2022_Early Detection and Classification of Breast Cancer in Mammography Images Using Fuzzy Anisotropic Diffusion Histogram Equalization Contrast Adaptive Limited (Fadhecal) and Multilevel OTSU Thresholding
| Format: | General Document |
|---|
| _version_ | 1860798078213160960 |
|---|---|
| building | INTELEK Repository |
| collection | Online Access |
| collectionurl | https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 |
| copyright | Copyright©PWB2025 |
| country | Malaysia |
| date | 2022-02-07 |
| format | General Document |
| id | 15822 |
| institution | UniSZA |
| internalnotes | Sila masukkan subject wajib Dissertations, Academic. Terima kasih... |
| originalfilename | 15822_58f78faca0f687e.pdf |
| person | Saifullah Harith Bin Suradi |
| recordtype | oai_dc |
| resourceurl | https://intelek.unisza.edu.my/intelek/pages/view.php?ref=15822 |
| sourcemedia | Server storage Scanned document |
| spelling | 15822 https://intelek.unisza.edu.my/intelek/pages/view.php?ref=15822 https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 General Document Malaysia Library Staff (Top Management) Library Staff (Management) Library Staff (Support) Terengganu Faculty of Health Sciences English application/pdf 1.5 Server storage Scanned document Universiti Sultan Zainal Abidin UniSZA Private Access UNIVERSITI SULTAN ZAINAL ABIDIN SAMBox 2.3.4; modified using iTextSharp™ 5.5.10 ©2000-2016 iText Group NV (AGPL-version) 140 2022-02-07 Copyright©PWB2025 15822_58f78faca0f687e.pdf 2022_Early Detection and Classification of Breast Cancer in Mammography Images Using Fuzzy Anisotropic Diffusion Histogram Equalization Contrast Adaptive Limited (Fadhecal) and Multilevel OTSU Thresholding Saifullah Harith Bin Suradi Breast cancer—Diagnosis Breast cancer is the global leading cancer-related mortality among women. Digital mammograms can be used as an initial step to detect breast cancer. Detecting breast cancer at an early stage can help to improve the patients’ survival rates. However, mammogram images suffer from low contrast and high image noises due to low radiation exposure factors. As a result, the extraction of breast cancer using the region of interests (ROIs) tool will be difficult and, thus, lead to misclassification. Digital mammograms with appropriate image enhancement and segmentation techniques will improve breast cancer detection. Hence, there are strong needs for the development of image enhancement techniques for mammogram images to improve the appearances. This study proposes a modified image enhancement technique, namely, Fuzzy Anisotropic Diffusion Histogram Equalization Contrast Adaptive Limited (FADHECAL) to reduce the noise of mammogram images while preserving contrast and brightness. This technique uses a combination of Fuzzy Clipped Inference System (FCIS) and Anisotropic Diffusion Filter (ADF). Image segmentation technique was used for mammogram images to extract the breast cancer lesions. FADHECAL was also incorporated with the Multilevel Otsu Thresholding segmentation technique to detect and classify the breast cancer lesions with different background of breast tissues. A total of 322 mammogram images were retrieved from the Mini Mammographic Image Analysis Society (MIAS) database. The performance of this FADHECAL was compared to Recursive Mean-Separate Histogram Equalization (RMSHE), Fast Discrete Curvelet Transform via Unequally Spaced Fast Fourier Transform (FDCT-USFFT) and Fuzzy Clipped Contrast-Limited Adaptive Histogram Equalization (FC-CLAHE). Image quality measurement tools of Absolute Mean Brightness Error (AMBE), Structural Similarity Index Measure (SSIM), Mean Absolute Error (MAE), Peak Signal-to-Noise Ratio (PSNR) and Universal Image Quality Index (UIQI) were used. The results have shown that FADHECAL has the most superior results among other selected enhancement techniques with 5.502 of AMBE, 0.901 of SSIM, 17.195 of MAE, 23.892 of PSNR, and 0.948 of UIQI values. The efficiency of FADHECAL that incorporated with Multilevel Otsu Thresholding Segmentation is 94.8%, and the error rate is 5.2%. In conclusion, FADHECAL can be used as a new ideal platform of image processing technique in mammogram images, especially for the early detection of breast cancer lesions. Dissertations, Academic Sila masukkan subject wajib Dissertations, Academic. Terima kasih... Breast Cancer Early Detection in Mammograms Fuzzy Anisotropic Diffusion in Image Processing Histogram Equalization For Contrast Enhancement Thesis |
| spellingShingle | 2022_Early Detection and Classification of Breast Cancer in Mammography Images Using Fuzzy Anisotropic Diffusion Histogram Equalization Contrast Adaptive Limited (Fadhecal) and Multilevel OTSU Thresholding |
| state | Terengganu |
| subject | Breast cancer—Diagnosis Dissertations, Academic |
| summary | Breast cancer is the global leading cancer-related mortality among women. Digital mammograms can be used as an initial step to detect breast cancer. Detecting breast cancer at an early stage can help to improve the patients’ survival rates. However, mammogram images suffer from low contrast and high image noises due to low radiation exposure factors. As a result, the extraction of breast cancer using the region of interests (ROIs) tool will be difficult and, thus, lead to misclassification. Digital mammograms with appropriate image enhancement and segmentation techniques will improve breast cancer detection. Hence, there are strong needs for the development of image enhancement techniques for mammogram images to improve the appearances. This study proposes a modified image enhancement technique, namely, Fuzzy Anisotropic Diffusion Histogram Equalization Contrast Adaptive Limited (FADHECAL) to reduce the noise of mammogram images while preserving contrast and brightness. This technique uses a combination of Fuzzy Clipped Inference System (FCIS) and Anisotropic Diffusion Filter (ADF). Image segmentation technique was used for mammogram images to extract the breast cancer lesions. FADHECAL was also incorporated with the Multilevel Otsu Thresholding segmentation technique to detect and classify the breast cancer lesions with different background of breast tissues. A total of 322 mammogram images were retrieved from the Mini Mammographic Image Analysis Society (MIAS) database. The performance of this FADHECAL was compared to Recursive Mean-Separate Histogram Equalization (RMSHE), Fast Discrete Curvelet Transform via Unequally Spaced Fast Fourier Transform (FDCT-USFFT) and Fuzzy Clipped Contrast-Limited Adaptive Histogram Equalization (FC-CLAHE). Image quality measurement tools of Absolute Mean Brightness Error (AMBE), Structural Similarity Index Measure (SSIM), Mean Absolute Error (MAE), Peak Signal-to-Noise Ratio (PSNR) and Universal Image Quality Index (UIQI) were used. The results have shown that FADHECAL has the most superior results among other selected enhancement techniques with 5.502 of AMBE, 0.901 of SSIM, 17.195 of MAE, 23.892 of PSNR, and 0.948 of UIQI values. The efficiency of FADHECAL that incorporated with Multilevel Otsu Thresholding Segmentation is 94.8%, and the error rate is 5.2%. In conclusion, FADHECAL can be used as a new ideal platform of image processing technique in mammogram images, especially for the early detection of breast cancer lesions. |
| title | 2022_Early Detection and Classification of Breast Cancer in Mammography Images Using Fuzzy Anisotropic Diffusion Histogram Equalization Contrast Adaptive Limited (Fadhecal) and Multilevel OTSU Thresholding |
| title_full | 2022_Early Detection and Classification of Breast Cancer in Mammography Images Using Fuzzy Anisotropic Diffusion Histogram Equalization Contrast Adaptive Limited (Fadhecal) and Multilevel OTSU Thresholding |
| title_fullStr | 2022_Early Detection and Classification of Breast Cancer in Mammography Images Using Fuzzy Anisotropic Diffusion Histogram Equalization Contrast Adaptive Limited (Fadhecal) and Multilevel OTSU Thresholding |
| title_full_unstemmed | 2022_Early Detection and Classification of Breast Cancer in Mammography Images Using Fuzzy Anisotropic Diffusion Histogram Equalization Contrast Adaptive Limited (Fadhecal) and Multilevel OTSU Thresholding |
| title_short | 2022_Early Detection and Classification of Breast Cancer in Mammography Images Using Fuzzy Anisotropic Diffusion Histogram Equalization Contrast Adaptive Limited (Fadhecal) and Multilevel OTSU Thresholding |
| title_sort | 2022_early detection and classification of breast cancer in mammography images using fuzzy anisotropic diffusion histogram equalization contrast adaptive limited (fadhecal) and multilevel otsu thresholding |