Spontaneous pneumomediastinum (SPM) is described as free air or gas located within the mediastinum that is not associated with any noticeable cause such as chest trauma. SPM has been associated with many conditions and triggers, including bronchial asthma, diabetic ketoacidosis, forceful straining during exercise, inhalation of drugs, as well as other activities associated with the Valsalva maneuver. The Macklin effect appears on thoracic computed tomography (CT) as linear collections of air contiguous to the bronchovascular sheaths. With the recent availability of multidetector-row CT, the Macklin effect has been seen in the clinical setting more frequently than expected. The aim of this review article is to describe the CT imaging spectrum of the Macklin effect in patients with SPM, focusing on the common appearance of the Macklin effect, pneumorrhachis, and persistent SPM with pneumatocele.

We investigated the value of deep learning (DL) in differentiating between benign and metastatic cervical lymph nodes (LNs) using pretreatment contrast-enhanced computed tomography (CT). This retrospective study analyzed 86 metastatic and 234 benign (non-metastatic) cervical LNs at levels I–V in 39 patients with oral squamous cell carcinoma (OSCC) who underwent preoperative CT and neck dissection. LNs were randomly divided into training (70%), validation (10%), and test (20%) sets. For the validation and test sets, cervical LNs at levels I–II were evaluated. Convolutional neural network analysis was performed using Xception architecture. Two radiologists evaluated the possibility of metastasis to cervical LNs using a 4-point scale. The area under the curve of the DL model and the radiologists’ assessments were calculated and compared at levels I–II, I, and II. In the test set, the area under the curves at levels I–II (0.898) and II (0.967) were significantly higher than those of each reader (both, p < 0.05). DL analysis of pretreatment contrast-enhanced CT can help classify cervical LNs in patients with OSCC with better diagnostic performance than radiologists’ assessments alone. DL may be a valuable diagnostic tool for differentiating between benign and metastatic cervical LNs.

Though a few reports have summarized the computed tomography (CT) findings of pulmonary metastases from angiosarcoma, the detailed CT findings of cysts are not well known, except for their characteristic thin walls. To retrospectively summarize the CT findings of pulmonary metastases from angiosarcoma, focusing mainly on the CT findings of cysts. Thirty-three patients with pulmonary metastases from angiosarcoma were selected retrospectively. Two radiologists reviewed and assessed patients’ chest CT images on a consensus basis for nodules, cysts, the CT halo sign, pneumothorax, pleural effusion, and enlarged lymph nodes. Cysts were also evaluated by wall thickness and smoothness, air-fluid levels, and vessels or bronchi penetrating the cysts. The relationship between cysts and pneumothorax was assessed using the Chi-square test. Nodules were found in 28 (85%) patients. Cysts were found in 19 (58%) patients; 17 had thin and smooth walls, 10 had thin and irregular walls, and four had thick and irregular walls. In addition, 12 patients showed vessels or bronchi penetrating the cysts, and six showed air-fluid levels. The CT halo sign, pneumothorax, pleural effusion, and mediastinal lymphadenopathy were seen in 19 (58%), 16 (48%), 26 (78.8%), and five (15.2%) patients, respectively. Pneumothorax occurred significantly more frequently in patients with cysts (P = 0.002). Cysts showed variability in their walls, and air-fluid levels and vessels or bronchi penetrating the cysts appeared to be characteristic findings, which may be useful for detection and accurate diagnosis in patients with pulmonary metastases from angiosarcoma.