PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 22, 2026Medical Physics0 citations

Self‐supervised out‐of‐distribution detection—Metal implants and other anomaly

View Full Paper
GRGokul RamasamyATAmara TariqSFSamuel J. Fahrenholtz

Key Points

  • The study aims to create an AI model to enhance the detection of anomalies and out-of-distribution data in CT scans.
  • Developed a generative architecture for both slice-level and series-level models.
  • Trained on over 2850 abdominal CT volumes from adults over 50 years old.
  • Tested performance on 544 prospective CT scans and an external dataset.
  • Computed anomaly scores for pixels/voxels to identify abnormalities.
  • Generative models achieved excellent results with negligible false positives.
  • True positive rate of 86.11% in prospective analysis.
  • Post-validation showed a 75.26% true positive rate using an external dataset.
  • Traditional methods displayed moderate success compared to generative approaches.

Abstract

Abstract Background Despite the high precision of deep learning models on internal tests on CT, their effectiveness often drops on external validation due to artifacts caused by patient motion and implants like metal or silicone that were not accounted for in the carefully curated training data. Potential wide categories of “unknown” anomalies within a CT exam makes training a supervised model for out‐of‐distribution (OOD) identification impractical, especially when considering unseen external data. Purpose To develop an artificial intelligence (AI) model to detect and identify anomalies/OOD data in abdominal–pelvis CT exams for the purpose of improving the performance of downstream applications. Methods Our proposed 2D and 3D generative architecture receives the third lumbar vertebra (L3) slice (slice‐level model) or all the slices from the series (series‐level model), generates a reconstruction and the secondary part of our architecture—anomaly score computation block, computes the anomalies pixels/voxels (slice‐level/series‐level) to identify anomalous L3‐slices/volumes (slice‐level/series‐level). We trained on data from over 2850 abdominal–pelvis CT volumes from adults over age 50 years collected throughout multiple Mayo Clinic campuses (60% female; mean age: 66. 9, 92. 4% non‐Hispanic White) and tested on a prospective test set of 544 CTs from July 2024 (47. 3% female; mean age: 70. 9, 94% non‐Hispanic White) as well as an external test set. Results We found that while traditional methods show moderate success, our generative models—Vector Quantized Variational Autoencoder (VQVAE) and Vision Transformer‐Masked Autoencoder (VIT‐MAE) —deliver excellent results with negligible false positives (FPs) and are also superior in identifying varied types of OOD samples. Prospective analysis showed the model was able to handle the under‐documentation of anomaly in radiology reports with 86. 11% true positive (TP) rate. We also performed external validation using the publicly available AbdominalCT‐1k dataset, which contains 1062 CT scans compiled from several existing benchmark datasets. The model achieved a 75. 26% TP rate, while the 24. 7% FP rate was primarily triggered by anomalies located outside the body. Conclusions The proposed method can be leveraged to detect both intra‐ and interclass OOD data from abdominal CT images and can assess the quality of CT datasets to provide actionable insights. This workflow is particularly valuable for nonshareable healthcare collaborations, where it can be deployed as a service within local firewalls for automated dataset curation without prior knowledge about the OOD types. The implementation of the algorithm is available in the GitHub: https: //github. com/gokul‐ramasamy/implantdetection. git.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Ramasamy et al. (2026) studied this question.

synapsesocial.com/papers/699a9e9f482488d673cd4d6chttps://doi.org/10.1002/mp.70339
Ask AI
Helpful
Bookmark
Share
View Full Paper