Preliminary study for prediction of benign vertebral compression fracture age by quantitative water fraction using modified Dixon sequences: an imaging biomarker of fracture age.

PURPOSE: This study aimed to evaluate whether quantitative water fraction parameters could predict fracture age in patients with benign vertebral compression fractures (VCFs). METHODS: A total of 38 thoracolumbar VCFs in 27 patients imaged using modified Dixon sequences for water fraction quantification on 3-T MRI were retrospectively reviewed. To calculate quantitative parameters, a radiologist independently measured the regions of interest in the bone marrow edema (BME) of the fractures. Furthermore, five features (BME, trabecular fracture line, condensation band, cortical or end plate fracture line, and paravertebral soft-tissue change) were analyzed. The fracture age was evaluated based on clear-onset symptoms and previously available images. A correlation analysis between the fracture age and water fraction was evaluated using a linear regression model, and a multivariable analysis of the dichotomized fracture age model was performed. RESULTS: The water fraction ratio was the only significant factor and was negatively correlated with the fracture age of VCFs in multiple linear regression (p = 0.047), whereas the water fraction was not significantly correlated (p = 0.052). Water fraction and water fraction ratio were significant factors in differentiating the fracture age of 1 year in multiple logistic regression (odds ratio 0.894, p = 0.003 and odds ratio 0.986, p = 0.019, respectively). Using a cutoff of 0.524 for the water fraction, the area under the curve, sensitivity, and specificity were 0.857, 85.7%, and 87.1%, respectively. CONCLUSIONS: Water fraction is a good imaging biomarker for the fracture healing process. The water fraction ratio of the compression fractures can be used to predict the fracture age of benign VCFs.

The impact of artificial intelligence on the reading times of radiologists for chest radiographs.

Whether the utilization of artificial intelligence (AI) during the interpretation of chest radiographs (CXRs) would affect the radiologists' workload is of particular interest. Therefore, this prospective observational study aimed to observe how AI affected the reading times of radiologists in the daily interpretation of CXRs. Radiologists who agreed to have the reading times of their CXR interpretations collected from September to December 2021 were recruited. Reading time was defined as the duration in seconds from opening CXRs to transcribing the image by the same radiologist. As commercial AI software was integrated for all CXRs, the radiologists could refer to AI results for 2 months (AI-aided period). During the other 2 months, the radiologists were automatically blinded to the AI results (AI-unaided period). A total of 11 radiologists participated, and 18,680 CXRs were included. Total reading times were significantly shortened with AI use, compared to no use (13.3 s vs. 14.8 s, p < 0.001). When there was no abnormality detected by AI, reading times were shorter with AI use (mean 10.8 s vs. 13.1 s, p < 0.001). However, if any abnormality was detected by AI, reading times did not differ according to AI use (mean 18.6 s vs. 18.4 s, p = 0.452). Reading times increased as abnormality scores increased, and a more significant increase was observed with AI use (coefficient 0.09 vs. 0.06, p < 0.001). Therefore, the reading times of CXRs among radiologists were influenced by the availability of AI. Overall reading times shortened when radiologists referred to AI; however, abnormalities detected by AI could lengthen reading times.

[Machine Learning vs. Statistical Model for Prediction Modelling: Application in Medical Imaging Research]. / 예측모형의 ë¨¸ì‹ ëŸ¬ë‹ ë°©ë²•ë¡ ê³¼ í†µê³„í•™ì  ë°©ë²•ë¡ ì˜ 비교: 영상의학 연구에서의 ì ìš©.

Clinical prediction models has been increasingly published in radiology research. In particular, as a radiomics research is being actively conducted, the prediction model is developed based on the traditional statistical model, as well as machine learning, to account for the high-dimensional data. In this review, we investigated the statistical and machine learning methods used in clinical prediction model research, and briefly summarized each analytical method for statistical model, machine learning, and statistical learning. Finally, we discussed several considerations for choosing the prediction modeling method.