Researchers developed an AI algorithm to identify smuggled marine wildlife in airport luggage using CT scans with high accuracy.
Key Details
- 1Marine wildlife trafficking is valued in the billions annually and threatens ecosystems.
- 2Scientists used airport CT scanners to collect 298 scans of 3 key trafficked items: shark fins, seahorses, and sea cucumbers.
- 3A neural network was trained to detect these items within diverse luggage conditions, including common concealment tricks.
- 4The algorithm achieved 92% overall success: 95% for shark fins, 96% for seahorses, and 86% for sea cucumbers.
- 5False positive rate was 13% (lowest for shark fins at 2%, highest for seahorses at 9%).
- 6Study authors have disclosed employment by the company producing the X-ray system used.
Why It Matters
This research showcases how imaging AI can address non-medical, high-impact challenges by automating illicit wildlife detection in large-scale airport screening. It highlights potential for real-world adoption—and limitations—of AI in operational radiology infrastructure.
Source
EurekAlert
Related News
•EurekAlert
UVA's $4M NIH Grant Backs AI to Optimize Cardiac MRI Therapies
UVA secures $4 million NIH funding to develop GenStrain, an AI model using MRI data to personalize cardiac pacing therapies.
•EurekAlert
Machine Learning Models Predict Cancer Risk with Routine Health Data
Researchers developed machine learning models using routinely collected health data to predict individual risk for 20 common cancers, outperforming traditional methods for several cancer types.
•EurekAlert
AI Deep Learning Model Enhances Echocardiogram RV Assessment and Prognosis
Researchers developed DROID-RV, a deep learning tool that automates right ventricular assessment from echocardiograms, showing strong prognostic links with cardiovascular outcomes.