Chest radiography is one of the most commonly performed radiographic examinations worldwide. Routinely acquired in the erect posteroanterior (PA) position, a chest radiograph displays substantial amounts of medical information when accurate patient positioning is achieved. However, a rotated PA chest radiograph has reduced diagnostic quality and appearances may mask or mimic chest pathology. Radiographic assessment of patient rotation around the sagittal plane has traditionally been undertaken by assessing the distance between the medial end of the clavicles and a line drawn through the spinous processes at the level of the clavicles. This approach continues to be advocated in radiographic technique textbooks internationally although no identified author has provided criteria to determine when a rotated PA chest radiograph should be repeated; determined the relationship between perceived clavicle to spinous process distance and actual degree of patient rotation; or considered the impact of body morphology, in particular the anteroposterior thoracic diameter, on radiographic appearances of rotation. Objectives To determine the impact of anteroposterior chest diameter on radiographic appearances of sagittal rotation on PA chest radiographs. Design Experimental study. Methods and Settings Sixty computed tomography thorax examinations, stratified for gender, were reviewed and data aggregated to determine average anteroposterior (AP) thoracic dimensions. A bespoke experimental unit was constructed specifically to enable testing of the impact of sagittal rotation on radiographic appearances. The experimental unit was situated within a calibrated circular frame enabling 360° rotation at 1° intervals around a central rotational point. The experimental unit components were varied in 1 cm intervals from 9 cm to 15 cm around the central rotation point to reflect varying AP chest diameters. At each interval, images were acquired at 0, 2, 5, 7, 10, and 15° sagittal rotation using a horizontal central ray, consistent centring point, and a source-image distance of 180 cm. Results A clear linear relationship between AP thoracic diameter and the radiographic appearances of sagittal rotation was noted. Considering significant rotation to be when the medial end of clavicle overlaps the spinous process on the radiographic image, this appearance occurred at a much smaller degree of rotation on wide AP thoracic diameters (15 cm, 5°) than narrower AP thoracic diameters (9 cm, 10°). Conclusions The routine application of the distance between the medial end of the clavicles and a line drawn through the spinous processes at the level of the clavicles as a method of assessing degree of sagittal rotation, diagnostic image quality, and need for repeat is flawed. Persistence in the application of this approach without cognisance of the impact of body morphology on radiographic appearances will result in persons with large AP thoracic diameters being more likely to have a PA chest radiograph repeated for a specified degree of rotation than persons with smaller AP thoracic diameters. / © 2015 Elsevier. Reproduced in accordance with the publisher's self-archiving policy.

No description available.

Image compression reduces the amount of space necessary to store digital images and allows quick transmission of images to other hospitals, departments, or clinics. However, the degradation of image quality due to compression may not be acceptable to radiologists or it may affect diagnostic results. A preliminary study was conducted using several chest images with common lung diseases and compressed with JPEG and wavelet techniques at various ratios. Twelve board-certified radiologists were recruited to perform two types of experiments. In the first part of the experiment, presence of lung disease, confidence of presence of lung disease, severity of lung disease, confidence of severity of lung disease, and difficulty of making a diagnosis were rated by radiologists. The six images presented were either uncompressed or compressed at 32:1 or 48:1 compression ratios. In the second part of the experiment, radiologists were asked to make subjective ratings by comparing the image quality of the uncompressed version of an image with the compressed version of the same image, and judging the acceptability of the compressed image for diagnosis. The second part examined a finer range of compression ratios (8:1, 16:1, 24:1, 32:1, 44:1, and 48:1). In all cases, radiologists were able to judge the presence of lung disease and experienced little difficulty diagnosing the images. Image degradation perceptibility increased as the compression ratio increased; however, among the levels of compression ratio tested, the quality of compressed images was judged to be only slightly worse than the original image. At higher compression ratios, JPEG images were judged to be less acceptable than wavelet-based images but radiologists believed that all the images were still acceptable for diagnosis. These results should be interpreted carefully because there were only six original images tested, but results indicate that compression ratios of up to 48:1 are acceptable using the two medically optimized compression methods, JPEG and wavelet techniques. / Master of Science

Submitted by JÚLIO HEBER SILVA (julioheber@yahoo.com.br) on 2017-04-05T17:19:40Z No. of bitstreams: 2 Dissertação - Afonso Ueslei da Fonseca - 2017.pdf: 9310150 bytes, checksum: 0fc9668df93eccbc288295e41256b328 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2017-04-06T11:07:11Z (GMT) No. of bitstreams: 2 Dissertação - Afonso Ueslei da Fonseca - 2017.pdf: 9310150 bytes, checksum: 0fc9668df93eccbc288295e41256b328 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Made available in DSpace on 2017-04-06T11:07:11Z (GMT). No. of bitstreams: 2 Dissertação - Afonso Ueslei da Fonseca - 2017.pdf: 9310150 bytes, checksum: 0fc9668df93eccbc288295e41256b328 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2017-03-27 / According to the World Health Organization (WHO), more than 900,000 children, younger than five years old, have died in 2015 due to pneumonia. Many of these deaths could be avoided with earlier and more accurate diagnosis to provide proper medicine administration. Chest radiography is one of the most recommended test by the WHO in order to detect childhood pneumonia, and it is commonly used in computer aided diagnostic (CAD) systems. A science role is to develop systems that require a more precise medical diagnosis and treatment cost reducing, but mainly death rate decreasing. It is highlighted that quality radiography demands equipments very well installed and calibrated and staff trained to handle them. However, due limited budget resources, mainly in most vulnerable areas, the image quality is significantly damaged, so turning the medical diagnosis harder. Therefore, this work presents a method composed of a set of preprocessing techniques for pediatric radiography. These techniques intend to have simple implementation and low computational cost. The main goal of this work is to increase performance, accuracy and robustness of CAD systems, to improve database standardization and also to collaborate with the professionals training. Thus, techniques were developed, such as, visual quality enhancement, removal of unnecessary or confidential information, reconstruction of degraded areas due to the information removal, orientation correction and definition of a region of interest. All techniques were evaluated using a children chest X-ray database divided into three classes and results show significantly improve when compared to methods presented in literature. We expect these contributions will assist to development and improvement of new systems, construction of more standardized databases, staff training and the development of new techniques. / Segundo a Organização Mundial de Saúde (OMS) mais de 900 mil crianças, menores de cinco anos, foram a óbito em 2015, devido a pneumonia. Muitas dessas mortes poderiam ser evitadas com um diagnóstico mais preciso, precoce e com correta administração de medicamentos. A radiografia de tórax é um dos exames preconizados para detecção de pneumonia pela OMS, sendo comumente usada em sistemas de diagnóstico assistido por computador (CAD). Desenvolver sistemas que apoiem diagnóstico médico mais preciso, reduzam custos de tratamento e principalmente diminuam o número de óbitos é um papel da ciência. Destaca-se que radiografias de qualidade requerem equipamentos devidamente instalados/calibrados e pessoal capacitado para opera-los. Todavia, dado os recursos financeiros limitados, principalmente em áreas mais vulneráveis, a qualidade das imagens fica significativamente comprometida, dificultando o trabalho de diagnóstico pelo médico. Assim, este trabalho traz um método composto por técnicas de pré-processamento de radiografias de tórax pediátricas. As técnicas foram idealizadas para serem de simples implementação e baixo custo computacional. Os principais objetivos do trabalho são promover ganho de performance, acurácia e robustez aos sistemas CAD, favorecer a construção de bases de imagens padronizadas e além disso colaborar com o treinamento de profissionais de saúde. Para atingir esses objetivos foram desenvolvidas técnicas de melhoria da qualidade visual, remoção de informações desnecessárias ou confidenciais e reconstrução das áreas degradadas decorrente da remoção dessas informações, correção de orientação e definição de regiões de interesse. Esse método foi avaliado utilizando uma base de radiografias de tórax infantil divida em três classes e resultados mostram ganhos significativos em comparação a métodos presentes na literatura. Espera-se que essas contribuições favoreçam o aperfeiçoamento de sistemas, construção de bases mais padronizadas, treinamento de profissionais e surgimento de novas técnicas.

No description available.

abstract: Medical images constitute a special class of images that are captured to allow diagnosis of disease, and their "correct" interpretation is vitally important. Because they are not "natural" images, radiologists must be trained to visually interpret them. This training process includes implicit perceptual learning that is gradually acquired over an extended period of exposure to medical images. This dissertation proposes novel computational methods for evaluating and facilitating perceptual training in radiologists. Part 1 of this dissertation proposes an eye-tracking-based metric for measuring the training progress of individual radiologists. Six metrics were identified as potentially useful: time to complete task, fixation count, fixation duration, consciously viewed regions, subconsciously viewed regions, and saccadic length. Part 2 of this dissertation proposes an eye-tracking-based entropy metric for tracking the rise and fall in the interest level of radiologists, as they scan chest radiographs. The results showed that entropy was significantly lower when radiologists were fixating on abnormal regions. Part 3 of this dissertation develops a method that allows extraction of Gabor-based feature vectors from corresponding anatomical regions of "normal" chest radiographs, despite anatomical variations across populations. These feature vectors are then used to develop and compare transductive and inductive computational methods for generating overlay maps that show atypical regions within test radiographs. The results show that the transductive methods produced much better maps than the inductive methods for 20 ground-truthed test radiographs. Part 4 of this dissertation uses an Extended Fuzzy C-Means (EFCM) based instance selection method to reduce the computational cost of transductive methods. The results showed that EFCM substantially reduced the computational cost without a substantial drop in performance. The dissertation then proposes a novel Variance Based Instance Selection (VBIS) method that also reduces the computational cost, but allows for incremental incorporation of new informative radiographs, as they are encountered. Part 5 of this dissertation develops and demonstrates a novel semi-transductive framework that combines the superior performance of transductive methods with the reduced computational cost of inductive methods. The results showed that the semi-transductive approach provided both an effective and efficient framework for detection of atypical regions in chest radiographs. / Dissertation/Thesis / Ph.D. Computer Science 2012