A high-order focus interaction model and oral ulcer dataset for oral ulcer segmentation.
Computer-aided diagnosis
Deep learning
High-order interactions
Medical image segmentation
Oral ulcer
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
29 Aug 2024
29 Aug 2024
Historique:
received:
08
06
2024
accepted:
31
07
2024
medline:
31
8
2024
pubmed:
31
8
2024
entrez:
29
8
2024
Statut:
epublish
Résumé
Computer-aided diagnosis has been slow to develop in the field of oral ulcers. One of the major reasons for this is the lack of publicly available datasets. However, oral ulcers have cancerous lesions and their mortality rate is high. The ability to recognize oral ulcers at an early stage in a timely and effective manner is a very critical issue. In recent years, although there exists a small group of researchers working on these, the datasets are private. Therefore to address this challenge, in this paper a multi-tasking oral ulcer dataset (Autooral) containing two major tasks of lesion segmentation and classification is proposed and made publicly available. To the best of our knowledge, we are the first team to make publicly available an oral ulcer dataset with multi-tasking. In addition, we propose a novel modeling framework, HF-UNet, for segmenting oral ulcer lesion regions. Specifically, the proposed high-order focus interaction module (HFblock) performs acquisition of global properties and focus for acquisition of local properties through high-order attention. The proposed lesion localization module (LL-M) employs a novel hybrid sobel filter, which improves the recognition of ulcer edges. Experimental results on the proposed Autooral dataset show that our proposed HF-UNet segmentation of oral ulcers achieves a DSC value of about 0.80 and the inference memory occupies only 2029 MB. The proposed method guarantees a low running load while maintaining a high-performance segmentation capability. The proposed Autooral dataset and code are available from https://github.com/wurenkai/HF-UNet-and-Autooral-dataset .
Identifiants
pubmed: 39209880
doi: 10.1038/s41598-024-69125-9
pii: 10.1038/s41598-024-69125-9
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
20085Subventions
Organisme : National Natural Science Foundation of China
ID : 81970941
Organisme : Priority Academic Program Development of Jiangsu Higher Education Institutions
ID : PAPD, 2018-87
Organisme : Critical Research and Development Project of Jiangsu Province
ID : BE2021723
Informations de copyright
© 2024. The Author(s).
Références
Zeng, X. et al. Difficult and complicated oral ulceration: An expert consensus guideline for diagnosis. Int. J. Oral Sci. 14, 28 (2022).
doi: 10.1038/s41368-022-00178-0
pubmed: 35650189
pmcid: 9160262
Guo, G. & Razmjooy, N. A new interval differential equation for edge detection and determining breast cancer regions in mammography images. Syst. Sci. Control Eng. 7, 346–356 (2019).
doi: 10.1080/21642583.2019.1681033
Liu, Q., Liu, Z., Yong, S., Jia, K. & Razmjooy, N. Computer-aided breast cancer diagnosis based on image segmentation and interval analysis. Automatika 61, 496–506 (2020).
doi: 10.1080/00051144.2020.1785784
Minhas, S. et al. Oral ulcers presentation in systemic diseases: An update. Open Access Maced. J. Med. Sci. 7, 3341 (2019).
doi: 10.3889/oamjms.2019.689
pubmed: 31949540
pmcid: 6953949
dos Santos, F. D. S. et al. Misdiagnosis of lip squamous cell carcinoma. RSBO Rev. Sul-Bras. Odontol. 9, 114–118 (2012).
Mortazavi, H. et al. Diagnostic features of common oral ulcerative lesions: An updated decision tree. Int. J. Dent. 2016, 7278925 (2016).
doi: 10.1155/2016/7278925
pubmed: 27781066
pmcid: 5066016
Valente, V. B. et al. Oral squamous cell carcinoma misdiagnosed as a denture-related traumatic ulcer: A clinical report. J. Prosthet. Dent. 115, 259–262 (2016).
doi: 10.1016/j.prosdent.2015.08.024
pubmed: 26581660
Long, J., Shelhamer, E. & Darrell, T. Fully convolutional networks for semantic segmentation. In Proc. of the IEEE conference on computer vision and pattern recognition, 3431–3440 (2015).
Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, 234–241 (Springer, 2015).
Yang, J. et al. Focal self-attention for local-global interactions in vision transformers. Preprint at http://arxiv.org/abs/2107.00641 (2021).
Naderi, M., Givkashi, M., Piri, F., Karimi, N. & Samavi, S. Focal-unet: Unet-like focal modulation for medical image segmentation. Preprint at http://arxiv.org/abs/2212.09263 (2022).
Yang, J., Li, C., Dai, X. & Gao, J. Focal modulation networks. Adv. Neural Inf. Process. Syst. 35, 4203–4217 (2022).
Rao, Y. et al. Hornet: Efficient high-order spatial interactions with recursive gated convolutions. Adv. Neural Inf. Process. Syst. 35, 10353–10366 (2022).
Wu, R. et al. Mhorunet: High-order spatial interaction unet for skin lesion segmentation. Biomed. Signal Process. Control 88, 105517 (2024).
doi: 10.1016/j.bspc.2023.105517
Anantharaman, R., Velazquez, M. & Lee, Y. Utilizing mask r-cnn for detection and segmentation of oral diseases. In 2018 IEEE international conference on bioinformatics and biomedicine (BIBM), 2197–2204 (IEEE, 2018).
Jain, M., Rai, C. et al. Early detection of oral ulcers using photographic evidence: A novel approach using ensemble of convolution neural network. In 2022 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI), 1–5 (IEEE, 2022).
Ding, H., Huang, Q. & Rodriguez, D. Modified locust swarm optimizer for oral cancer diagnosis. Biomed. Signal Process. Control 83, 104645 (2023).
doi: 10.1016/j.bspc.2023.104645
Oktay, O. et al. Attention u-net: Learning where to look for the pancreas. Preprint at http://arxiv.org/abs/1804.03999 (2018).
Azad, R., Al-Antary, M. T., Heidari, M. & Merhof, D. Transnorm: Transformer provides a strong spatial normalization mechanism for a deep segmentation model. IEEE Access 10, 108205–108215 (2022).
doi: 10.1109/ACCESS.2022.3211501
Ruan, J., Xiang, S., Xie, M., Liu, T. & Fu, Y. Malunet: A multi-attention and light-weight unet for skin lesion segmentation. In 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 1150–1156 (IEEE, 2022).
Ullah, Z., Usman, M., Jeon, M. & Gwak, J. Cascade multiscale residual attention cnns with adaptive ROI for automatic brain tumor segmentation. Inf. Sci. 608, 1541–1556 (2022).
doi: 10.1016/j.ins.2022.07.044
Zhao, X. et al. M[Formula: see text]snet: Multi-scale in multi-scale subtraction network for medical image segmentation. Preprint at http://arxiv.org/abs/2303.10894 (2023).
Ullah, Z., Usman, M., Latif, S. & Gwak, J. Densely attention mechanism based network for covid-19 detection in chest x-rays. Sci. Rep. 13, 261 (2023).
doi: 10.1038/s41598-022-27266-9
pubmed: 36609667
pmcid: 9816547
Hu, S., Liao, Z. & Xia, Y. Devil is in channels: Contrastive single domain generalization for medical image segmentation. Preprint at http://arxiv.org/abs/2306.05254 (2023).
Kirillov, A. et al. Segment anything. Preprint at http://arxiv.org/abs/2304.02643 (2023).
Wu, J. et al. Medical sam adapter: Adapting segment anything model for medical image segmentation. Preprint at http://arxiv.org/abs/2304.12620 (2023).
Chu, X. et al. Twins: Revisiting the design of spatial attention in vision transformers. Adv. Neural Inf. Process. Syst. 34, 9355–9366 (2021).
Wang, S., Li, B. Z., Khabsa, M., Fang, H. & Ma, H. Linformer: Self-attention with linear complexity. Preprint at http://arxiv.org/abs/2006.04768 (2020).
Rao, Y., Zhao, W., Zhu, Z., Lu, J. & Zhou, J. Global filter networks for image classification. Adv. Neural Inf. Process. Syst. 34, 980–993 (2021).
Ning, Z., Zhong, S., Feng, Q., Chen, W. & Zhang, Y. Smu-net: Saliency-guided morphology-aware u-net for breast lesion segmentation in ultrasound image. IEEE Trans. Med. Imaging 41, 476–490 (2021).
doi: 10.1109/TMI.2021.3116087
Lin, Y. et al. Rethinking boundary detection in deep learning models for medical image segmentation. In International Conference on Information Processing in Medical Imaging, 730–742 (Springer, 2023).
Wu, R., Liu, Y., Liang, P. & Chang, Q. H-vmunet: High-order vision mamba unet for medical image segmentation. Preprint at http://arxiv.org/abs/2403.13642 (2024).
Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. Preprint at http://arxiv.org/abs/1711.05101 (2017).
Wu, H., Zhong, J., Wang, W., Wen, Z. & Qin, J. Precise yet efficient semantic calibration and refinement in convnets for real-time polyp segmentation from colonoscopy videos. Proc. AAAI Conf. Artif. Intell. 35, 2916–2924 (2021).
Wu, H., Zhao, Z. & Wang, Z. Meta-unet: Multi-scale efficient transformer attention unet for fast and high-accuracy polyp segmentation. IEEE Trans. Autom. Sci. Eng. https://doi.org/10.1109/TASE.2023.3292373 (2023).
doi: 10.1109/TASE.2023.3292373
Ruan, J. & Xiang, S. Vm-unet: Vision mamba unet for medical image segmentation. Preprint at http://arxiv.org/abs/2402.02491 (2024).