1
|
Kulkarni S, Rabidas R. Fully convolutional network for automated detection and diagnosis of mammographic masses. MULTIMEDIA TOOLS AND APPLICATIONS 2023:1-22. [PMID: 37362703 PMCID: PMC10169189 DOI: 10.1007/s11042-023-14757-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/14/2021] [Revised: 01/19/2022] [Accepted: 02/05/2023] [Indexed: 06/28/2023]
Abstract
Breast cancer, though rare in male, is very frequent in female and has high mortality rate which can be reduced if detected and diagnosed at the early stage. Thus, in this paper, deep learning architecture based on U-Net is proposed for the detection of breast masses and its characterization as benign or malignant. The evaluation of the proposed architecture in detection is carried out on two benchmark datasets- INbreast and DDSM and achieved a true positive rate of 99.64% at 0.25 false positives per image for INbreast dataset while the same for DDSM are 97.36% and 0.38 FPs/I, respectively. For mass characterization, an accuracy of 97.39% with an AUC of 0.97 is obtained for INbreast while the same for DDSM are 96.81%, and 0.96, respectively. The measured results are further compared with the state-of-the-art techniques where the introduced scheme takes an edge over others.
Collapse
Affiliation(s)
- Sujata Kulkarni
- Department of Electronics & Communication Engineering, Assam University, Silchar, 788010 Assam India
| | - Rinku Rabidas
- Department of Electronics & Communication Engineering, Assam University, Silchar, 788010 Assam India
| |
Collapse
|
2
|
Yang X, Wang R, Zhao D, Yu F, Heidari AA, Xu Z, Chen H, Algarni AD, Elmannai H, Xu S. Multi-level threshold segmentation framework for breast cancer images using enhanced differential evolution. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104373] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
|
3
|
Razali NF, Isa IS, Sulaiman SN, Abdul Karim NK, Osman MK, Che Soh ZH. Enhancement Technique Based on the Breast Density Level for Mammogram for Computer-Aided Diagnosis. Bioengineering (Basel) 2023; 10:bioengineering10020153. [PMID: 36829647 PMCID: PMC9952042 DOI: 10.3390/bioengineering10020153] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2022] [Revised: 01/04/2023] [Accepted: 01/16/2023] [Indexed: 01/26/2023] Open
Abstract
Mass detection in mammograms has a limited approach to the presence of a mass in overlapping denser fibroglandular breast regions. In addition, various breast density levels could decrease the learning system's ability to extract sufficient feature descriptors and may result in lower accuracy performance. Therefore, this study is proposing a textural-based image enhancement technique named Spatial-based Breast Density Enhancement for Mass Detection (SbBDEM) to boost textural features of the overlapped mass region based on the breast density level. This approach determines the optimal exposure threshold of the images' lower contrast limit and optimizes the parameters by selecting the best intensity factor guided by the best Blind/Reference-less Image Spatial Quality Evaluator (BRISQUE) scores separately for both dense and non-dense breast classes prior to training. Meanwhile, a modified You Only Look Once v3 (YOLOv3) architecture is employed for mass detection by specifically assigning an extra number of higher-valued anchor boxes to the shallower detection head using the enhanced image. The experimental results show that the use of SbBDEM prior to training mass detection promotes superior performance with an increase in mean Average Precision (mAP) of 17.24% improvement over the non-enhanced trained image for mass detection, mass segmentation of 94.41% accuracy, and 96% accuracy for benign and malignant mass classification. Enhancing the mammogram images based on breast density is proven to increase the overall system's performance and can aid in an improved clinical diagnosis process.
Collapse
Affiliation(s)
- Noor Fadzilah Razali
- Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang, Permatang Pauh Campus, Bukit Mertajam 13500, Pulau Pinang, Malaysia
| | - Iza Sazanita Isa
- Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang, Permatang Pauh Campus, Bukit Mertajam 13500, Pulau Pinang, Malaysia
- Correspondence:
| | - Siti Noraini Sulaiman
- Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang, Permatang Pauh Campus, Bukit Mertajam 13500, Pulau Pinang, Malaysia
- Integrative Pharmacogenomics Institute (iPROMISE), Universiti Teknologi MARA Cawangan Selangor, Puncak Alam Campus, Puncak Alam 42300, Selangor, Malaysia
| | - Noor Khairiah Abdul Karim
- Department of Biomedical Imaging, Advanced Medical and Dental Institute, Universiti Sains Malaysia Bertam, Kepala Batas 13200, Pulau Pinang, Malaysia
- Breast Cancer Translational Research Programme (BCTRP), Advanced Medical and Dental Institute, Universiti Sains Malaysia Bertam, Kepala Batas 13200, Pulau Pinang, Malaysia
| | - Muhammad Khusairi Osman
- Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang, Permatang Pauh Campus, Bukit Mertajam 13500, Pulau Pinang, Malaysia
| | - Zainal Hisham Che Soh
- Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang, Permatang Pauh Campus, Bukit Mertajam 13500, Pulau Pinang, Malaysia
| |
Collapse
|
4
|
Zhang Q, Wang Y, Song L, Han M, Song H. Using an improved YOLOv5s network for the automatic detection of silicon on wheat straw epidermis of micrographs. J FIELD ROBOT 2022. [DOI: 10.1002/rob.22120] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Affiliation(s)
- Qianru Zhang
- College of Mechanical and Electronic Engineering Northwest A&F University Yangling Shaanxi China
- Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural Affairs Yangling Shaanxi China
- Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Services Yangling China
| | - Yunfei Wang
- College of Mechanical and Electronic Engineering Northwest A&F University Yangling Shaanxi China
- Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural Affairs Yangling Shaanxi China
- Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Services Yangling China
| | - Lei Song
- College of Mechanical and Electronic Engineering Northwest A&F University Yangling Shaanxi China
- Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural Affairs Yangling Shaanxi China
- Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Services Yangling China
| | - Mengxuan Han
- College of Mechanical and Electronic Engineering Northwest A&F University Yangling Shaanxi China
- Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural Affairs Yangling Shaanxi China
- Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Services Yangling China
| | - Huaibo Song
- College of Mechanical and Electronic Engineering Northwest A&F University Yangling Shaanxi China
- Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural Affairs Yangling Shaanxi China
- Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Services Yangling China
| |
Collapse
|
5
|
Towards non-data-hungry and fully-automated diagnosis of breast cancer from mammographic images. Comput Biol Med 2021; 139:105011. [PMID: 34753080 DOI: 10.1016/j.compbiomed.2021.105011] [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: 07/02/2021] [Revised: 10/12/2021] [Accepted: 10/31/2021] [Indexed: 11/21/2022]
Abstract
Analysing local texture and generating features are two key issues for automatic cancer detection in mammographic images. Recent researches have shown that deep neural networks provide a promising alternative to hand-driven features which suffer from curse of dimensionality and low accuracy rates. However, large and balanced training data are foremost requirements for deep learning-based models and these data are not always available publicly. In this work, we propose a fully-automated method for breast cancer diagnosis that performs training using small sets of data. Feature extraction from mammographic images is performed using a genetic-programming-based descriptor that exploits statistics on a local binary pattern-like local distribution defined in each pixel. The effectiveness of the suggested method is demonstrated on two challenging datasets, (1) the digital database for screening mammography and (2) the mammographic image analysis society digital mammogram database, for content-based image retrieval as well as for abnormality/malignancy classification. The experimental results show that the proposed method outperforms or achieves comparable results with deep learning-based methods even those with transfer learning and/or data-augmentation.
Collapse
|