Automating Scoliosis Measurements in Radiographic Studies with Machine Learning: Comparing Artificial Intelligence and Clinical Reports.

Scoliosis is a condition of abnormal lateral spinal curvature affecting an estimated 2 to 3% of the US population, or seven million people. The Cobb angle is the standard measurement of spinal curvature in scoliosis but is known to have high interobserver and intraobserver variability. Thus, the objective of this study was to build and validate a system for automatic quantitative evaluation of the Cobb angle and to compare AI generated and human reports in the clinical setting. After IRB was obtained, we retrospectively collected 2150 frontal view scoliosis radiographs at a tertiary referral center (January 1, 2019, to January 1, 2021, ≥ 16 years old, no hardware). The dataset was partitioned into 1505 train (70%), 215 validation (10%), and 430 test images (20%). All thoracic and lumbar vertebral bodies were segmented with bounding boxes, generating approximately 36,550 object annotations that were used to train a Faster R-CNN Resnet-101 object detection model. A controller algorithm was written to localize vertebral centroid coordinates and derive the Cobb properties (angle and endplate) of dominant and secondary curves. AI-derived Cobb angle measurements were compared to the clinical report measurements, and the Spearman rank-order demonstrated significant correlation (0.89, p < 0.001). Mean difference between AI and clinical report angle measurements was 7.34° (95% CI: 5.90-8.78°), which is similar to published literature (up to 10°). We demonstrate the feasibility of an AI system to automate measurement of level-by-level spinal angulation with performance comparable to radiologists.

Definitive Chemoradiation With Full-dose Gemcitabine for Unresectable Pancreatic Cancer: Efficacy of Involved-Field Radiotherapy.

OBJECTIVES: Definitive chemoradiotherapy for unresectable pancreatic cancer has traditionally involved 5-fluorouracil-based chemotherapy. Our institution has a long history of combining gemcitabine and radiotherapy (RT), and performed a retrospective review of all patients treated in this manner. MATERIALS AND METHODS: We reviewed the records of 180 patients treated from 1999 to 2012. Mean RT dose was 40.9 Gy in 2.2-Gy fractions, and targeted only radiographically apparent disease. Ninety-six percent of patients received full-dose gemcitabine-based chemotherapy with RT. Kaplan-Meier was used to analyze time-to-event endpoints, and Cox regression models were used to assess significant prognostic variables. RESULTS: Eighty-nine percent of patients completed RT without a toxicity-related treatment break. Median follow-up was 10.2 months. Twenty-nine percent of patients had a radiographic decrease in primary tumor size following treatment. Median overall survival was 11.8 months, time to distant metastasis (TDM) was 6.7 months, and time to local recurrence (TLR) was 8.3 months. On multivariate analysis, male sex, lower performance status, and higher posttreatment CA 19-9 level predicted for worse overall survival. Posttreatment, CA 19-9 was also associated with TDM and TLR, and radiographic tumor response was associated with better TLR. CONCLUSION: Definitive chemoradiation using full-dose gemcitabine is well tolerated and achieves survival outcomes comparable to reported trials in the literature.