Search

Detection of pulmonary nodules on chest x-rays is an important task for radiologists. Previous studies have shown improved detection rates using gray-scale inversion. The purpose of our study was to compare the efficacy of gray-scale inversion in improving the detection of pulmonary nodules on chest x-rays for radiologists and machine learning models (ML). We created a mixed dataset consisting of 60, 2-view (posteroanterior view - PA and lateral view) chest x-rays with computed tomography confirmed nodule(s) and 62 normal chest x-rays. Twenty percent of the cases were separated for a testing dataset (24 total images). Data augmentation through mirroring and transfer learning was used for the remaining cases (784 total images) for supervised training of 4 ML models (grayscale PA, grayscale lateral, gray-scale inversion PA, and gray-scale inversion lateral) on Google's cloud-based AutoML platform. Three cardiothoracic radiologists analyzed the complete 2-view dataset (n=120) and, for comparison to the ML, the single-view testing subsets (12 images each). Gray-scale inversion (area under the curve (AUC) 0.80, 95% confidence interval (CI) 0.75-0.85) did not improve diagnostic performance for radiologists compared to grayscale (AUC 0.84, 95% CI 0.79-0.88). Gray-scale inversion also did not improve diagnostic performance for the ML. The ML did demonstrate higher sensitivity and negative predictive value for grayscale PA (72.7% and 75.0%), grayscale lateral (63.6% and 66.6%), and gray-scale inversion lateral views (72.7% and 76.9%), comparing favorably to the radiologists (63.9% and 72.3%, 27.8% and 58.3%, 19.5% and 50.5% respectively). In the limited testing dataset, the ML did demonstrate higher sensitivity and negative predictive value for grayscale PA (72.7% and 75.0%), grayscale lateral (63.6% and 66.6%), and gray-scale inversion lateral views (72.7% and 76.9%), comparing favorably to the radiologists (63.9% and 72.3%, 27.8% and 58.3%, 19.5% and 50.5%, respectively). Further investigation of other post-processing algorithms to improve diagnostic performance of ML is warranted.

Penetrating injuries of the thorax and abdomen, such as gunshot and stabbing, are rare in children. We present the case of a pediatric patient with a history of remote gunshot injury presenting with a late aneurysm in the left ventricle. (Level of Difficulty: Intermediate.)

The purpose of this article is to present a more recent radiological review to pulmonologists, radiologists and other clinicians of: typical and atypical manifestations of intrathoracic sarcoidosis, and highlighting its mimic-drug induced sarcoid like reaction. There is an association between immunotherapy and the development of sarcoid-like reactions. Clinicians and radiologists should be aware of this entity. Sarcoidosis is a multisystem inflammatory disease, of unknown etiology that is characterized by non caseating granulomas. It most commonly involves the lungs and lymph nodes. The common features of this entity have been extensively described in literature; however, 25–30% of cases present with atypical features. This review addresses the different manifestations of pulmonary sarcoidosis, highlighting the atypical appearances, which maybe misdiagnosed in the absence of tissue diagnosis. Radiologists should not hesitate to recommend tissue sampling in the setting of atypical findings and for definite diagnosis.

OBJECTIVE. Adult neoplasms of the ribs are a heterogeneous group consisting of both benign and aggressive entities. Rib neoplasms have a variety of overlapping imaging features, with much of the imaging data disjointed across the musculoskeletal, thoracic, and oncologic imaging literature. Arrival at accurate diagnosis can therefore be quite challenging. This article consolidates this information and introduces the reader to an algorithmic approach to rib lesion evaluation based on imaging. CONCLUSION. Rib neoplasms are a diverse group of benign and malignant entities, which often makes determining an accurate diagnosis challenging. Evaluation requires a multipronged approach that incorporates radiographic imaging features, nonradiographic imaging findings, lesion location, and clinical data.

This study aimed to develop a risk stratification model to differentiate benign and malignant MRI-imaged musculoskeletal soft-tissue tumours, informing decisions surrounding biopsy and follow-up imaging.Imaging of patients who underwent MRI and subsequent biopsy to evaluate a soft-tissue mass was retrospectively reviewed. Features analysed included patient age; tumour size; shape; margins; enhancement pattern; signal intensity pattern; deep fascia, neurovascular bundle, bone and joint involvement; and the presence of necrosis, haemorrhage, oedema and intralesional fat. Univariate comparisons, by final histopathological status, employed t-tests and chi-square tests, followed by simple and multiple logistic regressions. Variables included in the final multiple regression model were used to define a three-level risk stratification strategy.One-hundred and ten patients were included in the analysis. Univariate relationships were identified between malignancy and age, tumour size, deep fascia involvement, neurovascular involvement, necrosis, haemorrhage, oedema and heterogeneous enhancement (all P 0.01). Final multiple regression modelling included size, enhancement and oedema. Thirty of 40 (75%) tumours5 cm with surrounding oedema ('high risk') were malignant, 13 of 47 (28%) tumours with one or more of tumour size5 cm, surrounding oedema or heterogeneous enhancement ('moderate risk') were malignant, and none of the 16 tumours ≤5 cm with the absence of surrounding oedema and heterogeneous enhancement ('low risk') were malignant.A model including tumour size, enhancement and oedema has potential to stratify soft-tissue tumours into high-, intermediate- and low-risk categories; this may inform decisions surrounding biopsy and follow-up imaging.

Vascular mediated airway compromise is a fairly common clinical scenario. The diagnosis of innominate artery compression may be challenging due to lack of standardized imaging criteria for diagnosis or for surgical intervention.

Fistulas between the aorta and surrounding organs are extremely rare but can be fatal if they are not identified and treated promptly. Most of these fistulas are associated with a history of trauma or vascular intervention. However, spontaneous aortic fistulas (AoFs) can develop in patients with weakened vasculature, which can be due to advanced atherosclerotic disease, collagen-vascular disease, vasculitides, and/or hematogenous infections. The clinical features of AoFs are often nonspecific, with patients presenting with bleeding manifestations, back or abdominal pain, fever, and shock. Confirmation with invasive endoscopy is often impractical in the acute setting. Imaging plays an important role in the management of AoFs, and multiphasic multidetector CT angiography is the initial imaging examination of choice. Obvious signs of AoF include intravenous contrast material extravasation into the fistulizing hollow organ, tract visualization, and aortic graft migration into the adjacent structure. However, nonspecific indirect signs such as loss of fat planes and ectopic foci of gas are seen more commonly. These indirect signs can be confused with other entities such as infection and postoperative changes. Management may involve complex and staged surgical procedures, depending on the patient's clinical status, site of the fistula, presence of infection, and anticipated tissue friability. As endovascular interventions become more common, radiologists will need to have a high index of suspicion for this entity in patients who have a history of aneurysms, vascular repair, or trauma and present with bleeding.

Midaortic syndrome (MAS) is characterized by narrowing of the descending aorta between the distal aortic arch and the aortic bifurcation. We present the case of a 4-year-old male presenting with a murmur and diagnosed with MAS. He was treated with a thoracoabdominal bypass graft.

BACKGROUND. Chest radiographs (CXRs) are typically obtained early in patients admitted with coronavirus disease (COVID-19) and may help guide prognosis and initial management decisions. OBJECTIVE. The purpose of this study was to assess the performance of an admission CXR severity scoring system in predicting hospital outcomes in patients admitted with COVID-19. METHODS. This retrospective study included 240 patients (142 men, 98 women; median age, 65 [range, 50-80] years) admitted to the hospital from March 16 to April 13, 2020, with COVID-19 confirmed by real-time reverse-transcriptase polymerase chain reaction who underwent chest radiography within 24 hours of admission. Three attending chest radiologists and three radiology residents independently scored patients' admission CXRs using a 0- to 24-point composite scale (sum of scores that range from 0 to 3 for extent and severity of disease in upper and lower zones of left and right lungs). Interrater reliability of the score was assessed using the Kendall W coefficient. The mean score was obtained from the six readers' scores for further analyses. Demographic variables, clinical characteristics, and admission laboratory values were collected from electronic medical records. ROC analysis was performed to assess the association between CXR severity and mortality. Additional univariable and multivariable logistic regression models incorporating patient characteristics and laboratory values were tested for associations between CXR severity and clinical outcomes. RESULTS. Interrater reliability of CXR scores ranged from 0.687 to 0.737 for attending radiologists, from 0.653 to 0.762 for residents, and from 0.575 to 0.666 for all readers. A composite CXR score of 10 or higher on admission achieved 53.0% (35/66) sensitivity and 75.3% (131/174) specificity for predicting hospital mortality. Hospital mortality occurred in 44.9% (35/78) of patients with a high-risk admission CXR score (≥ 10) versus 19.1% (31/162) of patients with a low-risk CXR score ( .05). CONCLUSION. For patients admitted with COVID-19, an admission CXR severity score may help predict hospital mortality, intubation, and CRRT. CLINICAL IMPACT. CXR may assist risk assessment and clinical decision-making early in the course of COVID-19.

Coronavirus disease 2019 (COVID-19), a recently emerged lower respiratory tract illness, has quickly become a pandemic. The purpose of this review is to discuss and differentiate typical imaging findings of COVID-19 from those of other diseases, which can appear similar in the first instance. The typical CT findings of COVID-19 are bilateral and peripheral predominant ground-glass opacities. As per the Fleischner Society consensus statement, CT is appropriate in certain scenarios, including for patients who are at risk for and/or develop clinical worsening. The probability that CT findings represent COVID-19, however, depends largely on the pretest probability of infection, which is in turn defined by community prevalence of infection. When the community prevalence of COVID-19 is low, a large gap exists between positive predictive values of chest CT versus those of reverse transcriptase polymerase chain reaction. This implies that with use of chest CT there are a large number of false-positive results. Imaging differentiation is important for management and isolation purposes and for appropriate disposition of patients with false-positive CT findings. Herein the authors discuss differential pathology with close imaging resemblance to typical CT imaging features of COVID-19 and highlight CT features that may help differentiate COVID-19 from other conditions.

Systemic arterial air embolism (SAAE) is a rare but potentially life-threatening condition that may occur when air enters into pulmonary veins or directly into the systemic circulation after pulmonary procedures (biopsy or resection) or penetrating trauma to the lung. While venous air embolism is commonly reported, arterial air embolism is rare. Even a minor injury to the chest along with positive-pressure ventilation can cause SAAE. Small amounts of air may cause neurological or cardiac symptoms depending on the affected arteries, while massive embolism can result in fatal cardiovascular collapse. We discuss the various causes of SAAE, including trauma, computed tomography-guided lung biopsy, and various intervention procedures such as mechanical circulatory support device implantation, coronary catheterization, and atrial fibrillation repair. SAAE diagnosis can be overlooked because its symptoms are not specific, and confirmation of the presence of air in the arterial system is difficult. Although computed tomography is the optimal imaging tool for diagnosis, patient instability and resuscitation often precludes its use. When imaging is performed, awareness of the causes of SAAE allows the radiologist to promptly diagnose the condition and relay findings to the clinicians so that treatment, namely hyperbaric oxygen therapy, may be started promptly.

Generalized arterial calcification of infancy (GACI) is a rare genetic disease that affects the circulatory system and the large- and medium-sized arteries throughout the body. GACI usually occurs during fetal development. Babies with GACI are diagnosed early, generally soon after birth and in some cases before birth by fetal ultrasound.

The purpose of this article is to review the normal postoperative appearance of various sternotomy configurations as well as the pathophysiologic and imaging characteristics of sternotomy complications on radiographs, MDCT, MRI, and scintigraphy.Clinical signs of sternotomy complications are nonspecific and often overlap with normal postoperative changes. Knowledge of normal and abnormal imaging findings is essential to guide management and treatment.

A 9-week-old girl presented with poor visual responsiveness and congenital seesaw nystagmus. Congenital seesaw nystagmus usually implies a structural anomaly, such as achiasma, and warrants evaluation with MRI (figure).1 Isolated absence of optic chiasm is extremely uncommon.2 In nondecussating retinal-fugal fiber syndrome (achiasmatic syndrome), there is failure of decussation of nasal retinal fibers, with the misrouted nasal fibers projecting and misaligning with projections from the temporal retina of the same eye, leading to reversal of the left and right half of visual field coordinates (“mirror reversal”).1 Mutation in a homeobox gene may underlie this aberration in pathfinding of retinal axons seen in achiasma.2

The clinical presentation of an axillary lump, in majority of cases, raises suspicion of an enlarged lymph node due to malignant causes. In this case report, we established a diagnosis of an axillary lump caused by fat necrosis. We present this case report with review of the literature to familiarize clinicians with this condition.

The use of selective salpingography and tubal cannulation in the management of patients with proximal tubal obstruction in the UK is variable in spite of a National Institute of Clinical Excellence (NICE) recommendation. A retrospective review was performed of patients who underwent selective salpingography and fallopian tube catheterisation (SS/TC). A total of 16 patients underwent this procedure. Patency of at least one tube was achieved in 16 of the 20 tubes attempted. Pregnancy was achieved in 35% of patients after the procedure. The ectopic pregnancy rate was 7%. One pregnancy occurred in a patient after the procedure was repeated. The availability of laparoscopy findings was valuable in identifying tubes with established disease and where the procedure might be expected to be unsuccessful or result in a high risk of ectopic pregnancy. Hence, selective salpingography and tubal cannulation procedure should be considered as a therapeutic option for all patients with proximal tubal block before considering IVF or tubal surgery.