☆ 4.6 Review

Transformers in medical image segmentation: A review

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2023)

Related references

Note: Only part of the references are listed.

Article Biology

SWTRU: Star-shaped Window Transformer Reinforced U-Net for medical image segmentation

Jianyi Zhang et al.

Summary: This paper presents a novel model, SWTRU, for medical image segmentation. By combining the U-Net network and Transformer model, SWTRU achieves accurate segmentation of highly complex and low-contrast images. The experimental results demonstrate the superior performance of SWTRU in various medical image segmentation tasks.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

RT-Unet: An advanced network based on residual network and transformer for medical image segmentation

Bo Li et al.

Summary: This paper proposes RT-Unet, which combines the advantages of Transformer and Residual network, for accurate medical segmentation. Experimental results demonstrate that RT-Unet outperforms other deep learning-based algorithms in terms of accuracy and efficiency.

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS (2022)

Add to Collection

Article Biology

TransCUNet: UNet cross fused transformer for medical image segmentation

Shen Jiang et al.

Summary: Accurate segmentation of medical images is crucial, but the complexity of shape and difference in structures of different objects, as well as the small scale of medical datasets, make it difficult to train effectively. To improve the segmentation performance, we propose TransCUNet, a multi-branch network model that effectively extracts high-level and low-level features of medical images of different modalities using cross residual fusion block, pyramidal pooling module, and gated axial-attention. Experimental results show that TransCUNet outperforms current mainstream segmentation methods and has great potential for clinical applications.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

Add to Collection

Proceedings Paper Engineering, Biomedical

LONG-RANGE 3D SELF-ATTENTION FOR MRI PROSTATE SEGMENTATION

Federico Pollastri et al.

Summary: In this paper, a novel architecture is proposed to address the problem of prostate segmentation from MRI. The designed model retrieves multi-scale 3D features and utilizes a self-attention transformer to gain a global field of view, bridging the gap between recent advances in 2D computer vision and 3D semantic segmentation. Experimental results demonstrate that the proposed method improves the accuracy of prostate segmentation from MRI.

2022 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (IEEE ISBI 2022) (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentation

Xiangyi Yan et al.

Summary: Recent advances in incorporating transformer models into medical image segmentation, particularly in conjunction with the U-Net model, have shown promising results. However, existing methods often overlook the axial-axis information provided by 3D volumes. This paper proposes the AFTer-UNet model, which combines the strengths of convolutional layers and transformers, considers both intra-slice and inter-slice cues, and achieves better performance with fewer parameters and reduced GPU memory usage.

2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022) (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

UNETR: Transformers for 3D Medical Image Segmentation

Ali Hatamizadeh et al.

Summary: Fully Convolutional Neural Networks (FCNNs) have been successful in medical image segmentation, but their limited ability to learn long-range dependencies is a challenge. Inspired by transformers in NLP, we propose a novel architecture called UNet Transformers (UNETR) to redefine volumetric medical image segmentation as a sequence prediction problem. By combining transformers and U-shaped network design in the encoder and decoder, we effectively capture global information and achieve semantic segmentation output.

2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022) (2022)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge

Victor M. Campello et al.

Summary: The emergence of deep learning has advanced cardiac magnetic resonance segmentation, yet current models lack generalizability. A recent competition emphasized the importance of data augmentation in training deep learning models and provided new data resources for future research.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2021)

Add to Collection

Article Health Care Sciences & Services

HybridCTrm: Bridging CNN and Transformer for Multimodal Brain Image Segmentation

Qixuan Sun et al.

Summary: This study proposes a hybrid multimodal segmentation method based on Transformer and CNN, showing superior performance over traditional fully CNN methods in most evaluation metrics. The study also analyzes the influence of Transformer depth on performance, visualizes the results, and explores how the hybrid methods improve segmentations.

JOURNAL OF HEALTHCARE ENGINEERING (2021)

Add to Collection

Article Biotechnology & Applied Microbiology

CST: A Multitask Learning Framework for Colorectal Cancer Region Mining Based on Transformer

Dong Sui et al.

Summary: This paper introduces a novel transfer learning protocol, called CST, for colorectal cancer region detection and segmentation task based on the transformer model, effectively constructing the cancer region detection and its segmentation jointly. With the incorporation of an autoencoder-based image-level decision approach, the detection accuracy is improved. The proposed method achieves better results on detection and segmentation tasks compared to other methods.

BIOMED RESEARCH INTERNATIONAL (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Cerebrovascular segmentation from TOF-MRA based on multiple-U-net with focal loss function

Xiaoyu Guo et al.

Summary: This study proposed an automatic cerebral vessel segmentation algorithm based on M-U-net for TOF-MRA data, which achieved better segmentation results than single U-net models. The feature fusion of three single U-nets effectively complemented the segmentation results, reaching a state-of-the-art level in comparison with existing algorithms.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2021)

Add to Collection

Article Oncology

A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy

Xuming Chen et al.

Summary: This study introduced a deep learning-based automatic segmentation algorithm, WBNet, which accurately and efficiently delineates major organs at risk (OARs) on CT images. WBNet outperformed other AS algorithms in terms of DSC values and delineation time, showing great effectiveness in clinical practice.

RADIOTHERAPY AND ONCOLOGY (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging

Dong Yang et al.

Summary: The study introduces a new automated machine learning algorithm, T-AutoML, which can search for the best neural architecture, hyper-parameters, and data augmentation strategies simultaneously, utilizing the modern transformer model to achieve high performance.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

Correlation of Chest CT and RT-PCR Testing for Coronavirus Disease 2019 (COVID-19) in China: A Report of 1014 Cases

Tao Ai et al.

RADIOLOGY (2020)

Add to Collection

Article Multidisciplinary Sciences

Video-based AI for beat-to-beat assessment of cardiac function

David Ouyang et al.

NATURE (2020)

Add to Collection

Article Public, Environmental & Occupational Health

The association between incidence and mortality of brain cancer and human development index (HDI): an ecological study

Zaher Khazaei et al.

BMC PUBLIC HEALTH (2020)

Add to Collection

Article Neurosciences

Automated processing pipeline for neonatal diffusion MRI in the developing Human Connectome Project

Matteo Bastiani et al.

NEUROIMAGE (2019)

Add to Collection

Article Biology

Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm

Mateusz Buda et al.

COMPUTERS IN BIOLOGY AND MEDICINE (2019)

Add to Collection

Article Computer Science, Interdisciplinary Applications

VoxelMorph: A Learning Framework for Deformable Medical Image Registration

Guha Balakrishnan et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2019)

Add to Collection

Review Computer Science, Interdisciplinary Applications

Kidney segmentation in ultrasound, magnetic resonance and computed tomography images: A systematic review

Helena R. Torres et al.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2018)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

Olivier Bernard et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2018)

Add to Collection

Article Computer Science, Artificial Intelligence

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Vijay Badrinarayanan et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

Add to Collection

Article Oncology

Radiogenomics of lower-grade glioma: algorithmically-assessed tumor shape is associated with tumor genomic subtypes and patient outcomes in a multi-institutional study with The Cancer Genome Atlas data

Maciej A. Mazurowski et al.

JOURNAL OF NEURO-ONCOLOGY (2017)

Add to Collection

Article Mathematical & Computational Biology

MRBrainS Challenge: Online Evaluation Framework for Brain Image Segmentation in 3T MRI Scans

Adrienne M. Mendrik et al.

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE (2015)

Add to Collection

© Peeref 2019-2024. All rights reserved.