The added value of PET/Ce-CT/DW-MRI fusion in assessment of hepatic focal lesions: PET/Ce-CT/DW-MRI fusion in hepatic focal lesion

Radiomics Study for Differentiating Focal Hepatic Lesions Based on Unenhanced CT Images

Objectives

To investigate the feasibility of computer-aided discriminative diagnosis among hepatocellular carcinoma (HCC), hepatic metastasis, hepatic hemangioma, hepatic cysts, hepatic adenoma, and hepatic focal nodular hyperplasia, based on radiomics analysis of unenhanced CT images.

Methods

452 patients with 77 with HCC, 104 with hepatic metastases, 126 with hepatic hemangioma, 99 with hepatic cysts, 24 with FNH, 22 with HA, who underwent CT examination from 2016 to 2018, were included. Radcloud Platform was used to extract radiomics features from manual delineation on unenhanced CT images. Most relevant radiomic features were selected from 1409 via LASSO (least absolute shrinkage and selection operator). The whole dataset was divided into training and testing set with the ratio of 8:2 using computer-generated random numbers. Support Vector Machine (SVM) was used to establish the classifier.

Results

The computer-aided diagnosis model was established based on radiomic features of unenhanced CT images. 27 optimal discriminative features were selected to distinguish the six different histopathological types of all lesions. The classifiers had good diagnostic performance, with the area under curve (AUC) values greater than 0.900 in training and validation groups. The overall accuracy of the training and testing set about differentiating the six different histopathological types of all lesions was 0.88 and 0.76 respectively. 34 optimal discriminative were selected to distinguish the benign and malignant tumors. The overall accuracy in the training and testing set was 0.89and 0.84 respectively.

Conclusions

The computer-aided discriminative diagnosis model based on unenhanced CT images has good clinical potential in distinguishing focal hepatic lesions with noninvasive radiomic features.

Three-dimensional structure tensor based PET/CT fusion in gradient domain

Gradient based image fusion can more effectively incorporate edge details using structure tensor, which is successfully used in 2D image fusion. In this study, we generalized and applied this gradient based image fusion method into 3D for non-small cell lung cancer PET/CT image fusion. According the characteristic of lung PET/CT images, we proposed a novel 3D structure tensor based feature, which can be used to construct a weighted structure tensor containing important local detail of both PET and CT images. The fusion gradient domain is deduced from a rank one tensor, which is the closest approximation of the weighted structure tensor in geometry. Based on the fusion gradient domain, final PET/CT fusion image is obtained by solving a Poisson equation. Comparing with the wavelet transform based fusion result, the average information entropy and average gradient measure of proposed fusion method increase 13.5% and 42.3%, respectively. The experimental results show that the proposed fusion method enables to effectively preserve lung vessel structure and sphere-like lesion detail while produces clear, stable and well consistent fusion images.