NESTOR DE BARROS

(Fonte: Lattes)
Índice h a partir de 2011
10
Lattes
Projetos de Pesquisa
Unidades Organizacionais
Departamento de Radiologia, Faculdade de Medicina - Docente
Instituto de Radiologia, Hospital das Clínicas, Faculdade de Medicina - Médico
LIM/44 - Laboratório de Ressonância Magnética em Neurorradiologia, Hospital das Clínicas, Faculdade de Medicina

Filtros

Limpar filtros

Configurações

Autor: BARROS, Nestor de ×

Resultados de Busca

Agora exibindo 1 - 10 de 27
  • bookPart
    Carcinoma de mama: diagnóstico
    (2016) MENDES, Daniele Carvalho Calvano; CHALA, Luciano Fernandes; BARROS, Nestor de; FILASSI, Jose Roberto
  • article 4 Citação(ões) na Scopus
    Radiological findings of breast involvement in benign and malignant systemic diseases
    (2018) MATSUMOTO, Renato Augusto Eidy Kiota; CATANI, Juliana Hiraoka; CAMPOY, Mirela Liberato; OLIVEIRA, Arthur Magalhães; BARROS, Nestor de
    Abstract Although the primary purpose of periodic mammograms in screening programs is to identify lesions suspected of being carcinomas, the findings are often related to systemic (benign or malignant) diseases, rather than breast cancer. Although the involvement of breast structures in systemic diseases is unusual, it can be included in the differential diagnosis of masses, skin changes, calcifications, asymmetry, and axillary lymphadenopathy. The main diagnostic entities that can be associated with such involvement are diabetes, chronic kidney disease, heart diseases, connective tissue diseases, HIV infection, lymphoma, leukemia, and metastases from primary tumors at other sites. In many cases, information related to knowledge and treatment of chronic diseases is not available to the radiologist at the time of evaluation of the mammography findings. The purpose of this essay is to offer relevant pictorial information to the general radiologist about systemic diseases involving the breast, expanding the range of differential diagnoses in order to avoid unnecessary invasive procedures.
  • conferenceObject
    Exploratory Learning with Convolutional Autoencoder for Discrimination of Architectural Distortion in Digital Mammography
    (2019) OLIVEIRA, Helder C. R. de; MELO, Carlos F. E.; CATANI, Juliana H.; BARROS, Nestor de; VIEIRA, Marcelo A. da Costa
    This work presents a deep learning approach based on autoencoder to improve the detection of architectural distortion (AD) in digital mammography. AD can be the earliest sign of breast cancer, appearing before the formation of any mass or calcification. However, it is very difficult to be detected and almost 50% of the cases are missed by the radiologists. Thus, we designed an autoencoder, based on a convolutional neural network (CNN), to work as a feature descriptor in a computer-aided detection (CAD) pipeline with the objective of detecting AD in digital mammography. This model was trained with 140,000 regions-of-interest (ROI) extracted from clinical mammograms. These samples were divided in two groups, with and without AD, according to the radiologist's report. Validation was done comparing the classifier performance when using the proposed autoencoder and other well-known feature descriptors, commonly used for the task of detecting AD in digital mammograms. The results showed that the performance of the autoencoder is slightly higher than that of other descriptors. However, the complexity and the computational cost of the autoencoder is much higher when compared to the hand-crafted descriptors.
  • bookPart
    Aplicação do ACR BI-RADS® nos métodos de imagem em mama
    (2017) BARROS, Nestor de; DEBS, Cecília Lemos; CASTRO, Flávio Spinola; COSTENARO, Marco; JACINTO, Bruna Maria Trompson; TUCUNDUVA, Tatiana
  • article 8 Citação(ões) na Scopus
    Suspicious amorphous microcalcifications detected on full-field digital mammography: correlation with histopathology
    (2018) FERREIRA, Vera Christina Camargo de Siqueira; ETCHEBEHERE, Elba Cristina Sá de Camargo; BEVILACQUA, José Luiz Barbosa; BARROS, Nestor de
    Abstract Objective: To evaluate suspicious amorphous calcifications diagnosed on full-field digital mammography (FFDM) and establish correlations with histopathology findings. Materials and Methods: This was a retrospective study of 78 suspicious amorphous calcifications (all classified as BI-RADS® 4) detected on FFDM. Vacuum-assisted breast biopsy (VABB) was performed. The histopathological classification of VABB core samples was as follows: pB2 (benign); pB3 (uncertain malignant potential); pB4 (suspicion of malignancy); and pB5 (malignant). Treatment was recommended for pB5 lesions. To rule out malignancy, surgical excision was recommended for pB3 and pB4 lesions. Patients not submitted to surgery were followed for at least 6 months. Results: Among the 78 amorphous calcifications evaluated, the histopathological analysis indicated that 8 (10.3%) were malignant/suspicious (6 classified as pB5 and 2 classified as pB4) and 36 (46.2%) were benign (classified as pB2). The remaining 34 lesions (43.6%) were classified as pB3: 33.3% were precursor lesions (atypical ductal hyperplasia, lobular neoplasia, or flat epithelial atypia) and 10.3% were high-risk lesions. For the pB3 lesions, the underestimation rate was zero. Conclusion: The diagnosis of precursor lesions (excluding atypical ductal hyperplasia, which can be pB4 depending on the severity and extent of the lesion) should not necessarily be considered indicative of underestimation of malignancy. Suspicious amorphous calcifications correlated more often with precursor lesions than with malignant lesions, at a ratio of 3:1.
  • conferenceObject
    Detection of Architectural Distortion with Deep Convolutional Neural Network and Data Augmentation of Limited Dataset
    (2019) COSTA, Arthur C.; OLIVEIRA, Helder C. R.; CATANI, Juliana H.; BARROS, Nestor de; MELO, Carlos F. E.; VIEIRA, Marcelo A. C.
    Early detection of breast cancer can increase treatment efficiency. One of the earliest signs of breast cancer is the Architectural Distortion (AD), which is a subtle contraction of the breast tissue, most of the time unnoticeable. A lot of techniques have been proposed over the years to aid the detection of AD in digital mammography but only a few using a deep learning approach. One of the most successful algorithms of deep neural architecture are the Convolutional Neural Networks (CNNs). However, to assure better CNN performance, the training step requires a large volume of data. This paper presents a deep CNN architecture designed for the automatic detection of AD in digital mammography images. For the training step, we considered the data augmentation approach, to overcome the limitation of clinical dataset. CNN performance was evaluated in terms of Receiver Operating Characteristic (ROC). The measured area under the ROC curve (AUC) was 0:87 for the proposed CNN in the task of AD detection in digital mammography.
  • article 5 Citação(ões) na Scopus
    Normalized glandular dose (DgN) coefficients from experimental mammographic x-ray spectra
    (2019) SANTOS, Josilene C.; TOMAL, Alessandra; BARROS, Nestor de; COSTA, Paulo R.
    Mean glandular dose is the quantity used for dosimetry in mammography and depends on breast-related characteristics, such as thickness and density, and on the x-ray spectrum used for breast imaging. This work aims to present an experimentally-based method to derive polyenergetic normalized glandular dose coefficients (DgN(p)) from the spectral difference between x-ray spectra incident and transmitted through breast phantoms with glandular/adipose proportions of 30/70 and 50/50 and thicknesses up to 4.5 cm. The spectra were produced by a Mammomat 3000 Nova system using radiographic techniques commonly applied for imaging compressed breast thickness lower than 6 cm (Mo/Mo, Mo/Rh and W/Rh spectra at 26 and 28 kVp). DgN(p) coefficients were compared with values estimated using Boones' method and data from breast images (DICOM Organ Dose and VolparaDose calculations). The DgN(p) were also evaluated in layers into the phantoms (depth-DgN(p)) using both x-ray spectra and thermoluminescent dosimeters (TLD-100). Maximum differences between DgN(p) from the method presented in this study and results using Boone's method was 11%, with larger differences for Mo/Rh spectra in relation to the Mo/Mo. The DgN(p) maximum differences to the coefficients obtained using patient images were 8.0%, for the DgN calculated using Volpara and 6.4% for the DgN from DICOM Organ Dose, for a 4.5 cm breast phantom with 30% glandularity. The DgN(p) estimated from the depth-DgN(p) distributions differ up to 5.2% to the coefficients obtained using the pair incident-transmitted spectra to calculate the DgN(p) directly in the whole phantom. The depth-DgN(p) distributions estimated with TLDs were consistent with the results observed using the experimental spectra, with maximum difference of 3.9%. In conclusion, polyenergetic x-ray spectrometry proved to be an applicable tool for research in dosimetry in mammography allowing spectral characterization. This approach can also be useful for investigation of the influence of x-ray spectra on glandular dose.
  • bookPart
    Métodos de imagem no diagnóstico das doenças mamárias
    (2017) BRESCIANI, Bárbara Helou; CASTRO, Flávio Spinola; MATSUMOTO, Renato Augusto Eidy Kiota; SHIMIZU, Carlos; BARROS, Nestor de
  • conferenceObject
    Reduction of false-positives in a CAD scheme for automated detection of architectural distortion in digital mammography
    (2018) OLIVEIRA, Helder C. R. de; MENCATTINI, Arianna; CASTI, Paola; MARTINELLI, Eugenio; NATALE, Corrado di; CATANI, Juliana H.; BARROS, Nestor de; MELO, Carlos F. E.; GONZAGA, Adilson; VIEIRA, Marcelo A. C.
    This paper proposes a method to reduce the number of false-positives (FP) in a computer-aided detection (CAD) scheme for automated detection of architectural distortion (AD) in digital mammography. AD is a subtle contraction of breast parenchyma that may represent an early sign of breast cancer. Due to its subtlety and variability, AD is more difficult to detect compared to microcalcifications and masses, and is commonly found in retrospective evaluations of false-negative mammograms. Several computer-based systems have been proposed for automated detection of AD in breast images. The usual approach is automatically detect possible sites of AD in a mammographic image (segmentation step) and then use a classifier to eliminate the false-positives and identify the suspicious regions (classification step). This paper focus on the optimization of the segmentation step to reduce the number of FPs that is used as input to the classifier. The proposal is to use statistical measurements to score the segmented regions and then apply a threshold to select a small quantity of regions that should be submitted to the classification step, improving the detection performance of a CAD scheme. We evaluated 12 image features to score and select suspicious regions of 74 clinical Full-Field Digital Mammography (FFDM). All images in this dataset contained at least one region with AD previously marked by an expert radiologist. The results showed that the proposed method can reduce the false positives of the segmentation step of the CAD scheme from 43.4 false positives (FP) per image to 34.5 FP per image, without increasing the number of false negatives.
  • bookPart
    Mama
    (2019) HSIEH, Su Jin Kim; ENDO, Érica; ZANETTA, Vitor Chiarini; BARROS, Nestor de; SHIMIZU, Carlos; BRESCIANI, Barbara H.; CASTRO, Flavio Spinola; COSTENARO, Marco Antonio; TUCUNDUVA, Tatiana Cardoso de Mello; FERREIRA, Vera C. C. S.