Anatomically Localized Detection of Six Acute Abdominal Emergencies on CT Using Multi-window Deep Learning: Development and Validation.
Authors
Affiliations (2)
Affiliations (2)
- Budapest University of Technology and Economics, Budapest, Hungary. [email protected].
- Department of Radiology, Ankara Bilkent City Hospital, Ankara, Türkiye.
Abstract
The purpose of this study is to develop and retrospectively validate a deep learning system for the classification and anatomically interpretable localization of six acute abdominal emergencies on CT using multi-window Hounsfield Unit (HU) encoding. A publicly available national teleradiology dataset of 1274 patients (42,922 bounding box annotations) was used for training and internal validation (896/189/189 patient-level split). Each CT slice was encoded into three diagnostic HU windows (soft tissue, bone/stone, angio/liver). A YOLOv11-Large model with a stride-4 (P2) head was trained at <math xmlns="http://www.w3.org/1998/Math/MathML"><mrow><mn>1280</mn> <mo>×</mo> <mn>1280</mn></mrow> </math> . Localization was evaluated using the clinical nine-region abdominal grid, and specificity was assessed in 80 target-negative patients. External validation used a radiologist-adjudicated 280-patient Stanford Merlin cohort (US), with model weights and thresholds applied without modification. Internal macro AUROC was 0.941, and macro F1 was 76.1%. Nine-region localization accuracy was 99.5% among detected cases and 90.9% including missed detections. Specificity in the target-negative cohort was 86.2%. On the external Stanford Merlin cohort, macro AUROC was 0.879 with all six classes <math xmlns="http://www.w3.org/1998/Math/MathML"><mrow><mo>≥</mo> <mn>0.80</mn></mrow> </math> ; AAA reached F1 0.889 at frozen thresholds; macro F1 was 0.545, increasing to 0.648 after recalibration. A multi-window CT detection model classified six acute abdominal emergencies with high discrimination on internal testing and preserved moderate-to-high discrimination on an external Stanford Merlin cohort. Region-level evaluation using the nine-region abdominal grid provided a clinically interpretable localization endpoint complementary to conventional detection metrics. However, variable class-level F1, reduced external operating-point performance, and retrospective design indicate that multisite prospective validation and site-specific threshold calibration are required before clinical deployment.