A comprehensive survey of deep learning research on medical image analysis with focus on transfer learning

S Atasever, N Azginoglu, DS Terzi, R Terzi - Clinical imaging, 2023 - Elsevier
This survey aims to identify commonly used methods, datasets, future trends, knowledge
gaps, constraints, and limitations in the field to provide an overview of current solutions used …

Medical image segmentation with domain adaptation: a survey

Y Li, Y Fan - arxiv preprint arxiv:2311.01702, 2023 - arxiv.org
Deep learning (DL) has shown remarkable success in various medical imaging data
analysis applications. However, it remains challenging for DL models to achieve good …

Adaptive refining-aggregation-separation framework for unsupervised domain adaptation semantic segmentation

Y Cao, H Zhang, X Lu, Y Chen, Z **ao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Unsupervised domain adaptation has attracted widespread attention as a promising method
to solve the labeling difficulties of semantic segmentation tasks. It trains a segmentation …

Design and implementation of convolutional neural networks accelerator based on multidie

Q Song, J Zhang, L Sun, G ** - IEEE Access, 2022 - ieeexplore.ieee.org
To achieve real-time object detection tasks with high throughput and low latency, this paper
proposes a multi-die hardware accelerator architecture. It implements three accelerators on …

Automated biomedical image classification using multi-scale dense dilated semi-supervised u-net with cnn architecture

B PR, A BK - Multimedia Tools and Applications, 2024 - Springer
Biomedical research heavily relies on automated image classification to enhance
understanding of protein structure and function. This study proposes a novel approach for …

MBDA-Net: Multi-source boundary-aware prototype alignment domain adaptation for polyp segmentation

J Yan, H Zhu, T Hou, N Chen, W Lu, Y Wang… - … Signal Processing and …, 2024 - Elsevier
Accurate segmentation of polyps in colonoscopy images is important for the prevention and
treatment of colorectal cancer. However, samples collected from different centers often …

Improved Two-Stage Transfer Learning Approach for ViT-Based Myocardial Infarction Detection

A Boukhamla, H Ouerghi, N Azizi… - Arabian Journal for …, 2024 - Springer
Myocardial infarction (MI) is a critical cardiovascular condition requiring precise diagnosis.
Accurate segmentation of myocardial pathologies in cardiac magnetic resonance (CMR) …

[HTML][HTML] Automatic vessel segmentation and reformation of non-contrast coronary magnetic resonance angiography using transfer learning-based three-dimensional …

L Lin, Y Zheng, Y Li, D Jiang, J Cao, J Wang… - Journal of …, 2025 - Elsevier
Background Coronary magnetic resonance angiography (CMRA) presents distinct
advantages, but its reliance on manual image post-processing is labor-intensive and …

Improved image semantic segmentation with domain adaptation for mechanical parts

X XIE, Y HUANG, T WAN, L XU, F HU - Mechanical Engineering …, 2022 - jstage.jst.go.jp
Non-contact detection methods based on computer vision are widely used in industrial
production. When collecting images, different light source schemes are often used to meet …