Correlated-Weighted Statistically Modeled Contourlet and Curvelet Coefficient Image-Based Breast Tumor Classification Using Deep Learning
Deep learning-based automatic classification of breast tumors using parametric imaging techniques from ultrasound (US) B-mode images is still an exciting research area. The Rician inverse Gaussian (RiIG) distribution is currently emerging as an appropriate example of statistical modeling. This study...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/1/69 |
| _version_ | 1797626044756262912 |
|---|---|
| author | Shahriar M. Kabir Mohammed I. H. Bhuiyan |
| author_facet | Shahriar M. Kabir Mohammed I. H. Bhuiyan |
| author_sort | Shahriar M. Kabir |
| collection | DOAJ |
| description | Deep learning-based automatic classification of breast tumors using parametric imaging techniques from ultrasound (US) B-mode images is still an exciting research area. The Rician inverse Gaussian (RiIG) distribution is currently emerging as an appropriate example of statistical modeling. This study presents a new approach of correlated-weighted contourlet-transformed RiIG (CWCtr-RiIG) and curvelet-transformed RiIG (CWCrv-RiIG) image-based deep convolutional neural network (CNN) architecture for breast tumor classification from B-mode ultrasound images. A comparative study with other statistical models, such as Nakagami and normal inverse Gaussian (NIG) distributions, is also experienced here. The weighted entitled here is for weighting the contourlet and curvelet sub-band coefficient images by correlation with their corresponding RiIG statistically modeled images. By taking into account three freely accessible datasets (Mendeley, UDIAT, and BUSI), it is demonstrated that the proposed approach can provide more than 98 percent accuracy, sensitivity, specificity, NPV, and PPV values using the CWCtr-RiIG images. On the same datasets, the suggested method offers superior classification performance to several other existing strategies. |
| first_indexed | 2024-03-11T10:05:02Z |
| format | Article |
| id | doaj.art-824d77d5f6124781b4569cf46abbaa8e |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T10:05:02Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-824d77d5f6124781b4569cf46abbaa8e2023-11-16T15:08:24ZengMDPI AGDiagnostics2075-44182022-12-011316910.3390/diagnostics13010069Correlated-Weighted Statistically Modeled Contourlet and Curvelet Coefficient Image-Based Breast Tumor Classification Using Deep LearningShahriar M. Kabir0Mohammed I. H. Bhuiyan1Department of Electrical and Electronic Engineering, Green University of Bangladesh, Dhaka 1207, BangladeshDepartment of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, BangladeshDeep learning-based automatic classification of breast tumors using parametric imaging techniques from ultrasound (US) B-mode images is still an exciting research area. The Rician inverse Gaussian (RiIG) distribution is currently emerging as an appropriate example of statistical modeling. This study presents a new approach of correlated-weighted contourlet-transformed RiIG (CWCtr-RiIG) and curvelet-transformed RiIG (CWCrv-RiIG) image-based deep convolutional neural network (CNN) architecture for breast tumor classification from B-mode ultrasound images. A comparative study with other statistical models, such as Nakagami and normal inverse Gaussian (NIG) distributions, is also experienced here. The weighted entitled here is for weighting the contourlet and curvelet sub-band coefficient images by correlation with their corresponding RiIG statistically modeled images. By taking into account three freely accessible datasets (Mendeley, UDIAT, and BUSI), it is demonstrated that the proposed approach can provide more than 98 percent accuracy, sensitivity, specificity, NPV, and PPV values using the CWCtr-RiIG images. On the same datasets, the suggested method offers superior classification performance to several other existing strategies.https://www.mdpi.com/2075-4418/13/1/69convolutional neural network (CNN)machine learningdeep learningbreast cancercontourletcurvelet |
| spellingShingle | Shahriar M. Kabir Mohammed I. H. Bhuiyan Correlated-Weighted Statistically Modeled Contourlet and Curvelet Coefficient Image-Based Breast Tumor Classification Using Deep Learning Diagnostics convolutional neural network (CNN) machine learning deep learning breast cancer contourlet curvelet |
| title | Correlated-Weighted Statistically Modeled Contourlet and Curvelet Coefficient Image-Based Breast Tumor Classification Using Deep Learning |
| title_full | Correlated-Weighted Statistically Modeled Contourlet and Curvelet Coefficient Image-Based Breast Tumor Classification Using Deep Learning |
| title_fullStr | Correlated-Weighted Statistically Modeled Contourlet and Curvelet Coefficient Image-Based Breast Tumor Classification Using Deep Learning |
| title_full_unstemmed | Correlated-Weighted Statistically Modeled Contourlet and Curvelet Coefficient Image-Based Breast Tumor Classification Using Deep Learning |
| title_short | Correlated-Weighted Statistically Modeled Contourlet and Curvelet Coefficient Image-Based Breast Tumor Classification Using Deep Learning |
| title_sort | correlated weighted statistically modeled contourlet and curvelet coefficient image based breast tumor classification using deep learning |
| topic | convolutional neural network (CNN) machine learning deep learning breast cancer contourlet curvelet |
| url | https://www.mdpi.com/2075-4418/13/1/69 |
| work_keys_str_mv | AT shahriarmkabir correlatedweightedstatisticallymodeledcontourletandcurveletcoefficientimagebasedbreasttumorclassificationusingdeeplearning AT mohammedihbhuiyan correlatedweightedstatisticallymodeledcontourletandcurveletcoefficientimagebasedbreasttumorclassificationusingdeeplearning |