET combined with mean absorbed dose for predicting outcome in radioembolization. These encouraging, but limited results, will need further validation in independent and larger datasets prior to any clinical adoption.

Radiomics in Oncological PET Imaging: A Systematic Review—Part 2, Infradiaphragmatic Cancers, Blood Malignancies, Melanoma and Musculoskeletal Cancers

“…Moreover, 4 retrospective studies were identified for liver cancer [ 69 , 70 , 71 , 72 ] with an average of 65.5 included patients (range 47–99). Among them, 1 used a separate validation cohort [ 69 ].…”

“…Among them, 1 used a separate validation cohort [ 69 ]. Two studies focused on the response prediction of 90Y-transarterial radioembolization treatment, one using 18F-FDG [ 70 ], the other using post therapy 90Y PET [ 72 ]. One study aimed at differentiating between hepatic lymphoma and hepatocellular carcinoma (AUC 0.87 on the training set, no validation cohort) [ 71 ].…”

Artificial intelligence (AI) and machine learning (ML) in precision oncology: a review on enhancing discoverability through multiomics integration

“… 2 Deep learning (DL) methods avoid the manual feature calculation step and automatically learn features from the images, which becomes more favorable in the radiomics world. Radiomics has been applied to many diseases and different tasks, including cancer detection, 3 prediction of tumor stage, 4 tumor genotypes, 5 tumor response, 6,7 toxicity, 8 local control/failure, 9 and survival 10,11 in oncology.…”