Preliminary Study on Deep Learning Picture Classification Model for Identification and Classification of Invasion Pattern of Oral Squamous Cell Carcinoma

doi:10.13701/j.cnki.kqyxyj.2023.10.013

Abstract

Abstract: Objective: To explore the feasibility and effect of the deep learning network model (ResNet-18) to determine the worst infiltration mode (worst pattern of invasion, WPOI) of oral squamous cell carcinoma (oral squamous cell carcinoma, OSCC). Methods: The 491 digital pathological sections collected by ResNet-18 model were trained to identify and distinguish non-tumor areas, WPOI 1-3 and WPOI 4-5, and the model was evaluated using the classification accuracy. Results: ResNet-18 neural network can effectively distinguish non-tumor areas of OSCC, WPOI 1-3 and WPOI 4-5, with an accuracy of 99.5%. Conclusion: The deep learning network model ResNet-18 can effectively distinguish the non-tumor areas of OSCC, WPOI 1-3, and WPOI 4-5, and assist physicians to improve the diagnosis speed.

Key words: oral squamous cell carcinoma, pathology, deep learning, ResNet, worst pattern of invasion

WU Tianci, YU Jiaxin, HUANG Xiaofeng, CHEN Sheng, WANG Yuxin, PU Yumei. Preliminary Study on Deep Learning Picture Classification Model for Identification and Classification of Invasion Pattern of Oral Squamous Cell Carcinoma[J]. Journal of Oral Science Research, 2023, 39(10): 917-922.

References

[1] Sung H, Ferlay J, Siegel RL, et al. Global Cancer Statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries [J]. CA Cancer J Clin, 2021, 71(3):209-249.
[2] 陈新,徐文华,周健,等.口腔鳞状细胞癌现状[J].口腔医学,2017,37(5):462-465.
[3] Vats R, Rai R, Kumar M. Detecting oral cancer: The potential of artificial intelligence [J]. Curr Med Imaging, 2022, 18(9):919-923.
[4] Malkani N, Kazmi S, Rashid MU. Epidemiological assessment of oral cancer burden in Pakistan [J]. Cancer Invest, 2021, 39(10):842-853.
[5] Lakhera KK, Nama Y, Maan P, et al. Worst pattern of invasion as a predictor of nodal metastasis in early-stage oral squamous cell carcinoma [J]. Indian J Surg Oncol, 2023, 14(1):160-168.
[6] Mishra A, Das A, Dhal I, et al. Worst pattern of invasion in oral squamous cell carcinoma is an independent prognostic factor [J]. J Oral Biol Craniofac Res, 2022, 12(6):771-776.
[7] Pu Y, Ding L, Wang Y, et al. Biopsy pattern of invasion type to determine the surgical approach in early-stage oral squamous cell carcinoma [J]. Virchows Arch, 2021, 479(1):109-119.
[8] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition [C]. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016:770-778.
[9] Warin K, Limprasert W, Suebnukarn S, et al. Performance of deep convolutional neural network for classification and detection of oral potentially malignant disorders in photographic images [J]. Int J Oral Maxillofac Surg, 2022, 51(5):699-704.
[10] Panigrahi S, Bhuyan R, Kumar K, et al. Multistage classification of oral histopathological images using improved residual network [J]. Math Biosci Eng, 2022, 19(2):1909-1925.
[11] Yang SY, Li SH, Liu JL, et al. Histopathology-based diagnosis of oral squamous cell carcinoma using deep learning [J]. J Dent Res, 2022, 101(11):1321-1327.
[12] Mishra A, Das A, Dhal I, et al. Worst pattern of invasion in oral squamous cell carcinoma is an independent prognostic factor [J]. J Oral Biol Craniofac Res, 2022, 12(6):771-776.
[13] LeCun Y, Bengio Y, Hinton G. Deep learning [J]. Nature, 2015, 521(7553):436-444.
[14] Ahn Y, Hwang JJ, Jung YH, et al. Automated mesiodens classification system using deep learning on panoramic radiographs of children [J]. Diagnostics (Basel), 2021, 11(8):1477.
[15] Kamat M, Rai BD, Puranik RS, et al. A comprehensive review of surgical margin in oral squamous cell carcinoma highlighting the significance of tumor-free surgical margins [J]. J Cancer Res Ther, 2019, 15(3):449-454.