홈 › Papers

Classification of Radiological Text in Small and Imbalanced Datasets in a Non-English Language

2024-09-30 · Vincent Beliveau, Helene Kaas, Martin Prener, Claes N. Ladefoged, Desmond Elliott, Gitte M. Knudsen, Lars H. Pinborg, Melanie Ganz

Natural language processing (NLP) in the medical domain can underperform in real-world applications involving small datasets in a non-English language with few labeled samples and imbalanced classes. There is yet no consensus on how to approach this problem. We evaluated a set of NLP models including BERT-like transformers, few-shot learning with sentence transformers (SetFit), and prompted large language models (LLM), using three datasets of radiology reports on magnetic resonance images of epilepsy patients in Danish, a low-resource language. Our results indicate that BERT-like models pretrained in the target domain of radiology reports currently offer the optimal performances for this scenario. Notably, the SetFit and LLM models underperformed compared to BERT-like models, with LLM performing the worst. Importantly, none of the models investigated was sufficiently accurate to allow for text classification without any supervision. However, they show potential for data filtering, which could reduce the amount of manual labeling required.

📄 PDF Abstract BibTeX arXiv:2409.20147

Code (1)

vbeliveau/radiology-text-classification 공식 구현 pytorch

Tasks

Few-Shot LearningSentencetext-classification Text Classification

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

ConvGeN: Convex space learning improves deep-generative oversampling for tabular imbalanced classification on smaller datasets

2022-06-20 · Kristian Schultz, Saptarshi Bej, Waldemar Hahn, Markus Wolfien 외

Data is commonly stored in tabular format. Several fields of research are prone to small imbalanced tabular data. Supervised Machine Learning on such data is often difficult due to class imbalance. Synthetic data generat…

Benchmarking Fraud Detection Image Generation imbalanced classification+2

Weakly-supervised positional contrastive learning: application to cirrhosis classification

2023-07-10 · Emma Sarfati, Alexandre Bône, Marc-Michel Rohé, Pietro Gori 외

Large medical imaging datasets can be cheaply and quickly annotated with low-confidence, weak labels (e.g., radiological scores). Access to high-confidence labels, such as histology-based diagnoses, is rare and costly. P…

Classification Contrastive Learning GPU

Deep learning for understanding multilabel imbalanced Chest X-ray datasets

2022-07-28 · Helena Liz, Javier Huertas-Tato, Manuel Sánchez-Montañés, Javier Del Ser 외

Over the last few years, convolutional neural networks (CNNs) have dominated the field of computer vision thanks to their ability to extract features and their outstanding performance in classification problems, for exam…

Deep Learning

Addressing Small and Imbalanced Medical Image Datasets Using Generative Models: A Comparative Study of DDPM and PGGANs with Random and Greedy K Sampling

2024-12-17 · Iman Khazrak, Shakhnoza Takhirova, Mostafa M. Rezaee, Mehrdad Yadollahi 외

The development of accurate medical image classification models is often constrained by privacy concerns and data scarcity for certain conditions, leading to small and imbalanced datasets. To address these limitations, t…

Denoising image-classification Image Classification Medical Image Classification

Learning Diagnosis of COVID-19 from a Single Radiological Image

2020-06-06 · arXiv:2006.12220 2020 6 · Pengyi Zhang, Yunxin Zhong, Xiaoying Tang, Yunlin Deng 외

Radiological image is currently adopted as the visual evidence for COVID-19 diagnosis in clinical. Using deep models to realize automated infection measurement and COVID-19 diagnosis is important for faster examination b…

COVID-19 Diagnosis Data Augmentation