Few Shot Learning for Medical Imaging: A Comparative Analysis of Methodologies and Formal Mathematical Framework

Nayem, Jannatul; Hasan, Sayed Sahriar; Amina, Noshin; Das, Bristy; Ali, Md Shahin; Ahsan, Md Manjurul; Raman, Shivakumar

doi:10.1007/978-3-031-47772-0_4

Cited by 5 publications

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Few-shot learning for COVID-19 chest X-ray classification with imbalanced data: an inter vs. intra domain study

Galán-Cuenca,

Gallego,

Saval-Calvo

et al. 2024

Pattern Anal Applic

View full text Add to dashboard Cite

Medical image datasets are essential for training models used in computer-aided diagnosis, treatment planning, and medical research. However, some challenges are associated with these datasets, including variability in data distribution, data scarcity, and transfer learning issues when using models pre-trained from generic images. This work studies the effect of these challenges at the intra- and inter-domain level in few-shot learning scenarios with severe data imbalance. For this, we propose a methodology based on Siamese neural networks in which a series of techniques are integrated to mitigate the effects of data scarcity and distribution imbalance. Specifically, different initialization and data augmentation methods are analyzed, and four adaptations to Siamese networks of solutions to deal with imbalanced data are introduced, including data balancing and weighted loss, both separately and combined, and with a different balance of pairing ratios. Moreover, we also assess the inference process considering four classifiers, namely Histogram, kNN, SVM, and Random Forest. Evaluation is performed on three chest X-ray datasets with annotated cases of both positive and negative COVID-19 diagnoses. The accuracy of each technique proposed for the Siamese architecture is analyzed separately. The results are compared to those obtained using equivalent methods on a state-of-the-art CNN, achieving an average F1 improvement of up to 3.6%, and up to 5.6% of F1 for intra-domain cases. We conclude that the introduced techniques offer promising improvements over the baseline in almost all cases and that the technique selection may vary depending on the amount of data available and the level of imbalance.

show abstract

Few-shot learning for COVID-19 chest X-ray classification with imbalanced data: an inter vs. intra domain study

Galán-Cuenca,

Gallego,

Saval-Calvo

et al. 2024

Pattern Anal Applic

View full text Add to dashboard Cite

show abstract

Prompt Learning with One-Shot Setting based Feature Space Analysis in Vision-and-Language Models

Hirohashi,

Hirakawa,

Yamashita

et al. 2024

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Bioinformatics in Agriculture and Ecology Using Few-Shots Learning From Field to Conservation

Shinde,

Nayak,

Ajalkar

et al. 2024

Applying Machine Learning Techniques to Bioinformatics

View full text Add to dashboard Cite

The integration of bioinformatics with contemporary machine-learning algorithms is transforming sustainable practices and conservation activities in biology and agriculture. Plant disease identification is an area where few-shot learning (FSL) excels because of data scarcity. This study applies FSL to computational biology to tackle agricultural and environmental concerns. Bioinformatics has a significant influence on sustainable farming and research, according to the report. The chapter introduces few-shot learning, and shows how it may address the lack of labelled data in several disciplines. Case studies, including explanations, demonstrate the manner in which the FSL method is widely used in ecological surveillance, environmental programs, and crop supervisors. The essay discusses ethical issues around machine learning in ecological systems and agriculture, emphasizing open and responsible data methods.

show abstract

Few Shot Learning for Medical Imaging: A Comparative Analysis of Methodologies and Formal Mathematical Framework

Cited by 5 publications

References 40 publications

Few-shot learning for COVID-19 chest X-ray classification with imbalanced data: an inter vs. intra domain study

Few-shot learning for COVID-19 chest X-ray classification with imbalanced data: an inter vs. intra domain study

Prompt Learning with One-Shot Setting based Feature Space Analysis in Vision-and-Language Models

Bioinformatics in Agriculture and Ecology Using Few-Shots Learning From Field to Conservation

Contact Info

Product

Resources

About