Background: Liver fibrosis (LF) continues to develop and eventually progresses to cirrhosis. However, LF and early-stage cirrhosis (ESC) can be reversed in some cases, while advanced cirrhosis is almost impossible to cure. Advances in quantitative imaging techniques have made it possible to replace the gold standard biopsy method with non-invasive imaging, such as radiomics. Therefore, the purpose of this study is to develop a radiomics model to identify LF and ESC. Methods: Patients with LF ( n = 108) and ESC ( n = 116) were enrolled in this study. As a control, patients with healthy livers were involved in the study ( n = 145). Diffusion-weighted imaging (DWI) data sets with three b -values (0, 400, and 800 s/mm 2 ) of enrolled cases were collected in this study. Then, radiomics features were extracted from manually delineated volumes of interest. Two modeling strategies were performed after univariate analysis and feature selection. Finally, an optimal model was determined by the receiver operating characteristic area under the curve (AUC). Results: The optimal models were built in plan 1. For model 1 in plan 1, the AUCs of the training and validation cohorts were 0.973 (95% confidence interval [CI] 0.946–1.000) and 0.948 (95% CI 0.903–0.993), respectively. For model 2 in plan 1, the AUCs of the training and validation cohorts were 0.944, 95% CI 0.905 to 0.983, and 0.968, 95% CI 0.940 to 0.996, respectively. Conclusions: Radiomics analysis of DWI images allows for accurate identification of LF and ESC, and the non-invasive biomarkers extracted from the functional DWI images can serve as a better alternative to biopsy.

Objective Intensity‐modulated radiation therapy (IMRT) plays an increasingly important role in clinical applications, and dose verification is particularly crucial for each patient. In the present study, we retrospectively analyzed the results of dose verification in 924 actual IMRT plans, including the relationship between gamma pass rates and the location of lesions, and the total number of monitor units, and the maximum area of the collected dose. Methods All the 924 IMRT plans implemented in a Varian Trilogy accelerator between 1 January 2014 and 31 March 2016 at Shandong Cancer Hospital were acquired. The Varian Eclipse planning system was used for all treatment planning and verification. Then, actual implemented plans were transplanted into a water phantom. Subsequently, the derived fluence was compared with the actual measured fluence by gamma analysis with the gamma criteria (3%/3 mm). Results A total of 924 IMRT plans were categorized into six groups, including the brain, head and neck, chest, abdomen, pelvis, and breast. The gamma pass rate average was >98% for 902 IMRT plans, whereas 22 plans did not pass the first time. A correlation was observed between the treatment site and gamma pass rate (P = 0.017). Meanwhile, a negative correlation was observed between the gamma pass rate and the total number of monitor units (P < 0.001), and the largest area of the acquisition dose (P < 0.001), respectively. Varian Trilogy accelerator IMRT QA data has a stable pass rate with a 100 confidence limit (CL) value of 95.19. Conclusion There was a correlation between the pass rate and the treatment site, the total number of monitor units, and the maximum area of collected dose. When using Mapcheck for patient plan dose verification, the gamma pass rate is very high, and only a few of them need to be analyzed.