A deep learning radiomics model based on CT images for predicting the biological activity of hepatic cystic echinococcosis

Abstract

Introduction: Hepatic cystic echinococcosis (HCE) is a widely seen parasitic infection. Biological activity is crucial for treatment planning. This work aims to explore the potential applications of a deep learning radiomics (DLR) model, based on CT images, in predicting the biological activity grading of hepatic cystic echinococcosis. Methods: A retrospective analysis of 160 patients with hepatic echinococcosis was performed (127 and 33 in training and validation sets). Volume of interests (VOIs) were drawn, and radiomics features and deep neural network features were extracted. Feature selection was performed on the training set, and radiomics score (Rad Score) and deep learning score (Deep Score) were calculated. Seven diagnostics models (based on logistic regression algorithm) for the biological activity grading were constructed using the selected radiomics features and two deep model features respectively. All models were evaluated using the receiver operating characteristic curve, and the area under the curve (AUC) was calculated. A nomogram was constructed using the combined model, and its calibration, discriminatory ability, and clinical utility were assessed. Results: 12, 6 and 10 optimal radiomics features, deep learning features were selected from two deep learning network (DLN) features, respectively. For biological activity grading of hepatic cystic echinococcosis, the combined model demonstrated strong diagnostic performance, with an AUC value of 0.888 (95% CI: 0.837-0.936) in the training set and 0.876 (0.761-0.964) in the validation set. The clinical decision analysis curve indicated promising results, while the calibration curve revealed that the nomogram's prediction result was highly compatible with the actual result. Conclusion: The DLR model can be used for predicting the biological activity grading of hepatic echinococcosis.

Keywords: 3D-ResNet; biological activity grading; deep learning; hepatic cystic echinococcosis; radiomics.

FIGURE 1

Demonstrates inclusion and exclusion workflow.

FIGURE 2

Workflow chart of the study. (A) VOI delineation, (B), Radiomics signature construction, (C) Deep learning signature construction, (D) DLR nomogram construction.

FIGURE 3

Selected radiomics and deep learning features. (A) Selected radiomics features, (B) Selected 3D-ResNet-34 features, (C) Selected 3D-ResNet-50 features.

FIGURE 4

ROC curves of radiomics, 3D-ResNet 34 and 3D-ResNet 50. (A) ROC curve of radiomics model, (B) ROC curve of 3DResNet 34 model, (C) ROC curve of 3DResNet 50 model.

FIGURE 5

ROC curves of radiomics and 3D-ResNet 34, Radiomics and 3D-ResNet 485 50, 3D-ResNet 34 and 3D-ResNet 50 and combined model. (A) ROC curve of radiomics and 3DResNet 34 model, (B) ROC curve of Radiomics and 3DResNet 50 model, (C) ROC curve of 3DResNet 34 and 3DResNet 50 model, (D) ROC curve of combined model.

FIGURE 6

(A) Constructed Nomogram; (B) calibration curve.

FIGURE 7

Decision curve.