Detecting mouse squamous cell carcinoma from submicron full‐field optical coherence tomography images by deep learning

Abstract

The standard medical practice for cancer diagnosis requires histopathology, which is an invasive and time-consuming procedure. Optical coherence tomography (OCT) is an alternative that is relatively fast, noninvasive, and able to capture three-dimensional structures of epithelial tissue. Unlike most previous OCT systems, which cannot capture crucial cellular-level information for squamous cell carcinoma (SCC) diagnosis, the full-field OCT (FF-OCT) technology used in this paper is able to produce images at sub-micron resolution and thereby facilitates the development of a deep learning algorithm for SCC detection. Experimental results show that the SCC detection algorithm can achieve a classification accuracy of 80% for mouse skin. Using the submicron FF-OCT imaging system, the proposed SCC detection algorithm has the potential for in-vivo applications.

A Comprehensive Review on Skin Cancer Detection Strategies using Deep Neural Networks

“…The suggested CNN classifier attained 95% accuracy after training and testing on dermoscopic images from the PH2 dataset. Additionally, when the number of layers in CNN was extended to 14 layers on dermoscopic pictures from the ISIC dataset, a higher accuracy rate of 97.78% was found (Ho et al, 2021). Regardless, adding layers consumes more resources and increases the complexity of processing.…”

Methods and applications of full-filed optical coherence tomography: a review

“…9(f) . 90 Moreover, the automatic classification algorithm based on a support vector machine is exploited to distinguish the adipose tissue in the hollow structure of breast tissue; combined with the texture features from ultrahigh-resolution FF-OCT image, the invasive ductal carcinoma (IDC) tissue, and normal fibrous matrix can be further distinguished. 91 …”

“…(e) H&E image of mouse squamous cell carcinoma skin; adapted from Ref. 90 . (f) The result of deep learning tissue classification algorithm for squamous cell carcinoma detection in FFOCT images of mouse skin, where the yellow circles represent the identified cancerous cells.…”

Imaging sebaceous gland using optical coherence tomography with deep learning assisted automatic identification

“…With the remarkable progress over recent years, deep learning has excelled in many computer vision applications [27–31]. In this article, we attempt to design a deep learning method to automatically classify on whether the images generated by our OCT system contain sebaceous gland or not.…”