This DE CT virtual noncalcium technique can subtract calcium from cancellous bone, allowing bone marrow assessment and potentially making posttraumatic bone bruises of the knee detectable with CT.

The aim of this study was to define the imaging characteristics of primary and recurrent gastrointestinal stromal tumors (GIST) in computed tomography with respect to the tumor size. Computed tomography was performed in 35 patients with histologically confirmed gastrointestinal stromal tumors and analyzed retrospectively by two experienced and independent radiologist. The following morphologic tumor characteristics of primary ( n=20) and ( n=16) recurrent tumors were evaluated according to tumor size, shape, homogeneity, density compared with liver, contrast enhancement, presence of calcifications, ulcerations, fistula or distant metastases and the anatomical relationship to the intestinal wall, and the infiltration of adjacent visceral organs. Small GIST (<5 cm) showed a sharp tumor margin with homogeneous density and structure on unenhanced and contrast-enhanced images, and were characterized by an intraluminal tumor growth. Intermediate sized GIST (>5-10 cm) demonstrated an irregular shape, inhomogeneous density on unenhanced and contrast-enhanced images, a combined intra- and extraluminal tumor growth with aggressive findings, and infiltration of adjacent organs in 9 primary diagnosed and 2 recurrent tumors. Large GIST (>10 cm), which were observed in 8 primary tumors and 11 recurrent tumors, showed an irregular margin with inhomogeneous density and aggressive findings, and were characterized by signs of malignancy such as distant and peritoneal metastases. Small recurrent tumors had a similar appearance as compared with large primary tumors. Computed tomography gives additional information with respect to the relationship of gastrointestinal stromal tumor to the gastrointestinal wall and surrounding organs, and it detects distant metastasis. Primary and recurrent GIST demonstrate characteristic CT imaging features which are related to tumor size. Aggressive findings and signs of malignancy are found in larger tumors and in recurrent disease. Computed tomography is useful in detection and characterization of primary and recurrent tumors with regard to tumor growth pattern, tumor size, and varied appearances of gastrointestinal stromal tumors, and indirectly gives hints regarding dignity and therefore prognostic outcome.

THORACIC IMAGINGC hest radiography is the most common radiologic examination, despite its inferiority to low-dose CT, for lung cancer screening (1). Some authors showed that up to 90% of "missed" lung cancer nodules can be found when the baseline chest radiograph is re-reviewed with the benefit of the follow-up examination showing the mass that has grown in size (2). Misdiagnoses of lung cancer can occur for many reasons. This oversight can be due to a lack of perception of the nodule, the decision to ignore a subtle density, and the satisfaction of search when another abnormality is identified (3-5). Lesion characteristics including size, density, and location make the detection of lung nodules more challenging on chest radiographs (6-8).To improve the efficacy of chest radiography for nodule detection, computer-aided detection (CAD) software has been developed and evaluated. In 2004, Kakeda et al (9) tested their CAD and reported that it was beneficial in analyzing radiographs with nodules but had an average falsepositive rate of 3.15 per image. de Hoop et al (10) showed Purpose: To compare the performance of radiologists in detecting malignant pulmonary nodules on chest radiographs when assisted by deep learning-based DCNN software with that of radiologists or DCNN software alone in a multicenter setting. Materials and Methods: Investigators at four medical centers retrospectively identified 600 lung cancer-containing chest radiographs and 200 normal chest radiographs. Each radiograph with a lung cancer had at least one malignant nodule confirmed by CT and pathologic examination. Twelve radiologists from the four centers independently analyzed the chest radiographs and marked regions of interest. Commercially available deep learning-based computer-aided detection software separately trained, tested, and validated with 19 330 radiographs was used to find suspicious nodules. The radiologists then reviewed the images with the assistance of DCNN software. The sensitivity and number of false-positive findings per image of DCNN software, radiologists alone, and radiologists with the use of DCNN software were analyzed by using logistic regression and Poisson regression.

This is a condensed summary of an international multisociety statement on ethics of artificial intelligence (AI) in radiology produced by the ACR, European Society of Radiology, RSNA, Society for Imaging Informatics in Medicine, European Society of Medical Imaging Informatics, Canadian Association of Radiologists, and American Association of Physicists in Medicine. AI has great potential to increase efficiency and accuracy throughout radiology, but it also carries inherent pitfalls and biases. Widespread use of AI-based intelligent and autonomous systems in radiology can increase the risk of systemic errors with high consequence and highlights complex ethical and societal issues. Currently, there is little experience using AI for patient care in diverse clinical settings. Extensive research is needed to understand how to best deploy AI in clinical practice. This statement highlights our consensus that ethical use of AI in radiology should promote well-being, minimize harm, and ensure that the benefits and harms are distributed among stakeholders in a just manner. We believe AI should respect human rights and freedoms, including dignity and privacy. It should be designed for maximum transparency and dependability. Ultimate responsibility and accountability for AI remains with its human designers and operators for the foreseeable future. The radiology community should start now to develop codes of ethics and practice for AI that promote any use that helps patients and the common good and should block use of radiology data and algorithms for financial gain without those two attributes.

Insertion of percutaneous iliosacral screws with fluoroscopic guidance is associated with a relatively high screw malposition rate and long radiation exposure. We asked whether radiation exposure was reduced and screw position improved in patients having percutaneous iliosacral screw insertion using computer-assisted navigation compared with patients having conventional fluoroscopic screw placement. We inserted 26 screws in 24 patients using the navigation system and 35 screws in 32 patients using the conventional fluoroscopic technique. Two subgroups were analyzed, one in which only one iliosacral screw was placed and another with additional use of an external fixator. We determined screw positions by computed tomography and compared operation time, radiation exposure, and screw position. We observed no difference in operative times. Radiation exposure was reduced for the patients and operating room personnel with computer assistance. The postoperative computed tomography scan showed better screw position and fewer malpositioned screws in the three-dimensional navigated groups. Computer navigation reduced malposition rate and radiation exposure. Level of Evidence: Level II, therapeutic study. See the Guidelines for Authors for a complete description of levels of evidence.

This is a condensed summary of an international multisociety statement on ethics of artificial intelligence (AI) in radiology produced by the ACR, European Society of Radiology, RSNA, Society for Imaging Informatics in Medicine, European Society of Medical Imaging Informatics, Canadian Association of Radiologists, and American Association of Physicists in Medicine. AI has great potential to increase efficiency and accuracy throughout radiology, but also carries inherent pitfalls and biases. Widespread use of AI-based intelligent and autonomous systems in radiology can increase the risk of systemic errors with high consequence, and highlights complex ethical and societal issues. Currently, there is little experience using AI for patient care in diverse clinical settings. Extensive research is needed to understand how to best deploy AI in clinical practice. This statement highlights our consensus that ethical use of AI in radiology should promote well-being, minimize harm, and ensure that the benefits and harms are distributed among stakeholders in a just manner. We believe AI should respect human rights and freedoms, including dignity and privacy. It should be designed for maximum transparency and dependability. Ultimate responsibility and accountability for AI remains with its human designers and operators for the foreseeable future. The radiology community should start now to develop codes of ethics and practice for AI which promote any use that helps patients and the common good and should block use of radiology data and algorithms for financial gain without those two attributes.

No abstract

No abstract