Abstract—The clinical diagnosis of breast cancer in real life is
a comprehensive process which needs to consider different
sources of information and use different medical examination
methods according to different stages of the disease. First,
routine and more economical medical examination should be
carried out according to the needs of the disease, and then more
accurate but expensive examination should be carried out
according to the condition. When the data is seriously missing
while the required features are selected, it will seriously affect
the accuracy of the traditional comprehensive diagnosis model.
A large amount of data is missing due to partial inspections that
have not been performed within a certain period of time. At this
time, the accuracy of traditional model will be greatly reduced.
In order to solve this problem, this paper proposes a progressive
breast cancer diagnosis strategy using multi-criteria and
multi-classifier fusion that realizes the development according
to the course of disease and continuously supplements the
examination information to achieve a progressive
comprehensive diagnosis of breast cancer. The architecture also
has good scalability, which can be extended to more types of
classifiers and input information of different modes, so as to
achieve multi-criteria and multi-source comprehensive decision.
Compared with the traditional multi-source breast cancer
comprehensive diagnosis strategy, the experimental results
show that the progressive breast cancer comprehensive
diagnosis strategy has better predictive performance and
clinical practicability.
Index Terms—Breast cancer, multi-classifier fusion,
multi-modal fusion, progressive diagnosis.
The authors are with the College of Computer Science and Technology,
Donghua University, Shanghai, China (e-mail: jyli@dhu.edu.cn,
2181829@mail.dhu.edu.cn, chen.qian@dhu.edu.cn).
Cite: Jiyun Li, Chenxi Jia, and Chen Qian, "Progressive Breast Cancer Diagnosis Model Based on Multi-classifier and Multi-modal Fusion," International Journal of Machine Learning and Computing vol. 11, no. 6, pp. 387-392, 2021.
Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).