Margin-Aware Intra-Class Novelty Identification for Medical Images

07/31/2021
by   Xiaoyuan Guo, et al.
25

Traditional anomaly detection methods focus on detecting inter-class variations while medical image novelty identification is inherently an intra-class detection problem. For example, a machine learning model trained with normal chest X-ray and common lung abnormalities, is expected to discover and flag idiopathic pulmonary fibrosis which a rare lung disease and unseen by the model during training. The nuances from intra-class variations and lack of relevant training data in medical image analysis pose great challenges for existing anomaly detection methods. To tackle the challenges, we propose a hybrid model - Transformation-based Embedding learning for Novelty Detection (TEND) which without any out-of-distribution training data, performs novelty identification by combining both autoencoder-based and classifier-based method. With a pre-trained autoencoder as image feature extractor, TEND learns to discriminate the feature embeddings of in-distribution data from the transformed counterparts as fake out-of-distribution inputs. To enhance the separation, a distance objective is optimized to enforce a margin between the two classes. Extensive experimental results on both natural image datasets and medical image datasets are presented and our method out-performs state-of-the-art approaches.

READ FULL TEXT

page 7

page 9

page 17

page 19

page 24

page 25

page 27

research
06/23/2020

Anomaly Detection with Deep Perceptual Autoencoders

Anomaly detection is the problem of recognizing abnormal inputs based on...
research
07/24/2023

AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays

Unsupervised anomaly detection in medical images such as chest radiograp...
research
01/19/2023

Position Regression for Unsupervised Anomaly Detection

In recent years, anomaly detection has become an essential field in medi...
research
08/29/2020

Puzzle-AE: Novelty Detection in Images through Solving Puzzles

Autoencoder (AE) has proved to be an effective framework for novelty det...
research
12/21/2022

Joint Embedding of 2D and 3D Networks for Medical Image Anomaly Detection

Obtaining ground truth data in medical imaging has difficulties due to t...
research
07/28/2023

Multi-layer Aggregation as a key to feature-based OOD detection

Deep Learning models are easily disturbed by variations in the input ima...
research
03/05/2019

Probabilistic Modeling for Novelty Detection with Applications to Fraud Identification

Novelty detection is the unsupervised problem of identifying anomalies i...

Please sign up or login with your details

Forgot password? Click here to reset