BARF: a new direct and cross-based binary residual feature fusion with uncertainty-aware module for medical image classification
Authors:
- Moloud Abdar,
- Mohammad Amin Fahami,
- Satarupa Chakrabarti,
- Abbas Khosravi,
- Paweł Pławiak,
- U Rajendra Acharya,
- Ryszard Tadeusiewicz,
- Saeid Nahavandi
Abstract
Automatic medical image classification is widely used in the early diagnosis of various diseases. The computer-aided diagnosis (CAD) systems enable accurate disease detection, and treatment. Nowadays, DL-based CAD systems have been able to achieve promising results in most of the healthcare applications. Also, uncertainty quantification in the existing DL methods have not gained enough attention in the field of medical research. To fill this gap, we propose a novel, simple and effective fusion model with uncertainty-aware module for medical image classification called Binary Residual Feature fusion (BARF). To deal with uncertainty, we applied the Monte Carlo (MC) dropout during inference to obtain the mean and standard deviation of the predictions. The proposed model has two main strategies: direct and cross validated using four different medical image datasets. Our experimental results demonstrate that the proposed model is efficient for medical image classification in real clinical settings.
- Record ID
- CUTd84ace56c50e483c88838ce3fd17321c
- Publication categories
- ;
- Author
- Journal series
- Information Sciences, ISSN 0020-0255, e-ISSN 1872-6291
- Issue year
- 2021
- Vol
- 577
- Pages
- 353-378
- Other elements of collation
- fot.; schem.; tab.; wykr.; Bibliografia (na s.) - 377-378; Bibliografia (liczba pozycji) - 55; Oznaczenie streszczenia - Abstr.; Data udostępnienia on-line - 2021-07-06; Numeracja w czasopiśmie - Vol. 577
- Keywords in English
- medical image classification, fusion model, deep learning, early fusion, uncertainty quantification
- DOI
- DOI:10.1016/j.ins.2021.07.024 Opening in a new tab
- URL
- https://www.sciencedirect.com/science/article/pii/S0020025521007143?via%3Dihub Opening in a new tab
- Language
- eng (en) English
- Score (nominal)
- 200
- Publication indicators
- Citation count
- 68
- Additional fields
- Indeksowana w: Web of Science, Scopus
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUTd84ace56c50e483c88838ce3fd17321c/
- URN
urn:pkr-prod:CUTd84ace56c50e483c88838ce3fd17321c
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.