NTSM: a non-salient target segmentation model for oral mucosal diseases.
Convolutional neural network
Depthwise separable convolution
Medical image segmentation
Non-salient target
Oral mucosal diseases
Journal
BMC oral health
ISSN: 1472-6831
Titre abrégé: BMC Oral Health
Pays: England
ID NLM: 101088684
Informations de publication
Date de publication:
03 May 2024
03 May 2024
Historique:
received:
20
01
2024
accepted:
27
03
2024
medline:
3
5
2024
pubmed:
3
5
2024
entrez:
2
5
2024
Statut:
epublish
Résumé
Oral mucosal diseases are similar to the surrounding normal tissues, i.e., their many non-salient features, which poses a challenge for accurate segmentation lesions. Additionally, high-precision large models generate too many parameters, which puts pressure on storage and makes it difficult to deploy on portable devices. To address these issues, we design a non-salient target segmentation model (NTSM) to improve segmentation performance while reducing the number of parameters. The NTSM includes a difference association (DA) module and multiple feature hierarchy pyramid attention (FHPA) modules. The DA module enhances feature differences at different levels to learn local context information and extend the segmentation mask to potentially similar areas. It also learns logical semantic relationship information through different receptive fields to determine the actual lesions and further elevates the segmentation performance of non-salient lesions. The FHPA module extracts pathological information from different views by performing the hadamard product attention (HPA) operation on input features, which reduces the number of parameters. The experimental results on the oral mucosal diseases (OMD) dataset and international skin imaging collaboration (ISIC) dataset demonstrate that our model outperforms existing state-of-the-art methods. Compared with the nnU-Net backbone, our model has 43.20% fewer parameters while still achieving a 3.14% increase in the Dice score. Our model has high segmentation accuracy on non-salient areas of oral mucosal diseases and can effectively reduce resource consumption.
Sections du résumé
BACKGROUND
BACKGROUND
Oral mucosal diseases are similar to the surrounding normal tissues, i.e., their many non-salient features, which poses a challenge for accurate segmentation lesions. Additionally, high-precision large models generate too many parameters, which puts pressure on storage and makes it difficult to deploy on portable devices.
METHODS
METHODS
To address these issues, we design a non-salient target segmentation model (NTSM) to improve segmentation performance while reducing the number of parameters. The NTSM includes a difference association (DA) module and multiple feature hierarchy pyramid attention (FHPA) modules. The DA module enhances feature differences at different levels to learn local context information and extend the segmentation mask to potentially similar areas. It also learns logical semantic relationship information through different receptive fields to determine the actual lesions and further elevates the segmentation performance of non-salient lesions. The FHPA module extracts pathological information from different views by performing the hadamard product attention (HPA) operation on input features, which reduces the number of parameters.
RESULTS
RESULTS
The experimental results on the oral mucosal diseases (OMD) dataset and international skin imaging collaboration (ISIC) dataset demonstrate that our model outperforms existing state-of-the-art methods. Compared with the nnU-Net backbone, our model has 43.20% fewer parameters while still achieving a 3.14% increase in the Dice score.
CONCLUSIONS
CONCLUSIONS
Our model has high segmentation accuracy on non-salient areas of oral mucosal diseases and can effectively reduce resource consumption.
Identifiants
pubmed: 38698377
doi: 10.1186/s12903-024-04193-x
pii: 10.1186/s12903-024-04193-x
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
521Subventions
Organisme : National Natural Science Foundation of China
ID : 61973250
Informations de copyright
© 2024. The Author(s).
Références
Radwan-Oczko M, Sok´o l I, Babu´ska K, Owczarek-Drabi´nska JE. Prevalence and characteristic of oral mucosa lesions. Symmetry. 2022;14(2):307.
doi: 10.3390/sym14020307
Jubair F, Al-karadsheh O, Malamos D, Al Mahdi S, Saad Y, Hassona Y. A novel lightweight deep convolutional neural network for early detection of oral cancer. Oral Dis. 2022;28(4):1123–30.
doi: 10.1111/odi.13825
pubmed: 33636041
Paderno A, Piazza C, Del Bon F, Lancini D, Tanagli S, Deganello A, Peretti G, De Momi E, Patrini I, Ruperti M, et al. Deep learning for automatic segmentation of oral and oropharyngeal cancer using narrow band imaging: preliminary experience in a clinical perspective. Front Oncol. 2021;11:626602.
doi: 10.3389/fonc.2021.626602
pubmed: 33842330
Zanjani FG, Moin DA, Claessen F, Cherici T, Parinussa S, Pourtaherian A, Zinger S, With PH. Mask-mcnet: Instance segmentation in 3d point cloud of intra-oral scans. In: Medical Image Computing and Computer Assisted Intervention (MICCAI). Shenzhen: 2019;128–36.
Zhu H, Cao Z, Lian L, Ye G, Gao H, Wu J. Cariesnet: a deep learning approach for segmentation of multi-stage caries lesion from oral panoramic x-ray image. Neural Comput Appl. 2022;35:1–9.
Xie F, Zhang P, Jiang T, She J, Shen X, Xu P, Zhao W, Gao G, Guan Z. Lesion segmentation framework based on convolutional neural networks with dual attention mechanism. Electronics. 2021;10(24):3103.
doi: 10.3390/electronics10243103
Xie F, Xu P, Xi X, Gu X, Zhang P, Wang H, Shen X. Oral mucosal disease recognition based on dynamic self-attention and feature discriminant loss. Oral Dis. 2023;00:1–14.
Mondal A, Ghosh S, Ghosh A. Partially camouflaged object tracking using modified probabilistic neural network and fuzzy energy based active contour. Int J Comput Vision. 2017;122:116–48.
doi: 10.1007/s11263-016-0959-5
Li A, Zhang J, Lv Y, Liu B, Zhang T, Dai Y. Uncertainty-aware joint salient object and camouflaged object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Kuala Lumpur: 2021;10071–81.
Yan J, Le T-N, Nguyen K-D, Tran M-T, Do T-T, Nguyen TV. Mirrornet: Bio-inspired camouflaged object segmentation. IEEE Access. 2021;9:43290–300.
doi: 10.1109/ACCESS.2021.3064443
Zois DS, Raginsky M. Active object detection on graphs via locally informative trees. In: 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP). Vietri sul Mare: 2016;1–6.
Mohan CK, Mehrotra KG, Varshney PK, Yang J. Temporal uncertainty reasoning networks for evidence fusion with applications to object detection and tracking. Information Fusion. 2007;8(3):281–94.
doi: 10.1016/j.inffus.2006.03.005
Ju J, Li J, Chang Z, Liang Y, Guan Z, Xu P, Xie F, Wang H. Incorporating multi-stage spatial visual cues and active localization offset for pancreas segmentation. Pattern Recogn Lett. 2023;170:85–92.
doi: 10.1016/j.patrec.2023.05.004
Pang Y, Zhao X, Xiang TZ, Zhang L, Lu H. Zoom in and out: A mixedscale triplet network for camouflaged object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Louisiana: 2022;2160–70.
He R, Dong Q, Lin J, Lau RW. Weakly-supervised camouflaged object detection with scribble annotations. In: Sponsored by the Association for the Advancement of Artificial Intelligence (AAAI). Washington DC: 2023;781–9.
Li M, Xie Y, Ma L. Paying attention for adjacent areas: Learning discriminative features for large-scale 3d scene segmentation. Pattern Recogn. 2022;129:108722.
doi: 10.1016/j.patcog.2022.108722
Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV). Munich: 2018;801–18.
Mehta S, Rastegari M, Caspi A, Shapiro L, Hajishirzi H. Espnet: Efficient spatial pyramid of dilated convolutions for semantic segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV). Munich: 2018;552–568.
Paszke A, Chaurasia A, Kim S, Culurciello E. Enet: A deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:1606.02147. 2016;1–10.
Chollet F. Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Hawaii: 2017;1251–8.
Liu J, Zhou Q, Qiang Y, Kang B, Wu X, Zheng B. Fddwnet: a lightweight convolutional neural network for real-time semantic segmentation. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Barcelona: 2020;2373–7.
Gao Y, Zhou M, Metaxas DN. Utnet: a hybrid transformer architecture for medical image segmentation. In: Medical Image Computing and Computer Assisted Intervention (MICCAI). Strasbourg: 2021;61–71.
He K, Gan C, Li Z, Rekik I, Yin Z, Ji W, Gao Y, Wang Q, Zhang J, Shen D. Transformers in medical image analysis. Intelligent Medicine. 2023;3(1):59–78.
doi: 10.1016/j.imed.2022.07.002
Valanarasu JMJ, Patel VM. Unext: Mlp-based rapid medical image segmentation network. In: Medical Image Computing and Computer Assisted Intervention (MICCAI). Singapore: 2022;23–33.
Ruan J, Xiang S, Xie M, Liu T, Fu Y. Malunet: A multi-attention and lightweight unet for skin lesion segmentation. In: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). NV: 2022;1150–6.
Ruan J, Xie M, Gao J, Liu T, Fu Y. Ege-unet: an efficient group enhanced unet for skin lesion segmentation. In: Medical Image Computing and Computer Assisted Intervention (MICCAI). BC: 2023;481–90.
Vernaza P, Chandraker M. Learning random-walk label propagation for weakly-supervised semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Hawaii: 2017;2953–61.
Yamashita R, Nishio M, Do RKG, Togashi K. Convolutional neural networks: an overview and application in radiology. Insights Imaging. 2018;9:611–29.
doi: 10.1007/s13244-018-0639-9
pubmed: 29934920
Wu T, Tang S, Zhang R, Cao J, Zhang Y. Cgnet: A light-weight context guided network for semantic segmentation. IEEE Trans Image Process. 2020;30:1169–79.
doi: 10.1109/TIP.2020.3042065
pubmed: 33306466
Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention (MICCAI). Munich: 2015;234–41.
Oktay O, Schlemper J, Folgoc LL, Lee M, Heinrich M, Misawa K, Mori K, McDonagh S, Hammerla NY, Kainz B et al. Attention u-net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999. 2018;1–10.
Isensee F, Jaeger PF, Kohl SA, Petersen J, Maier-Hein KH. nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021;18(2):203–11.
doi: 10.1038/s41592-020-01008-z
pubmed: 33288961
Chen B, Liu Y, Zhang Z, Lu G, Kong AWK. Transattunet: Multi-level attention-guided u-net with transformer for medical image segmentation. IEEE Trans Emerg Topics Comput Intell. 2023;8(1):55–68.
Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell. 2017;39(4):640–51.
Cheng B, Misra I, Schwing AG, Kirillov A, Girdhar R. Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Louisiana: 2022;1290–1299.
Jain J, Li J, Chiu MT, Hassani A, Orlov N, Shi H. Oneformer: One transformer to rule universal image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver: 2023;2989–98.