BIOMAT Database Logo BIOMAT Database Logo

Anatomy-aware self-supervised learning for anomaly detection in chest radiographs. 2023

Junya Sato, and Yuki Suzuki, and Tomohiro Wataya, and Daiki Nishigaki, and Kosuke Kita, and Kazuki Yamagata, and Noriyuki Tomiyama, and Shoji Kido
Department of Artificial Intelligence Diagnostic Radiology, Osaka University Graduate School of Medicine, 2-2, Yamadaoka, Suita, Osaka 565-0871, Japan.

In this study, we present a self-supervised learning (SSL)-based model that enables anatomical structure-based unsupervised anomaly detection (UAD). The model employs an anatomy-aware pasting (AnatPaste) augmentation tool that uses a threshold-based lung segmentation pretext task to create anomalies in normal chest radiographs used for model pretraining. These anomalies are similar to real anomalies and help the model recognize them. We evaluate our model using three open-source chest radiograph datasets. Our model exhibits area under curves of 92.1%, 78.7%, and 81.9%, which are the highest among those of existing UAD models. To the best of our knowledge, this is the first SSL model to employ anatomical information from segmentation as a pretext task. The performance of AnatPaste shows that incorporating anatomical information into SSL can effectively improve accuracy.

UI MeSH Term Description Entries

Related Publications

Junya Sato, and Yuki Suzuki, and Tomohiro Wataya, and Daiki Nishigaki, and Kosuke Kita, and Kazuki Yamagata, and Noriyuki Tomiyama, and Shoji Kido
Unsupervised anomaly detection for posteroanterior chest X-rays using multiresolution patch-based self-supervised learning.
February 2023, Scientific reports,
Junya Sato, and Yuki Suzuki, and Tomohiro Wataya, and Daiki Nishigaki, and Kosuke Kita, and Kazuki Yamagata, and Noriyuki Tomiyama, and Shoji Kido
Structure-aware protein self-supervised learning.
April 2023, Bioinformatics (Oxford, England),
Junya Sato, and Yuki Suzuki, and Tomohiro Wataya, and Daiki Nishigaki, and Kosuke Kita, and Kazuki Yamagata, and Noriyuki Tomiyama, and Shoji Kido
Unsupervised Deep Anomaly Detection in Chest Radiographs.
April 2021, Journal of digital imaging,
Junya Sato, and Yuki Suzuki, and Tomohiro Wataya, and Daiki Nishigaki, and Kosuke Kita, and Kazuki Yamagata, and Noriyuki Tomiyama, and Shoji Kido
Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning.
June 2022, IEEE transactions on neural networks and learning systems,
Junya Sato, and Yuki Suzuki, and Tomohiro Wataya, and Daiki Nishigaki, and Kosuke Kita, and Kazuki Yamagata, and Noriyuki Tomiyama, and Shoji Kido
SWSSL: Sliding Window-Based Self-Supervised Learning for Anomaly Detection in High-Resolution Images.
December 2023, IEEE transactions on medical imaging,
Junya Sato, and Yuki Suzuki, and Tomohiro Wataya, and Daiki Nishigaki, and Kosuke Kita, and Kazuki Yamagata, and Noriyuki Tomiyama, and Shoji Kido
Uncertainty-aware prototypical learning for anomaly detection in medical images.
July 2024, Neural networks : the official journal of the International Neural Network Society,
Junya Sato, and Yuki Suzuki, and Tomohiro Wataya, and Daiki Nishigaki, and Kosuke Kita, and Kazuki Yamagata, and Noriyuki Tomiyama, and Shoji Kido
AAWS-Net: Anatomy-aware weakly-supervised learning network for breast mass segmentation.
January 2021, PloS one,
Junya Sato, and Yuki Suzuki, and Tomohiro Wataya, and Daiki Nishigaki, and Kosuke Kita, and Kazuki Yamagata, and Noriyuki Tomiyama, and Shoji Kido
Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection.
January 2024, IEEE transactions on pattern analysis and machine intelligence,
Junya Sato, and Yuki Suzuki, and Tomohiro Wataya, and Daiki Nishigaki, and Kosuke Kita, and Kazuki Yamagata, and Noriyuki Tomiyama, and Shoji Kido
A semi-supervised learning-based quality evaluation system for digital chest radiographs.
November 2023, Medical physics,
Junya Sato, and Yuki Suzuki, and Tomohiro Wataya, and Daiki Nishigaki, and Kosuke Kita, and Kazuki Yamagata, and Noriyuki Tomiyama, and Shoji Kido
CAiD: Context-Aware Instance Discrimination for Self-supervised Learning in Medical Imaging.
July 2022, Proceedings of machine learning research,
Copied contents to your clipboard!