Prediction of treatment response to transarterial radioembolization of liver metastases: Radiomics analysis of pre-treatment cone-beam CT: A proof of concept study

Abstract

To investigate the potential of texture analysis and machine learning to predict treatment response to transarterial radioembolization (TARE) on pre-interventional cone-beam computed tomography (CBCT) images in patients with liver metastases. Materials and Methods: In this IRB-approved retrospective single-center study 36 patients with a total of 104 liver metastases (56 % male, mean age 61.1 ± 13 years) underwent CBCT prior to TARE and follow-up imaging 6 months after therapy. Treatment response was evaluated according to RECIST version 1.1 and dichotomized into disease control (partial response/stable disease) versus disease progression (progressive disease). After target lesion segmentation, 104 radiomics features corresponding to seven different feature classes were extracted with the pyRadiomics package. After dimension reduction machine learning classifications were performed on a custom artificial neural network (ANN). Ten-fold cross validation on a previously unseen test data set was performed. Results: The average administered cumulative activity from TARE was 1.6 Gbq (± 0.5 Gbq). At a mean follow-up of 5.9 ± 0.8 months disease control was achieved in 82 % of metastases. After dimension reduction, 15 of 104 (15 %) texture analysis features remained for further analysis. On a previously unseen set of liver metastases the Multilayer Perceptron ANN yielded a sensitivity of 94.2 %, specificity of 67.7 % and an area-under-the receiver operating characteristics curve of 0.85. Conclusion:Our study indicates that texture analysis-based machine learning may has potential to predict treatment response to TARE using pre-treatment CBCT images of patients with liver metastases with high accuracy.leading to an accumulation in liver metastases with resulting radiation-induced cell death [2]. As TARE is a costly and highly demanding therapy requiring a multi-disciplinary team including interventional radiologists, oncologists and nuclear medicine specialists, careful patient selection is crucial.Previous studies have investigated the value of pre-treatment

Performance and clinical applicability of machine learning in liver computed tomography imaging: a systematic review

“…The last and most diverse category we found eligible to compare was miscellaneous, including 29 journal article [ 6 , 8 , 9 , 33 , 50 , 52 , 56 , 71 , 161 , 164 , 173 – 179 , 181 – 184 , 186 – 188 , 191 , 194 , 195 , 205 , 206 ] and 8 proceeding paper [ 27 , 180 , 185 , 189 , 190 , 192 , 193 , 207 ] total thirty-seven studies. The aims of the studies are clinical-oriented.…”

Imaging in interventional oncology, the better you see, the better you treat

“…Only some pilot studies have suggested radiomics features might be associated with outcome after TARE for HCC, liver metastases and intrahepatic cholangiocarcinoma. [89][90][91][92][93] Furthermore, good results were found for CT-radiomics predicting completeness of ablation in colorectal liver metastases, adrenal metastases and pulmonary malignancies. 94,95 In addition, Ma et al 96 used radiomics from contrast-enhanced ultrasound (CEUS) for prediction of recurrence in HCC lesions.…”

“…Transarterial radioembolization (TARE) has been investigated less extensively compared to TACE. Only some pilot studies have suggested radiomics features might be associated with outcome after TARE for HCC, liver metastases and intrahepatic cholangiocarcinoma 89–93 . Furthermore, good results were found for CT‐radiomics predicting completeness of ablation in colorectal liver metastases, adrenal metastases and pulmonary malignancies 94,95 .…”

Machine Learning Combined with Radiomics Facilitating the Personal Treatment of Malignant Liver Tumors

“…Nevertheless, they did not observe significant additional prognostic value in these radiomics features for predicting overall survival when compared to information obtained solely from clinical parameters. Kobe et al [42] aimed to predict treatment response to TARE in patients with liver metastases using pre-treatment CT images, employing both traditional machine learning and deep learning algorithms. The model achieved an AUC of 0.850, a sensitivity of 94.2%, and a specificity of 67.7% in a testing set.…”