Assisted deep learning framework for multi-class skin lesion classification considering a binary classification support

被引：36

作者：

Harangi, Balazs ^{[1
]}

Baran, Agnes ^{[1
]}

Hajdu, Andras ^{[1
]}

机构：

[1] Univ Debrecen, Fac Informat, POB 400, H-4002 Debrecen, Hungary

来源：

BIOMEDICAL SIGNAL PROCESSING AND CONTROL | 2020年 / 62卷

关键词：

Assisted learning; Deep learning; Ensemble learning; Skin lesion;

D O I：

10.1016/j.bspc.2020.102041

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

In this paper, we propose a deep convolutional neural network framework to classify dermoscopy images into seven classes. With taking the advantage that these classes can be merged into two (healthy/diseased) ones we can train a part of the network regarding this binary task only. Then, the confidences regarding the binary classification are used to tune the multi-class confidence values provided by the other part of the network, since the binary task can be solved more accurately. For both the classification tasks we used GoogLeNet Inception-v3, however, any CNN architectures could be applied for these purposes. The whole network is trained in the usual way, and as our experimental results on the skin lesion image classification show, the accuracy of the multi-class problem has been remarkably raised (by 7% considering the balanced multi-class accuracy) via embedding the more reliable binary classification outcomes. (C) 2020 The Authors. Published by Elsevier Ltd.

引用

页数：7

共 50 条

[21] Support vector machines for multi-class classification
Mayoraz, E
Alpaydin, E
[J]. ENGINEERING APPLICATIONS OF BIO-INSPIRED ARTIFICIAL NEURAL NETWORKS, VOL II, 1999, 1607 : 833 - 842
[22] Multi-Class Classification of Support Vector Machines Based on Double Binary Tree
Liu, Guixiong
Zhang, Xiaoping
Zhou, Songbin
[J]. ICNC 2008: FOURTH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 2, PROCEEDINGS, 2008, : 102 - 105
[23] Binary and Multi-class Parkinsonian Disorders Classification Using Support Vector Machines
Morisi, Rita
Gnecco, Giorgio
Lanconelli, Nico
Zanigni, Stefano
Manners, David Neil
Testa, Claudia
Evangelisti, Stefania
Gramegna, Laura Ludovica
Bianchini, Claudio
Cortelli, Pietro
Tonon, Caterina
Lodi, Raffaele
[J]. PATTERN RECOGNITION AND IMAGE ANALYSIS (IBPRIA 2015), 2015, 9117 : 379 - 386
[24] Multi-Class Skin Diseases Classification Using Deep Convolutional Neural Network and Support Vector Machine
Hameed, Nazia
Shabut, Antesar M.
Hossain, M. A.
[J]. 2018 12TH INTERNATIONAL CONFERENCE ON SOFTWARE, KNOWLEDGE, INFORMATION MANAGEMENT & APPLICATIONS (SKIMA), 2018, : 23 - +
[25] ADVERSARIAL LEARNING OF LABEL DEPENDENCY: A NOVEL FRAMEWORK FOR MULTI-CLASS CLASSIFICATION
Tsai, Che-Ping
Lee, Hung-Yi
[J]. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 3847 - 3851
[26] A federated learning framework for training multi-class OCT classification models
Gholami, Sina
Leng, Theodore
Alam, Minhaj Nur
[J]. INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2023, 64 (09)
[27] Multi-class Classification Using an Improved Multiobjective Simultaneous Learning Framework
Bharill, Neha
Tiwari, Aruna
[J]. PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON SOFT COMPUTING FOR PROBLEM SOLVING (SOCPROS 2011), VOL 2, 2012, 131 : 821 - 831
[28] Generalization and learning rate of multi-class support vector classification and regression
Dong, Zijie
Gong, Jiawen
Zou, Bin
Wang, Yichi
Xu, Jie
[J]. INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING, 2022, 20 (05)
[29] Interpretable deep learning systems for multi-class segmentation and classification of non-melanoma skin cancer
Thomas, Simon M.
Lefevre, James G.
Baxter, Glenn
Hamilton, Nicholas A.
[J]. MEDICAL IMAGE ANALYSIS, 2021, 68
[30] A multi-class skin Cancer classification using deep convolutional neural networks
Saket S. Chaturvedi
Jitendra V. Tembhurne
Tausif Diwan
[J]. Multimedia Tools and Applications, 2020, 79 : 28477 - 28498

← 1 2 3 4 5 →