Automatic Breast Mass Segmentation and Classification Using Subtraction of Temporally Sequential Digital Mammograms

Abstract

Cancer remains a major cause of morbidity and mortality globally, with 1 in 5 of all new cancers arising in the breast. The introduction of mammography for the radiological diagnosis of breast abnormalities, significantly decreased their mortality rates. Accurate detection and classification of breast masses in mammograms is especially challenging for various reasons, including low contrast and the normal variations of breast tissue density. Various Computer-Aided Diagnosis (CAD) systems are being developed to assist radiologists with the accurate classification of breast abnormalities. Methods: In this study, subtraction of temporally sequential digital mammograms and machine learning are proposed for the automatic segmentation and classification of masses. The performance of the algorithm was evaluated on a dataset created especially for the purposes of this study, with 320 images from 80 patients (two time points and two views of each breast) with precisely annotated mass locations by two radiologists. Results: Ninety-six features were extracted and ten classifiers were tested in a leave-one-patient-out and k-fold cross-validation process. Using Neural Networks, the detection of masses was 99.9% accurate. The classification accuracy of the masses as benign or suspicious increased from 92.6%, using the state-of-the-art temporal analysis, to 98%, using the proposed methodology. The improvement was statistically significant (p-value < 0.05). Conclusion: These results demonstrate the effectiveness of the subtraction of temporally consecutive mammograms for the diagnosis of breast masses. Clinical and Translational Impact Statement:The proposed algorithm has the potential to substantially contribute to the development of automated breast cancer Computer-Aided Diagnosis systems with significant impact on patient prognosis.

A Review of Computer-Aided Breast Cancer Diagnosis Using Sequential Mammograms

“…To address some of the limitations, subtraction of temporally sequential mammograms exploits the whole prior screening, by subtracting the registered version of the prior images from recent ones. With direct subtraction of the mammogram pairs, ROIs that remained unchanged between screenings are effectively removed, which improves the detection and classification performance (90.3% accuracy and 0.87 AUC for the classification of MCs [58] or 98% accuracy and 0.98 AUC for the classification of masses [60]).…”

“…Temporal subtraction was also applied to the detection and classification of breast masses. A new dataset was collected by Loizidou et al, consisting of 80 pairs of digital temporally sequential mammograms [60]. This dataset is also available online with open access [61].…”

Breast cancer detection through attention based feature integration model

“…Considering the improvisation of the structure of CNN, the [10] removal of the completely linked layers are utilized for classifying CNN, as well as an intermediate level of features and features of high level for the support vector machine (SVMs) for classification of breast mass (BM). The Leaky rectified linear unit (ReLu) is used as the function of activation and utilized for dropout to the completely linked layers for building the CNN model along four layers of CNN and three completely linked layers for the classification of BM [11].…”

Expanding Horizons: The Realities of CAD, the Promise of Artificial Intelligence, and Machine Learning’s Role in Breast Imaging beyond Screening Mammography

“…Investigators have recently employed such networks in medical tasks, such as determining osteoarthritis progression on sequential knee radiographs [ 32 ] and for retinopathy grading [ 33 ]. Within breast imaging, several recent articles, including a review by Loizidou et al, and a few commercial products have emerged that specifically utilize temporal changes in medical images for better diagnosis [ 34 ]. For instance, Bai et al compared several different types of AI networks for cancer classification, finding that the best performance was achieved with a model capable of image comparisons [ 35 ].…”

“…For instance, Bai et al compared several different types of AI networks for cancer classification, finding that the best performance was achieved with a model capable of image comparisons [ 35 ]. Using a different novel technique based on image subtraction, a study by Loizidou et al demonstrated 99% accuracy in distinguishing masses from normal tissue in their dataset [ 34 ].…”