Interpretable deep learning approach for oral cancer classification using guided attention inference network
AffiliationThe University of Arizona, Wyant College of Optical Sciences
MetadataShow full item record
CitationFigueroa, K. C., Song, B., Sunny, S., Li, S., Gurushanth, K., Mendonca, P., Mukhia, N., Patrick, S., Gurudath, S., Raghavan, S., Imchen, T., Leivon, S. T., Kolur, T., Shetty, V., Bushan, V., Ramesh, R., Pillai, V., Wilder-Smith, P., Sigamani, A., … Liang, R. (2022). Interpretable deep learning approach for oral cancer classification using guided attention inference network. Journal of Biomedical Optics.
JournalJournal of Biomedical Optics
RightsCopyright © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License.
Collection InformationThis item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at firstname.lastname@example.org.
AbstractSignificance: Convolutional neural networks (CNNs) show the potential for automated classification of different cancer lesions. However, their lack of interpretability and explainability makes CNNs less than understandable. Furthermore, CNNs may incorrectly concentrate on other areas surrounding the salient object, rather than the network's attention focusing directly on the object to be recognized, as the network has no incentive to focus solely on the correct subjects to be detected. This inhibits the reliability of CNNs, especially for biomedical applications. Aim: Develop a deep learning training approach that could provide understandability to its predictions and directly guide the network to concentrate its attention and accurately delineate cancerous regions of the image. Approach: We utilized Selvaraju et al.'s gradient-weighted class activation mapping to inject interpretability and explainability into CNNs. We adopted a two-stage training process with data augmentation techniques and Li et al.'s guided attention inference network (GAIN) to train images captured using our customized mobile oral screening devices. The GAIN architecture consists of three streams of network training: classification stream, attention mining stream, and bounding box stream. By adopting the GAIN training architecture, we jointly optimized the classification and segmentation accuracy of our CNN by treating these attention maps as reliable priors to develop attention maps with more complete and accurate segmentation. Results: The network's attention map will help us to actively understand what the network is focusing on and looking at during its decision-making process. The results also show that the proposed method could guide the trained neural network to highlight and focus its attention on the correct lesion areas in the images when making a decision, rather than focusing its attention on relevant yet incorrect regions. Conclusions: We demonstrate the effectiveness of our approach for more interpretable and reliable oral potentially malignant lesion and malignant lesion classification. © The Authors.
NoteOpen access article
VersionFinal published version
Except where otherwise noted, this item's license is described as Copyright © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License.
- Deep learning for liver tumor diagnosis part II: convolutional neural network interpretation using radiologic imaging features.
- Authors: Wang CJ, Hamm CA, Savic LJ, Ferrante M, Schobert I, Schlachter T, Lin M, Weinreb JC, Duncan JS, Chapiro J, Letzen B
- Issue date: 2019 Jul
- Exploring uncertainty measures in convolutional neural network for semantic segmentation of oral cancer images.
- Authors: Song B, Li S, Sunny S, Gurushanth K, Mendonca P, Mukhia N, Patrick S, Peterson T, Gurudath S, Raghavan S, Tsusennaro I, Leivon S, Kolur T, Shetty V, Bushan V, Ramesh R, Pillai V, Wilder-Smith P, Suresh A, Kuriakose MA, Birur P, Liang R
- Issue date: 2022 Nov
- Explainability and controllability of patient-specific deep learning with attention-based augmentation for markerless image-guided radiotherapy.
- Authors: Terunuma T, Sakae T, Hu Y, Takei H, Moriya S, Okumura T, Sakurai H
- Issue date: 2022 Nov 10
- Exploring convolutional neural networks with transfer learning for diagnosing Lyme disease from skin lesion images.
- Authors: Hossain SI, de Goër de Herve J, Hassan MS, Martineau D, Petrosyan E, Corbin V, Beytout J, Lebert I, Durand J, Carravieri I, Brun-Jacob A, Frey-Klett P, Baux E, Cazorla C, Eldin C, Hansmann Y, Patrat-Delon S, Prazuck T, Raffetin A, Tattevin P, Vourc'h G, Lesens O, Nguifo EM
- Issue date: 2022 Mar