Automatic computer-aided diagnosis system for mass detection and classification in mammography
- PDF / 3,357,042 Bytes
- 33 Pages / 439.642 x 666.49 pts Page_size
- 7 Downloads / 222 Views
Automatic computer-aided diagnosis system for mass detection and classification in mammography Ilhame Ait Lbachir1
· Imane Daoudi1 · Saadia Tallal1
Received: 11 October 2019 / Revised: 25 June 2020 / Accepted: 13 July 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Mammography is currently the most powerful technique for early detection of breast cancer. To assist radiologists to better interpret mammogram images, computer-aided detection and diagnosis (CAD) systems have been proposed. This paper proposes a complete CAD system for mass detection and diagnosis, which consists of four steps. The first step consists of the preprocessing where the image is enhanced and the noise removed. In the second step, the abnormalities are segmented using the proposed HRAK algorithm. In the third step, the false positives are reduced using texture and shape features and the bagged trees classifier. Finally, the support vector machine (SVM) is used to classify the abnormalities as malignant or benign. The proposed CAD system is verified with both the MIAS and CBIS-DDSM databases. The experimental results proved to be successful. The accuracy detection rate achieves 93,15% for sensitivity and 0,467 FPPI for MIAS and 90,85% for sensitivity and 0,65 FPPI for CBIS-DDSM. The accuracy classification rate achieves 94,2% and the AUC 0,95 for MIAS and 90,44% and 0,9 for CBIS-DDSM. Keywords Computer-aided diagnosis · Mass detection · Mammography · Mass classification
1 Introduction Breast cancer is a global health issue among women worldwide. Only early detection can reduce the rate of mortality and increase recovery. Thus, early detection is crucial to improve breast cancer prognostic. There are multiple tools and control strategies to visualize and analyze breast cancer, such as thermography, echography, MRI and ultrasound [24]. Ilhame Ait Lbachir
[email protected] Imane Daoudi [email protected] Saadia Tallal [email protected] 1
Engineering Research Laboratory, ENSEM-Hassan II University, BP: 8118, Casablanca, Morocco
Multimedia Tools and Applications
Nonetheless, mammography is currently the most efficient technique for early detection of breast cancer. Mammography is a breast image that uses low-dose x-rays to visualize and detect cancer. However, the analysis of masses in mammography remains a challenging task due to the low contrast of the images and the density of the breast tissue. Therefore, radiologists can miss sometimes the detection of abnormalities if they only diagnose by experience. That’s why in the few last decade, CAD systems have been developed. A CAD system is a computer-based system designed to help and assist radiologists in their decisions and interpretations [16]. We distinguish two types of CAD systems: Computer-aided detection systems (CADe) and Computer-aided diagnosis systems (CADx). The main difference is that the first aims to identify and locate abnormal signs in the breast while the second aims to evaluate and classify a lesion into malignant/ben
Data Loading...
