Share Email Print

Proceedings Paper

Hyperspectral microscopic imaging of skin squamous cell carcinoma
Author(s): Zhenfei Sheng; Xiaofa Zhang; Zelong Qiu; Chunguang Zhang; Hao Wang; Xi Huang; Zhiwei Tan; Weijie Qiu; Pengchong Wang; Wenyao Liu; Maoqiang Duan; Xiaoli Huang; Yiping Liu; Yuwei Xing; Binbin Lin
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Acousto-optic tunable filter (AOTF) is a new type of light splitter with fast tuning, stable structure and portability. In this paper, a hyperspectral microscopic imaging system is constructed by combining non-collinear AOTF with optical inverted microscopy. The feasibility of data augmentation based on hyperspectral images for object detection of skin squamous cell carcinoma is studied. The hyperspectral images collected from unstained sections of skin squamous cell carcinoma are processed into dataset. At the same time, the mature open source object detection model is selected and trained for 20,000 times. Using the trained model to detect the lesion area of other unstained sections, it is found that the model trained by hyperspectral image dataset has a good ability to distinguish the non-lesion area, and there is no false detection. And the model has a relatively accurate detection ability for large lesion area, but the results of the model for small lesion area are not ideal. After analysis, it is considered that the number of samples can be increased firstly, especially in small lesions, and the same to the hyperspectral images. In addition, the model for lesion detection can be further optimized. By increasing the complexity of the model, the model can learn more details and information in the image during the training process. The preliminary results of the experiment prove that hyperspectral imaging is feasible for data augmentation of lesion object detection dataset. This paper provides a new method for the object detection data augmentation of skin squamous cell carcinoma.

Paper Details

Date Published: 17 May 2019
PDF: 6 pages
Proc. SPIE 11170, 14th National Conference on Laser Technology and Optoelectronics (LTO 2019), 1117025 (17 May 2019); doi: 10.1117/12.2533591
Show Author Affiliations
Zhenfei Sheng, Fujian Normal Univ. (China)
Xiaofa Zhang, Fujian Normal Univ. (China)
Zelong Qiu, Fujian Normal Univ. (China)
Chunguang Zhang, Fujian Normal Univ. (China)
Key Lab. of Spectral Imaging Technology (China)
Hao Wang, Fujian Normal Univ. (China)
Xi Huang, Fujian Normal Univ. (China)
Zhiwei Tan, Fujian Normal Univ. (China)
Weijie Qiu, Fujian Normal Univ. (China)
Pengchong Wang, Fujian Normal Univ. (China)
Key Lab. of Spectral Imaging Technology (China)
Wenyao Liu, Fujian Normal Univ. Hospital (China)
Maoqiang Duan, Fujian Normal Univ. (China)
Shenyang Institute of Automation (China)
Xiaoli Huang, Fujian Normal Univ. (China)
Institute of Scientific and Technical Information of Liaoning Province (China)
Yiping Liu, Fujian Normal Univ. (China)
Yuwei Xing, Fujian Normal Univ. (China)
Binbin Lin, Fujian Normal Univ. (China)

Published in SPIE Proceedings Vol. 11170:
14th National Conference on Laser Technology and Optoelectronics (LTO 2019)
Jianqiang Zhu; Weibiao Chen; Zhenxi Zhang; Minlin Zhong; Pu Wang; Jianrong Qiu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?