Characterization of the imaging settings in screening mammography using a tracking and reporting system: A multi-center and multi-vendor analysis.

A tracking and reporting system was developed to monitor radiation dose in X-ray breast imaging. We used our tracking system to characterize and compare the mammographic practices of five breast imaging centers located in the United States and Brazil. Clinical data were acquired using eight mammography systems comprising three modalities: computed radiography (CR), full-field digital mammography (FFDM), and digital breast tomosynthesis (DBT). Our database consists of metadata extracted from 334,234 images. We analyzed distributions and correlations of compressed breast thickness (CBT), compression force, target-filter combinations, X-ray tube voltage, and average glandular dose (AGD). AGD reference curves were calculated based on AGD distributions as a function of CBT. These curves represent an AGD reference for a particular population and system. Differences in AGD and imaging settings were attributed to a combination of factors, such as improvements in technology, imaging protocol, and patient demographics. The tracking system allows the comparison of various imaging settings used in screening mammography, as well as the tracking of patient- and population-specific breast data collected from different populations.

Design and implementation of a radiation dose tracking and reporting system for mammography and digital breast tomosynthesis.

A tracking system has been implemented to monitor radiation dose for digital mammography (DM) and digital breast tomosynthesis (DBT). This system communicates with a PACS through DICOM messages that allow the image metadata to be stored in a relational database. The tracking system accepts X-ray breast images, maps the image metadata into a SQL database, and allows a client-side application to report the data using a business intelligence framework. The database contains the DICOM information of 54,244 studies (235,225 images) acquired from four Selenia Dimensions systems. The average time to receive the images, and then extract and write the metadata into the database is 2.28 s for a DM and 3.84 s for a DBT image. Using the stored metadata, physics reports are generated based on chosen criteria (i.e., system model, mammography unit, breast data, acquisition techniques, physician, etc.). Our results show that the mean average glandular dose (AGD) varies significantly with compressed breast thickness and age. We observed an overall dose increase of 25.6% between DM and DBT (1.76 vs 2.21 mGy).

Evaluation of a Computer-Aided Diagnosis System in the Classification of Lesions in Breast Strain Elastography Imaging.

Purpose: Evaluation of the performance of a computer-aided diagnosis (CAD) system based on the quantified color distribution in strain elastography imaging to evaluate the malignancy of breast tumors. Methods: The database consisted of 31 malignant and 52 benign lesions. A radiologist who was blinded to the diagnosis performed the visual analysis of the lesions. After six months with no eye contact on the breast images, the same radiologist and other two radiologists manually drew the contour of the lesions in B-mode ultrasound, which was masked in the elastography image. In order to measure the amount of hard tissue in a lesion, we developed a CAD system able to identify the amount of hard tissue, represented by red color, and quantify its predominance in a lesion, allowing classification as soft, intermediate, or hard. The data obtained with the CAD system were compared with the visual analysis. We calculated the sensitivity, specificity, and area under the curve (AUC) for the classification using the CAD system from the manual delineation of the contour by each radiologist. Results: The performance of the CAD system for the most experienced radiologist achieved sensitivity of 70.97%, specificity of 88.46%, and AUC of 0.853. The system presented better performance compared with his visual diagnosis, whose sensitivity, specificity, and AUC were 61.29%, 88.46%, and 0.829, respectively. The system obtained sensitivity, specificity, and AUC of 67.70%, 84.60%, and 0.783, respectively, for images segmented by Radiologist 2, and 51.60%, 92.30%, and 0.771, respectively, for those segmented by the Resident. The intra-class correlation coefficient was 0.748. The inter-observer agreement of the CAD system with the different contours was good in all comparisons. Conclusions: The proposed CAD system can improve the radiologist performance for classifying breast masses, with excellent inter-observer agreement. It could be a promising tool for clinical use.

Application of Artificial Neural Network Models in Segmentation and Classification of Nodules in Breast Ultrasound Digital Images.

This research presents a methodology for the automatic detection and characterization of breast sonographic findings. We performed the tests in ultrasound images obtained from breast phantoms made of tissue mimicking material. When the results were considerable, we applied the same techniques to clinical examinations. The process was started employing preprocessing (Wiener filter, equalization, and median filter) to minimize noise. Then, five segmentation techniques were investigated to determine the most concise representation of the lesion contour, enabling us to consider the neural network SOM as the most relevant. After the delimitation of the object, the most expressive features were defined to the morphological description of the finding, generating the input data to the neural Multilayer Perceptron (MLP) classifier. The accuracy achieved during training with simulated images was 94.2%, producing an AUC of 0.92. To evaluating the data generalization, the classification was performed with a group of unknown images to the system, both to simulators and to clinical trials, resulting in an accuracy of 90% and 81%, respectively. The proposed classifier proved to be an important tool for the diagnosis in breast ultrasound.

Contribution to the radiation protection for sunglasses standards.

Literature establishes safe limits on the exposure of the eyes to ultraviolet radiation, for the range of 180-400 nm, including spectrally weighted and the total ultraviolet radiant exposure. Most standards for sunglasses protection only require ultraviolet protection in the spectral range of 280-380 nm to ensure the limits for effective spectrally weighted radiant exposure. Calculations of these limits were performed for 27 Brazilian state capitals, and they led to a change in the upper UVA limit to 400 nm on the 2013 review of the Brazilian standard. Moreover, because the sunlight irradiance in Brazil is quite high, integration over the 280- to 400-nm range yields an ultraviolet radiant exposure that is an average of 49% greater than that for the 280- to 380-nm range. These conclusions suggest revision on the standards.

Mammographic image denoising and enhancement using the Anscombe transformation, adaptive wiener filtering, and the modulation transfer function.

A new restoration methodology is proposed to enhance mammographic images through the improvement of contrast features and the simultaneous suppression of noise. Denoising is performed in the first step using the Anscombe transformation to convert the signal-dependent quantum noise into an approximately signal-independent Gaussian additive noise. In the Anscombe domain, noise is filtered through an adaptive Wiener filter, whose parameters are obtained by considering local image statistics. In the second step, a filter based on the modulation transfer function of the imaging system in the whole radiation field is applied for image enhancement. This methodology can be used as a preprocessing module for computer-aided detection (CAD) systems to improve the performance of breast cancer screening. A preliminary assessment of the restoration algorithm was performed using synthetic images with different levels of quantum noise. Afterward, we evaluated the effect of the preprocessing on the performance of a previously developed CAD system for clustered microcalcification detection in mammographic images. The results from the synthetic images showed an increase of up to 11.5 dB (p = 0.002) in the peak signal-to-noise ratio. Moreover, the mean structural similarity index increased up to 8.3 % (p < 0.001). Regarding CAD performance, the results suggested that the preprocessing increased the detectability of microcalcifications in mammographic images without increasing the false-positive rates. Receiver operating characteristic analysis revealed an average increase of 14.1 % (p = 0.01) in overall CAD performance when restored image sets were used.

Online mammographic images database for development and comparison of CAD schemes.

Considering the difficulties in finding good-quality images for the development and test of computer-aided diagnosis (CAD), this paper presents a public online mammographic images database free for all interested viewers and aimed to help develop and evaluate CAD schemes. The digitalization of the mammographic images is made with suitable contrast and spatial resolution for processing purposes. The broad recuperation system allows the user to search for different images, exams, or patient characteristics. Comparison with other databases currently available has shown that the presented database has a sufficient number of images, is of high quality, and is the only one to include a functional search system.

A device for quality evaluation of operational parameters in mammography X-ray tubes / Um dispositivo para avaliação de qualidade de parâmetros operacionais em tubos de raios X mamográficos

Esse trabalho descreve o desenvolvimento de um sistema para medição de importantes parâmetros operacionais de equipamentos mamográficos, como kVp, corrente de tubo, tempo de exposição, dose e camada semi-redutora (CSR) em qualquer posição do campo. Esse sistema baseia-se num dispositivo com sensor semicondutor de Si, posicionado sob o tubo de raios X (sobre a mesinha do equipamento,por exemplo), que detecta os fótons e produz uma correnteelétrica proporcional à intensidade do feixe. Esse sinal é enviado a uma placa digitalizadora acoplada a um notebook no qual um software realiza sua leitura e tratamento. A medição da kVp se baseia na relação entre dois sinais, um filtrado e outro não (referência) a partir do mesmo sensor. Esse sinal é obtido detectando-se a saída do sensor sobre o qual gira uma cunha de alumínio circular durante uma exposição de raios X. Com uma única exposição, o software permite determinar os parâmetros pela análise desse sinal. Além disso, a CSR em qualquer posição do campo pode ser determinada a partir de um procedimento de simulação computacional desenvolvido previamente. Curvas de calibração são armazenadas para queo software compare a leitura real do sensor com os dados armazenados para determinar a precisão de operação do tubo sob investigação. Testes de desenvolvimento com uma unidade Trex Medical Contour 2000 mostraram que a resposta do sistema é concordante com dispositivos calibrados usados para verificar os parâmetros. Uma vantagem desse sistema é a possibilidade de armazenar umagrande quantidade de informações requisitadas por programas de controle de qualidade.

This work describes the development of a system designed to measure important operational parameters of mammography equipment, as kVp, tube current, exposure time, dose and half-value layer (HVL) in any field location. This system is based on a device with a Si semiconductor sensor, placed under the X-ray tube (over the unit table, for example), which detects the X-ray photons...

Digitizing radiographic films: a simple way to evaluate indirect digital images

OBJECTIVES: This study applied a simple method to evaluate the performance of three digital devices (two scanners and one digital camera) using the reproducibility of pixel values attributed to the same radiographic image. METHODS: Using the same capture parameters, a radiographic image was repeatedly digitized in order to determine the variability of pixel values given to the image throughout the digitization process. One coefficient value was obtained and was called pixel value reproducibility. RESULTS: A significant difference in pixel values was observed among the three devices for the digitized images (ANOVA, p<0.00001). There was significant pixel value variability at the same digitization conditions for one scanner and the digital camera. CONCLUSIONS: Digital devices may assign pixel values differently in consecutive digitization depending on the optical density of the radiographic image and the equipment. The pixel value reproducibility was not satisfactory as tested for two devices. It is maybe advisable knowing the digitization variations regarding pixel values whenever using digital radiography images in longitudinal clinical examinations.

Contrast enhancement in dense breast images to aid clustered microcalcifications detection.

This paper presents a method to provide contrast enhancement in dense breast digitized images, which are difficult cases in testing of computer-aided diagnosis (CAD) schemes. Three techniques were developed, and data from each method were combined to provide a better result in relation to detection of clustered microcalcifications. Results obtained during the tests indicated that, by combining all the developed techniques, it is possible to improve the performance of a processing scheme designed to detect microcalcification clusters. It also allows operators to distinguish some of these structures in low-contrast images, which were not detected via conventional processing before the contrast enhancement. This investigation shows the possibility of improving CAD schemes for better detection of microcalcifications in dense breast images.

Digitizing radiographic films: a simple way to evaluate indirect digital images.

OBJECTIVES: This study applied a simple method to evaluate the performance of three digital devices (two scanners and one digital camera) using the reproducibility of pixel values attributed to the same radiographic image. METHODS: Using the same capture parameters, a radiographic image was repeatedly digitized in order to determine the variability of pixel values given to the image throughout the digitization process. One coefficient value was obtained and was called pixel value reproducibility. RESULTS: A significant difference in pixel values was observed among the three devices for the digitized images (ANOVA, p<0.00001). There was significant pixel value variability at the same digitization conditions for one scanner and the digital camera. CONCLUSIONS: Digital devices may assign pixel values differently in consecutive digitization depending on the optical density of the radiographic image and the equipment. The pixel value reproducibility was not satisfactory as tested for two devices. It is maybe advisable knowing the digitization variations regarding pixel values whenever using digital radiography images in longitudinal clinical examinations.

Evaluating noise in digitized radiographic images by means of histogram

To evaluate the performance of three digital devices regarding the noise added to digital radiographic images containing different optical densities. METHODS: A radiographic image was digitized repeatedly ten times using two scanners (HP 4c/T and HP 5370C) and a digital camera (Nikon 990). A histogram tool measured a mean pixel value and the standard deviation of the region of interest in each image. Both values were used to calculate the image noise at the different optical densities. RESULTS: The noise values found were different for all devices and optical densities. There was a statistically significant difference (p<0.05) between the scanner HP 4c/T and the digital camera regarding the noise values. There was a significant correlation (p<0.05) between the noise values found for the HP 4c/T scanner and the digital camera and between both scanners (p<0.01). CONCLUSION: The noise added to the image was higher for scanner HP 4c/T and less for the digital camera. The noise was higher at the lower optical densities for the scanners. It seems that depending on the equipment and the optical density, a variable amount of noise can be incorporated to the images.

OBJETIVOS: Avaliar três equipamentos digitais em relação ao ruído agregado as imagens radiográficas digitalizadas contendo diferentes densidades ópticas. MATERIAL AND MÉTODO: Uma imagem radiográfica foi digitalizada seqüencialmente dez vezes usando dois escaneres (HP 4c/T and HP 5370C) e uma câmera digital (Nikon 990). Por meio do histograma foram medidos os valores de pixels e os desvios-padrões da região de interesse de cada imagem. Ambos valores foram utilizados para o cálculo do ruído nas diferentes densidades ópticas. RESULTADOS: Os valores encontrados para o ruído foram diferentes para cada equipamento e para cada densidade óptica. Houve uma diferença estatística significante entre os valores de ruído encontrados para o escaner HP 4c/T e a câmera digital (p<0.05). Houve uma correlação significante entre os valores do ruído encontrados para o escaner HP 4c/T e a câmera digital (p<0.05) e entre os dois escaneres (p<0.01). CONCLUSÕES: O ruído agregado à imagem foi maior para o escaner HP 4c/T e menor para a câmera digital. O ruído foi maior nas densidades ópticas menores para os dois escaneres. Dependendo do equipamento e da densidade óptica uma quantidade variável de ruído pode ser agregado às imagens.

Reproducibility of pixel values for two photostimulable phosphor plates in consecutive standardized scannings.

The objective of the present study was to determine the reproducibility of the pixel values obtained with the Digora system (Soredex, Finland). Exposures were standardized, with variation in exposure and scanning time of two photostimulable phosphor plates containing a stepwedge image. The smallest variation in pixel values ranged from 50 to 75%, with the widest variations being observed in less dense steps. A significant difference in pixel values was observed in terms of X-ray exposure and scanning times and between the two plates themselves (ANOVA, p < 0.01). Using the present methodology, the reproducibility of pixel values was not satisfactory for the tested white photostimulable plates. This wide variation in digitalization might be influenced by the amount of X-rays that sensitized the plates. It may be important to establish the reproducibility of the pixel values in quantitative studies using digital image.

Reproducibility of pixel values for two photostimulable phosphor plates in consecutive standardized scannings / Reprodutibilidade dos valores de "pixels" de duas placas de fósforo fotoestimuláveis em leituras padronizadas consecutivas

The objective of the present study was to determine the reproducibility of the pixel values obtained with the Digora system (Soredex, Finland). Exposures were standardized, with variation in exposure and scanning time of two photostimulable phosphor plates containing a stepwedge image. The smallest variation in pixel values ranged from 50 to 75 percent, with the widest variations being observed in less dense steps. A significant difference in pixel values was observed in terms of X-ray exposure and scanning times and between the two plates themselves (ANOVA, p < 0.01). Using the present methodology, the reproducibility of pixel values was not satisfactory for the tested white photostimulable plates. This wide variation in digitalization might be influenced by the amount of X-rays that sensitized the plates. It may be important to establish the reproducibility of the pixel values in quantitative studies using digital image.

O objetivo do presente trabalho foi determinar a reprodutibilidade dos valores de "pixels" obtidos com o sistema Digora (Soredex, Finlândia). As exposições foram padronizadas, com variação no tempo de exposição e leitura de duas placas de fósforo fotoestimuláveis contendo a imagem de um penetrômetro. A menor variação nos valores de "pixels" foi de 50 a 75 por cento, sendo as maiores variações oriundas nas faixas mais claras. Uma diferença significante nos valores de "pixels" foi observada em relação ao tempo de exposição e leitura das placas e entre as duas placas (ANOVA, p < 0,01). Utilizando a presente metodologia, a reprodutibilidade dos valores de "pixels" das placas testadas do sistema Digora não foi satisfatória. Essa grande variação na digitalização pode ter sido influenciada pela quantidade de Raios X que sensibilizou as placas. Isso pode ser importante para estabelecer a reprodutibilidade dos valores de "pixels" em estudos quantitativos usando imagem digital.

Evaluating noise in digitized radiographic images by means of histogram.

UNLABELLED: To evaluate the performance of three digital devices regarding the noise added to digital radiographic images containing different optical densities. METHODS: A radiographic image was digitized repeatedly ten times using two scanners (HP 4c/T and HP 5370C) and a digital camera (Nikon 990). A histogram tool measured a mean pixel value and the standard deviation of the region of interest in each image. Both values were used to calculate the image noise at the different optical densities. RESULTS: The noise values found were different for all devices and optical densities. There was a statistically significant difference (p<0.05) between the scanner HP 4c/T and the digital camera regarding the noise values. There was a significant correlation (p<0.05) between the noise values found for the HP 4c/T scanner and the digital camera and between both scanners (p<0.01). CONCLUSION: The noise added to the image was higher for scanner HP 4c/T and less for the digital camera. The noise was higher at the lower optical densities for the scanners. It seems that depending on the equipment and the optical density, a variable amount of noise can be incorporated to the images.

Banco de imagens mamográficas para treinamento na interpretação de imagens digitais / Digital image database for mammography interpretation training

OBJETIVO: Disponibilizar aos profissionais da radiologia um "software" para treinamento na interpretação de imagens mamográficas em sistemas digitais. MATERIAIS E MÉTODOS: Foi desenvolvido um "software" em Delphi associado a uma base de dados em Interbase, com a finalidade de armazenar imagens de exames mamográficos associados aos seus laudos em categorias BI-RADS®. As imagens foram previamente qualificadas e digitalizadas em "scanner" a laser Lumiscan 75. O treinamento se faz com imagens apresentadas em monitores comerciais de 17 polegadas, no tamanho 18 Î 24 cm. O "software" permite visualizar cada projeção das mamas individualmente, médio-lateral oblíqua e crânio-caudal, ou as quatro imagens simultaneamente. Permite acessar as imagens e os laudos existentes ou interpretar as imagens utilizando o sistema de categorias BI-RADS®, em que o "software" compara o laudo do usuário com as informações do banco de dados, apontando acertos e erros da interpretação. RESULTADOS: O usuário adquire familiaridade com sistemas digitais, laudos em categorias BI-RADS® e aspectos de qualidade do processo gerador das imagens relativo à detecção de fibras e microcalcificações. CONCLUSÃO: O "software" disponível na intranet da Universidade Federal de São Paulo é ferramenta valiosa para os profissionais interessados em sistemas digitais.

OBJECTIVE: To make a software available for training professionals in the interpretation of mammography images on digital systems. MATERIALS AND METHODS: The software was developed in Delphi and linked to a Interbase database to store mammographic images in association with the BI-RADS® category results. Images were previously qualified and digitized using a Lumiscan 75 laser scanner. Training is done on 18 × 24 cm images displayed on a 172 commercial monitor. The software allows displaying of each breast view individually, medial-lateral oblique and cranial-caudal views, or four images simultaneously. The user selects an exam from the database and makes a diagnosis classifying the image into BI-RADS® categories. At the end of the process, the software compares the user's interpretation with the data stored in the database and than yields scores. RESULTS: The user becomes familiar with digital systems, images interpretation using BI-RADS® categories and with the quality of the image generating process regarding the detection of fibers and microcalcifications. CONCLUSION: The software is available at "Universidade Federal de São Paulo", São Paulo, Brazil, intranet and is a valuable tool for training professionals interested in digital systems.

Uma ferramenta para treinamento na avaliação de imagens mamográficas via Internet / A training tool for mammography images evaluation via Internet

Este trabalho consiste na implementação de um esquema computacional instalado em um "site" associado à "homepage" do Laboratório de Análise e Digitalização de Imagens do Departamento de Engenharia Elétrica da Escola de Engenharia de São Carlos ¾ Universidade de São Paulo, São Carlos, SP, para proporcionar um procedimento de interatividade com o usuário remoto na elaboração de laudo a partir da análise de imagens mamográficas via rede, com avaliação automática do parecer emitido. Isto foi feito a partir da implantação de um banco de imagens mamográficas digitalizadas, adequadamente pré-selecionadas, associado a uma base de dados com os laudos fornecidos por radiologistas especialistas. Como o processo tem a finalidade de ser utilizado para treinamento na avaliação diagnóstica em mamografia, o laudo do especialista é disponibilizado para comparação após a finalização de cada avaliação, juntamente com o parecer fornecido pelo usuário e sua porcentagem de acerto. Esse esquema, denominado "Laudos Online", objetiva também permitir ao usuário aprimorar seus conhecimentos, funcionando como uma ferramenta de ensino a distância.

A segmentation technique to detect masses in dense breast digitized mammograms.

This article describes a segmentation technique that uses the watershed transformation to provide mass detection in dense breast digitized images. The technique consists of four steps: preprocessing, which isolates the breast from the image background; histogram equalization to enhance the contrast; watershed transformation, which calculates the gradient for the whole image; and a topography technique that organizes the segmented parts. We processed 109 regions of interest extracted from mammograms. Preliminary results showed 20% false positive and 85.4% true positive detection regarding the equalized images containing masses. Good results were obtained with this technique. However, additional techniques should be developed to eliminate noise in some images. This technique could be an important tool in mammography.

Computer technique for digital radiographic images correction based on the digitizer characteristic curve.

This article presents a computer correction technique for radiographic digital images based on digitization process inaccuracy in pixel gray levels relative to the respective image optical densities. The technique consists of determining the digitizer characteristic curve by digitizing a step-wedge radiographic image with known optical densities. Calibration is done by determining the mathematical function that automatically adjusts the pixel gray levels to the expected values according to the manufacturer. Two laser film digitizers were investigated for which discrepancies between measured and expected pixel values were reported. For these cases, the proposed algorithm automatically adjusted the pixel gray levels of the digitized images. Using this method, the digital images show more accurate values of gray levels compared to the original radiographic image. In addition, it allows the development of uniform images databases.