Chest radiographs (CXR) are the most performed imaging tests and rank high among the radiographic exams with suboptimal quality and high rejection rates. Suboptimal CXRs can cause delays in patient care and pitfalls in radiographic interpretation, given their ubiquitous use in the diagnosis and management of acute and chronic ailments. Suboptimal CXRs can also compound and lead to high inter-radiologist variations in CXR interpretation. While advances in radiography with transitions to computerized and digital radiography have reduced the prevalence of suboptimal exams, the problem persists. Advances in machine learning and artificial intelligence (AI), particularly in the radiographic acquisition, triage, and interpretation of CXRs, could offer a plausible solution for suboptimal CXRs. We review the literature on suboptimal CXRs and the potential use of AI to help reduce the prevalence of suboptimal CXRs.

Majority of health institutions in Croatia do not have medical physicists in diagnostic radiology. Regarding this, in the west region of Croatia collaboration between public health institution and University Hospital Rijeka was initiated in 2015. Quality Assurance program was implemented in these public health institutions during 2015 and 2016 and the next step was to assess patient doses for the most frequent X-ray examinations. This included five public health institutions: 1 university hospital, 1 general hospital, 1 special hospital, 2 public health institutions with 13 facilities. The aim of this study was to carry out assessment of patient doses and to establish local diagnostic reference levels of entrance surface air kerma for every institution for six most frequent X-ray examinations. Also, local diagnostic reference levels for the whole west region of Croatia were established and compared with the national diagnostic reference levels and latest published data. Median entrance surface air kerma values for thorax PA, thorax LAT, cervical spine AP, thoracic spine AP, lumbar spine AP, pelvis AP and sinuses are 0.14 mGy, 0.50 mGy, 0.52 mGy, 1.50 mGy, 2.52 mGy, 2.03 mGy, and 1.03 mGy, respectively. Diagnostic reference levels proposed for our region were comparable with other studies.