1
|
Jiang Q, Ye H, Yang B, Cao F. Label-Decoupled Medical Image Segmentation With Spatial-Channel Graph Convolution and Dual Attention Enhancement. IEEE J Biomed Health Inform 2024; 28:2830-2841. [PMID: 38376972 DOI: 10.1109/jbhi.2024.3367756] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/22/2024]
Abstract
Deep learning-based methods have been widely used in medical image segmentation recently. However, existing works are usually difficult to simultaneously capture global long-range information from images and topological correlations among feature maps. Further, medical images often suffer from blurred target edges. Accordingly, this paper proposes a novel medical image segmentation framework named a label-decoupled network with spatial-channel graph convolution and dual attention enhancement mechanism (LADENet for short). It constructs learnable adjacency matrices and utilizes graph convolutions to effectively capture global long-range information on spatial locations and topological dependencies between different channels in an image. Then a label-decoupled strategy based on distance transformation is introduced to decouple an original segmentation label into a body label and an edge label for supervising the body branch and edge branch. Again, a dual attention enhancement mechanism, designing a body attention block in the body branch and an edge attention block in the edge branch, is built to promote the learning ability of spatial region and boundary features. Besides, a feature interactor is devised to fully consider the information interaction between the body and edge branches to improve segmentation performance. Experiments on benchmark datasets reveal the superiority of LADENet compared to state-of-the-art approaches.
Collapse
|
2
|
Dong C, Du G. An enhanced real-time human pose estimation method based on modified YOLOv8 framework. Sci Rep 2024; 14:8012. [PMID: 38580704 PMCID: PMC10997650 DOI: 10.1038/s41598-024-58146-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2024] [Accepted: 03/26/2024] [Indexed: 04/07/2024] Open
Abstract
The objective of human pose estimation (HPE) derived from deep learning aims to accurately estimate and predict the human body posture in images or videos via the utilization of deep neural networks. However, the accuracy of real-time HPE tasks is still to be improved due to factors such as partial occlusion of body parts and limited receptive field of the model. To alleviate the accuracy loss caused by these issues, this paper proposes a real-time HPE model called CCAM - Person based on the YOLOv8 framework. Specifically, we have improved the backbone and neck of the YOLOv8x-pose real-time HPE model to alleviate the feature loss and receptive field constraints. Secondly, we introduce the context coordinate attention module (CCAM) to augment the model's focus on salient features, reduce background noise interference, alleviate key point regression failure caused by limb occlusion, and improve the accuracy of pose estimation. Our approach attains competitive results on multiple metrics of two open-source datasets, MS COCO 2017 and CrowdPose. Compared with the baseline model YOLOv8x-pose, CCAM-Person improves the average precision by 2.8% and 3.5% on the two datasets, respectively.
Collapse
Affiliation(s)
- Chengang Dong
- Nanjing University of Aeronautics and Astronautics, Nanjing, 210000, Jiangsu, China
| | - Guodong Du
- Nanjing University of Aeronautics and Astronautics, Nanjing, 210000, Jiangsu, China.
| |
Collapse
|
3
|
Klein T, Gladytz T, Millward JM, Cantow K, Hummel L, Seeliger E, Waiczies S, Lippert C, Niendorf T. Dynamic parametric MRI and deep learning: Unveiling renal pathophysiology through accurate kidney size quantification. NMR IN BIOMEDICINE 2024; 37:e5075. [PMID: 38043545 DOI: 10.1002/nbm.5075] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/17/2023] [Revised: 09/22/2023] [Accepted: 10/19/2023] [Indexed: 12/05/2023]
Abstract
Renal pathologies often manifest as alterations in kidney size, providing a valuable avenue for employing dynamic parametric MRI as a means to derive kidney size measurements for the diagnosis, treatment, and monitoring of renal disease. Furthermore, this approach holds significant potential in supporting MRI data-driven preclinical investigations into the intricate mechanisms underlying renal pathophysiology. The integration of deep learning algorithms is crucial in achieving rapid and precise segmentation of the kidney from temporally resolved parametric MRI, facilitating the use of kidney size as a meaningful (pre)clinical biomarker for renal disease. To explore this potential, we employed dynamic parametric T2 mapping of the kidney in rats in conjunction with a custom-tailored deep dilated U-Net (DDU-Net) architecture. The architecture was trained, validated, and tested on manually segmented ground truth kidney data, with benchmarking against an analytical segmentation model and a self-configuring no new U-Net. Subsequently, we applied our approach to in vivo longitudinal MRI data, incorporating interventions that emulate clinically relevant scenarios in rats. Our approach achieved high performance metrics, including a Dice coefficient of 0.98, coefficient of determination of 0.92, and a mean absolute percentage error of 1.1% compared with ground truth. The DDU-Net enabled automated and accurate quantification of acute changes in kidney size, such as aortic occlusion (-8% ± 1%), venous occlusion (5% ± 1%), furosemide administration (2% ± 1%), hypoxemia (-2% ± 1%), and contrast agent-induced acute kidney injury (11% ± 1%). This approach can potentially be instrumental for the development of dynamic parametric MRI-based tools for kidney disorders, offering unparalleled insights into renal pathophysiology.
Collapse
Affiliation(s)
- Tobias Klein
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
- Digital Health - Machine Learning Research Group, Hasso Plattner Institute for Digital Engineering, University of Potsdam, Potsdam, Germany
| | - Thomas Gladytz
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
| | - Jason M Millward
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
| | - Kathleen Cantow
- Institute of Translational Physiology, Charité - Universitätsmedizin, Berlin, Germany
| | - Luis Hummel
- Institute of Translational Physiology, Charité - Universitätsmedizin, Berlin, Germany
| | - Erdmann Seeliger
- Institute of Translational Physiology, Charité - Universitätsmedizin, Berlin, Germany
| | - Sonia Waiczies
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
| | - Christoph Lippert
- Digital Health - Machine Learning Research Group, Hasso Plattner Institute for Digital Engineering, University of Potsdam, Potsdam, Germany
- Hasso Plattner Institute for Digital Health, Icahn School of Medicine at Mount Sinai, New York City, New York, USA
| | - Thoralf Niendorf
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
- Experimental and Clinical Research Center, a joint cooperation between the Charité Medical Faculty and the Max Delbrück Center for Molecular Medicine, Berlin, Germany
| |
Collapse
|
4
|
Luan S, Ou-Yang J, Yang X, Wei W, Xue X, Zhu B. A multi-modal vision-language pipeline strategy for contour quality assurance and adaptive optimization. Phys Med Biol 2024; 69:065005. [PMID: 38373347 DOI: 10.1088/1361-6560/ad2a97] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2023] [Accepted: 02/19/2024] [Indexed: 02/21/2024]
Abstract
Objective.Accurate delineation of organs-at-risk (OARs) is a critical step in radiotherapy. The deep learning generated segmentations usually need to be reviewed and corrected by oncologists manually, which is time-consuming and operator-dependent. Therefore, an automated quality assurance (QA) and adaptive optimization correction strategy was proposed to identify and optimize 'incorrect' auto-segmentations.Approach.A total of 586 CT images and labels from nine institutions were used. The OARs included the brainstem, parotid, and mandible. The deep learning generated contours were compared with the manual ground truth delineations. In this study, we proposed a novel contour quality assurance and adaptive optimization (CQA-AO) strategy, which consists of the following three main components: (1) the contour QA module classified the deep learning generated contours as either accepted or unaccepted; (2) the unacceptable contour categories analysis module provided the potential error reasons (five unacceptable category) and locations (attention heatmaps); (3) the adaptive correction of unacceptable contours module integrate vision-language representations and utilize convex optimization algorithms to achieve adaptive correction of 'incorrect' contours.Main results. In the contour QA tasks, the sensitivity (accuracy, precision) of CQA-AO strategy reached 0.940 (0.945, 0.948), 0.962 (0.937, 0.913), and 0.967 (0.962, 0.957) for brainstem, parotid and mandible, respectively. The unacceptable contour category analysis, the(FI,AccI,Fmicro,Fmacro)of CQA-AO strategy reached (0.901, 0.763, 0.862, 0.822), (0.855, 0.737, 0.837, 0.784), and (0.907, 0.762, 0.858, 0.821) for brainstem, parotid and mandible, respectively. After adaptive optimization correction, the DSC values of brainstem, parotid and mandible have been improved by 9.4%, 25.9%, and 13.5%, and Hausdorff distance values decreased by 62%, 70.6%, and 81.6%, respectively.Significance. The proposed CQA-AO strategy, which combines QA of contour and adaptive optimization correction for OARs contouring, demonstrated superior performance compare to conventional methods. This method can be implemented in the clinical contouring procedures and improve the efficiency of delineating and reviewing workflow.
Collapse
Affiliation(s)
- Shunyao Luan
- School of Integrated Circuits, Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, People's Republic of China
| | - Jun Ou-Yang
- School of Integrated Circuits, Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, People's Republic of China
| | - Xiaofei Yang
- School of Integrated Circuits, Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, People's Republic of China
| | - Wei Wei
- Department of Radiation Oncology, Hubei Cancer Hospital, TongJi Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, People's Republic of China
| | - Xudong Xue
- Department of Radiation Oncology, Hubei Cancer Hospital, TongJi Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, People's Republic of China
| | - Benpeng Zhu
- School of Integrated Circuits, Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, People's Republic of China
| |
Collapse
|
5
|
Wang W, Pan B, Ai Y, Li G, Fu Y, Liu Y. ParaCM-PNet: A CNN-tokenized MLP combined parallel dual pyramid network for prostate and prostate cancer segmentation in MRI. Comput Biol Med 2024; 170:107999. [PMID: 38244470 DOI: 10.1016/j.compbiomed.2024.107999] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2023] [Revised: 12/28/2023] [Accepted: 01/13/2024] [Indexed: 01/22/2024]
Abstract
The precise prostate gland and prostate cancer (PCa) segmentations enable the fusion of magnetic resonance imaging (MRI) and ultrasound imaging (US) to guide robotic prostate biopsy systems. This precise segmentation, applied to preoperative MRI images, is crucial for accurate image registration and automatic localization of the biopsy target. Nevertheless, describing local prostate lesions in MRI remains a challenging and time-consuming task, even for experienced physicians. Therefore, this research work develops a parallel dual-pyramid network that combines convolutional neural networks (CNN) and tokenized multi-layer perceptron (MLP) for automatic segmentation of the prostate gland and clinically significant PCa (csPCa) in MRI. The proposed network consists of two stages. The first stage focuses on prostate segmentation, while the second stage uses a prior partition from a previous stage to detect the cancerous regions. Both stages share a similar network architecture, combining CNN and tokenized MLP as the feature extraction backbone to creating a pyramid-structured network for feature encoding and decoding. By employing CNN layers of different scales, the network generates scale-aware local semantic features, which are integrated into feature maps and inputted into an MLP layer from a global perspective. This facilitates the complementarity between local and global information, capturing richer semantic features. Additionally, the network incorporates an interactive hybrid attention module to enhance the perception of the target area. Experimental results demonstrate the superiority of the proposed network over other state-of-the-art image segmentation methods for segmenting the prostate gland and csPCa tissue in MRI images.
Collapse
Affiliation(s)
- Weirong Wang
- State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, 150001, China
| | - Bo Pan
- State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, 150001, China
| | - Yue Ai
- Hangzhou Wiseking Medical Robot Co., Ltd, Hangzhou, 310000, China
| | - Gonghui Li
- Department of Urology, Sir Run Run Shaw Hospital, Medicine School of Zhejiang University, Hangzhou, 310000, China
| | - Yili Fu
- State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, 150001, China.
| | - Yanjie Liu
- State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, 150001, China
| |
Collapse
|
6
|
Lin Y, Wang J, Liu Q, Zhang K, Liu M, Wang Y. CFANet: Context fusing attentional network for preoperative CT image segmentation in robotic surgery. Comput Biol Med 2024; 171:108115. [PMID: 38402837 DOI: 10.1016/j.compbiomed.2024.108115] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Revised: 01/30/2024] [Accepted: 02/04/2024] [Indexed: 02/27/2024]
Abstract
Accurate segmentation of CT images is crucial for clinical diagnosis and preoperative evaluation of robotic surgery, but challenges arise from fuzzy boundaries and small-sized targets. In response, a novel 2D segmentation network named Context Fusing Attentional Network (CFANet) is proposed. CFANet incorporates three key modules to address these challenges, namely pyramid fusing module (PFM), parallel dilated convolution module (PDCM) and scale attention module (SAM). Integration of these modules into the encoder-decoder structure enables effective utilization of multi-level and multi-scale features. Compared with advanced segmentation method, the Dice score improved by 2.14% on the dataset of liver tumor. This improvement is expected to have a positive impact on the preoperative evaluation of robotic surgery and to support clinical diagnosis, especially in early tumor detection.
Collapse
Affiliation(s)
- Yao Lin
- College of Electrical and Information Engineering, Hunan University, Changsha, 410082, China; National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, 410082, China
| | - Jiazheng Wang
- College of Electrical and Information Engineering, Hunan University, Changsha, 410082, China; National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, 410082, China.
| | - Qinghao Liu
- College of Electrical and Information Engineering, Hunan University, Changsha, 410082, China; National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, 410082, China
| | - Kang Zhang
- College of Electrical and Information Engineering, Hunan University, Changsha, 410082, China; National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, 410082, China
| | - Min Liu
- College of Electrical and Information Engineering, Hunan University, Changsha, 410082, China; National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, 410082, China; Research Institute of Hunan University in Chongqing, Chongqing, 401135, China.
| | - Yaonan Wang
- College of Electrical and Information Engineering, Hunan University, Changsha, 410082, China; National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, 410082, China
| |
Collapse
|
7
|
Jiang X, Zheng H, Yuan Z, Lan K, Wu Y. HIMS-Net: Horizontal-vertical interaction and multiple side-outputs network for cyst segmentation in jaw images. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2024; 21:4036-4055. [PMID: 38549317 DOI: 10.3934/mbe.2024178] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/02/2024]
Abstract
Jaw cysts are mainly caused by abnormal tooth development, chronic oral inflammation, or jaw damage, which may lead to facial swelling, deformity, tooth loss, and other symptoms. Due to the diversity and complexity of cyst images, deep-learning algorithms still face many difficulties and challenges. In response to these problems, we present a horizontal-vertical interaction and multiple side-outputs network for cyst segmentation in jaw images. First, the horizontal-vertical interaction mechanism facilitates complex communication paths in the vertical and horizontal dimensions, and it has the ability to capture a wide range of context dependencies. Second, the feature-fused unit is introduced to adjust the network's receptive field, which enhances the ability of acquiring multi-scale context information. Third, the multiple side-outputs strategy intelligently combines feature maps to generate more accurate and detailed change maps. Finally, experiments were carried out on the self-established jaw cyst dataset and compared with different specialist physicians to evaluate its clinical usability. The research results indicate that the Matthews correlation coefficient (Mcc), Dice, and Jaccard of HIMS-Net were 93.61, 93.66 and 88.10% respectively, which may contribute to rapid and accurate diagnosis in clinical practice.
Collapse
Affiliation(s)
- Xiaoliang Jiang
- College of Mechanical Engineering, Quzhou University, Quzhou 324000, China
| | - Huixia Zheng
- Department of Stomatology, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People's Hospital, Quzhou 324000, China
| | - Zhenfei Yuan
- Department of Stomatology, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People's Hospital, Quzhou 324000, China
| | - Kun Lan
- College of Mechanical Engineering, Quzhou University, Quzhou 324000, China
| | - Yaoyang Wu
- Department of Computer and Information Science, University of Macau, Macau 999078, China
| |
Collapse
|
8
|
Charoenkwan P, Chumnanpuen P, Schaduangrat N, Shoombuatong W. Accelerating the identification of the allergenic potential of plant proteins using a stacked ensemble-learning framework. J Biomol Struct Dyn 2024:1-13. [PMID: 38385478 DOI: 10.1080/07391102.2024.2318482] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2023] [Accepted: 02/08/2024] [Indexed: 02/23/2024]
Abstract
Plant-allergenic proteins (PAPs) have the potential to induce allergic reactions in certain individuals. While these proteins are generally innocuous for the majority of people, they can elicit an immune response in those with particular sensitivities. Thus, screening and prioritizing the allergenic potential of plant proteins is indispensable for the development of diagnostic tools, therapeutic interventions or medications to treat allergic reactions. However, investigating the allergenic potential of plant proteins based on experimental methods is costly and labour-intensive. Therefore, we develop StackPAP, a three-layer stacking ensemble framework for accurate large-scale identification of PAPs. In StackPAP, at the first layer, we conducted a comprehensive analysis of an extensive set of feature descriptors. Subsequently, we selected and fused five potential sequence-based feature descriptors, including amphiphilic pseudo-amino acid composition, dipeptide deviation from expected mean, amino acid composition, pseudo amino acid composition and dipeptide composition. Additionally, we applied an efficient genetic algorithm (GA-SAR) to determine informative feature sets. In the second layer, 12 powerful machine learning (ML) methods, in combination with all the informative feature sets, were employed to construct a pool of base classifiers. Finally, 13 potential base classifiers were selected using the GA-SAR method and combined to develop the final meta-classifier. Our experimental results revealed the promising prediction performance of StackPAP, with an accuracy, Matthew's correlation coefficient and AUC of 0.984, 0.969 and 0.993, respectively, as judged by the independent test dataset. In conclusion, both cross-validation and independent test results indicated the superior performance of StackPAP compared with several ML-based classifiers. To accelerate the identification of the allergenicity of plant proteins, we developed a user-friendly web server for StackPAP (https://pmlabqsar.pythonanywhere.com/StackPAP). We anticipate that StackPAP will be an efficient and useful tool for rapidly screening PAPs from a vast number of plant proteins.Communicated by Ramaswamy H. Sarma.
Collapse
Affiliation(s)
- Phasit Charoenkwan
- Modern Management and Information Technology, College of Arts, Media and Technology, Chiang Mai University, Thailand
| | - Pramote Chumnanpuen
- Department of Zoology, Faculty of Science, Kasetsart University, Bangkok, Thailand
- Omics Center for Agriculture, Bioresources, Food, and Health, Kasetsart University (OmiKU), Bangkok, Thailand
| | - Nalini Schaduangrat
- Center for Research Innovation and Biomedical Informatics, Faculty of Medical Technology, Mahidol University, Bangkok, Thailand
| | - Watshara Shoombuatong
- Center for Research Innovation and Biomedical Informatics, Faculty of Medical Technology, Mahidol University, Bangkok, Thailand
| |
Collapse
|
9
|
Chen Y, Yang W, Lu J, Sun J, Rao L, Zhao H, Peng X, Ni D. A modified U-net with graph representation for dose prediction in esophageal cancer radiotherapy plans. Comput Med Imaging Graph 2024; 111:102318. [PMID: 38088017 DOI: 10.1016/j.compmedimag.2023.102318] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2023] [Revised: 11/29/2023] [Accepted: 11/30/2023] [Indexed: 01/08/2024]
Abstract
The manual design of esophageal cancer radiotherapy plan is time-consuming and labor-intensive. Automatic planning (AP) is prevalent nowadays to increase physicists' work efficiency. Because of the intuitiveness of dose distribution in AP evaluation, obtaining reasonable dose prediction provides effective guarantees to generate a satisfactory AP. Existing fully convolutional network-based methods for predicting dose distribution in esophageal cancer radiotherapy plans often capture features in a limited receptive field. Additionally, the correlations between voxel pairs are often ignored. This work modifies the U-net architecture and exploits graph convolution to capture long-range information for dose prediction in esophageal cancer plans. Meanwhile, attention mechanism gets correlations between planning target volume (PTV) and organs at risk, and adaptively learns their feature weights. Finally, a novel loss function that considers features between voxel pairs is used to highlight the predictions. 152 subjects with prescription doses of 50 Gy or 60 Gy are collected in this study. The mean absolute error and standard deviation of conformity index, homogeneity index, and max dose for PTV achieved by the proposed method are 0.036 ± 0.030, 0.036 ± 0.027, and 0.930 ± 1.162, respectively, which outperform other state-of-the-art models. The superior performance demonstrates that our proposed method has great potential for AP generation.
Collapse
Affiliation(s)
- Yanlin Chen
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China; Medical UltraSound Image Computing (MUSIC) Lab, Shenzhen University, Shenzhen, China
| | - Wei Yang
- School of Biomedical Engineering, Southern Medical University, Guangzhou, China
| | - Jiayang Lu
- Department of Radiation Oncology, Cancer Hospital of Shantou University Medical College, Shantou, China
| | - Jinyan Sun
- School of Medicine, Foshan University, Foshan, China
| | - Linshang Rao
- Shenzhen Mindray Bio-Medical Electronics Co., Ltd., Shenzhen, China
| | - Huanmiao Zhao
- School of Biomedical Engineering, Southern Medical University, Guangzhou, China
| | - Xun Peng
- Department of Radiation Oncology, Cancer Hospital of Shantou University Medical College, Shantou, China.
| | - Dong Ni
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China; Medical UltraSound Image Computing (MUSIC) Lab, Shenzhen University, Shenzhen, China.
| |
Collapse
|
10
|
Zi-An Z, Xiu-Fang F, Xiao-Qiang R, Yun-Yun D. Uncertainty-guided cross learning via CNN and transformer for semi-supervised honeycomb lung lesion segmentation. Phys Med Biol 2023; 68:245010. [PMID: 37988756 DOI: 10.1088/1361-6560/ad0eb2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2023] [Accepted: 11/21/2023] [Indexed: 11/23/2023]
Abstract
Objective. Deep learning networks such as convolutional neural networks (CNN) and Transformer have shown excellent performance on the task of medical image segmentation, however, the usual problem with medical images is the lack of large-scale, high-quality pixel-level annotations, which is a very time-consuming and laborious task, and its further leads to compromised the performance of medical image segmentation under limited annotation conditions.Approach. In this paper, we propose a new semi-supervised learning method, uncertainty-guided cross learning, which uses a limited number of annotated samples along with a large number of unlabeled images to train the network. Specifically, we use two networks with different learning paradigms, CNN and Transformer, for cross learning, and use the prediction of one of them as a pseudo label to supervise the other, so that they can learn from each other, fully extract the local and global features of the images, and combine explicit and implicit consistency regularization constraints with pseudo label methods. On the other hand, we use epistemic uncertainty as a guiding message to encourage the model to learn high-certainty pixel information in high-confidence regions, and minimize the impact of erroneous pseudo labels on the overall learning process to improve the performance of semi-supervised segmentation methods.Main results. We conducted honeycomb lung lesion segmentation experiments using a honeycomb lung CT image dataset, and designed several sets of comparison experiments and ablation experiments to validate the effectiveness of our method. The final experimental results show that the Dice coefficient of our proposed method reaches 88.49% on the test set, and our method achieves state-of-the-art performance in honeycomb lung lesion segmentation compared to other semi-supervised learning methods.Significance. Our proposed method can effectively improve the accuracy of segmentation of honeycomb lung lesions, which provides an important reference for physicians in the diagnosis and treatment of this disease.
Collapse
Affiliation(s)
- Zhao Zi-An
- College of Software, Taiyuan University of Technology, Jinzhong 030600, People's Republic of China
| | - Feng Xiu-Fang
- College of Software, Taiyuan University of Technology, Jinzhong 030600, People's Republic of China
| | - Ren Xiao-Qiang
- Shanxi Provincial People's Hospital, Taiyuan 030012, People's Republic of China
| | - Dong Yun-Yun
- College of Software, Taiyuan University of Technology, Jinzhong 030600, People's Republic of China
| |
Collapse
|
11
|
Chen H, Deng Y, Li B, Li Z, Chen H, Jing B, Li C. BézierSeg: Parametric Shape Representation for Fast Object Segmentation in Medical Images. Life (Basel) 2023; 13:life13030743. [PMID: 36983898 PMCID: PMC10052690 DOI: 10.3390/life13030743] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2023] [Revised: 02/17/2023] [Accepted: 02/19/2023] [Indexed: 03/12/2023] Open
Abstract
Background: Delineating the lesion area is an important task in image-based diagnosis. Pixel-wise classification is a popular approach to segmenting the region of interest. However, at fuzzy boundaries, such methods usually result in glitches, discontinuity or disconnection, inconsistent with the fact that lesions are solid and smooth. Methods: To overcome these problems and to provide an efficient, accurate, robust and concise solution that simplifies the whole segmentation pipeline in AI-assisted applications, we propose the BézierSeg model which outputs Bézier curves encompassing the region of interest. Results: Directly modeling the contour with analytic equations ensures that the segmentation is connected and continuous, and that the boundary is smooth. In addition, it offers sub-pixel accuracy. Without loss of precision, the Bézier contour can be resampled and overlaid with images of any resolution. Moreover, clinicians can conveniently adjust the curve’s control points to refine the result. Conclusions: Our experiments show that the proposed method runs in real time and achieves accuracy competitive with pixel-wise segmentation models.
Collapse
Affiliation(s)
- Haichou Chen
- Collaborative Innovation Center for Cancer Medicine, State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
- Department of Information, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Yishu Deng
- Collaborative Innovation Center for Cancer Medicine, State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
- Department of Information, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
- School of Electronics and Information Technology (School of Microelectronics), Sun Yat-sen University, Guangzhou 510275, China
| | - Bin Li
- Collaborative Innovation Center for Cancer Medicine, State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
- Department of Information, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Zeqin Li
- Collaborative Innovation Center for Cancer Medicine, State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
- Department of Information, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Haohua Chen
- Collaborative Innovation Center for Cancer Medicine, State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
- Department of Information, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Bingzhong Jing
- Collaborative Innovation Center for Cancer Medicine, State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
- Department of Information, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
- Correspondence: (B.J.); (C.L.)
| | - Chaofeng Li
- Collaborative Innovation Center for Cancer Medicine, State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
- Department of Information, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
- Correspondence: (B.J.); (C.L.)
| |
Collapse
|
12
|
Zhang Z, Jiang Y, Qiao H, Wang M, Yan W, Chen J. SIL-Net: A Semi-Isotropic L-shaped network for dermoscopic image segmentation. Comput Biol Med 2022; 150:106146. [PMID: 36228460 DOI: 10.1016/j.compbiomed.2022.106146] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2022] [Revised: 09/13/2022] [Accepted: 09/24/2022] [Indexed: 11/28/2022]
Abstract
BACKGROUND Dermoscopic image segmentation using deep learning algorithms is a critical technology for skin cancer detection and therapy. Specifically, this technology is a spatially equivariant task and relies heavily on Convolutional Neural Networks (CNNs), which lost more effective features during cascading down-sampling or up-sampling. Recently, vision isotropic architecture has emerged to eliminate cascade procedures in CNNs as well as demonstrates superior performance. Nevertheless, it cannot be used for the segmentation task directly. Based on these discoveries, this research intends to explore an efficient architecture which not only preserves the advantages of the isotropic architecture but is also suitable for clinical dermoscopic diagnosis. METHODS In this work, we introduce a novel Semi-Isotropic L-shaped network (SIL-Net) for dermoscopic image segmentation. First, we propose a Patch Embedding Weak Correlation (PEWC) module to address the issue of no interaction between adjacent patches during the standard Patch Embedding process. Second, a plug-and-play and zero-parameter Residual Spatial Mirror Information (RSMI) path is proposed to supplement effective features during up-sampling and optimize the lesion boundaries. Third, to further reconstruct deep features and get refined lesion regions, a Depth Separable Transpose Convolution (DSTC) based up-sampling module is designed. RESULTS The proposed architecture obtains state-of-the-art performance on dermoscopy benchmark datasets ISIC-2017, ISIC-2018 and PH2. Respectively, the Dice coefficient (DICE) of above datasets achieves 89.63%, 93.47%, and 95.11%, where the Mean Intersection over Union (MIoU) are 82.02%, 88.21%, and 90.81%. Furthermore, the robustness and generalizability of our method has been demonstrated through additional experiments on standard intestinal polyp datasets (CVC-ClinicDB and Kvasir-SEG). CONCLUSION Our findings demonstrate that SIL-Net not only has great potential for precise segmentation of the lesion region but also exhibits stronger generalizability and robustness, indicating that it meets the requirements for clinical diagnosis. Notably, our method shows state-of-the-art performance on all five datasets, which highlights the effectiveness of the semi-isotropic design mechanism.
Collapse
Affiliation(s)
- Zequn Zhang
- College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China.
| | - Yun Jiang
- College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China.
| | - Hao Qiao
- College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China.
| | - Meiqi Wang
- College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China.
| | - Wei Yan
- College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China.
| | - Jie Chen
- College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China.
| |
Collapse
|