A Transfer Learning Architecture Based on a Support Vector Machine for Histopathology Image Classification

被引:38
作者
Fan, Jiayi [1 ]
Lee, JangHyeon [2 ]
Lee, YongKeun [1 ]
机构
[1] Seoul Natl Univ Sci & Technol, Grad Sch Nano It Design Fus, Seoul 01811, South Korea
[2] Korea Univ, Dept Mat Sci & Engn, Seoul 02841, South Korea
来源
APPLIED SCIENCES-BASEL | 2021年 / 11卷 / 14期
关键词
image classification; support vector machine; transfer learning; ECOC; SVM;
D O I
10.3390/app11146380
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Recently, digital pathology is an essential application for clinical practice and medical research. Due to the lack of large annotated datasets, the deep transfer learning technique is often used to classify histopathology images. A softmax classifier is often used to perform classification tasks. Besides, a Support Vector Machine (SVM) classifier is also popularly employed, especially for binary classification problems. Accurately determining the category of the histopathology images is vital for the diagnosis of diseases. In this paper, the conventional softmax classifier and the SVM classifier-based transfer learning approach are evaluated to classify histopathology cancer images in a binary breast cancer dataset and a multiclass lung and colon cancer dataset. In order to achieve better classification accuracy, a methodology that attaches SVM classifier to the fully-connected (FC) layer of the softmax-based transfer learning model is proposed. The proposed architecture involves a first step training the newly added FC layer on the target dataset using the softmax-based model and a second step training the SVM classifier with the newly trained FC layer. Cross-validation is used to ensure no bias for the evaluation of the performance of the models. Experimental results reveal that the conventional SVM classifier-based model is the least accurate on either binary or multiclass cancer datasets. The conventional softmax-based model shows moderate classification accuracy, while the proposed synthetic architecture achieves the best classification accuracy.
引用
收藏
页数:16
相关论文
共 24 条
[1]   Towards multilevel mental stress assessment using SVM with ECOC: an EEG approach [J].
Al-shargie, Fares ;
Tang, Tong Boon ;
Badruddin, Nasreen ;
Kiguchi, Masashi .
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2018, 56 (01) :125-136
[2]  
Alawad M., 2019, 2019 56th ACM/IEEE Design Automation Conference (DAC), P1
[3]   Voice Pathology Detection Using Deep Learning on Mobile Healthcare Framework [J].
Alhussein, Musaed ;
Muhammad, Ghulam .
IEEE ACCESS, 2018, 6 :41034-41041
[4]  
AlTalli Haneen, 2020, 2020 International Conference on Assistive and Rehabilitation Technologies (iCareTech), P126, DOI 10.1109/iCareTech49914.2020.00031
[5]  
[Anonymous], P IEEE C COMP VIS PA
[6]   Evaluating reproducibility of AI algorithms in digital pathology with DAPPER [J].
Bizzego, Andrea ;
Bussola, Nicole ;
Chierici, Marco ;
Maggio, Valerio ;
Francescatto, Margherita ;
Cima, Luca ;
Cristoforetti, Marco ;
Jurman, Giuseppe ;
Furlanello, Cesare .
PLOS COMPUTATIONAL BIOLOGY, 2019, 15 (03)
[7]  
Borkowski A.A., 2019, ARXIV191212142V1
[8]  
Chunming Wu, 2010, Proceedings of the 2010 International Conference on Intelligent Computation Technology and Automation (ICICTA 2010), P932, DOI 10.1109/ICICTA.2010.16
[9]   Automatic detection of invasive ductal carcinoma in whole slide images with Convolutional Neural Networks [J].
Cruz-Roa, Angel ;
Basavanhally, Ajay ;
Gonzalez, Fabio ;
Gilmore, Hannah ;
Feldman, Michael ;
Ganesan, Shridar ;
Shih, Natalie ;
Tomaszewski, John ;
Madabhushi, Anant .
MEDICAL IMAGING 2014: DIGITAL PATHOLOGY, 2014, 9041
[10]   Artificial intelligence and computational pathology [J].
Cui, Miao ;
Zhang, David Y. .
LABORATORY INVESTIGATION, 2021, 101 (04) :412-422