Suhas G Sapate1, Abhishek Mahajan2, Sanjay N Talbar3, Nilesh Sable2, Subhash Desai2, Meenakshi Thakur2. 1. Centre of Excellence in Signal & Image Processing, SGGS Institute of Engineering & Technology, Nanded, Maharashtra, India; Department of CSE, Ashokrao Mane Group of Institutions, Vathar, Kolhapur, Maharashtra, India. Electronic address: sapatesuhas@sggs.ac.in. 2. Department of Radiodiagnosis, Tata Memorial Centre, Parel, Mumbai, Maharashtra, India. 3. Centre of Excellence in Signal & Image Processing, SGGS Institute of Engineering & Technology, Nanded, Maharashtra, India; Department of E&TC, SGGS Institute of Engineering & Technology, Nanded, Maharashtra, India.
Abstract
BACKGROUND AND OBJECTIVE: Early detection is the important key to reduce breast cancer mortality rate. Detecting the mammographic abnormality as a subtle sign of breast cancer is essential for the proper diagnosis and treatment. The aim of this preliminary study is to develop algorithms which detect suspicious lesions and characterize them to reduce the diagnostic errors regarding false positives and false negatives. METHODS: The proposed hybrid mechanism detects suspicious lesions automatically using connected component labeling and adaptive fuzzy region growing algorithm. A novel neighboring pixel selection algorithm reduces the computational complexity of the seeded region growing algorithm used to finalize lesion contours. These lesions are characterized using radiomic features and then classified as benign mass or malignant tumor using k-NN and SVM classifiers. Two datasets of 460 full field digital mammograms (FFDM) utilized in this clinical study consists of 210 images with malignant tumors, 30 with benign masses and 220 normal breast images that are validated by radiologists expert in mammography. RESULTS: The qualitative assessment of segmentation results by the expert radiologists shows 91.67% sensitivity and 58.33% specificity. The effects of seven geometric and 48 textural features on classification accuracy, false positives per image (FPsI), sensitivity and specificity are studied separately and together. The features together achieved the sensitivity of 84.44% and 85.56%, specificity of 91.11% and 91.67% with FPsI of 0.54 and 0.55 using k-NN and SVM classifiers respectively on local dataset. CONCLUSIONS: The overall breast cancer detection performance of proposed scheme after combining geometric and textural features with both classifiers is improved in terms of sensitivity, specificity, and FPsI.
BACKGROUND AND OBJECTIVE: Early detection is the important key to reduce breast cancer mortality rate. Detecting the mammographic abnormality as a subtle sign of breast cancer is essential for the proper diagnosis and treatment. The aim of this preliminary study is to develop algorithms which detect suspicious lesions and characterize them to reduce the diagnostic errors regarding false positives and false negatives. METHODS: The proposed hybrid mechanism detects suspicious lesions automatically using connected component labeling and adaptive fuzzy region growing algorithm. A novel neighboring pixel selection algorithm reduces the computational complexity of the seeded region growing algorithm used to finalize lesion contours. These lesions are characterized using radiomic features and then classified as benign mass or malignant tumor using k-NN and SVM classifiers. Two datasets of 460 full field digital mammograms (FFDM) utilized in this clinical study consists of 210 images with malignant tumors, 30 with benign masses and 220 normal breast images that are validated by radiologists expert in mammography. RESULTS: The qualitative assessment of segmentation results by the expert radiologists shows 91.67% sensitivity and 58.33% specificity. The effects of seven geometric and 48 textural features on classification accuracy, false positives per image (FPsI), sensitivity and specificity are studied separately and together. The features together achieved the sensitivity of 84.44% and 85.56%, specificity of 91.11% and 91.67% with FPsI of 0.54 and 0.55 using k-NN and SVM classifiers respectively on local dataset. CONCLUSIONS: The overall breast cancer detection performance of proposed scheme after combining geometric and textural features with both classifiers is improved in terms of sensitivity, specificity, and FPsI.
Authors: Shivaji D Pawar; Kamal K Sharma; Suhas G Sapate; Geetanjali Y Yadav; Roobaea Alroobaea; Sabah M Alzahrani; Mustapha Hedabou Journal: Front Public Health Date: 2022-04-25
Authors: Devadhas Devakumar; Goutham Sunny; Balu Krishna Sasidharan; Stephen R Bowen; Ambily Nadaraj; L Jeyseelan; Manu Mathew; Aparna Irodi; Rajesh Isiah; Simon Pavamani; Subhashini John; Hannah Mary T Thomas Journal: J Med Phys Date: 2021-09-08
Authors: Michele Avanzo; Lise Wei; Joseph Stancanello; Martin Vallières; Arvind Rao; Olivier Morin; Sarah A Mattonen; Issam El Naqa Journal: Med Phys Date: 2020-06 Impact factor: 4.071