Bridging the Gap between Structured and Free-form Radiology Reporting: A Case-study on Coronary CT Angiography

Free-form radiology reports associated with coronary computed tomography angiography (CCTA) include nuanced and complicated linguistics to report cardiovascular disease. Standardization and interpretation of such reports is crucial for clinical use of CCTA. Coronary Artery Disease Reporting and Data System (CAD-RADS) has been proposed to achieve such standardization by implementing a strict template-based report writing and assignment of a score between 0 and 5 indicating the severity of coronary artery lesions. Even after its introduction, free-form unstructured report writing remains popular among radiologists. In this work, we present our attempts at bridging the gap between structured and unstructured reporting by natural language processing. We present machine learning models that while being trained only on structured reports, can predict CAD-RADS scores by analysis of free-text of unstructured radiology reports. The best model achieves 98% accuracy on structured reports and 92% 1-margin accuracy (difference of \le 1 in the predicted and the actual scores) for free-form unstructured reports. Our model also performs well under very difficult circumstances including nuanced and widely varying terminology used for reporting cardiovascular functions and diseases, scarcity of labeled data for training our model, and uneven class label distribution.

Interventional Treatment of Bronchiectasis Macrosomia Based on Multirow CT Tomography Monitoring

We present in this paper an in-depth study and analysis of bronchiectasis haemoptysis by multirow CT tomography and a multifaceted treatment and analysis of the interventions monitored by the scan. Although coronary CT is of great clinical value in the diagnosis and monitoring of coronary artery disease, the potential radiation damage caused by coronary CT should not be underestimated because CT imaging is based on X-rays and the actual effective dose is 5–30 mSv, which is reported in the literature to be high when using conventional imaging modalities for coronary CT. Although there is no direct evidence of a definite causal relationship between X-ray exposure during CT examinations and tumorigenesis, theoretically, even small doses of radiation exposure may pose some potential health risk. Therefore, in clinical practice, coronary CT examinations should be performed in strict compliance with the radiation protection rule “as low as reasonably achievable” (ALARA) recognized by the radiation industry. For longitudinal openings in the range of 0° to 59° and transverse openings in the range of 0° to 44°, the CB2 catheter is significantly more stable than the MIK catheter, and for longitudinal openings in the range of 60° to 119° and transverse openings in the range of 0° to 44°, the CB2 catheter is more stable than the MIK catheter. For longitudinal openings from 0° to 120° and lateral openings from 45° to 90°, there was no significant difference in cannulation stability between the CB2 and MIK catheters. There was a potential tendency for MIK cannulation stability to be higher than CB2 for longitudinal openings in the range of 120° to 180° and lateral openings in the range of 45° to 90°, but there was no significant difference.