X-Ray image enhancement, along with many other medical image processing applications, requires the segmentation of images into bone, soft tissue, and open beam regions. We apply a machine learning approach to this problem, presenting an end-to-end solution which results in robust and efficient inference. Since medical institutions frequently do not have the resources to process and label the large quantity of X-Ray images usually needed for neural network training, we design an end-to-end solution for small datasets, while achieving state-of-the-art results. Our implementation produces an overall accuracy of 92%, F1 score of 0.92, and an AUC of 0.98, surpassing classical image processing techniques, such as clustering and entropy based methods, while improving upon the output of existing neural networks used for segmentation in non-medical contexts. The code used for this project is available online.
HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation
Iran University of Science and Technology(伊朗科技大学);RWTH Aachen University(亚琛工业大学);Shahid Beheshti University(沙希德·贝赫什提大学);University of Montreal(蒙特利尔大学);Polytechnique Montreal(蒙特利尔理工学院);Quebec AI Institute(魁北克人工智能研究所);University of Regensburg(雷根斯堡大学);Fraunhofer Institute for Digital Medicine MEVIS(弗劳恩霍夫数字医学MEVIS研究所)
ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentation
Xiamen University(厦门大学);University of Washington(华盛顿大学);Peking University(北京大学);University of Hull(赫尔大学);Chinese University of Hong Kong(香港中文大学);Hong Kong Institute of Medical Engineering(香港医学工程研究所);Hong Kong Centre for Cerebro-cardiovascular Health Engineering(香港心脑血管健康工程中心);ShanghaiTech University(上海科技大学);Shanghai United Imaging Intelligence Co., Ltd.(上海联影智能医疗科技有限公司);Shanghai Clinical Research and Trial Center(上海临床研究与试验中心)
MSLAU-Net: A Hybrid CNN-Transformer Network for Medical Image Segmentation
College of Computer Science and Engineering(计算机科学与工程学院);College of Artificial Intelligence(人工智能学院);Department of Pharmacy(药学部);Department of Prosthodontics(修复学部);Chongqing Key Laboratory of Oral Diseases(重庆口腔疾病重点实验室);Chongqing Municipal Key Laboratory of Oral Biomedical Engineering of Higher Education(重庆市口腔生物医学工程高等教育重点实验室);School of Computer Science and Engineering(计算机科学与工程学院);Southeast University(东南大学)
CNN-Transformer Rectified Collaborative Learning for Medical Image Segmentation
School of Information and Communication Engineering, Dalian University of Technology(大连理工大学信息与通信工程学院);Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province(辽宁省泛在网络与服务软件重点实验室);DUT-RU International School of Information Science and Engineering, Dalian University of Technology(大连理工大学-鲁东大学国际信息科学与工程学院);Affiliated Zhongshan Hospital of Dalian University(大连大学附属中山医院)
TFCNs: A CNN-Transformer Hybrid Network for Medical Image Segmentation
Xiamen University(厦门大学);Beihang University(北京航空航天大学);University of Hull(赫尔大学);Chinese Academy of Sciences(中国科学院)
医学图像分割是医学信息分析中最基本的任务之一。到目前为止,已经提出了各种解决方案,包括许多基于深度学习的技术,如U-Net,FC-DenseNet等。然而,由于医学图像中存在固有的放大和失真,以及存在与正常组织密度相似的病变,高精度医学图像分割仍然是一项极具挑战性的任务。在本文中,我们提出了TFCN(Transformers for Fully Convolutional denseNet),通过将ResLinear-Transformer(RL-Transformer)和卷积线性注意块(CLAB)引入FC-DenseNet来解决这个问题。TFCN不仅能够利用CT图像中更多的潜在信息进行特征提取,而且通过CLAB模块可以更有效地捕获和传播语义特征并过滤非语义特征。我们的实验结果表明,TFCN可以达到最先进的性能,在Synapse数据集上的骰子得分为83.72%。此外,我们评估了TFCN对COVID-19公共数据集上病变面积影响的稳健性。Python代码将在https://github.com/HUANGLIZI/TFCNs上公开。
ConvFormer: Plug-and-Play CNN-Style Transformers for Improving Medical Image Segmentation
Huazhong University of Science and Technology(华中科技大学);Union Hospital, Tongji Medical College, Huazhong University of Science and Technology(华中科技大学同济医学院附属协和医院)
SegTransVAE: Hybrid CNN -- Transformer with Regularization for medical image segmentation
VinBrain JSC.(VinBrain联合股份公司);University of Science, Ho Chi Minh City(胡志明市科学大学);Vietnam National University, Ho Chi Minh City(胡志明市越南国家大学);Vin University(文大大学)
BEFUnet: A Hybrid CNN-Transformer Architecture for Precise Medical Image Segmentation
School of Electrical Engineering, Iran University of Science and Technology(伊朗科学技术大学电气工程学院);University College of Nabi Akram(纳比·阿克拉姆大学学院);Department of Electrical Engineering, Qazvin Branch, Iran(伊朗加兹温分校电气工程系)
ACM-UNet: Adaptive Integration of CNNs and Mamba for Efficient Medical Image Segmentation
Wuhan University of Technology(武汉理工大学);Chinese Academy of Medical Sciences and Peking Union Medical College(中国医学科学院北京协和医学院);Zhongnan Hospital of Wuhan University(武汉大学中南医院)
A BERT-Style Self-Supervised Learning CNN for Disease Identification from Retinal Images
School of Computing and Augmented Intelligence, Arizona State University(计算与增强智能学院,亚利桑那州立大学);McKeley School of Engineering, Washington University in St. Louis(工程学院,华盛顿大学圣路易斯分校);Department of Neurology, Mayo Clinic(神经病学部,梅奥诊所)
HyM-UNet: Synergizing Local Texture and Global Context via Hybrid CNN-Mamba Architecture for Medical Image Segmentation
School of Information and Communication Engineering, Beijing University of Posts and Communications (BUPT)(信息与通信工程学院,北京邮电大学);Alibaba Cloud AI Labs(阿里云人工智能实验室)
MedPrompt: LLM-CNN Fusion with Weight Routing for Medical Image Segmentation and Classification
1 ,2 Department of Electrical;Electronic Engineering,\ University of Engineering;3Department of Computer Science \& Engineering,\ University of Engineering \& Technology, Rajshahi-6204, Bangladesh
TEC-Net: Vision Transformer Embrace Convolutional Neural Networks for Medical Image Segmentation
Shaanxi University of Science and Technology(陕西科技大学);Xi’an Jiaotong University(西安交通大学);Griffith University(格里菲斯大学);Northwestern Polytechnical University(西北工业大学);Brunel University London(伦敦布鲁内尔大学)
MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation
Pakistan Institute of Engineering & Applied Sciences(巴基斯坦工程与应用科学学院);PIEAS Artificial Intelligence Center (PAIC)(PIEAS人工智能中心);Center for Mathematical Sciences(数学科学中心)
Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation
ETH Zurich(苏黎世联邦理工学院)
当训练数据集代表测试时预期会遇到的变化时,卷积神经网络(CNN)对于监督学习问题非常有效。在医学图像分割中,当训练图像和测试图像在其采集细节(例如扫描仪模型或协议)方面不匹配时,这一前提就被违反了。在这种情况下,CNN的显着性能下降在文献中有很好的记录。为了解决这个问题,我们将分割CNN设计为两个子网络的级联:一个相对较浅的图像归一化CNN,然后是一个对归一化图像进行分割的深度CNN。我们使用训练数据集训练这两个子网络,该训练数据集由来自特定扫描仪和协议设置的注释图像组成。现在,在测试时,我们在预测分割标签的隐式先验的指导下,调整\emph{each test image}的图像归一化子网络。我们采用了一个独立训练的去噪自动编码器(DAE),以模拟这样一个隐含的前合理的解剖分割标签。我们在三个解剖结构的多中心磁共振成像数据集上验证了所提出的想法:大脑,心脏和前列腺。所提出的测试时间适应一致地提供性能改进,展示了该方法的承诺和通用性。由于不知道第二子网络深度CNN的架构,因此所提出的设计可以与任何分割网络一起使用,以提高对成像扫描仪和协议变化的鲁棒性。我们的代码可在:\url{https://github.com/neerakara/test-time-adaptable-neural-networks-for-domain-generalization} .
PHTrans: Parallelly Aggregating Global and Local Representations for Medical Image Segmentation
Beijing University of Posts and Telecommunications(北京邮电大学);Dalian University of Technology(大连理工大学);Guilin University of Electronic Technology(桂林电子科技大学);Guangdong Provincial People’s Hospital(广东省人民医院);Guangdong Academy of Medical Sciences(广东省医学科学院)
BRAU-Net++: U-Shaped Hybrid CNN-Transformer Network for Medical Image Segmentation
College of Computer Science and Engineering, Chongqing University of Technology(重庆理工大学计算机科学与工程学院);College of Computer Science, Chongqing University(重庆大学计算机学院);College of Artificial Intelligence, Chongqing University of Technology(重庆理工大学人工智能学院);The First Affiliated Hospital of Chongqing Medical University(重庆医科大学附属第一医院);Faculty of Computing and Information Technology, King Abdulaziz University(阿卜杜勒阿齐兹大学计算与信息技术学院)
Are Vision xLSTM Embedded UNet More Reliable in Medical 3D Image Segmentation?
Machine Intelligence Unit Indian Statistical Institute(机器智能单位印度统计研究所);Department of Computer Science and Engineering Jadavpur University(计算机科学与工程系贾梵布尔大学);Department of Computer Science and Engineering Alipurduar Government Engineering and Management College(计算机科学与工程系阿里普杜尔政府工程与管理学院)