Perspective+ Unet: Enhancing Segmentation with Bi-Path Fusion and Efficient Non-Local Attention for Superior Receptive Fields
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；College of Electronics and Information Engineering, Shenzhen University（深圳大学电子与信息工程学院）
Jintong Hu, Siyan Chen, Zhiyi Pan, Sen Zeng, Wenming Yang
Precise segmentation of medical images is fundamental for extracting critical clinical information, which plays a pivotal role in enhancing the accuracy of diagnoses, formulating effective treatment plans, and improving patient outcomes. Although Convolutional Neural Networks (CNNs) and non-local attention methods have achieved notable success in medical image segmentation, they either struggle to capture long-range spatial dependencies due to their reliance on local features, or face significant computational and feature integration challenges when attempting to address this issue with global attention mechanisms. To overcome existing limitations in medical image segmentation, we propose a novel architecture, Perspective+ Unet. This framework is characterized by three major innovations: (i) It introduces a dual-pathway strategy at the encoder stage that combines the outcomes of traditional and dilated convolutions. This not only maintains the local receptive field but also significantly expands it, enabling better comprehension of the global structure of images while retaining detail sensitivity. (ii) The framework incorporates an efficient non-local transformer block, named ENLTB, which utilizes kernel function approximation for effective long-range dependency capture with linear computational and spatial complexity. (iii) A Spatial Cross-Scale Integrator strategy is employed to merge global dependencies and local contextual cues across model stages, meticulously refining features from various levels to harmonize global and local information. Experimental results on the ACDC and Synapse datasets demonstrate the effectiveness of our proposed Perspective+ Unet. The code is available in the supplementary material.
Isfahan University of Technology（伊斯法罕理工大学）；McMaster University（麦克马斯特大学）；Seattle University（西雅图大学）
Recently, many attempts have been made to construct a transformer base U-shaped architecture, and new methods have been proposed that outperformed CNN-based rivals. However, serious problems such as blockiness and cropped edges in predicted masks remain because of transformers' patch partitioning operations. In this work, we propose a new U-shaped architecture for medical image segmentation with the help of the newly introduced focal modulation mechanism. The proposed architecture has asymmetric depths for the encoder and decoder. Due to the ability of the focal module to aggregate local and g…
LKM-UNet: Large Kernel Vision Mamba UNet for Medical Image Segmentation
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Institute of Wenzhou, Zhejiang University（浙江大学温州研究院）；The Second Affiliated Hospital, Zhejiang University School of Medicine（浙江大学医学院附属第二医院）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Notre Dame（圣母大学）
DSVM-UNet : Enhancing VM-UNet with Dual Self-distillation for Medical Image Segmentation
Faculty of Military Health Service, Naval Medical University, China（海军医学院军事卫生服务学院）；School of Computer Science and Technology, Shanghai University of Electric Power, China（上海电力大学计算机科学与技术学院）
UNetVL: Enhancing 3D Medical Image Segmentation with Chebyshev KAN Powered Vision-LSTM
Electrical Engineering and Computer Science Department, University of Michigan, Ann Arbor, USA（密歇根大学电气工程与计算机科学系）；Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, USA（佐治亚理工学院和埃默里大学沃森·霍尔生物医学工程系）；Computer Science Department, University of Michigan, Ann Arbor, USA（密歇根大学计算机科学系）；Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology（佐治亚理工学院沃森·霍尔生物医学工程系）；Emory University, Atlanta, USA（埃默里大学）
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）
PBE-UNet: A light weight Progressive Boundary-Enhanced U-Net with Scale-Aware Aggregation for Ultrasound Image Segmentation
Department of Computer Science, Shaoxing University（绍兴大学计算机科学系）；National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Northeastern University（工业智能化与系统优化国家级前沿科学中心，东北大学）；College of Computer Science, Chongqing University（重庆大学计算机学院）；School of Computer and Computing Science, Hangzhou City University（杭州市大学计算机与计算科学学院）；ZJU-UIUC Institute, Zhejiang University（浙江大学ZJU-UIUC研究院）；Information Technology R&D Innovation Center of Peking University（北京大学信息技术研发创新中心）
Optimizing Neural Network Architecture for Medical Image Segmentation Using Monte Carlo Tree Search
Xi'an Kedagaoxin University, Faculty of Science（西安科大新大学科学学院）；Xi'an Kedagaoxin University, School of International Education（西安科大新大学国际教育学院）；Saint Petersburg State University（圣彼得堡国立大学）
Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining
Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院保罗·C·劳特伯生物医学成像研究中心）；Peng Cheng Laboratory（鹏城实验室）；University of Chinese Academy of Sciences（中国科学院大学）；The University of Hong Kong（香港大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
OSDMamba: Enhancing Oil Spill Detection from Remote Sensing Images Using Selective State Space Model
Department of Computer Science, University of Exeter（计算机科学系，埃克塞特大学）；College of Oceanography and Space Informatics, China University of Petroleum (East China)（海洋科学与空间信息学院，中国石油大学（华东））
Panoptic Segmentation and Labelling of Lumbar Spine Vertebrae using Modified Attention Unet
A. K. Choudhury School of Information Technology, University of Calcutta（加尔各答大学A. K.乔杜里信息技术学院）；Rammohan College, University of Calcutta（加尔各答大学拉莫汉学院）；Indian Statistical Institute（印度统计研究所）
本研究提出基于改进注意力 U-Net 架构和新型掩码逻辑的方法，用于 3D 腰椎 MRI 数据的椎骨全景分割与标注，实现 99.5% 的高准确率，显著推进该领域最先进技术。
School of Advanced Technology, Xi’an Jiaotong-Liverpool University（西交利物浦大学先进技术学院）；School of Electronics and Information Engineering, Beihang University（北京航空航天大学电子信息工程学院）；Cambridge University（剑桥大学）；Beijing Shijitan Hospital, Capital Medical University（首都医科大学附属北京世纪坛医院）；University of Liverpool（利物浦大学）
MBZUAI（穆罕默德·本·扎耶德人工智能大学）；Aalto University（阿尔托大学）；Weizmann Institute of Science（魏茨曼科学研究所）；University of Central Florida（中佛罗里达大学）
Accurate 3D mitochondria instance segmentation in electron microscopy (EM) is a challenging problem and serves as a prerequisite to empirically analyze their distributions and morphology. Most existing approaches employ 3D convolutions to obtain representative features. However, these convolution-based approaches struggle to effectively capture long-range dependencies in the volume mitochondria data, due to their limited local receptive field. To address this, we propose a hybrid encoder-decoder framework based on a split spatio-temporal attention module that efficiently computes spatial and t…
TTT-Unet: Enhancing U-Net with Test-Time Training Layers for Biomedical Image Segmentation
Lehigh University（里海大学）；Northeastern University（东北大学）；University of Notre Dame（圣母大学）；University of Georgia（佐治亚大学）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
SCUNet++: Swin-UNet and CNN Bottleneck Hybrid Architecture with Multi-Fusion Dense Skip Connection for Pulmonary Embolism CT Image Segmentation
Hangzhou Dianzi University（杭州电子科技大学）；Second Affiliated Hospital of the Chinese University of Hong Kong（香港中文大学第二附属医院）；Shenzhen Research Institute of Big Data（深圳市大数据研究院）
Deep Ensemble approach for Enhancing Brain Tumor Segmentation in Resource-Limited Settings
University of Ibadan（伊巴丹大学）；African Institute for Mathematical Sciences（非洲数学科学研究所）；University of Cape Town（开普敦大学）；South African National Bioinformatics Institute（南非国家生物信息学研究所）；University of Western Cape（西开普大学）；Carnegie Mellon University（卡内基梅隆大学）；McGill University（麦吉尔大学）；Lawson Health Research Institute（劳森健康研究所）；University of British Columbia（不列颠哥伦比亚大学）
SwinMamba: A hybrid local-global mamba framework for enhancing semantic segmentation of remotely sensed images
Xi'an Jiaotong-Liverpool University（西交利物浦大学）；University of Liverpool（利物浦大学）；Nanyang Technological University（南洋理工大学）；SJTUSME-COSMOPlat Joint Research Center for New Generation Industrial Intelligent Technology（上海交通大学机械与动力工程学院-卡奥斯新一代工业智能技术联合研究中心）
FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks
College of Computer Science, Sichuan University, Chengdu, China（四川大学计算机学院）；Tongji Hospital Tongji Medical College, Huazhong University of Science（华中科技大学同济医院同济医学院）；Department of Computer Science, University of Maryland, College Park, America (Work done prior to joining University of Maryland)（马里兰大学计算机系）
Fujian Agriculture and Forestry University（福建农林大学）；Digital Fujian Research Institute of Big Data for Agriculture and Forestry（数字福建农林大数据研究院）
Accurate segmentation of the blood vessels of the retina is an important step in clinical diagnosis of ophthalmic diseases. Many deep learning frameworks have come up for retinal blood vessels segmentation tasks. However, the complex vascular structure and uncertain pathological features make the blood vessel segmentation still very challenging. A novel U-shaped network named Multi-module Concatenation which is based on Atrous convolution and multi-kernel pooling is put forward to retinal vessels segmentation in this paper. The proposed network structure retains three layers the essential stru…
Purpose: The purpose of this study is to investigate the robustness of a commonly-used convolutional neural network for image segmentation with respect to visually-subtle adversarial perturbations, and suggest new methods to make these networks more robust to such perturbations. Materials and Methods: In this retrospective study, the accuracy of brain tumor segmentation was studied in subjects with low- and high-grade gliomas. A three-dimensional UNet model was implemented to segment four different MR series (T1-weighted, post-contrast T1-weighted, T2- weighted, and T2-weighted FLAIR) into fou…
Ashford and St Peter’s Hospitals NHS Foundation Trust（阿什福德和圣彼得医院 NHS 基金会信托）；University of Lincoln（林肯大学）
In this paper we propose a 2D deep residual Unet with 104 convolutional layers (DR-Unet104) for lesion segmentation in brain MRIs. We make multiple additions to the Unet architecture, including adding the 'bottleneck' residual block to the Unet encoder and adding dropout after each convolution block stack. We verified the effect of introducing the regularisation of dropout with small rate (e.g. 0.2) on the architecture, and found a dropout of 0.2 improved the overall performance compared to no dropout, or a dropout of 0.5. We evaluated the proposed architecture as part of the Multimodal Brain …
Huazhong University of Science and Technology（华中科技大学）；Shenzhen University（深圳大学）
Deep convolutional neural network (CNN) achieves remarkable performance for medical image analysis. UNet is the primary source in the performance of 3D CNN architectures for medical imaging tasks, including brain tumor segmentation. The skip connection in the UNet architecture concatenates features from both encoder and decoder paths to extract multi-contextual information from image data. The multi-scaled features play an essential role in brain tumor segmentation. However, the limited use of features can degrade the performance of the UNet approach for segmentation. In this paper, we propose…
EAGLE: An Efficient Global Attention Lesion Segmentation Model for Hepatic Echinococcosis
School of Computer Technology and Application, Qinghai University（青海大学计算机技术与应用学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Intelligent Computing and Application Laboratory of Qinghai Province, Qinghai University（青海省智能计算与应用实验室）；School of Chemical Engineering, Qinghai University（青海大学化学工程学院）；Department of General Surgery, Affiliated Hospital of Qinghai University（青海大学附属医院普外科）；Department of Medical Engineering Integration and Translational Application, Affiliated Hospital of Qinghai University（青海大学附属医院医学工程整合与转化应用系）
Otto von Guericke University Magdeburg（马格德堡奥托-冯-格里克大学）；Faculty of Computer Science, Otto von Guericke University Magdeburg（马格德堡奥托-冯-格里克大学计算机学院）；Data and Knowledge Engineering Group, Otto von Guericke University Magdeburg（马格德堡奥托-冯-格里克大学数据与知识工程组）；Biomedical Magnetic Resonance, Otto von Guericke University Magdeburg（马格德堡奥托-冯-格里克大学生物医学磁共振研究所）；Research Campus STIMULATE, Otto von Guericke University Magdeburg（马格德堡奥托-冯-格里克大学STIMULATE研究园区）；Institute for Medical Engineering, Otto von Guericke University Magdeburg（马格德堡奥托-冯-格里克大学医学工程研究所）；Center for Behavioral Brain Sciences, Magdeburg（马格德堡行为脑科学中心）；Magdeburg（马格德堡（注：单独“Magdeburg”为城市名，非机构名，根据要求未提取））
Magnetic resonance imaging (MRI) provides high spatial resolution and excellent soft-tissue contrast without using harmful ionising radiation. Dynamic MRI is an essential tool for interventions to visualise movements or changes of the target organ. However, such MRI acquisition with high temporal resolution suffers from limited spatial resolution - also known as the spatio-temporal trade-off of dynamic MRI. Several approaches, including deep learning based super-resolution approaches, have been proposed to mitigate this trade-off. Nevertheless, such an approach typically aims to super-resolve …
The University of Hong Kong（香港大学）；The University of Hong Kong-Shenzhen Hospital（香港大学深圳医院）
In this work, we propose a new segmentation network by integrating DenseUNet and bidirectional LSTM together with attention mechanism, termed as DA-BDense-UNet. DenseUNet allows learning enough diverse features and enhancing the representative power of networks by regulating the information flow. Bidirectional LSTM is responsible to explore the relationships between the encoded features and the up-sampled features in the encoding and decoding paths. Meanwhile, we introduce attention gates (AG) into DenseUNet to diminish responses of unrelated background regions and magnify responses of salient…
Leiden University Medical Center（莱顿大学医学中心）；Sharif University of Technology（谢里夫理工大学）；Netherlands Cancer Institute（荷兰癌症研究所）；Delft University of Technology（代尔夫特理工大学）
Manual or automatic delineation of the esophageal tumor in CT images is known to be very challenging. This is due to the low contrast between the tumor and adjacent tissues, the anatomical variation of the esophagus, as well as the occasional presence of foreign bodies (e.g. feeding tubes). Physicians therefore usually exploit additional knowledge such as endoscopic findings, clinical history, additional imaging modalities like PET scans. Achieving his additional information is time-consuming, while the results are error-prone and might lead to non-deterministic results. In this paper we aim t…
Shenzhen University（深圳大学）；Huazhong University of Science and Technology（华中科技大学）
The brain tumor segmentation task aims to classify tissue into the whole tumor (WT), tumor core (TC), and enhancing tumor (ET) classes using multimodel MRI images. Quantitative analysis of brain tumors is critical for clinical decision making. While manual segmentation is tedious, time-consuming, and subjective, this task is at the same time very challenging to automatic segmentation methods. Thanks to the powerful learning ability, convolutional neural networks (CNNs), mainly fully convolutional networks, have shown promising brain tumor segmentation. This paper further boosts the performance…
Topo-VM-UNetV2: Encoding Topology into Vision Mamba UNet for Polyp Segmentation
Department of Computer Science, University of Texas Rio Grande Valley（德克萨斯理工大学里奥格兰德分校计算机科学系）；Department of Mathematical Sciences, The University of Texas at Dallas（德克萨斯大学达拉斯分校数学科学系）
Microsoft Research（微软研究院）；Carnegie Mellon University（卡内基梅隆大学）；University of California, San Diego（加州大学圣地亚哥分校）；Imperial College London（帝国理工学院）
We propose the autofocus convolutional layer for semantic segmentation with the objective of enhancing the capabilities of neural networks for multi-scale processing. Autofocus layers adaptively change the size of the effective receptive field based on the processed context to generate more powerful features. This is achieved by parallelising multiple convolutional layers with different dilation rates, combined by an attention mechanism that learns to focus on the optimal scales driven by context. By sharing the weights of the parallel convolutions we make the network scale-invariant, with onl…
Convolutional neural networks (CNNs) have achieved remarkable success in automatically segmenting organs or lesions on 3D medical images. Recently, vision transformer networks have exhibited exceptional performance in 2D image classification tasks. Compared with CNNs, transformer networks have an appealing advantage of extracting long-range features due to their self-attention algorithm. Therefore, we propose a CNN-Transformer combined model, called BiTr-Unet, with specific modifications for brain tumor segmentation on multi-modal MRI scans. Our BiTr-Unet achieves good performance on the BraTS…
