aceGENERATIVE AI FOR HIRSCHSPRUNG DISEASE: CAN SYNTHETIC FLUORESCENCE CONFOCAL MICROSCOPY IMAGES ENHANCE INTRAOPERATIVE DETECTION OF GANGLIONIC BOWEL?
Background Accurate identification of ganglionated bowel is essential during laparoscopic pull-through for Hirschsprung Disease (HD), yet intraoperative biopsy interpretation is time-sensitive and operator-dependent. Fluorescence confocal microscopy (FCM) provides rapid imaging of fresh tissue, and deep-learning (DL) has the potential to extract diagnostic patterns from these images automatically. However, DL development is limited by HD rarity and images scarcity. Generative-AI may address this gap by synthesiz…
Adding 913 conditional-GAN simulated ganglionic tiles to 461 real ganglionic and 1374 real aganglionic FCM tiles improved a CNN's ability to discriminate ganglionic bowel on an independent real-image test set of 590 aganglionic and 198 ganglionic tiles, raising accuracy from 75% to 84% and sensitivity from 78% to 91% .
Model development was constrained by disease rarity and limited real image availability, with training based on only 461 real ganglionic tiles from a one-year single-procedure cohort.
Evidence
- Peer-reviewedJournal of Pediatric Surgery2026-09-11
How should this claim be treated?
Truvace Impact Record TRV-2026-1066, v1: “GENERATIVE AI FOR HIRSCHSPRUNG DISEASE: CAN SYNTHETIC FLUORESCENCE CONFOCAL MICROSCOPY IMAGES ENHANCE INTRAOPERATIVE DETECTION OF GANGLIONIC BOWEL?.” Truvace, 2026-09-13. /record/TRV-2026-1066 (accessed at citation time). sha256 8e9965580b6cea97…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-1066 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.