Conference proceeding
Data-Driven Deep Supervision for Skin Lesion Classification
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT I, Vol.13431, pp.721-731
Lecture Notes in Computer Science
01/01/2022
DOI: 10.1007/978-3-031-16431-6_68
Abstract
Automatic classification of pigmented, non-pigmented, and depigmented non-melanocytic skin lesions have garnered lots of attention in recent years. However, imaging variations in skin texture, lesion shape, depigmentation contrast, lighting condition, etc. hinder robust feature extraction, affecting classification accuracy. In this paper, we propose a new deep neural network that exploits input data for robust feature extraction. Specifically, we analyze the convolutional network's behavior (field-of-view) to find the location of deep supervision for improved feature extraction. To achieve this, first we perform activation mapping to generate an object mask, highlighting the input regions most critical for classification output generation. Then the network layer whose layer-wise effective receptive field matches the approximated object shape in the object mask is selected as our focus for deep supervision. Utilizing different types of convolutional feature extractors and classifiers on three melanoma detection datasets and two vitiligo detection datasets, we verify the effectiveness of our new method.
Details
- Title: Subtitle
- Data-Driven Deep Supervision for Skin Lesion Classification
- Creators
- Suraj Mishra - University of Notre DameYizhe Zhang - Nanjing University of Science and TechnologyLi Zhang - Qingdao UniversityTianyu Zhang - University of ConnecticutX. Sharon Hu - University of Notre DameDanny Z. Chen - University of Notre Dame
- Contributors
- Linwei Wang (Editor) - Rochester Institute of TechnologyQi Dou (Editor) - Chinese University of Hong KongP. Thomas Fletcher (Editor) - University of VirginiaStefanie Speidel (Editor)Shuo Li (Editor) - Case Western Reserve University
- Resource Type
- Conference proceeding
- Publication Details
- MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT I, Vol.13431, pp.721-731
- Publisher
- Springer Nature
- Series
- Lecture Notes in Computer Science
- DOI
- 10.1007/978-3-031-16431-6_68
- ISSN
- 0302-9743
- eISSN
- 1611-3349
- Number of pages
- 11
- Grant note
- CCF-1617735 / NSF; National Science Foundation (NSF)
- Language
- English
- Date published
- 01/01/2022
- Academic Unit
- Computer Science
- Record Identifier
- 9984696721102771
Metrics
1 Record Views