Machine-learning classification of non-melanoma skin cancers from image features obtained by optical coherence tomography

Optical coherence tomography angiography (OCTA) offers a noninvasive label-free solution for imaging retinal vasculatures at the capillary level resolution. In principle, improved resolution implies a better chance to reveal subtle microvascular distortions associated with eye diseases that are asymptomatic in early stages. However, massive screening requires experienced clinicians to manually examine retinal images, which may result in human error and hinder objective screening. Recently, quantitative OCTA features have been developed to standardize and document retinal vascular changes. The feasibility of using quantitative OCTA features for machine learning classification of different retinopathies has been demonstrated. Deep learning-based applications have also been explored for automatic OCTA image analysis and disease classification. In this article, we summarize recent developments of quantitative OCTA features, machine learning image analysis, and classification.

Download Full-text

Optical coherence tomography for identification of malignant pulmonary nodules based on random forest machine learning algorithm

PLoS ONE ◽

10.1371/journal.pone.0260600 ◽

2021 ◽

Vol 16 (12) ◽

pp. e0260600

Author(s):

Ming Ding ◽

Shi-yu Pan ◽

Jing Huang ◽

Cheng Yuan ◽

Qiang Zhang ◽

...

Keyword(s):

Machine Learning ◽

Optical Coherence Tomography ◽

Random Forest ◽

Attenuation Coefficient ◽

Learning Algorithm ◽

Pulmonary Nodules ◽

Image Features ◽

Machine Learning Algorithm ◽

Optical Coherence ◽

P Values

Objective To explore the feasibility of using random forest (RF) machine learning algorithm in assessing normal and malignant peripheral pulmonary nodules based on in vivo endobronchial optical coherence tomography (EB-OCT). Methods A total of 31 patients with pulmonary nodules were admitted to Department of Respiratory Medicine, Zhongda Hospital, Southeast University, and underwent chest CT, EB-OCT and biopsy. Attenuation coefficient and up to 56 different image features were extracted from A-line and B-scan of 1703 EB-OCT images. Attenuation coefficient and 29 image features with significant p-values were used to analyze the differences between normal and malignant samples. A RF classifier was trained using 70% images as training set, while 30% images were included in the testing set. The accuracy of the automated classification was validated by clinically proven pathological results. Results Attenuation coefficient and 29 image features were found to present different properties with significant p-values between normal and malignant EB-OCT images. The RF algorithm successfully classified the malignant pulmonary nodules with sensitivity, specificity, and accuracy of 90.41%, 77.87% and 83.51% respectively. Conclusion It is clinically practical to distinguish the nature of pulmonary nodules by integrating EB-OCT imaging with automated machine learning algorithm. Diagnosis of malignant pulmonary nodules by analyzing quantitative features from EB-OCT images could be a potentially powerful way for early detection of lung cancer.

Download Full-text

Medical images classification for skin cancer using quantitative image features with optical coherence tomography

Journal of Innovative Optical Health Sciences ◽

10.1142/s1793545816500036 ◽

2016 ◽

Vol 09 (02) ◽

pp. 1650003 ◽

Cited By ~ 14

Author(s):

Wei Gao ◽

Valery P. Zakharov ◽

Oleg O. Myakinin ◽

Ivan A. Bratchenko ◽

Dmitry N. Artemyev ◽

...

Keyword(s):

Optical Coherence Tomography ◽

Skin Cancer ◽

Basal Cell ◽

Image Features ◽

Skin Tumors ◽

P Value ◽

Optical Coherence ◽

Quantitative Image ◽

Basal Cell Carcinomas

Optical coherence tomography (OCT) is employed in the diagnosis of skin cancer. Particularly, quantitative image features extracted from OCT images might be used as indicators to classify the skin tumors. In the present paper, we investigated intensity-based, texture-based and fractal-based features for automatically classifying the melanomas, basal cell carcinomas and pigment nevi. Generalized estimating equations were used to test for differences between the skin tumors. A modified p value of [Formula: see text][Formula: see text]0.001 was considered statistically significant. Significant increase of mean and median of intensity and significant decrease of mean and median of absolute gradient were observed in basal cell carcinomas and pigment nevi as compared with melanomas. Significant decrease of contrast, entropy and fractal dimension was also observed in basal cell carcinomas and pigment nevi as compared with melanomas. Our results suggest that the selected quantitative image features of OCT images could provide useful information to differentiate basal cell carcinomas and pigment nevi from the melanomas. Further research is warranted to determine how this approach may be used to improve the classification of skin tumors.

Download Full-text