Effects of a comprehensive brain computed tomography deep learning model on radiologist detection accuracy.

OBJECTIVES: Non-contrast computed tomography of the brain (NCCTB) is commonly used to detect intracranial pathology but is subject to interpretation errors. Machine learning can augment clinical decision-making and improve NCCTB scan interpretation. This retrospective detection accuracy study assessed the performance of radiologists assisted by a deep learning model and compared the standalone performance of the model with that of unassisted radiologists. METHODS: A deep learning model was trained on 212,484 NCCTB scans drawn from a private radiology group in Australia. Scans from inpatient, outpatient, and emergency settings were included. Scan inclusion criteria were age ≥ 18 years and series slice thickness ≤ 1.5 mm. Thirty-two radiologists reviewed 2848 scans with and without the assistance of the deep learning system and rated their confidence in the presence of each finding using a 7-point scale. Differences in AUC and Matthews correlation coefficient (MCC) were calculated using a ground-truth gold standard. RESULTS: The model demonstrated an average area under the receiver operating characteristic curve (AUC) of 0.93 across 144 NCCTB findings and significantly improved radiologist interpretation performance. Assisted and unassisted radiologists demonstrated an average AUC of 0.79 and 0.73 across 22 grouped parent findings and 0.72 and 0.68 across 189 child findings, respectively. When assisted by the model, radiologist AUC was significantly improved for 91 findings (158 findings were non-inferior), and reading time was significantly reduced. CONCLUSIONS: The assistance of a comprehensive deep learning model significantly improved radiologist detection accuracy across a wide range of clinical findings and demonstrated the potential to improve NCCTB interpretation. CLINICAL RELEVANCE STATEMENT: This study evaluated a comprehensive CT brain deep learning model, which performed strongly, improved the performance of radiologists, and reduced interpretation time. The model may reduce errors, improve efficiency, facilitate triage, and better enable the delivery of timely patient care. KEY POINTS: • This study demonstrated that the use of a comprehensive deep learning system assisted radiologists in the detection of a wide range of abnormalities on non-contrast brain computed tomography scans. • The deep learning model demonstrated an average area under the receiver operating characteristic curve of 0.93 across 144 findings and significantly improved radiologist interpretation performance. • The assistance of the comprehensive deep learning model significantly reduced the time required for radiologists to interpret computed tomography scans of the brain.

Pseudothrombosis due to blood-contrast level in the infrarenal vena cava.

Filling defects within the inferior vena cava (IVC) are common findings on computed tomography (CT); nevertheless, a majority of these defects are attributed to artifacts. The documentation pertaining to pseudothrombosis specifically affecting the infrarenal vena cava is notably insufficient in current literature. The aim of this study is to present a case demonstrating a blood-contrast level in the infrarenal vena cava, resembling an intraluminal filling defect.

Acute acalculous cholecystitis with portal cavernoma: A case report with literature review.

Portal cavernoma cholangiopathy (PCC) refers to morphological changes in the intrahepatic, extrahepatic biliary system, along with the gallbladder (GB), induced by portal cavernoma (PC). Acute acalculous cholecystitis (AAC) represents an infrequent clinical manifestation of PCC. Given the inadequacy of documentation within medical literature, AAC may go undiagnosed among patients with PC presenting symptoms of right upper quadrant pain. The current study aims to report a case of acute acalculous cholecystitis secondary to portal cavernoma, focusing on radiological findings, with a brief review of literature.

Preoperative magnetic resonance imaging of anal fistulas with scrotal extension: a retrospective study.

Introduction: This study aimed to elucidate the magnetic resonance (MR) characteristics of anal fistulas extending to the scrotum, and the applicable rules, and to correlate MR features with surgical findings. Methods: We conducted a retrospective study in 150 consecutive patients with anal fistulas extending into the scrotum, who were diagnosed and underwent surgery at University Medical Center Ho Chi Minh City between January 2017 and April 2022. MR findings were evaluated and compared with surgical findings using Cohens kappa coefficient (k) with a 95% confidence interval. Results: 150 patients (mean age 37.6 ± 10.9 years) with 166 fistulas, including 150 anal fistulas with scrotal extension. Most fistulas were low transsphincteric (80.0%, 120/150 patients). There was a strong agreement for primary tract classification and detecting the location of internal openings between MRI and surgical findings with k = 0.83 (0.780.87) and k = 0.89 (0.85 0.93) (p<0.001), respectively. There is a significant correlation between the location of internal openings and the type of fistula (p<0.05). Low transsphincteric fistulas were predominant in the anterior group (103/122 patients vs. 10/19 patients), while in the posterior group, it was more common in the high transsphincteric fistulas (7/19 patients vs. 14/122 patients), and the intersphincteric fistulas (1/19 patients vs. 5/122 patients); and the suprasphincteric fistulas were only seen in the posterior group (1 patient). Conclusion: Anal fistulas with scrotal extension are exceptions to Goodsalls rule. Albeit long-tract fistulas, most are low transsphincteric and have anterior internal openings.

Pial arteriovenous fistula associated with vein of Galen dilatation in adult: A case report and MRI findings.

Pial arteriovenous fistula (PAVF) is a rare intracranial vascular lesion where direct communication exists between one or more pial arteries and a cerebral vein, without an intervening nidus and located in the subpial meningeal space. When the drainage of PAVF involves a dilated, but already formed vein of Galen (VOG), it should be distinguished from other vascular lesions located in this area, because their angio-architecture, natural history and treatment options are different. A 33-year-old female was admitted to our hospital with a history of new-onset generalized tonic-clonic seizures. Clinical examination showed no neurological deficit. Magnetic resonance imaging (MRI) and magnetic resonance angiography (MRA) depicted an arteriovenous fistula that was fed by the pial branches from left posterior cerebral artery and drained into the medial atrial vein before joining the VOG confluence and causing VOG dilatation. No nidus between the feeding arteries and draining vein, dural feeding arteries, or anatomical variations commonly seen with true vein of Galen aneurysmal malformations (VOGM) were found. These finding suggested a diagnosis of a PAVF associated with vein of Galen dilatation, which was confirmed by digital subtraction angiography. The patient was treated with transarterial glue embolization in 1 section, resulting in nearly complete occlusion of the fistula. Conventional MRI and MRA are noninvasive modalities that can provide valuable information regarding the anatomic localization of the fistula point, the feeding arteries, the venous sac, and their relationship with surrounding structures. These techniques are helpful for accurate diagnosis and treatment planning.

Late Onset of Organizing Pneumonia Following SARS-CoV-2 Infection: A Case Report of Successful Management and Review Literature.

A late consequence of COVID-19, organizing pneumonia is characterized by significant imaging and pathological abnormalities. The goals of this study are to better understand these abnormalities. The use of corticoid continues to be the recommended course of treatment for COVID-19. On the other hand, it is not clear whether or not corticoid has the same impact on organizing pneumonia after COVID-19. A 53-year-old male patient was identified with organized pneumonia following COVID-19 infection. He was diagnosed after experiencing severe respiratory symptoms several days with no improvement. We initiated a high dose of corticoid based on imaging and pathological findings and observed a significant response. In addition, we looked into the research that has been done concerning the diagnosis and treatment of this peculiar ailment. Patients who have been diagnosed with pneumonia after COVID 19 are required to undergo a reevaluation that includes a chest CT scan, and some of these patients may be candidates for an early lung biopsy. The most effective and convincing therapy for COVID-19-induced organizing pneumonia is corticoid treatment at a dose equivalent to 0.5 mg/kg/day of prednisone.

Superiority of left heart deformation in early anthracycline-related cardiac dysfunction detection.

OBJECTIVE: This study aimed to assess the incidence of early cancer therapy-related cardiac dysfunction (CTRCD) and the characteristics of left and right heart deformations during anthracycline chemotherapy. METHODS: We prospectively enrolled a cohort of 351 chemotherapy-naïve women with breast cancer and cardiovascular risk factors who were scheduled to receive anthracycline. The left ventricular ejection fraction (LVEF), left ventricular global longitudinal strain (LV-GLS) and right ventricular and left atrial longitudinal strains were evaluated using echocardiography at baseline, before every subsequent cycles and at 3 weeks after the final anthracycline dose. CTRCD was defined as a new LVEF reduction by ≥10 percentage points to an LVEF<50% and/or a new relative decline in GLS by >15% from the baseline value. RESULTS: Eighteen (5.1%) patients had evidence of asymptomatic CTRCD during anthracycline treatment, and 50% developed CTRCD before completing the chemotherapy regimen. In the CTRCD group, while LV-GLS decrease significantly after the first dose of anthracycline, the reduction of right ventricular free-wall longitudinal strain and left atrial reservoir strain were observed after the second dose. Other strain indices could not be used to identify early CTRCD. CONCLUSIONS: Cardiotoxicity appeared soon after the initiation of anthracycline chemotherapy. Among the left-heart and right-heart mechanics, LV-GLS remains the best deformation indicator for detecting early CTRCD.

Diffuse axonal injury: a case report and MRI findings.

Diffuse axonal injury (DAI) is one of the most severe types of primary traumatic brain injury. In recent years, MR imaging has been gaining popularity as an adjunctive imaging method in patients with DAI. In this case report, we describe MRI findings of an 11-year-old male patient diagnosed with DAI and discuss the role of different sequences in the evaluation of DAI.