Cancer is one of the common diseases. Quantitative biomarkers extracted from standard-of-care computed tomography (CT) scan can create a robust clinical decision tool for the diagnosis of hepatocellular carcinoma (HCC). According to the current clinical methods, the situation usually accounts for high expenditure of time and resources. To improve the current clinical diagnosis and therapeutic procedure, this paper proposes a deep learning-based approach, called Successive Encoder-Decoder (SED), to assist in the automatic interpretation of liver lesion/tumor segmentation through CT images. The SED framework consists of two different encoder-decoder networks connected in series. The first network aims to remove unwanted voxels and organs and to extract liver locations from CT images. The second network uses the results of the first network to further segment the lesions. For practical purpose, the predicted lesions on individual CTs were extracted and reconstructed on 3D images. The experiments conducted on 4300 CT images and LiTS dataset demonstrate that the liver segmentation and the tumor prediction achieved 0.92 and 0.75 in Dice score, respectively, by as-proposed SED method.

The research was based on the image recognition technology of artificial intelligence, which is expected to assist physicians in making correct decisions through deep learning. The liver dataset used in this study was derived from the open source website (LiTS) and the data provided by the Kaohsiung Chang Gung Memorial Hospital. CT images were used for organ recognition and lesion segmentation; the proposed Residual-Dense-Attention (RDA) U-Net can achieve high accuracy without the use of contrast. In this study, U-Net neural network was used to combine ResBlock in ResNet with Dense Block in DenseNet in the coder part, allowing the training to maintain the parameters while reducing the overall recognition computation time. The decoder was equipped with Attention Gates to suppress the irrelevant areas of the image while focusing on the significant features. The RDA model was used to identify and segment liver organs and lesions from CT images of the abdominal cavity, and excellent segmentation was achieved for the liver located on the left side, right side, near the heart, and near the lower abdomen with other organs. Better recognition was also achieved for large, small, and single and multiple lesions. The study was able to reduce the overall computation time by about 28% compared to other convolutions, and the accuracy of liver and lesion segmentation reached 96% and 94.8%, with IoU values of 89.5% and 87%, and AVGDIST of 0.28 and 0.80, respectively.

Background: Since the advent of a new generation of inflow-sensitive inversion recovery (IFIR) technology, three-dimensional non-contrast-enhanced magnetic resonance angiography is being used to obtain hepatic vessel images without applying gadolinium contrast agent. The purpose of this study was to explore the diagnostic efficacy of non-contrast-enhanced magnetic resonance angiography (non-CE MRA), contrast-enhanced magnetic resonance angiography (CMRA), and computed tomography angiography (CTA) in the preoperative evaluation of living liver donors. Methods: A total of 43 liver donor candidates who were evaluated for living donor liver transplantation completed examinations. Donors’ age, gender, renal function (eGFR), and previous CTA and imaging were recorded before non-CE MRA and CMRA. CTA images were used as the standard. Results: Five different classifications of hepatic artery patterns (types I, III, V, VI, VIII) and three different classifications of portal vein patterns (types I, II, and III) were identified among 43 candidates. The pretransplant vascular anatomy was well identified using combined non-CE MRA and CMRA of hepatic arteries (100%), PVs (98%), and hepatic veins (100%) compared with CTA images. Non-CE MRA images had significantly stronger contrast signal intensity of portal veins (p < 0.01) and hepatic veins (p < 0.01) than CMRA. No differences were found in signal intensity of the hepatic artery between non-CE MRA and CMRA. Conclusion: Combined non-CE MRA and CMRA demonstrate comparable diagnostic ability to CTA and provide enhanced biliary anatomy information that assures optimum donor safety.

Due to the fact that previous studies have rarely investigated the recognition rate discrepancy and pathology data error when applied to different databases, the purpose of this study is to investigate the improvement of recognition rate via deep learning-based liver lesion segmentation with the incorporation of hospital data. The recognition model used in this study is H-DenseUNet, which is applied to the segmentation of the liver and lesions, and a mixture of 2D/3D Hybrid-DenseUNet is used to reduce the recognition time and system memory requirements. Differences in recognition results were determined by comparing the training files of the standard LiTS competition data set with the training set after mixing in an additional 30 patients. The average error value of 9.6% was obtained by comparing the data discrepancy between the actual pathology data and the pathology data after the analysis of the identified images imported from Kaohsiung Chang Gung Memorial Hospital. The average error rate of the recognition output after mixing the LiTS database with hospital data for training was 1%. In the recognition part, the Dice coefficient was 0.52 after training 50 epochs using the standard LiTS database, while the Dice coefficient was increased to 0.61 after adding 30 hospital data to the training. After importing 3D Slice and ITK-Snap software, a 3D image of the lesion and liver segmentation can be developed. It is hoped that this method could be used to stimulate more research in addition to the general public standard database in the future, as well as to study the applicability of hospital data and improve the generality of the database.

Microvascular invasion (MVI) in hepatocellular carcinoma (HCC) is a histopathological marker and risk factor for HCC recurrence. We integrated diffusion-weighted imaging (DWI) and magnetic resonance (MR) image findings of tumors into a scoring system for predicting MVI. In total, 228 HCC patients with pathologically confirmed MVI who underwent surgical resection or liver transplant between November 2012 and March 2021 were enrolled retrospectively. Patients were divided into a right liver lobe group (n = 173, 75.9%) as the model dataset and a left liver lobe group (n = 55, 24.1%) as the model validation dataset. Multivariate logistic regression identified two-segment involved tumor (Score: 1; OR: 3.14; 95% CI: 1.22 to 8.06; p = 0.017); ADC_min ≤ 0.95 × 10⁻³ mm²/s (Score: 2; OR: 10.88; 95% CI: 4.61 to 25.68; p = 0.000); and largest single tumor diameter ≥ 3 cm (Score: 1; OR: 5.05; 95% CI: 2.25 to 11.30; p = 0.000), as predictive factors for the scoring model. Among all patients, sensitivity was 89.66%, specificity 58.04%, positive predictive value 68.87%, and negative predictive value 84.41%. For validation of left lobe group, sensitivity was 80.64%, specificity 70.83%, positive predictive value 78.12%, and negative predictive value 73.91%. The scoring model using ADC_min, largest tumor diameter, and two-segment involved tumor provides high sensitivity and negative predictive value in MVI prediction for use in routine functional MR.