Breast Mass Detection in Mammography Based on Image Template Matching and CNN

Abstract

In recent years, computer vision technology has been widely used in the field of medical image processing. However, there is still a big gap between the existing breast mass detection methods and the real-world application due to the limited detection accuracy. It is known that humans locate the regions of interest quickly and further identify whether these regions are the targets we found. In breast cancer diagnosis, we locate all the potential regions of breast mass by glancing at the mammographic image from top to bottom and from left to right, then further identify whether these regions are a breast mass. Inspired by the process of human detection of breast mass, we proposed a novel breast mass detection method to detect breast mass on a mammographic image by stimulating the process of human detection. The proposed method preprocesses the mammographic image via the mathematical morphology method and locates the suspected regions of breast mass by the image template matching method. Then, it obtains the regions of breast mass by classifying these suspected regions into breast mass and background categories using a convolutional neural network (CNN). The bounding box of breast mass obtained by the mathematical morphology method and image template matching method are roughly due to the mathematical morphology method, which transforms all of the brighter regions into approximate circular areas. For regression of a breast mass bounding box, the optimal solution should be searched in the feasible region and the Particle Swarm Optimization (PSO) is suitable for solving the problem of searching the optimal solution within a certain range. Therefore, we refine the bounding box of breast mass by the PSO algorithm. The proposed breast mass detection method and the compared detection methods were evaluated on the open database Digital Database for Screening Mammography (DDSM). The experimental results demonstrate that the proposed method is superior to all of the compared detection methods in detection performance.

A Newly Hybrid Version of African Vultures Optimization Algorithm and Sine Cosine Algorithm for Mammographic Masses and its Diagnosis

“…In the initial stage the result of all phase contain in preprocessing unit is demonstrated by fig. (11).Further, two different very closely spaced mass members possibly will be bonded and preserved as a lone if the distance (dist) amid the very close value on the separate limits is < the threshold. All this procedure has been demonstrated in fig.…”

“…al. [11] proposed the CAD system containing majorly four phases: preprocessing of mammograms using various morphological operations, finding the region of interest, identifying the breast mass in the obtained ROI and creating bounding box around the breast mass. After preprocessing the mammogram image, the region of interest is found using template matching method and identification of suspicious breast mass is done through CNN model.…”

Systematic analysis of the test design and performance of AI/ML-based medical devices approved for triage/detection/diagnosis in the USA and Japan

“…The constantly updated and improved head CT, mammogram, and chest CT databases may be one of the reasons for such technological advances. Indeed, digital databases such as the Digital Database for Screening Mammography (DDSM) 85 , or ChexPert 86 are known for their large-scale database and are frequently used in studies on image analysis algorithm development. Furthermore, the National Institute of Health created the ChestNet-14 87 dataset available through Kaggle (an online community periodically organizing data science competitions).…”

A Survey of Convolutional Neural Network in Breast Cancer

“…Sun et al [ 182 ] were inspired by human detection to propose a novel model for breast cancer detection based on the mammographic image. The mathematical morphology method was used to preprocess the images.…”