Comparing Mammographic Images

Ângelo, Michele Fúlvia; Patrocinio, Ana Claudia; Schiabel, Homero; Medeiros, Regina Bitelli; Pires, Silvio Ricardo

doi:10.1109/memb.2008.919024

Cited by 5 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although it is very important to detect and classify masses and microcalcifications, the correct image preparation using preprocessing and editing tools is a crucial step [40, 41]. When digital images and a display system are used, the system must be able to simulate the actual tools that are used by specialists in printed images analysis (Figure 5).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

CADe System Integrated within the Electronic Health Record

Vállez

Bueno

Déniz

et al. 2013

BioMed Research International

View full text Add to dashboard Cite

The latest technological advances and information support systems for clinics and hospitals produce a wide range of possibilities in the storage and retrieval of an ever-growing amount of clinical information as well as in detection and diagnosis. In this work, an Electronic Health Record (EHR) combined with a Computer Aided Detection (CADe) system for breast cancer diagnosis has been implemented. Our objective is to provide to radiologists a comprehensive working environment that facilitates the integration, the image visualization, and the use of aided tools within the EHR. For this reason, a development methodology based on hardware and software system features in addition to system requirements must be present during the whole development process. This will lead to a complete environment for displaying, editing, and reporting results not only for the patient information but also for their medical images in standardised formats such as DICOM and DICOM-SR. As a result, we obtain a CADe system which helps in detecting breast cancer using mammograms and is completely integrated into an EHR.

show abstract

Section: Methodsmentioning

confidence: 99%

“…There are several preprocessing techniques that improve image perception highlighting some areas, illuminating the image, or removing the noise [40, 41]. Contrast enhancement is one of the most widely used techniques for improving image visualization and has great application oriented to medical images.…”

Section: Methodsmentioning

confidence: 99%

CADe System Integrated within the Electronic Health Record

Vállez

Bueno

Déniz

et al. 2013

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…The authors would like to thank Capes, FAPESP grants #2009/16206-1, #2013/20387-7 and #2011/14094-1, and CNPq grants #303182/2011-3 and #470571/ 2013-6. has increased in the last years, technologies such as ComputerAided Diagnosis-based (CAD) schemes have been the subject of extensive researches in the past two decades [8], [9], [10], [11], [12], [13]. Intelligent techniques are used as classification procedures in CAD schemes [14] and their performances depend on several classification stages, as well as the extraction and selection of suitable features [14].…”

Section: Introductionmentioning

confidence: 99%

Optimum-Path Forest Applied for Breast Masses Classification

Ribeiro

Costa

Papa

et al. 2014

2014 IEEE 27th International Symposium on Computer-Based Medical Systems

View full text Add to dashboard Cite

Abstract-In Computer-Aided Diagnosis-based schemes in mammography analysis each module is interconnected, which directly affects the system operation as a whole. The identification of mammograms with and without masses is highly needed to reduce the false positive rates regarding the automatic selection of regions of interest for further image segmentation. This study aims to evaluate the performance of three techniques in classifying regions of interest as containing masses or without masses (without clinical findings), as well as the main contribution of this work is to introduce the Optimum-Path Forest (OPF) classifier in this context, which has never been done so far. Thus, we have compared OPF against with two sorts of neural networks in a private dataset composed by 120 images: Radial Basis Function and Multilayer Perceptron (MLP). Texture features have been used for such purpose, and the experiments have demonstrated that MLP networks have been slightly better than OPF, but the former is much faster, which can be a suitable tool for real-time recognition systems.

show abstract

“…Com o objetivo de auxiliar no diagnóstico de achados mamográficos, tecnologias como os esquemas de Computer-Aided Diagnosis (CAD) -ou diagnóstico auxiliado por computador -têm sido alvo de pesquisas extensivas pelas últimas duas décadas (DOI et al, 1995;DOI, MACMAHON e KATSURAGAWA, 1997;DOI et al, 1999;GIGER, 1999;LI et al, 2010;ARBACH et al, 2003;BALL et al, 2004;PATROCINIO et al 2004a;ZHENG et al, 2004;ZWIGGELAAR et al, 2004;RIBEIRO et al, 2007aRIBEIRO et al, , 2007bZHENG, 2008, p. 325;ANGELO et al, 2008;ZHANG, 2012). Existem dois principais tipos de esquemas CAD: o CADe (relativo a Computer-Aided Detection), que está mais voltado para a detecção de estruturas de interesse, ou seja, para ajudar radiologistas a encontrar sinais de interesse mamograficamente ocultos à visão humana; e o CADx (relativo ao propriamente Computer-Aided Diagnosis), que funciona como um segundo observador, sendo mais amplo e responsável em dar uma opnião sobre uma específica lesão.…”

Section: Lista De Abreviaturas E Siglasunclassified

Esquema CADx para classificação de nódulos em imagens mamográficas digitais baseado na segmentação pelo modelo EICAMM

Ribeiro¹

View full text Add to dashboard Cite

Ao concluir mais uma etapa da minha vida acadêmica, minha imensa gratidão a Deus, por dar-me forças a cada dia e saúde para continuar. A minha filha Barbara Bellin de Carvalho, que nasceu durante o desenvolvimento deste trabalho, por ser um anjo, carinhosa, delicada, uma florzinha... Pela paciência ao me esperar durante as horas que não pude estar com ela. Por vibrar com a minha chegada! Ao meu marido Rodrigo Ferreira de Carvalho e aos meus pais José Urias Batista Ribeiro e Vera Lúcia Bellin Ribeiro, por todo incentivo e cuidados com a Barbara enquanto eu desenvolvia as pesquisas e experimentos do doutorado. Ao Prof. Dr. Homero Schiabel, que nos anos de convivência, contribuiu para meu crescimento científico. À Profª Drª Roseli A. F. Romero pelo apoio, empenho, dedicação e toda a ajuda fornecida na realização deste trabalho. À Profª Drª Patrícia R. Oliveira pela contribuição científica ao desenvolver a melhoria do método ICAMM que resultou no modelo EICAMM (Enhanced ICA Misture Model) em seu trabalho de doutorado "Métodos auto-organizáveis para segmentação de imagens" e por toda ajuda fornecida para o desenvolvimento das pesquisas sobre segmentação. Aos meus ex-alunos da Universidade Sagrado Coração (USC) e amigos de laboratório Ms. Renan Caldeira Menechelli e Ms. Karem D. Marcomini Marcomini obrigada por toda a contribuição no desenvolvimento deste trabalho. Ao Ms. José Rogério B. Barbosa Filho por fornecer as imagens do banco DDSM. A todos que direta ou indiretamente contribuíram para o desenvolvimento desta pesquisa. "A mente que se abre a uma nova ideia jamais volta ao seu tamanho original."

show abstract

Comparing Mammographic Images

Cited by 5 publications

References 24 publications

CADe System Integrated within the Electronic Health Record

CADe System Integrated within the Electronic Health Record

Optimum-Path Forest Applied for Breast Masses Classification

Esquema CADx para classificação de nódulos em imagens mamográficas digitais baseado na segmentação pelo modelo EICAMM

Contact Info

Product

Resources

About