Deep Learning-Based CT Imaging for the Diagnosis of Liver Tumor

Abstract

The objective of this research was to investigate the application value of deep learning-based computed tomography (CT) images in the diagnosis of liver tumors. Fifty-eight patients with liver tumors were selected, and their CT images were segmented using a convolutional neural network (CNN) algorithm. The segmentation results were quantitatively evaluated using the Dice similarity coefficient (DSC), precision, and recall. All the patients were examined and diagnosed by CT enhanced delayed scan technique, and the CT scan results were compared with the pathological findings. The results showed that the DSC, precision, and recall of the CNN algorithm reached 0.987, 0.967, and 0.954, respectively. The images segmented by the CNN were clearer. The diagnostic result of the examination on 56 cases by CT enhanced delay scanning was consistent with that of pathological diagnosis. According to the result of pathological diagnosis, there were 6 cases with hepatic cyst, 9 with hepatic hemangioma, 12 cases with liver metastasis, 10 cases with hepatoblastoma, 3 cases with focal nodular hyperplasia, and 18 cases with primary liver cancer. The result of CT enhanced delay scanning on 58 patients was consistent with that of pathological diagnosis, and the total diagnostic coincidence rate reached 96.55%. In conclusion, the CNN algorithm can perform accurate and efficient segmentation, with high resolution, providing a more scientific basis for the segmentation of liver tumors in CT images. CT enhanced scanning technology has a good effect on the diagnosis and differentiation of liver tumor patients, with high diagnostic coincidence rate. It has important value for the diagnosis of liver tumor and is worthy of clinical application.

Figure 1

The basic structure of CNN.

Figure 2

The results of liver tumor image segmentation by different algorithms. (a) The original CT image of the liver tumor. (b) The segmentation results using the HED algorithm. (c) The segmentation results using the U-Net algorithm. (d) The segmentation results using the CNN algorithm.

Figure 3

Evaluation indicators of different lesion segmentation algorithms. (a) DSC comparison results of HED algorithm, CNN algorithm, and U-Net algorithm. (b) Precision comparison of HED algorithm, CNN algorithm, and U-Net algorithm. (c) Recall comparison of HED algorithm, CNN algorithm, and U-Net algorithm. ^∗Compared with CNN algorithm and U-Net algorithm, p < 0.05.

Figure 4

Diagnostic coincidence rate between CT scan and pathological results.