Automated quantitative assessment of amorphous calcifications: Towards improved malignancy risk stratification

• Published in: Computers in biology and medicine 2022-07, Vol.146, p.105504-105504, Article 105504
• Main Authors: Marathe, Kalyani, Marasinou, Chrysostomos, Li, Beibin, Nakhaei, Noor, Li, Bo, Elmore, Joann G., Shapiro, Linda, Hsu, William
• Format: Article
• Language: English
• Subjects: Algorithms; Benign; Biopsy; Breast; Breast - diagnostic imaging; Breast - pathology; Breast cancer; Breast Diseases - diagnostic imaging; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - pathology; Calcification; Classification; Cluster analysis; Clustering; Datasets; Digital imaging; Feature extraction; Female; Humans; Machine learning; Malignancy; Mammography; Mammography - methods; Medical imaging; Microcalcifications; Quantitative analysis; Radiographic Image Interpretation, Computer-Assisted - methods; Radiomics; Risk Assessment; Test sets; Vector quantization
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.105504

Amorphous calcifications noted on mammograms (i.e., small and indistinct calcifications that are difficult to characterize) are associated with high diagnostic uncertainty, often leading to biopsies. Yet, only 20% of biopsied amorphous calcifications are cancer. We present a quantitative approach for distinguishing between benign and actionable (high-risk and malignant) amorphous calcifications using a combination of local textures, global spatial relationships, and interpretable handcrafted expert features. Our approach was trained and validated on a set of 168 2D full-field digital mammography exams (248 images) from 168 patients. Within these 248 images, we identified 276 image regions with segmented amorphous calcifications and a biopsy-confirmed diagnosis. A set of local (radiomic and region measurements) and global features (distribution and expert-defined) were extracted from each image. Local features were grouped using an unsupervised k-means clustering algorithm. All global features were concatenated with clustered local features and used to train a LightGBM classifier to distinguish benign from actionable cases. On the held-out test set of 60 images, our approach achieved a sensitivity of 100%, specificity of 35%, and a positive predictive value of 38% when the decision threshold was set to 0.4. Given that all of the images in our test set resulted in a recommendation of a biopsy, the use of our algorithm would have identified 15 images (25%) that were benign, potentially reducing the number of breast biopsies. Quantitative analysis of full-field digital mammograms can extract subtle shape, texture, and distribution features that may help to distinguish between benign and actionable amorphous calcifications. •A clustering-based approach improves the assessment of amorphous calcifications.•Unsupervised clustering identifies a consistent set of local shape and texture-based features.•Global features like variation in microcalcification size and spatial distribution predict high risk/malignant cases.•Quantitative analysis of the calcifications and their surroundings helps distinguish between benign versus actionable cases.