Radiomics based detection and characterization of suspicious lesions on full field digital mammograms. (September 2018)

• Record Type: Journal Article
• Authors: Sapate, Suhas G.; Mahajan, Abhishek; Talbar, Sanjay N.; Sable, Nilesh; Desai, Subhash; Thakur, Meenakshi
• Is Part Of: Computer methods and programs in biomedicine. Volume 163(2018)
• Page Start: 1
• Page End: 20
• Publication Date: 2018-09
• Subjects: Breast cancer -- Digital mammogram -- Fuzzy region growing -- Radiomic features -- Geometric features -- Textural features; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2018.05.017
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Proposed scheme segments out suspicious lesions from digital mammograms automatically using adaptive fuzzy region growing method. Proposed segmentation scheme incorporates a novel neighboring pixel selection algorithm which reduces computational complexity. The segmentation results showed 91.67% sensitivity and 58.33% specificity. k-NN and SVM classifiers with radiomic features such as geometric and textural features improves specificity upto 91.67% with False Positives per Image of 0.55 only. The radiologists involved in the study have appreciated the potential of the proposed scheme and hence it can be used in a CAD system to assist them in clinical breast cancer diagnosis. 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.