Diagnostic Value of MRI Features in Dual-phenotype Hepatocellular Carcinoma: A Preliminary Study.

This study aimed to explore the magnetic resonance imaging (MRI) features of dual-phenotype hepatocellular carcinoma (DPHCC) and their diagnostic value.The data of 208 patients with primary liver cancer were retrospectively analysed between January 2016 and June 2021. Based on the pathological diagnostic criteria, 27 patients were classified into the DPHCC group, 113 patients into the noncholangiocyte-phenotype hepatocellular carcinoma (NCPHCC) group, and 68 patients with intrahepatic cholangiocarcinoma (ICC) were classified into the ICC group. Two abdominal radiologists reviewed the preoperative MRI features by a double-blind method. The MRI features and key laboratory and clinical indicators were compared between the groups. The potentially valuable MRI features and key laboratory and clinical characteristics for predicting DPHCC were identified by univariate and multivariate analyses, and the odds ratios (ORs) were recorded. In multivariate analysis, tumour without capsule (P = 0.046, OR = 9.777), dynamic persistent enhancement (P = 0.006, OR = 46.941), and targetoid appearance on diffusion-weighted imaging (DWI) (P = 0.021, OR = 30.566) were independently significant factors in the detection of DPHCC compared to NCPHCC. Serum alpha-fetoprotein (AFP) > 20 µg/L (P = 0.036, OR = 67.097) and prevalence of hepatitis B virus (HBV) infection (P = 0.020, OR = 153.633) were independent significant factors in predicting DPHCC compared to ICC. The differences in other tumour marker levels and imaging features between the groups were not significant. In MR enhanced and diffusion imaging, tumour without capsule, persistent enhancement and DWI targetoid findings, combined with AFP > 20 µg/L and HBV infection-positive laboratory results, can help to diagnose DPHCC and differentiate it from NCPHCC and ICC. These results suggest that clinical, laboratory and MRI features should be integrated to construct an AI diagnostic model for DPHCC.

Development of Deep Learning-based Automatic Scan Range Setting Model for Lung Cancer Screening Low-dose CT Imaging.

RATIONALE AND OBJECTIVES: To develop an automatic setting of a deep learning-based system for detecting low-dose computed tomography (CT) lung cancer screening scan range and compare its efficiency with the radiographer's performance. MATERIALS AND METHODS: This retrospective study was performed using 1984 lung cancer screening low-dose CT scans obtained between November 2019 and May 2020. Among 1984 CT scans, 600 CT scans were considered suitable for an observational study to explore the relationship between the scout landmarks and the actual lung boundaries. Further, 1144 CT scans data set was used for the development of a deep learning-based algorithm. This data set was split into an 8:2 ratio divided into a training set (80%, n = 915) and a validation set (20%, n = 229). The performance of the deep learning algorithm was evaluated in the test set (n = 240) using actual lung boundaries and radiographers' scan ranges. RESULTS: The mean differences between the upper and lower boundaries of the deep learning-based algorithm and the actual lung boundaries were 4.72 ± 3.15 mm and 16.50 ± 14.06 mm, respectively. The accuracy and over-scanning of the scan ranges generated by the system were 97.08% (233/240) and 0% (0/240) for the upper boundary, and 96.25% (231/240) and 29.58% (71/240) for the lower boundary. CONCLUSION: The developed deep learning-based algorithm system can effectively predict lung cancer screening low-dose CT scan range with high accuracy using only the frontal scout.

How does the pancreatic solid pseudopapillary neoplasm confuse us: Analyzing from the point view of MRI-based radiomics?

OBJECTIVES: To construct MRI-based radiomics logistic model in differentiating solid pseudopapillary neoplasm (SPN) from three differential diseases containing adenocarcinoma, neuroendocrine tumor (NET), and cystadenoma of pancreas. MATERIALS AND METHODS: A total of 21 SPNs and 140 differential diseases were enrolled. The MRI images of T1WI, T2WI, DWI, and contrast-enhanced (CE) sequences were taken to delineate the volume of interest, and the corresponding radiomics features were calculated. After the preprocess of data balance and image standardize, the data was divided into training set (6 SPNs and 42 differential diseases) and validation set (15 SPNs and 98 differential diseases) with a proportion of 7:3, randomly. Then after feature selection, four MRI-based logistic models included T1WI, T2WI, DWI, CE, and sum logistic models (Log-T1WI, Log-T2WI, Log-DWI, Log-CE, and Log-sum) were established. The receiver operation curve (ROC) was depicted to evaluate the efficacy of each model. RESULTS: To the single MRI sequence, the AUCs of Log-T1WI, Log-T2WI, Log-DWI, and Log-CE were similar. Seemingly the AUCs of Log-T2WI were slightly higher with 0. 876 (95%CI, 0.797-0.956) in the training set and 0.853 (95%CI, 0.708-0.998) in the validation set. The Log-sum of four MRI sequences displayed better differentiating efficiency, with AUCs of 0.929 (95%CI, 0.877-0.980) in the training set and 0.925 (95%CI, 0.845-1.000) in the validation set. The Log-Ra/Clin model combined clinical information and radiomics showed the highest AUC of 0.962 (95%CI, 0.919-0.985). CONCLUSIONS: MRI-based radiomics analysis helped to discern SPNs from radiologically misdiagnosed adenocarcinoma, neuroendocrine tumor, and cystadenoma of pancreas. The efficacy of single sequence logistic model was similar. The Log-sum combined four sequences and Log-Ra/Clin combined clinical information and radiomics demonstrated the better performance in distinction.