A Microcalcification Detection System in Mammograms based on ANN Clustering

Risultato della ricerca: Conference contribution

Abstract

Breast cancer is one of the leading causes to women mortality in the world. Clustered microcalcifications (MCs) in mammograms can be an important early sign of breast cancer, the detection is important to prevent and treat the disease. In this work, we present a novel method for the detection of MCs in mammograms which consists of regions of Interest (ROIs) segmentation, based on a spatial filter that allows the detection of small and large microcalcifications, clustering and classification of MCs by Artificial Neural Network. The system has been tested on a public dataset of digital images and compared with previous approaches. The results demonstrate that the proposed approach could achieve significantly higher FROC curves: our CAD system achieve a cluster-based sensitivity of 70, 80, and 90 % at 0.31, 0.69, and 1.6 FPs/image, respectively.
Lingua originaleEnglish
Titolo della pubblicazione ospite2018 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2018 - Proceedings
Pagine1-4
Numero di pagine4
Stato di pubblicazionePublished - 2018

Fingerprint

Calcinosis
Cluster Analysis
breast
cancer
mortality
computer aided design
Breast Neoplasms
filters
causes
sensitivity
curves
Mortality

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging
  • Nuclear and High Energy Physics

Cita questo

Raso, G., Cascio, D., Taormina, V., & Abbene, L. (2018). A Microcalcification Detection System in Mammograms based on ANN Clustering. In 2018 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2018 - Proceedings (pagg. 1-4)

A Microcalcification Detection System in Mammograms based on ANN Clustering. / Raso, Giuseppe; Cascio, Donato; Taormina, Vincenzo; Abbene, Leonardo.

2018 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2018 - Proceedings. 2018. pag. 1-4.

Risultato della ricerca: Conference contribution

Raso, G, Cascio, D, Taormina, V & Abbene, L 2018, A Microcalcification Detection System in Mammograms based on ANN Clustering. in 2018 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2018 - Proceedings. pagg. 1-4.
Raso G, Cascio D, Taormina V, Abbene L. A Microcalcification Detection System in Mammograms based on ANN Clustering. In 2018 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2018 - Proceedings. 2018. pag. 1-4
Raso, Giuseppe ; Cascio, Donato ; Taormina, Vincenzo ; Abbene, Leonardo. / A Microcalcification Detection System in Mammograms based on ANN Clustering. 2018 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2018 - Proceedings. 2018. pagg. 1-4
@inproceedings{aaca1f71837c4b229e10d44b08aa1b0b,
title = "A Microcalcification Detection System in Mammograms based on ANN Clustering",
abstract = "Breast cancer is one of the leading causes to women mortality in the world. Clustered microcalcifications (MCs) in mammograms can be an important early sign of breast cancer, the detection is important to prevent and treat the disease. In this work, we present a novel method for the detection of MCs in mammograms which consists of regions of Interest (ROIs) segmentation, based on a spatial filter that allows the detection of small and large microcalcifications, clustering and classification of MCs by Artificial Neural Network. The system has been tested on a public dataset of digital images and compared with previous approaches. The results demonstrate that the proposed approach could achieve significantly higher FROC curves: our CAD system achieve a cluster-based sensitivity of 70, 80, and 90 {\%} at 0.31, 0.69, and 1.6 FPs/image, respectively.",
author = "Giuseppe Raso and Donato Cascio and Vincenzo Taormina and Leonardo Abbene",
year = "2018",
language = "English",
isbn = "978-1-5386-8494-8",
pages = "1--4",
booktitle = "2018 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2018 - Proceedings",

}

TY - GEN

T1 - A Microcalcification Detection System in Mammograms based on ANN Clustering

AU - Raso, Giuseppe

AU - Cascio, Donato

AU - Taormina, Vincenzo

AU - Abbene, Leonardo

PY - 2018

Y1 - 2018

N2 - Breast cancer is one of the leading causes to women mortality in the world. Clustered microcalcifications (MCs) in mammograms can be an important early sign of breast cancer, the detection is important to prevent and treat the disease. In this work, we present a novel method for the detection of MCs in mammograms which consists of regions of Interest (ROIs) segmentation, based on a spatial filter that allows the detection of small and large microcalcifications, clustering and classification of MCs by Artificial Neural Network. The system has been tested on a public dataset of digital images and compared with previous approaches. The results demonstrate that the proposed approach could achieve significantly higher FROC curves: our CAD system achieve a cluster-based sensitivity of 70, 80, and 90 % at 0.31, 0.69, and 1.6 FPs/image, respectively.

AB - Breast cancer is one of the leading causes to women mortality in the world. Clustered microcalcifications (MCs) in mammograms can be an important early sign of breast cancer, the detection is important to prevent and treat the disease. In this work, we present a novel method for the detection of MCs in mammograms which consists of regions of Interest (ROIs) segmentation, based on a spatial filter that allows the detection of small and large microcalcifications, clustering and classification of MCs by Artificial Neural Network. The system has been tested on a public dataset of digital images and compared with previous approaches. The results demonstrate that the proposed approach could achieve significantly higher FROC curves: our CAD system achieve a cluster-based sensitivity of 70, 80, and 90 % at 0.31, 0.69, and 1.6 FPs/image, respectively.

UR - http://hdl.handle.net/10447/376278

UR - http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8821248

M3 - Conference contribution

SN - 978-1-5386-8494-8

SP - 1

EP - 4

BT - 2018 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2018 - Proceedings

ER -