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.

The aim of this study was to investigate physiological changes in cardiac area and diameters between inspiratory and expiratory chest computed tomography (CT), and to assess their correlation with lung size change and influence on cardiothoracic ratio (CTR) measurements. The institutional review board of our institution approved this study, and informed consent was waived. Forty-three subjects underwent inspiratory and expiratory chest CT as part of routine clinical care. On both inspiratory and expiratory scans, lung volumes and maximum lung diameters (transverse and vertical directions) were measured. The maximum cardiac cross-sectional area (CSA) and the maximum transverse cardiac diameter were measured on both scans, and the CT-based CTR was calculated. Changes in the lung and cardiac measurements were expressed as the expiratory/inspiratory (E/I) ratios. Comparisons between inspiratory and expiratory measurements were made by the Wilcoxon signed-rank test. Correlations between the E/I ratios of lung and heart measurements were evaluated by Spearman’s rank correlation analysis. Cardiac CSA and transverse cardiac diameter was significantly larger on expiratory than on inspiratory CT (p < 0.0001). Significant negative correlations were found between the E/I ratios of these cardiac measurements and the E/I ratios of lung volume and vertical lung diameter (p < 0.01). CT-based CTR was significantly larger on expiration than on inspiration (p < 0.0001). Heart size on chest CT depends on the phase of ventilation, and is correlated with changes in lung volume and craniocaudal lung diameter. The CTR is also significantly influenced by ventilation.