Deep Learning for Medical Anomaly Detection – A Survey

Глубокое обучение для обнаружения медицинских аномалий: обзор
Clinton Fookes, Harshala Gammulle, Sridha Sridharan, Simon Denman, Tharindu Fernando
2021-07-18

deep learningdeep model interpretationmedical anomaly detectionmedical applicationstraining algorithms
Machine learning–based medical anomaly detection is an important problem that has been extensively studied. Numerous approaches have been proposed across various medical application domains and we observe several similarities across these distinct applications. Despite this comparability, we observe a lack of structured organisation of these diverse research applications such that their advantages and limitations can be studied. The principal aim of this survey is to provide a thorough theoretical analysis of popular deep learning techniques in medical anomaly detection. In particular, we contribute a coherent and systematic review of state-of-the-art techniques, comparing and contrasting their architectural differences as well as training algorithms. Furthermore, we provide a comprehensive overview of deep model interpretation strategies that can be used to interpret model decisions. In addition, we outline the key limitations of existing deep medical anomaly detection techniques and propose key research directions for further investigation.
1
It comprehensively summarizes interpretation strategies for explaining deep models’ medical anomaly detection decisions.
2
It provides a systematic theoretical review of state-of-the-art deep learning techniques for medical anomaly detection.
3
The review compares deep anomaly detection architectures and their associated training algorithms.
4
The survey highlights key limitations of existing methods and proposes research directions for future investigation.
5
The survey identifies common patterns across medical anomaly detection applications despite their diverse clinical domains.

deep learning–based medical anomaly detection across diverse medical application domains

theoretical analysis and systematic comparison of detection techniques, architectures, training algorithms, model interpretation strategies, limitations, and research directions

Publication Details
Publication Date
2021-07-18
Journal
Publisher
ISSN
Cited by
403
Access Type
Author Information
Authors
Clinton Fookes
Harshala Gammulle
Sridha Sridharan
Simon Denman
Tharindu Fernando
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%