Detecting Outliers with Poisson Image Interpolation
This addresses the problem of detecting rare pathologies in primary care settings where supervised learning is impractical, though it appears incremental as it builds on existing foreign patch interpolation strategies.
The paper tackles pathological anomaly detection in medical images by proposing a self-supervised method using Poisson image interpolation, which outperforms state-of-the-art methods on tasks like identifying lung anomalies in chest X-rays and heart defects in fetal ultrasound images.
Supervised learning of every possible pathology is unrealistic for many primary care applications like health screening. Image anomaly detection methods that learn normal appearance from only healthy data have shown promising results recently. We propose an alternative to image reconstruction-based and image embedding-based methods and propose a new self-supervised method to tackle pathological anomaly detection. Our approach originates in the foreign patch interpolation (FPI) strategy that has shown superior performance on brain MRI and abdominal CT data. We propose to use a better patch interpolation strategy, Poisson image interpolation (PII), which makes our method suitable for applications in challenging data regimes. PII outperforms state-of-the-art methods by a good margin when tested on surrogate tasks like identifying common lung anomalies in chest X-rays or hypo-plastic left heart syndrome in prenatal, fetal cardiac ultrasound images. Code available at https://github.com/jemtan/PII.