mlsanityData to 14 Oct 2026

Technical outlier detection via convolutional variational autoencoder for the ADMANI breast mammogram dataset

arXiv 2305.12068 ↗First posted 20 May 2023eess.IV cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The ADMANI datasets (annotated digital mammograms and associated non-image datasets) from the Transforming Breast Cancer Screening with AI programme (BRAIx) run by BreastScreen Victoria in Australia are multi-centre, large scale, clinically curated, real-world databases. The datasets are expected to aid in the development of clinically relevant Artificial Intelligence (AI) algorithms for breast cancer detection, early diagnosis, and other applications. To ensure high data quality, technical outliers must be removed before any downstream algorithm development. As a first step, we randomly select 30,000 individual mammograms and use Convolutional Variational Autoencoder (CVAE), a deep generative neural network, to detect outliers. CVAE is expected to detect all sorts of outliers, although its detection performance differs among different types of outliers. Traditional image processing techniques such as erosion and pectoral muscle analysis can compensate for the poor performance of CVAE in certain outlier types. We identify seven types of technical outliers: implant, pacemaker, cardiac loop recorder, improper radiography, atypical lesion/calcification, incorrect exposure parameter and improper placement. The outlier recall rate for the test set is 61% if CVAE, erosion and pectoral muscle analysis each select the top 1% images ranked in ascending or descending order according to image outlier score under each detection method, and 83% if each selects the top 5% images. This study offers an overview of technical outliers in the ADMANI dataset and suggests future directions to improve outlier detection effectiveness.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 41 references that are in the map. First posted on arXiv 20 May 2023.

Builds on

15 of 41 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  4. 2019Deep Learning for Anomaly Detection: A Surveycited by 358
  5. 2016Adversarial Feature Learningcited by 350
  6. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 224
  7. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
  8. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  9. 2018Anomaly Detection using One-Class Neural Networkscited by 82
  10. 2019Unsupervised Anomaly Localization using Variational Auto-Encoderscited by 73
  11. 2018Context-encoding Variational Autoencoder for Unsupervised Anomaly Detectioncited by 64
  12. 2020Anomaly detection through latent space restoration using vector-quantized variational autoencoderscited by 45
3 more
  1. 2017Robust, Deep and Inductive Anomaly Detectioncited by 24
  2. 2018Anomaly Detection for Skin Disease Images Using Variational Autoencodercited by 20
  3. 2020Robust Output Regulation of the Linearized Boussinesq Equations with Boundary Control and Observationcited by 6

Built on by

Not cited yet.