Automated human cell classification in sparse datasets using few-shot learning

Abstract

Classifying and analyzing human cells is a lengthy procedure, often involving a trained professional. In an attempt to expedite this process, an active area of research involves automating cell classification through use of deep learning-based techniques. In practice, a large amount of data is required to accurately train these deep learning models. However, due to the sparse human cell datasets currently available, the performance of these models is typically low. This study investigates the feasibility of using few-shot learning-based techniques to mitigate the data requirements for accurate training. The study is comprised of three parts: First, current state-of-the-art few-shot learning techniques are evaluated on human cell classification. The selected techniques are trained on a non-medical dataset and then tested on two out-of-domain, human cell datasets. The results indicate that, overall, the test accuracy of state-of-the-art techniques decreased by at least 30% when transitioning from a non-medical dataset to a medical dataset. Reptile and EPNet were the top performing techniques tested on the BCCD dataset and HEp-2 dataset respectively. Second, this study evaluates the potential benefits, if any, to varying the backbone architecture and training schemes in current state-of-the-art few-shot learning techniques when used in human cell classification. To this end, the best technique identified in the first part of this study, EPNet, is used for experimentation. In particular, the study used 6 different network backbones, 5 data augmentation methodologies, and 2 model training schemes. Even with these additions, the overall test accuracy of EPNet decreased from 88.66% on non-medical datasets to 44.13% at best on the medical datasets. Third, this study presents future directions for using few-shot learning in human cell classification. In general, few-shot learning in its current state performs poorly on human cell classification. The study proves that attempts to modify existing network architectures are not effective and concludes that future research effort should be focused on improving robustness towards out-of-domain testing using optimization-based or self-supervised few-shot learning techniques.

Intelligent Academic Specialties Selection in Higher Education for Ukrainian Entrants: A Recommendation System

“…The usage of association rules mining allowed us to answer these questions. Applying this and other data mining methods in education remains relevant and has enough use-cases ( Villegas-Ch et al 2021 ; Walsh et al 2022 ).…”

Generative and Contrastive Combined Support Sample Synthesis Model for Few-/Zero-Shot Surface Defect Recognition

“…In medical image processing, due to the difficulty of biopsy label acquisition, Qinghua et al first attempted to introduce the few-shot learning into the ultrasound breast tumor diagnosis system [31] and achieved excellent performance. In recent years, the few-shot method has been widely used in the medical field, including the recognition of COVID-19 from rare chest images [32], human cell categorization in rare datasets [33], autism facial feature categorization [34], skin image categorization [35], and healthcare safety monitoring [36].…”

Critically synchronized brain waves form an effective, robust and flexible basis for human memory and learning

“…The experiments presented below are clearly beyond human training capacity, but nevertheless represent a very good set of preliminary stress tests to provide support for all our claims, from Critical Encoding to Memory Robustness. The demonstration that back propagation step is not generally required for very good performance of continues learning as well as small footprint of nodes and input data involved in memory formation are representative of human few-shot learning [66][67][68][69] as well as relevant to the larger issues introduced in our paper.…”