OBJECTIVE: The present study was aimed at evaluating the performance of residents trained in the reading of conventional and digital mammography images with a specific computational tool. MATERIALS AND METHODS: The training was accomplished in the Laboratory of Medical Images Qualification (QualIM - Laboratório de Qualificação de Imagens Médicas). Residents in radiology performed approximately 1,000 readings of a set of 60 images acquired from a statistical phantom (Alvim®) presenting microcalcifications and fibers with different sizes. The analysis of the residents' performance in the detection of these structures was based on statistical parameters. RESULTS: Values for detection probability were respectively 0.789 and 0.818 for conventional and digital systems. False-positive rates were 8% and 6%, and true-positive rates, 66% and 70% respectively. The total kappa value was 0.553 for readings on the negatoscope (hard-copy readings), and 0.615 on the monitor (soft-copy readings). The area under the ROC curve was 0.716 for hard-copy readings and 0.810 for soft-copy readings. CONCLUSION: The training has showed to be effective, with a positive impact on the residents' performance, representing an interesting educational tool. The results of the present study suggest that this method of training based on the reading of images from phantoms can improve the practitioners' performance in the interpretation of mammographic images.

Keywords: Digital image, Teaching & learning, Mammography, Educational tool, Soft-copy reading, Hard-copy reading

OBJECTIVE: A software called QualIM® - Qualificação de Imagens Médicas was developed for training of practitioners in the interpretation of digital mammograms classified according to BI-RADS® categories, utilizing images manipulation tools on state-of-the-art displays. MATERIALS ANDMETHODS: A Delphi 7-based system stores data resulting from mammographic findings interpretation during the training, comparing them with a golden-standard data set. The database includes computed radiography, direct radiography and digitized images. The software converts computed radiography and direct radiography images into TIFF format, preserving their original spatial and contrast resolution. During the training, the images are manipulated with the aid of the software tools (zoom, inversion, digital rulers and others). Depending on the image complexity, up to eight mammographic views, six ultrasonography images and two anatomopathological images can be displayed. RESULTS: The training was initiated in 2007 and is currently included in the radiology residency program. Based on data entered by the practitioner, the software automatically generates a BI-RADS compliant text that is compared with a database. CONCLUSION: The QualIM software is a digital educational tool aimed at assisting practitioners in the recognition of visual patterns on mammographic images as well as in the interpretation of mammograms based on the BI-RADS classification.

Keywords: Training, Digital mammography, Displays

In digital mammography, imaging acquisition, display and storage processes are separated and individually optimized. Radiation transmitted through the breast is absorbed by an electronic detector with an accurate response over a wide range of intensities. Once these data are stored, they can be displayed by means of computer image-processing techniques to allow arbitrary settings of image brightness, contrast and magnification, without the need for further radiological exposure of the patient. In this article, the current state of the art in technology for digital mammography and clinical trials data supporting the use of this technology are reviewed. In addition, several potentially useful applications, currently under development with digital mammography, are described.

Keywords: Mammography, Breast cancer, Digital radiography, Full-field digital mammography

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.

Keywords: Data base, Mammography, Digital, Quality control

The authors report a case of primary hypertrophic osteoarthropathy in a 29-year-old male with swollen joints. Physical examination revealed also digital clubbing and convexity of the nails. All other causes of secondary forms of hypertrophic osteoarthropathy were excluded. The main radiological abnormalities found were bone cortical hypertrophy and periosteal proliferation. Abnormalities of the joint spaces were not observed.

Keywords: Hypertrophic osteoarthropathy, Pachydermoperiostosis, Digital clubbing

Several technological developments are contributing to increase the use of imaging techniques in biomedical research and clinical medicine. Many investigators have attempted to develop computerized routines for automated detection and quantitative analysis of abnormalities in radiological images. These routines have been referred to as computer-aided diagnosis. In this paper we discuss the basic concepts of computer-aided diagnosis and review the literature.

Keywords: Computer-aided diagnosis, Digital radiography, Image processing, Computer vision, Artificial intelligence

Objective: To propose a reproducible, user friendly and low cost method for digitization of radiographic films of all the standard sizes, focusing efforts on chest X-ray films. Materials and Methods: The focus on low cost have dictated the use of an A4 scanner with transparency adapter, as well as an optimized image stitching software that takes advantage of the scanner geometry and constant capture area, besides the knowledge of the standard X-ray film sizes. Results: The end result of the proposed method is a high resolution image with good contrast and no perceptible stitching artifacts. Conclusion: The proposed digitization method with an A4 scanner allows reproducibility, excellent image quality and high degree of certainty in the identification of lesions.

Keywords: Digital radiology; Teleradiology; Image stitching.

Objetivo: A principal utilidade da tomografia por emissão de pósitrons com 18-fluordeoxiglicose (FDG-PET) está no estadiamento do câncer de pulmão. Porém, ela também pode ser utilizada para diferenciar lesões pulmonares indeterminadas, mas seu impacto na ressecção cirúrgica de lesões benignas é desconhecido. O objetivo deste estudo foi comparar a prevalência de lesões benignas em toracotomias feitas por suspeição de câncer de pulmão, antes e após a introdução do FDG-PET, em um centro de referência de cirurgia torácica. Materiais e Métodos: Os autores analisaram, prospectivamente, uma base de dados cirúrgicos de todos os pacientes consecutivos submetidos a toracotomia por câncer de pulmão suspeito ou comprovado e compararam a prevalência de lesões benignas em dois grupos ao longo de dois anos consecutivos, respectivamente antes (grupo I) e depois (grupo II) da introdução da FDG-PET. Resultados: Ressecção cirúrgica foi feita em 1.233 pacientes durante o período do estudo. A prevalência de lesões benignas na cirurgia nos grupos I e II foi similar (44/626 e 41/607, ambas correspondendo a 7%), e também no grupo II, entre aqueles submetidos a FDG-PET e os restantes (21/301 e 20/306 respectivamente, ambos correspondendo a 7%). No grupo II, dos 21 pacientes com lesões benignas submetidos a FDG-PET, 19 tiveram um estudo falso-positivo (valor médio padrão de captação 5.3 [faixa 2.6–12.7]). Desses, respectivamente 13 e 4 pacientes tiveram broncoscopia não diagnóstica e biópsia transtorácica percutânea de pulmão antes da toracotomia. Não houve diferença na proporção de lesões benignas diferentes ressecadas entre o grupo I e aqueles submetidos a FDG-PET no grupo II. Conclusão: A introdução da FDG-PET não alterou a proporção de pacientes submetidos a toracotomia por lesões benignas, principalmente devido à avidez pelo isótopo de algumas lesões não malignas. Tais resultados falsos-positivos devem ser considerados nos casos em que se contempla a possibilidade de ressecção cirúrgica em pacientes com câncer de pulmão não confirmado.

Keywords: Tomografia por emissão de pósitrons; Tomografia computadorizada; Pulmão – lesões benignas ou congênitas; Câncer de pulmão – diagnóstico e estadiamento; Câncer de pulmão – cirurgia.

Objetivo: Avaliar a percepção de médicos residentes em radiologia de 4º ano sobre as melhores modalidades de imagem na investigação de neoplasias e trauma. Materiais e Métodos: Vinte e sete médicos residentes de 4º ano de quatro programas de residência em radiologia americanos participaram do estudo. Aos participantes foi perguntado sobre a melhor modalidade de imagem para se avaliar o cérebro e a coluna vertebral, pulmões, abdome e o sistema musculoesquelético. As modalidades de imagem disponíveis foram: RM, TC, ultrassonografia, PET e radiografia simples. Todos os achados foram comparados com os Critérios de Adequação de Exames de Imagem e Radioterapia do ACR. Resultados: A RM foi escolhida como melhor modalidade de imagem para se avaliar neoplasias encefálicas, espinhais, abdominais e musculoesqueléticas por 96,3%, 100%, 70,4% e 63% dos residentes, respectivamente. A TC foi escolhida por 88,9% dos residentes para avaliar neoplasias pulmonares. A modalidade de imagem ótima para se avaliar trauma foi a TC para lesões encefálicas (100%), espinhais (92,6%), pulmonares (96,3%), abdominais (92,6%) e grandes lesões traumáticas musculoesqueléticas (74,1%); a RM foi escolhida para lesões esportivas (96,3%). Observou-se concordância com os critérios de adequação do ACR. Conclusão: Houve concordância entre a percepção dos residentes sobre as melhores modalidades de imagem para avaliação de neoplasias e trauma e os critérios de adequação do ACR.

Keywords: Formação de residentes; Educação médica; Modalidades de imagem.

OBJETIVO: Avaliar a completude das fissuras, resposta radiológica ao tratamento e análise quantitativa por TC (AQTC) em população de pacientes com enfisema grave submetidos ao implante de valvas endobrônquicas (VEB). MATERIAIS E MÉTODOS: Foram estudados exames de TC multidetectores de 29 pacientes, realizados com protocolo de baixo dose, cortes finos, sem contraste. Dois radiologistas revisaram, retrospectivamente, os exames em consenso. A completude das fissuras foi estimada em escala de 5% e a resposta radiológica (atelectasia/perda volumétrica do lobo alvo) foi avaliada. AQTC foi realizada nos exames pré e pós-tratamento utilizando programa completamente automático. RESULTADOS: Resposta radiológica positiva foi vista em 16/29 pacientes. Os 13 pacientes sem resposta à TC apresentavam fissuras incompletas e completude média das fissuras obliquas de 72,8%, contra 88,3% no outro grupo. Os resultados mais significativos da AQTC mostraram redução do volume pulmonar (VP) total (média de 542 ml), VP tratado (700 ml) e volume de enfisema (331,4 ml) no grupo com resposta positiva, que também apresentou melhora nos testes funcionais. CONCLUSÃO: O benefício das VEB é maior em pacientes com fissuras completas e que desenvolvem atelectasia lobar. Nos pacientes sem resposta radiológica encontramos maior prevalência de fissuras incompletas e grau de incompletude das fissuras. Nossa AQTC automática detectou as alterações pós-tratamento, principalmente considerado a análise do pulmão tratado.

Keywords: Enfisema; Terapia de colapso pulmonar; Tomografia computadorizada.

OBJECTIVE: To analyze the radiological aspects of pulmonary atelectasis in newborns on mechanical ventilation and treated in an intensive care unit, associating the characteristics of atelectasis with the positioning of the head and endotracheal tube seen on the chest X-ray, as well as with the clinical variables. MATERIALS AND METHODS: This was a retrospective cross-sectional study of 60 newborns treated between 1985 and 2015. Data were collected from medical records and radiology reports. To identify associations between variables, we used Fisher’s exact test. The level of significance was set at p < 0.05. RESULTS: The clinical characteristics associated with improper positioning of the endotracheal tube were prematurity and a birth weight of less than 1000 g. Among the newborns evaluated, the most common comorbidity was hyaline membrane disease. Atelectasis was seen most frequently in the right upper lobe, although cases of total atelectasis were more common in the left lung. Malpositioning of the head showed a trend toward an association with atelectasis in the left upper lobe. CONCLUSION: Pulmonary atelectasis is a common complication in newborns on mechanical ventilation. Radiological evaluation of the endotracheal tube placement provides relevant information for the early correction of this condition.

Keywords: Pulmonary atelectasis/diagnostic imaging; Respiration, artificial; Infant, newborn; Premature birth; Infant, low birth weight.

The discipline of radiology and diagnostic imaging has evolved greatly in recent years. We have observed an exponential increase in the number of exams performed, subspecialization of medical fields, and increases in accuracy of the various imaging methods, making it a challenge for the radiologist to “know everything about all exams and regions”. In addition, imaging exams are no longer only qualitative and diagnostic, providing now quantitative information on disease severity, as well as identifying biomarkers of prognosis and treatment response. In view of this, computer-aided diagnosis systems have been developed with the objective of complementing diagnostic imaging and helping the therapeutic decision-making process. With the advent of artificial intelligence, “big data”, and machine learning, we are moving toward the rapid expansion of the use of these tools in daily life of physicians, making each patient unique, as well as leading radiology toward the concept of multidisciplinary approach and precision medicine. In this article, we will present the main aspects of the computational tools currently available for analysis of images and the principles of such analysis, together with the main terms and concepts involved, as well as examining the impact that the development of artificial intelligence has had on radiology and diagnostic imaging.

Keywords: Artificial intelligence; Machine learning; Computer aided diagnosis; Radiomics.

OBJECTIVE: To evaluate the impact of artificial intelligence (AI) on undergraduate medical students’ choice of radiology as a specialty. MATERIALS AND METHODS: In February 2019, an anonymous online survey was sent to medical students. The research contemplated questions on how much students think they know about AI technologies, how much AI discourages them from choosing radiology as a specialty, and whether they believe there is a threat to the radiology job market. RESULTS: A total of 101 students, most of them doing their internship, answered the questionnaire. More than half of them (52.5%) said they believe AI poses a threat to the radiology job market, but 64.3% claimed not to have proper knowledge about these new technologies, and 31.7% said they would like more information on the technologies’ operation and progress before making a decision on whether or not to practice radiology as a specialty. CONCLUSION: A significant proportion of the surveyed students perceive AI as a threat to the radiological practice, which impacts their career choice. However, the majority claims to have insufficient knowledge of it and believes more information is needed for decision-making.

Keywords: Artificial intelligence; Radiology; Medical students; Education; Specialty.

Os nervos cranianos representam extensões das estruturas funcionais do cérebro que cruzam a cabeça e o pescoço. Eles estão ligados a diferentes estruturas cranianas e se relacionam com diversas doenças. Uma compreensão profunda de sua complexa anatomia e aparência normal de imagem permite ao examinador identificar e caracterizar com mais precisão as anormalidades. A ressonância magnética com contraste é uma importante ferramenta para avaliar essas estruturas, especialmente as sequências tridimensionais de precessão livre de estado estacionário, que proporcionam alta resolução espacial e de partes moles, apesar da fina espessura dos nervos cranianos. Na maioria dos casos, os achados de imagem são inespecíficos, e uma anamnese completa, exame físico dirigido e testes laboratoriais são necessários para estreitar o diagnóstico diferencial. Este ensaio iconográfico ilustra e discute doenças congênitas, traumáticas e vasculares dos nervos cranianos, mostrando imagens em uma abordagem fisiopatológica.

Keywords: Neuroimagem/métodos; Radiologia/métodos; Ressonância magnética/métodos; Nervos cranianos/diagnóstico por imagem.

OBJETIVO: Avaliar os padrões tomográficos relacionados aos agentes etiológicos da pneumonia em pacientes durante o primeiro ano após transplante renal. MATERIAIS E MÉTODOS: Foram analisados dados de prontuários de 956 pacientes submetidos a transplante renal, no período de 2013 a 2018, em um centro transplantador renal do nordeste do Brasil. Nos pacientes que desenvolveram pneumonia, os agentes etiológicos foram classificados em bactérias piogênicas, micobactérias, fungos, vírus e pneumonia polimicrobiana, enquanto os padrões tomográficos foram classificados em consolidação, broncopneumonia, pneumonia intersticial e nódulos e massas. Para verificar associação estatística entre micro-organismos e padrões tomográficos, foi utilizado o teste exato de Fisher, com p < 0,001. RESULTADOS: Foram encontrados 101 casos de pneumonia, dos quais 60 (59,4%) tiveram agente etiológico identificado, sendo as bactérias piogênicas as mais frequentes, detectadas em 22 (36,7%) dos casos. Entre os pacientes com agente causal identificado, o padrão tomográfico predominante foi o de nódulos e massas, identificado em 25 (41,7%) casos. Foi observada associação entre bactérias piogênicas e o padrão de consolidação, fungos com nódulos e massas, bem como entre agentes virais e padrão intersticial. CONCLUSÃO: Foi demonstrada associação estatística entre micro-organismos causadores de pneumonia e padrões tomográficos, informação que pode contribuir para o planejamento da terapia de pacientes transplantados renais.

Keywords: Pneumonia; Transplante de rim; Tomografia computadorizada.