Delving into masked autoencoders for multi-label thorax disease classification

J Xiao, Y Bai, A Yuille, Z Zhou - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Abstract Vision Transformer (ViT) has become one of the most popular neural architectures
due to its simplicity, scalability, and compelling performance in multiple vision tasks …

[HTML][HTML] Review of multimodal machine learning approaches in healthcare

F Krones, U Marikkar, G Parsons, A Szmul, A Mahdi - Information Fusion, 2025 - Elsevier
Abstract Machine learning methods in healthcare have traditionally focused on using data
from a single modality, limiting their ability to effectively replicate the clinical practice of …

Seeking an optimal approach for Computer-aided Diagnosis of Pulmonary Embolism

NU Islam, Z Zhou, S Gehlot, MB Gotway, J Liang - Medical image analysis, 2024 - Elsevier
Pulmonary Embolism (PE) represents a thrombus (“blood clot”), usually originating from a
lower extremity vein, that travels to the blood vessels in the lung, causing vascular …

A survey of the impact of self-supervised pretraining for diagnostic tasks in medical X-ray, CT, MRI, and ultrasound

B VanBerlo, J Hoey, A Wong - BMC Medical Imaging, 2024 - Springer
Self-supervised pretraining has been observed to be effective at improving feature
representations for transfer learning, leveraging large amounts of unlabelled data. This …

[HTML][HTML] Learning anatomically consistent embedding for chest radiography

Z Zhou, H Luo, J Pang, X Ding, M Gotway… - BMVC: proceedings of …, 2023 - ncbi.nlm.nih.gov
Self-supervised learning (SSL) approaches have recently shown substantial success in
learning visual representations from unannotated images. Compared with photographic …

ViTs as backbones: Leveraging vision transformers for feature extraction

O Elharrouss, Y Himeur, Y Mahmood, S Alrabaee… - Information …, 2025 - Elsevier
Abstract The emergence of Vision Transformers (ViTs) has marked a significant shift in the
field of computer vision, presenting new methodologies that challenge traditional …

Toward Lightweight Diabetic Retinopathy Classification: A Knowledge Distillation Approach for Resource-Constrained Settings

N Islam, MMH Jony, E Hasan, S Sutradhar, A Rahman… - Applied Sciences, 2023 - mdpi.com
Diabetic retinopathy (DR), a consequence of diabetes, is one of the prominent contributors
to blindness. Effective intervention necessitates accurate classification of DR; this is a need …

Foundation Ark: Accruing and Reusing Knowledge for Superior and Robust Performance

DA Ma, J Pang, MB Gotway, J Liang - International Conference on Medical …, 2023 - Springer
Deep learning nowadays offers expert-level and sometimes even super-expert-level
performance, but achieving such performance demands massive annotated data for training …

Prediction of visceral pleural invasion of clinical stage I lung adenocarcinoma using thoracoscopic images and deep learning

Y Shimada, T Ojima, Y Takaoka, A Sugano, Y Someya… - Surgery Today, 2024 - Springer
Purpose To develop deep learning models using thoracoscopic images to identify visceral
pleural invasion (VPI) in patients with clinical stage I lung adenocarcinoma, and to verify if …

ThyFusion: A lightweight attribute enhancement module for thyroid nodule diagnosis using gradient and frequency-domain awareness

G Chen, N Zhu, J Lin, B Pu, H Luo, K Li - Neurocomputing, 2025 - Elsevier
Accurate classification of thyroid nodules is a critical step in clinical diagnosis and plays a
crucial role in guiding subsequent treatment planning. However, current deep learning …