Open AccessTriplet loss for Chromosome Classification
Author(s) -
Pranshav Gajjar,
Pooja Shah,
Akash Vegada,
Jainish Savalia
Publication year - 2022
Publication title -
journal of innovative image processing
Language(s) - English
Resource type - Journals
ISSN - 2582-4252
DOI - 10.36548/jiip.2022.1.001
Subject(s) - computer science , hyperparameter , chromosome , karyotype , artificial intelligence , convolutional neural network , pattern recognition (psychology) , perceptron , process (computing) , similarity (geometry) , field (mathematics) , machine learning , artificial neural network , data mining , biology , mathematics , genetics , pure mathematics , gene , operating system , image (mathematics)
The analysis of chromosomes, known as karyotyping, is essential in diagnosing various human genetic disorders and chromosomal aberrations. It can detect a variety of genetic diseases and provide a deeper insight into the human body. However, the process of manual karyotyping is highly time-consuming and requires accomplished professionals with a deep understanding in the field. An automated process is thus highly desirable to assist cytogeneticists and mitigate the cognitive load procured during karyotyping. With that intention, a similarity learning approach is proposed in this paper using ‘Triplet Loss’ for procuring high-dimensional embeddings. The Offline Triplet Loss, Semi-Hard Online mining, and associated hyperparameters are thoroughly tested and explored, and the obtained embeddings are used to classify the images into their respective chromosome classes and Denver groups. A comparative analysis on various embedding-classifying algorithms such as Multi-Layer Perceptron (MLP) and Nearest Neighbours is also demonstrated in this paper, along with experiments on associated distance metrics. The proposed methodologies deliver a superlative performance when compared to a baseline Convolutional Neural Network (CNN), on a publicly available chromosome classification dataset.