An automated toolbox for microcalcification cluster modeling for mammographic imaging

Abstract

Background: Mammographic imaging is essential for breast cancer detection and diagnosis. In addition to masses, calcifications are of concern and the early detection of breast cancer also heavily relies on the correct interpretation of suspicious microcalcification clusters. Even with advances in imaging and the introduction of novel techniques such as digital breast tomosynthesis and contrast-enhanced mammography, a correct interpretation can still be challenging given the subtle nature and large variety of calcifications.

Purpose: Computer simulated lesion models can serve to develop, optimize, or improve imaging techniques. In addition to their use in comparative (virtual clinical trial) detection experiments, these models have potential application in training deep learning models and in the understanding and interpretation of breast lesions. Existing simulation methods, however, often lack the capacity to model the diversity occurring in breast lesions or to generate models relevant for a specific case. This study focuses on clusters of microcalcifications and introduces an automated, flexible toolbox designed to generate microcalcification cluster models customized to specific tasks.

Methods: The toolbox allows users to control a large number of simulation parameters related to model characteristics such as lesion size, calcification shape, or number of microcalcifications per cluster. This leads to the capability of creating models that range from regular to complex clusters. Based on the input parameters, which are either tuned manually or pre-set for a specific clinical type, different sets of models can be simulated depending on the use case. Two lesion generation methods are described. The first method generates three-dimensional microcalcification clusters models based on geometrical shapes and transformations. The second method creates two-dimensional (2D) microcalcification cluster models for a specific 2D mammographic image. This novel method employs radiomics analysis to account for local textures, ensuring the simulated microcalcification cluster is appropriately integrated within the existing breast tissue. The toolbox is implemented in the Python language and can be conveniently run through a Jupyter Notebook interface, openly accessible at https://gitlab.kuleuven.be/medphysqa/deploy/breast-calcifications. Validation studies performed by radiologists assessed the level of malignancy and realism of clusters tuned with specific parameters and inserted in mammographic images.

Results: The flexibility of the toolbox with multiple simulation methods is illustrated, as well as the compatibility with different simulation frameworks and image types. The automation allows for the straightforward and fast generation of diverse microcalcification cluster models. The generated models are most likely applicable for various tasks as they can be configured in a variety of ways and inserted in different types of mammographic images of multiple acquisition systems. Validation studies confirmed the capacity to simulate realistic clusters and capture clinical properties when tuned with appropriate parameter settings.

Conclusion: This simulation toolbox offers a flexible means of simulating microcalcification cluster models with potential use in both technical and clinical research in mammography imaging. The 3D generation methods allow for specifying many characteristics regarding the calcification shape and cluster architecture, and the 2D generation method presents a novel manner to create microcalcification clusters tailored to existing breast textures.

Keywords: mammography; microcalcification cluster; simulation.

FIGURE 1

Pipeline to create a cluster from local textures: step 1) choose a grid cell; step 2) create a mask with candidate calcifications; step 3) filter candidate calcifications for size and circularity; step 4) build a cluster starting at the location with highest contrast.

FIGURE 2

Structure of the toolbox to determine the parameter settings and generate models.

FIGURE 3

Four generated 3D microcalcification cluster models with versatility of calcifications increasing from left to right. All clusters are 30 × 30 × 30  mm and contain 20 microcalcifications.

FIGURE 4

Two examples of generated 3D microcalcification cluster models of a specific clinical type inserted in a 2D mammographic “For presentation” image: (a) shows a milk‐of‐calcium‐type cluster; and (b) a coarse heterogeneous‐type cluster.

FIGURE 5

A pair of generated 2D microcalcification cluster models with low variety for (a), and more variety for (b). Both clusters are obtained for the same location in the same mammographic image.

FIGURE 6

Two examples of generated 2D microcalcification cluster models of a specific clinical type inserted in a 2D mammographic “For presentation” image: (a) a typically benign cluster; and (b) a cluster of suspicious morphology.

FIGURE 7

Four examples of generated models inserted in different types of mammographic images. (a) A reconstructed slice of a 3D punctate cluster inserted in a “For Processing” DBT image acquired on a Siemens MAMMOMAT Revelation system; (b) A 3D pleomorphic cluster inserted in a phantom breast and projected by the VICTRE platform to obtain a DM image; (c) A 2D cluster of suspicious morphology in a “For Processing” DM image acquired on a GEHC Essential system; (d) A 2D cluster of suspicious morphology in a “For Presentation” DM image acquired on a Siemens MAMMOMAT Inspiration system.

FIGURE 8

Results of a validation study of images with 3D microcalcification cluster models inserted. Scores ranged from 1: “most probably benign” to 6: “most probably malignant” for the assessment of the level of malignancy, and from 1: “extremely confident simulated” to 6: “extremely confident real” for the assessment of the realism.

FIGURE 9

Results of a validation study of images with 2D microcalcification cluster models inserted. Scores ranged from 1: “most probably benign” to 6: “most probably malignant” for the assessment of the level of malignancy, and from 1: “extremely confident simulated” to 6: “extremely confident real” for the assessment of the realism.