1
|
Wang KN, Zhuang S, Ran QY, Zhou P, Hua J, Zhou GQ, He X. DLGNet: A dual-branch lesion-aware network with the supervised Gaussian Mixture model for colon lesions classification in colonoscopy images. Med Image Anal 2023; 87:102832. [PMID: 37148864 DOI: 10.1016/j.media.2023.102832] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/16/2022] [Revised: 01/20/2023] [Accepted: 04/20/2023] [Indexed: 05/08/2023]
Abstract
Colorectal cancer is one of the malignant tumors with the highest mortality due to the lack of obvious early symptoms. It is usually in the advanced stage when it is discovered. Thus the automatic and accurate classification of early colon lesions is of great significance for clinically estimating the status of colon lesions and formulating appropriate diagnostic programs. However, it is challenging to classify full-stage colon lesions due to the large inter-class similarities and intra-class differences of the images. In this work, we propose a novel dual-branch lesion-aware neural network (DLGNet) to classify intestinal lesions by exploring the intrinsic relationship between diseases, composed of four modules: lesion location module, dual-branch classification module, attention guidance module, and inter-class Gaussian loss function. Specifically, the elaborate dual-branch module integrates the original image and the lesion patch obtained by the lesion localization module to explore and interact with lesion-specific features from a global and local perspective. Also, the feature-guided module guides the model to pay attention to the disease-specific features by learning remote dependencies through spatial and channel attention after network feature learning. Finally, the inter-class Gaussian loss function is proposed, which assumes that each feature extracted by the network is an independent Gaussian distribution, and the inter-class clustering is more compact, thereby improving the discriminative ability of the network. The extensive experiments on the collected 2568 colonoscopy images have an average accuracy of 91.50%, and the proposed method surpasses the state-of-the-art methods. This study is the first time that colon lesions are classified at each stage and achieves promising colon disease classification performance. To motivate the community, we have made our code publicly available via https://github.com/soleilssss/DLGNet.
Collapse
Affiliation(s)
- Kai-Ni Wang
- School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; State Key Laboratory of Digital Medical Engineering, Southeast University, Nanjing, China; Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University, Nanjing, China
| | - Shuaishuai Zhuang
- The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Qi-Yong Ran
- School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; State Key Laboratory of Digital Medical Engineering, Southeast University, Nanjing, China; Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University, Nanjing, China
| | - Ping Zhou
- School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; State Key Laboratory of Digital Medical Engineering, Southeast University, Nanjing, China; Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University, Nanjing, China
| | - Jie Hua
- The First Affiliated Hospital of Nanjing Medical University, Nanjing, China; Liyang People's Hospital, Liyang Branch Hospital of Jiangsu Province Hospital, Liyang, China
| | - Guang-Quan Zhou
- School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; State Key Laboratory of Digital Medical Engineering, Southeast University, Nanjing, China; Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University, Nanjing, China.
| | - Xiaopu He
- The First Affiliated Hospital of Nanjing Medical University, Nanjing, China.
| |
Collapse
|
2
|
Ran QY, Miao J, Zhou SP, Hua SH, He SY, Zhou P, Wang HX, Zheng YP, Zhou GQ. Automatic 3-D spine curve measurement in freehand ultrasound via structure-aware reinforcement learning spinous process localization. Ultrasonics 2023; 132:107012. [PMID: 37071944 DOI: 10.1016/j.ultras.2023.107012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/23/2022] [Revised: 03/18/2023] [Accepted: 04/10/2023] [Indexed: 05/03/2023]
Abstract
Freehand 3-D ultrasound systems have been advanced in scoliosis assessment to avoid radiation hazards, especially for teenagers. This novel 3-D imaging method also makes it possible to evaluate the spine curvature automatically from the corresponding 3-D projection images. However, most approaches neglect the three-dimensional spine deformity by only using the rendering images, thus limiting their usage in clinical applications. In this study, we proposed a structure-aware localization model to directly identify the spinous processes for automatic 3-D spine curve measurement using the images acquired with freehand 3-D ultrasound imaging. The pivot is to leverage a novel reinforcement learning (RL) framework to localize the landmarks, which adopts a multi-scale agent to boost structure representation with positional information. We also introduced a structure similarity prediction mechanism to perceive the targets with apparent spinous process structures. Finally, a two-fold filtering strategy was proposed to screen the detected spinous processes landmarks iteratively, followed by a three-dimensional spine curve fitting for the spine curvature assessments. We evaluated the proposed model on 3-D ultrasound images among subjects with different scoliotic angles. The results showed that the mean localization accuracy of the proposed landmark localization algorithm was 5.95 pixels. Also, the curvature angles on the coronal plane obtained by the new method had a high linear correlation with those by manual measurement (R = 0.86, p < 0.001). These results demonstrated the potential of our proposed method for facilitating the 3-D assessment of scoliosis, especially for 3-D spine deformity assessment.
Collapse
Affiliation(s)
- Qi-Yong Ran
- The School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University, Nanjing, China
| | - Juzheng Miao
- The School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China
| | - Si-Ping Zhou
- The School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University, Nanjing, China
| | - Shi-Hao Hua
- The School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University, Nanjing, China
| | - Si-Yuan He
- The School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University, Nanjing, China
| | - Ping Zhou
- The School of Biological Science and Medical Engineering, Southeast University, Nanjing, China
| | - Hong-Xing Wang
- The Department of Rehabilitation Medicine, Zhongda Hospital, Southeast University, Nanjing, China
| | - Yong-Ping Zheng
- The Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong, China
| | - Guang-Quan Zhou
- The School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University, Nanjing, China.
| |
Collapse
|
3
|
Chen YF, Liu TH, Chen SP, Pan GZ, Lu XH, Lu GJ, Zhong SX, Cai LX, Cui QC, Ran QY. Watery diarrhea syndrome caused by multihormonal malignant pancreatic islet cell tumor secreting somatostatin, vasoactive intestinal peptide, serotonin, and prostaglandin E--a clinicopathological, biochemical, immunohistochemical, and ultrastructural study. Pancreas 1986; 1:80-9. [PMID: 2883647 DOI: 10.1097/00006676-198601000-00015] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/03/2023]
Abstract
The pathophysiological, biochemical, histological, ultrastructural, and immunohistochemical characters of a case of malignant pancreatic islet cell tumor with watery diarrhea syndrome were carefully investigated. Four hormones or mediators--somatostatin (SST), vasoactive intestinal peptide (VIP), serotonin, and prostaglandin E--were markedly elevated in the circulation. The diagnosis was further confirmed by exploratory laparotomy and autopsy. The contents of SST and VIP in tumor tissues were very high. Gel chromatography of tumor extract revealed single peaks for both SST and VIP. Immunohistochemical studies of tumor tissues showed numerous immunoreactive cells to anti-SST, moderate amount of VIP-positive cells, and a few hCG-, insulin-, and glucagon-positive cells. In conclusion, this is an unusual case of Verner-Morrison syndrome in which three kinds of bioactive hormones or mediators were simultaneously secreted; peptides, amine, and prostaglandin.
Collapse
|