An automated screening model for aortic emergencies using convolutional neural networks and cropped computed tomography angiography images of the aorta.

PURPOSE: Patients with aortic emergencies, such as aortic dissection and rupture, are at risk of rapid deterioration, necessitating prompt diagnosis. This study introduces a novel automated screening model for computed tomography angiography (CTA) of patients with aortic emergencies, utilizing deep convolutional neural network (DCNN) algorithms. METHODS: Our model (Model A) initially predicted the positions of the aorta in the original axial CTA images and extracted the sections containing the aorta from these images. Subsequently, it predicted whether the cropped images showed aortic lesions. To compare the predictive performance of Model A in identifying aortic emergencies, we also developed Model B, which directly predicted the presence or absence of aortic lesions in the original images. Ultimately, these models categorized patients based on the presence or absence of aortic emergencies, as determined by the number of consecutive images expected to show the lesion. RESULTS: The models were trained with 216 CTA scans and tested with 220 CTA scans. Model A demonstrated a higher area under the curve (AUC) for patient-level classification of aortic emergencies than Model B (0.995; 95% confidence interval [CI], 0.990-1.000 vs. 0.972; 95% CI, 0.950-0.994, respectively; p = 0.013). Among patients with aortic emergencies, the AUC of Model A for patient-level classification of aortic emergencies involving the ascending aorta was 0.971 (95% CI, 0.931-1.000). CONCLUSION: The model utilizing DCNNs and cropped CTA images of the aorta effectively screened CTA scans of patients with aortic emergencies. This study would help develop a computer-aided triage system for CT scans, prioritizing the reading for patients requiring urgent care and ultimately promoting rapid responses to patients with aortic emergencies.

Patient with penile metastasis from prostate cancer and survival over 5 years: A case report with longitudinal evaluation using computed tomography and magnetic resonance imaging.

Penile metastasis of malignant tumors is a very rare condition, often occurring as a part of systemic metastases, and is therefore associated with a poor prognosis. Although there have been reports of magnetic resonance imaging findings of penile metastasis, longitudinal imaging changes have not been presented previously. We report a case of a 80-year-old male patient with penile metastasis from prostate adenocarcinoma. First magnetic resonance imaging demonstrated multiple penile nodules in the left corpus cavernosum corpora cavernosa, and these nodules were fused and across the septum of the penis, forming an enlarged, diffusely spreading mass on the follow-up exam 5 years later. In this case, a longitudinal evaluation of magnetic resonance imaging demonstrated the course of the extension of the rare penile metastasis.

Chylothorax treated with targeted sclerotherapy by direct puncture of the lymphatic leakage site.

We report a novel application of targeted sclerotherapy to eradicate high-output chylothorax. The patient underwent thoracic duct embolization; however, cannulation of the thoracic duct failed, and thoracic duct disruption was performed. Leakage continued; therefore, the leakage site in the mediastinum was punctured directly under fluoroscopic guidance and a drainage catheter was inserted, followed by sclerotherapy using OK-432. Finally, leakage stopped and chylothorax improved. This technique may be useful for refractory chylothorax in patients where thoracic duct embolization fails.

Extensive perivascular dissemination of cerebral miliary tuberculomas: a case report and review of the literature.

Cerebral tuberculosis (TB) presents most frequently as meningitis in the basilar cistern; however, it can also manifest in various other ways, such as localized encephalitis, abscess, and tuberculoma. Here, focusing on imaging findings, we report an immunocompetent case who demonstrated multiple parenchymal lesions and was diagnosed with cerebral TB after testing positive on QuantiFERON (QTF); her clinical signs/symptoms and laboratory findings responded well to anti-TB medication therapy. The patient was a 60-year-old woman with the chief complaints of headache and consciousness disturbance. On admission, cerebrospinal fluid (CSF) examination showed increased monocyte predominance. T2-weighted images showed multiple, widely distributed hyperintense lesions in the periventricular and deep white matter. Gadolinium-enhanced three-dimensional gradient echo T1-weighed images revealed numerous granules or faint, small, enhanced foci in lesions in the periventricular and deep white matter, central gray matter, and hippocampus. Some abnormal sulcal enhancement was detected in the pia mater, indicating meningitis. Clinically, the diagnosis was difficult to make, but as the QTF result was positive, anti-TB drugs were administered, after which both the symptoms and CSF cell count showed improvement.