1
|
Rauf Z, Khan AR, Sohail A, Alquhayz H, Gwak J, Khan A. Lymphocyte detection for cancer analysis using a novel fusion block based channel boosted CNN. Sci Rep 2023; 13:14047. [PMID: 37640739 PMCID: PMC10462751 DOI: 10.1038/s41598-023-40581-z] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/12/2022] [Accepted: 08/13/2023] [Indexed: 08/31/2023] Open
Abstract
Tumor-infiltrating lymphocytes, specialized immune cells, are considered an important biomarker in cancer analysis. Automated lymphocyte detection is challenging due to its heterogeneous morphology, variable distribution, and presence of artifacts. In this work, we propose a novel Boosted Channels Fusion-based CNN "BCF-Lym-Detector" for lymphocyte detection in multiple cancer histology images. The proposed network initially selects candidate lymphocytic regions at the tissue level and then detects lymphocytes at the cellular level. The proposed "BCF-Lym-Detector" generates diverse boosted channels by utilizing the feature learning capability of different CNN architectures. In this connection, a new adaptive fusion block is developed to combine and select the most relevant lymphocyte-specific features from the generated enriched feature space. Multi-level feature learning is used to retain lymphocytic spatial information and detect lymphocytes with variable appearances. The assessment of the proposed "BCF-Lym-Detector" show substantial improvement in terms of F-score (0.93 and 0.84 on LYSTO and NuClick, respectively), which suggests that the diverse feature extraction and dynamic feature selection enhanced the feature learning capacity of the proposed network. Moreover, the proposed technique's generalization on unseen test sets with a good recall (0.75) and F-score (0.73) shows its potential use for pathologists' assistance.
Collapse
Affiliation(s)
- Zunaira Rauf
- Pattern Recognition Lab, Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, Nilore, 45650, Islamabad, Pakistan
- PIEAS Artificial Intelligence Center (PAIC), Pakistan Institute of Engineering and Applied Sciences, Nilore, 45650, Islamabad, Pakistan
| | - Abdul Rehman Khan
- Pattern Recognition Lab, Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, Nilore, 45650, Islamabad, Pakistan
| | - Anabia Sohail
- Pattern Recognition Lab, Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, Nilore, 45650, Islamabad, Pakistan
- Department of Electrical Engineering and Computer Science, Khalifa University of Science and Technology, Abu Dhabi, UAE
| | - Hani Alquhayz
- Department of Computer Science and Information, College of Science in Zulfi, Majmaah University, 11952, Al-Majmaah, Saudi Arabia
| | - Jeonghwan Gwak
- Department of Software, Korea National University of Transportation, Chungju, 27469, Republic of Korea.
| | - Asifullah Khan
- Pattern Recognition Lab, Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, Nilore, 45650, Islamabad, Pakistan.
- PIEAS Artificial Intelligence Center (PAIC), Pakistan Institute of Engineering and Applied Sciences, Nilore, 45650, Islamabad, Pakistan.
- Center for Mathematical Sciences, Pakistan Institute of Engineering and Applied Sciences, Nilore, 45650, Islamabad, Pakistan.
| |
Collapse
|
2
|
Peng T, Gu Y, Zhang J, Dong Y, DI G, Wang W, Zhao J, Cai J. A Robust and Explainable Structure-Based Algorithm for Detecting the Organ Boundary From Ultrasound Multi-Datasets. J Digit Imaging 2023; 36:1515-1532. [PMID: 37231289 PMCID: PMC10406792 DOI: 10.1007/s10278-023-00839-4] [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: 02/22/2023] [Revised: 04/19/2023] [Accepted: 04/20/2023] [Indexed: 05/27/2023] Open
Abstract
Detecting the organ boundary in an ultrasound image is challenging because of the poor contrast of ultrasound images and the existence of imaging artifacts. In this study, we developed a coarse-to-refinement architecture for multi-organ ultrasound segmentation. First, we integrated the principal curve-based projection stage into an improved neutrosophic mean shift-based algorithm to acquire the data sequence, for which we utilized a limited amount of prior seed point information as the approximate initialization. Second, a distribution-based evolution technique was designed to aid in the identification of a suitable learning network. Then, utilizing the data sequence as the input of the learning network, we achieved the optimal learning network after learning network training. Finally, a scaled exponential linear unit-based interpretable mathematical model of the organ boundary was expressed via the parameters of a fraction-based learning network. The experimental outcomes indicated that our algorithm 1) achieved more satisfactory segmentation outcomes than state-of-the-art algorithms, with a Dice score coefficient value of 96.68 ± 2.2%, a Jaccard index value of 95.65 ± 2.16%, and an accuracy of 96.54 ± 1.82% and 2) discovered missing or blurry areas.
Collapse
Affiliation(s)
- Tao Peng
- School of Future Science and Engineering, Soochow University, Suzhou, China
- Department of Health Technology and Informatics, Hong Kong Polytechnic University, Hong Kong, China
- Department of Radiation Oncology, UT Southwestern Medical Center, Dallas, TX USA
| | - Yidong Gu
- School of Future Science and Engineering, Soochow University, Suzhou, China
- Department of Medical Ultrasound, the Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou, Jiangsu China
| | - Ji Zhang
- Department of Radiology, The Affiliated Taizhou People’s Hospital of Nanjing Medical University, Taizhou, Jiangsu Province, China
| | - Yan Dong
- Department of Ultrasonography, The First Affiliated Hospital of Soochow University, Suzhou, Jiangsu Province, China
| | - Gongye DI
- Department of Ultrasonic, The Affiliated Taizhou People’s Hospital of Nanjing Medical University, Taizhou, Jiangsu Province, China
| | - Wenjie Wang
- Department of Radio-Oncology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou, Jiangsu China
| | - Jing Zhao
- Department of Ultrasound, Tsinghua University Affiliated Beijing Tsinghua Changgung Hospital, Beijing, China
| | - Jing Cai
- Department of Health Technology and Informatics, Hong Kong Polytechnic University, Hong Kong, China
| |
Collapse
|
3
|
Wu Y, Wu B, Zhang Y, Wan S. A novel method of data and feature enhancement for few-shot image classification. Soft comput 2023. [DOI: 10.1007/s00500-023-07816-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/15/2023]
|
4
|
Yan J, Cai J, Xu Z, Guo R, Zhou W, Yan H, Xu Z, Wang Y. Tongue crack recognition using segmentation based deep learning. Sci Rep 2023; 13:511. [PMID: 36627326 PMCID: PMC9832139 DOI: 10.1038/s41598-022-27210-x] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2022] [Accepted: 12/28/2022] [Indexed: 01/12/2023] Open
Abstract
Tongue cracks refer to fissures with different depth and shapes on the tongue's surface, which can characterize the pathological characteristics of spleen and stomach. Tongue cracks are of great significance to the objective study of tongue diagnosis. However, tongue cracks are small and complex, existing methods are difficult to extract them effectively. In order to achieve more accurate extraction and identification of tongue crack, this paper proposes to apply a deep learning network based on image segmentation (Segmentation-Based Deep-Learning, SBDL) to extract and identify tongue crack. In addition, we have studied the quantitative description of tongue crack features. Firstly, the pre-processed tongue crack samples were amplified by using adding salt and pepper noise, changing the contrast and horizontal mirroring; secondly, the annotation tool Crack-Tongue was used to label tongue crack; thirdly, the tongue crack extraction model was trained by using SBDL; fourthly, the cracks on the tongue surface were detected and located by the segmentation network, and then the output and features of the segmentation network were put into the decision network for the classification of crack tongue images; finally, the tongue crack segmentation and identification results were quantitatively evaluated. The experimental results showed that the tongue crack extraction and recognition results based on SBDL were better than Mask Region-based Convolutional Neural Network (Mask R-CNN), DeeplabV3+, U-Net, UNet++ and Semantic Segmentation with Adversarial Learning (SegAN). This method effectively solved the inaccurate tongue crack extraction caused by the tongue crack's color being close to the surrounding tongue coating's color. This method can achieve better tongue crack extraction and recognition results on a small tongue crack data set and provides a new idea for tongue crack recognition, which is of practical value for tongue diagnosis objectification.
Collapse
Affiliation(s)
- Jianjun Yan
- Shanghai Key Laboratory of Intelligent Sensing and Detection Technology, East China University of Science and Technology, 130 Meilong Road, Shanghai, 200237, China.
| | - Jinxing Cai
- Shanghai Key Laboratory of Intelligent Sensing and Detection Technology, East China University of Science and Technology, 130 Meilong Road, Shanghai, 200237, China
| | - Zi Xu
- Shanghai Key Laboratory of Intelligent Sensing and Detection Technology, East China University of Science and Technology, 130 Meilong Road, Shanghai, 200237, China
| | - Rui Guo
- Comprehensive Laboratory of Four Diagnostic Methods, Shanghai University of Traditional Chinese Medicine, Shanghai, 201203, China
| | - Wei Zhou
- Shanghai Key Laboratory of Intelligent Sensing and Detection Technology, East China University of Science and Technology, 130 Meilong Road, Shanghai, 200237, China
| | - Haixia Yan
- Comprehensive Laboratory of Four Diagnostic Methods, Shanghai University of Traditional Chinese Medicine, Shanghai, 201203, China
| | - Zhaoxia Xu
- Comprehensive Laboratory of Four Diagnostic Methods, Shanghai University of Traditional Chinese Medicine, Shanghai, 201203, China
| | - Yiqin Wang
- Comprehensive Laboratory of Four Diagnostic Methods, Shanghai University of Traditional Chinese Medicine, Shanghai, 201203, China
| |
Collapse
|
5
|
Performance analysis of seven Convolutional Neural Networks (CNNs) with transfer learning for Invasive Ductal Carcinoma (IDC) grading in breast histopathological images. Sci Rep 2022; 12:19200. [PMID: 36357456 PMCID: PMC9649772 DOI: 10.1038/s41598-022-21848-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/24/2022] [Accepted: 10/04/2022] [Indexed: 11/11/2022] Open
Abstract
Computer-aided Invasive Ductal Carcinoma (IDC) grading classification systems based on deep learning have shown that deep learning may achieve reliable accuracy in IDC grade classification using histopathology images. However, there is a dearth of comprehensive performance comparisons of Convolutional Neural Network (CNN) designs on IDC in the literature. As such, we would like to conduct a comparison analysis of the performance of seven selected CNN models: EfficientNetB0, EfficientNetV2B0, EfficientNetV2B0-21k, ResNetV1-50, ResNetV2-50, MobileNetV1, and MobileNetV2 with transfer learning. To implement each pre-trained CNN architecture, we deployed the corresponded feature vector available from the TensorFlowHub, integrating it with dropout and dense layers to form a complete CNN model. Our findings indicated that the EfficientNetV2B0-21k (0.72B Floating-Point Operations and 7.1 M parameters) outperformed other CNN models in the IDC grading task. Nevertheless, we discovered that practically all selected CNN models perform well in the IDC grading task, with an average balanced accuracy of 0.936 ± 0.0189 on the cross-validation set and 0.9308 ± 0.0211on the test set.
Collapse
|