Automated Estimation of Anatomical Risk Metrics for Endoscopic Sinus Surgery Using Deep Learning
This work addresses the need for efficient preoperative assessment in endoscopic sinus surgery to minimize risks like cerebrospinal fluid leakage, representing an incremental improvement over existing manual methods.
The paper tackled the problem of time-consuming manual measurement of anatomical risk scores for endoscopic sinus surgery by developing an automated deep learning pipeline, achieving mean absolute errors of 0.506mm for Keros, 4.516° for Gera, and 0.802mm/0.777mm for TMS scores.
Endoscopic sinus surgery requires careful preoperative assessment of the skull base anatomy to minimize risks such as cerebrospinal fluid leakage. Anatomical risk scores like the Keros, Gera and Thailand-Malaysia-Singapore score offer a standardized approach but require time-consuming manual measurements on coronal CT or CBCT scans. We propose an automated deep learning pipeline that estimates these risk scores by localizing key anatomical landmarks via heatmap regression. We compare a direct approach to a specialized global-to-local learning strategy and find mean absolute errors on the relevant anatomical measurements of 0.506mm for the Keros, 4.516° for the Gera and 0.802mm / 0.777mm for the TMS classification.