Search

Abstract: Feasible clinical application of any automated segmenting methodology demands more than just accuracy. Amendment to the automated delineation is necessary when the algorithm fails, however, integrated solution to such a scenario is largely absent in literature. Hence in this survey we devised an architecture that does both the automated and interactive lung field localizations using a single segmenting engine—random walker algorithm—so that intuitive amendment is only necessary when the automated generated delineation is unsatisfactory. The algorithm proceeds by first extracting 18 intensity profiles running horizontally, each of them equally spacing apart, and in each intensity profile three extreme points denoting the two lungs and the esophagus are determined through profile matching. This done, the algorithm removes profiles that do not intersect with the lung, and the rest of the extreme points are plugged into random walker algorithm to perform segmentation. The achieved accuracy in localization by the above was 0.8875 in terms of overlap measure (the maximum value for this parameter is 1) over 341 images. In the case where unsatisfactory delineation prompts amendment necessary, the user can interactively segment the lung by just a shift on some of the previous-determined points to the desired locations, and random walker algorithm is run again with the amended input. By such a fusion, the benefits of both the automated and interactive segmentation are shared in a single architecture. [Copyright &y& Elsevier]

Objective. To determine the correlation between certain quality indicators for imaging services and the accurate interpretation of radiological exams for four frequent complaints: breast lumps, gastrointestinal discomfort, back pain, and symptoms of tuberculosis. Methods. Twenty-six radiology services in Argentina, Bolivia, Colombia, Cuba, and Mexico were assessed. The mammography and conventional radiographic/fluoroscopic equipment used in selected services were evaluated utilizing common protocols, data sheets, testing instruments, phantoms, and calibrated dosimetry systems. The studies were performed in medium-complexity facilities. Informed consent was obtained from all patients studied, and the confidentiality of results was guaranteed. The following parameters were documented: type of facility (public vs. private); population covered; patient workload; radiological and image-processing equipment and supplies; education and training of professional and technical staff; quality assurance and preventive maintenance programs, and adherence to radiation safety standards. The performance of x-ray units, image receptors and processors; darkroom and image viewing conditions; patient doses and image quality, were determined using standardized parameters in all cases. Independent panels of radiologists, recognized as experts by the local radiological society, assessed the quality of the clinical images obtained and performed a radiological interpretation for each patient using the same films and clinical history available to the institution's imaging physicians. The agreement between the panel of expert's reports and those of local radiologists was taken as an indicator of the radiological diagnostic accuracy. Results. Analyses were carried out of 366 mammograms, 343 radiological procedures for gastrointestinal complaints, 319 X-rays of the spinal column, and 157 chest radiographs. The agreement between the radiological interpretation of the panel of experts and of the local physician ranged from 70% to 100%, except in the case of spinal column films in Cuba (57.8%) and of mammograms in Mexico (33.3%), which the panel of experts found to be among those having the poorest quality. There was a significant positive correlation between the accuracy of the radiological interpretation and the quality of the radiological images. Image quality showed a positive correlation with the technicians' level of education and training. Studies performed in services that had automatic film processors and that complied with the indicators established for screen-film contact yielded better images and a higher proportion of studies with concordant results. More than 50% of the viewboxes did not satisfy the quality criteria for luminance and homogeneity. Conclusions. A good quality image is critical to achieving an accurate diagnosis. Emphasis should be placed on the continuing education of radiology technicians and on the acquisition and maintenance of adequate equipment and accessories, especially viewboxes, intensifying screens, and automatic film processors, given the impact they have on image quality. [ABSTRACT FROM AUTHOR]