Automatic identification of frontal (posteroanterior/anteroposterior) vs. lateral chest radiographs is an important preprocessing step in medical imaging. A recent approach by Amura et al. (Procs SPIE 2002; 4684: 308-315) is based on manual selection and combination of about 500 radiographs to generate as much as 24 templates by pixel-wise summing up the references, and a correctness rate of 99...

Many radiological studies can reveal the presence of several co-existing abnormalities, each one represented by a distinct visual pattern. In this article we address the problem of learning a distance metric for plain radiographs that captures a notion of “radiological similarity”: two chest radiographs are considered to be similar if they share similar abnormalities. Deep convolutional neural ...

We retrospectively reviewed the medical records and chest radiographs of 118 patients who presented during January 1998 to October 2002 at Songklanagarin Hospital in Hat Yai, Songkhla Province, Thailand who had a high serum immunofluorescent assay titer for leptospirosis. Twenty-nine of 118 (24%) patients had abnormal chest films. Nearly all of these patients had respiratory symptoms and needed...

OBJECTIVE To determine the change in chest radiograph use if each chest radiograph requires a separate order and clinical indication. DESIGN Prospective, nonrandomized, controlled design with an intervention. SETTING The pediatric intensive care unit (PICU) at Primary Children's Medical Center, Salt Lake City, UT. PATIENTS The study comprised 3,727 PICU patients treated between 1992 and 1...

Machine learning approaches hold great potential for the automated detection of lung nodules in chest radiographs, but training the algorithms requires vary large amounts of manually annotated images, which are difficult to obtain. Weak labels indicating whether a radiograph is likely to contain pulmonary nodules are typically easier to obtain at scale by parsing historical free-text radiologic...

Initial clinical experience with a system for the digitization, processing, and display of film radiographs is described. Film is digitized using a high-intensity laser scanner; the recorded image data may then be subjected to a wide variety of processing options, with display of processed images on television monitors. The possibilities of clinical applications to processing and display of che...

A novel active shape model (ASM) segmentation scheme is proposed, for the detection of the lung field boundaries in chest radiographs. The proposed scheme is robust in the presence of weak lung field boundaries, which are recognized as a common cause of missegmentation. This situation is prevalent in chest radiographs obtained from patients with abnormalities, such as lung consolidations, or ev...

OBJECTIVES To evaluate the chest radiographs of children diagnosed with non-severe pneumonia on the basis of the current World Health Organization guidelines (fast breathing alone) for radiological evidence of pneumonia. DESIGN Descriptive analysis. SETTING Outpatient departments of six hospitals in four cities in Pakistan. PARTICIPANTS 2000 children with non-severe pneumonia were enrolle...

BACKGROUND Many otherwise healthy Kenyans are required to obtain chest radiographs as part of routine medical examination to exclude pulmonary TB, a condition of significant public health concern. Many of these people are required to have these radiographs taken yearly as part of routine check-up. No local data is available to support this practice. Though a quick procedure to perform and readi...

Recent advances in deep learning have led to a promising performance many medical image analysis tasks. As the most commonly performed radiological exam, chest radiographs are particularly important modality for which variety of applications been researched. The release multiple, large, publicly available X-ray datasets recent years has encouraged research interest and boosted number publicatio...