© 2023 All Rights Reserved

Classification and Grading of Squamous Cell Carcinoma Tissue Images Using Machine Learning

Sindhoora K M1, Spandana K U1, Ragahvendra U2, Sharada Rai3, Raghu Radhakrishnan4, K K Mahato1, Nirmal Mazumder1, *
1Department of Biophysics, Manipal School of Life Sciences, Manipal Academy of Higher Education, Manipal, India – 576104
2Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India -576104
3Department of Pathology, Kasturba Medical College, Mangalore, Karnataka, India – 575001
4Department of Oral Pathology, Manipal College of Dental Sciences, Manipal, Manipal Academy of Higher Education, Manipal, India-576104


Histopathological tissue grading plays an important role in disease diagnosis and treatment. Manual grading of tissue is a tedious and time-consuming process due to the complex nature of biological entities, which in turn demands an expert pathologist to record an accurate output. Besides, the manual analysis is highly subjective. To overcome these limitations, an automatic fast, and robust image analysis technique that delivers well-processed images with defined image quality criteria is desirable. Machine learning (ML) is one such area of research that performs statistical learning with the help of various multivariate analytical methods such as, independent component analysis, principal component analysis (PCA), multivariate regression, etc. These methods aid in the identification of significant features during training of the ML algorithm, which may later be utilized for classification or prediction of test data set. Further, advanced methods such as deep learning (DL) support the automated classification of the sample data. In the present study, we trained various ML and DL-based image classification models, among which support vector machine (SVM) and convolutional neural network (CNN) produced good results in the classification of squamous cell carcinoma (SCC) tissue images.

File with abstract


Sindhoora Kaniyala Melanthota
PhD student


File with report


Ask question