MVI-Mind: A Novel Deep-Learning Strategy Using Computed Tomography (CT)-Based Radiomics for End-to-End High Efficiency Prediction of Microvascular Invasion in Hepatocellular Carcinoma

Abstract

Microvascular invasion (MVI) in hepatocellular carcinoma (HCC) directly affects a patient’s prognosis. The development of preoperative noninvasive diagnostic methods is significant for guiding optimal treatment plans. In this study, we investigated 138 patients with HCC and presented a novel end-to-end deep learning strategy based on computed tomography (CT) radiomics (MVI-Mind), which integrates data preprocessing, automatic segmentation of lesions and other regions, automatic feature extraction, and MVI prediction. A lightweight transformer and a convolutional neural network (CNN) were proposed for the segmentation and prediction modules, respectively. To demonstrate the superiority of MVI-Mind, we compared the framework’s performance with that of current, mainstream segmentation, and classification models. The test results showed that MVI-Mind returned the best performance in both segmentation and prediction. The mean intersection over union (mIoU) of the segmentation module was 0.9006, and the area under the receiver operating characteristic curve (AUC) of the prediction module reached 0.9223. Additionally, it only took approximately 1 min to output a prediction for each patient, end-to-end using our computing device, which indicated that MVI-Mind could noninvasively, efficiently, and accurately predict the presence of MVI in HCC patients before surgery. This result will be helpful for doctors to make rational clinical decisions.

Dual-Energy Computed Tomography Iodine Imaging Combined with Laboratory Data for Preoperative Evaluation of Microvascular Invasion in Patients with Hepatocellular Carcinoma: A Two-Center Study

“…Although conventional CT signs such as nonsmooth boundaries, hypohalos, and internal arteries may suggest the presence of MVI, the diagnostic accuracy relies on image quality and expertise of the radiologist. MVI prediction based on deep learning methods is considered a reliable method [10,[28][29][30], and such methods are being increasingly well-established; however, clear interpretable quantitative metrics are still required. Recent studies have shown that quantitative IC plays an important role in tumor diagnosis.…”

“…However, the use of one or two morphological features to establish MVI diagnosis is di cult and inaccurate. Therefore, it is important to improve the diagnostic accuracy by combining quantitative parameters with morphological features [8][9][10]. Radiomics employs high-throughput computation to extract multiple quantitative features from medical images (such as computed tomography [CT] and magnetic resonance imaging [MRI]), which can reveal intratumoral heterogeneity [11].…”

Data-Driven Assisted Decision Making for Surgical Procedure of Hepatocellular Carcinoma Resection and Prognostic Prediction: Development and Validation of Machine Learning Models

“…To automate surgical-procedure-assisted decision making, deep learning-based lesion segmentation models were proposed. In this study, a lightweight transformer architecture called Segformer [ 20 ] was adopted for automatic segmentation of liver tumors, which not only reduced the difficulty of training, but also verified better performance [ 21 ]. The architecture includes a novel hierarchical Transformer encoder and a lightweight all-multilayer perceptron (MLP) decoder.…”

Deep learning based radiomics for gastrointestinal cancer diagnosis and treatment: A minireview

“…The results produced by the four models were excellent, with the DL model achieving better results for a few metrics such as AUC (0.906), and sensitivity (93.2%) in the validation set. Wang et al [ 53 ] devised a new DL model named MVI-Mind that consisted of a light-weight transformer for segmentation and a CNN for prediction of microvascular invasion, and several DL techniques were used to compare the proposed methods. The MVI-Mind attained highest mean intersection over union of 0.9006 and accuracy of 99.47% as compared with other DL segmentation algorithms, and it maintained its superiority in prediction and obtained AUC values of 0.9223, 0.8962, and 0.9100 for arterial phase, portal venous phase and delayed period CT images, respectively.…”