Background/Objectives: To develop and validate a model system using deep learning algorithms for the automatic detection of type A aortic dissection (AD), and differentiate it from normal and type B AD patients. Methods: In this retrospective study, a deep learning model is developed, based on aortic computed tomography angiography (CTA) scans of 498 patients using training, validation and test sets of 398, 50 and 50 patients, respectively. An independent test set of 316 patients is used to validate and evaluate its performance. Results: Our model comprises two components. The first one is an objection detection model, which can identify the aorta from CTA. The second one is a dissection classification model, which can automatically detect the presence of aortic dissection and determine its type based on Stanford classification. Overall, the sensitivity and specificity for Type A AD were 0.969 and 0.982, for Type B AD were 0.946 and 0.996 and for normal cases were 0.988 and 1.000, respectively. The average processing time per CTA scan was 7.9 ± 2.8 s. (mean ± standard deviation). Conclusions: This deep learning automatic model can accurately and quickly detect type A AD patients, and could serve as an imaging triage in an emergency setting and facilitate early intervention and surgery to decrease the mortality rates of type A AD patients.

The differences in chest computed tomography (CT) image quality may affect the tumor stage. The aim of this study was to compare the image quality and accuracy of chest CT via central vein and peripheral vein enhancement. Fifty consecutive patients were enrolled from a tertiary medical center in Taiwan from May 2016 to March 2019. All the patients received a chest CT via central vein enhancement prior to neoadjuvant concurrent chemoradiation in order to compare the chest CT that was obtained via the peripheral vein. In addition, blind independent central reviews of chest CT via central vein and peripheral vein enhancement were conducted. For T and N stage, chest CT via central vein enhancement had a greater consistency with endoscopic ultrasonography and positron-emission tomography-computed tomography findings (kappa coefficients 0.4471 and 0.5564, respectively). In addition, chest CT via central vein enhancement also showed excellent agreement in the blind independent central review (kappa coefficient 0.9157). The changes in the T and N stage resulted in stage migration in 16 patients. Chest CT via central vein enhancement eliminated peripheral vein regurgitation and also provided more precise clinical staging. This study is registered under the registered NCT number 02887261.

Background: The International Society of Urological Pathology (ISUP) grade and positive surgical margins (PSMs) after radical prostatectomy (RP) may reflect the prognosis of prostate cancer (PCa) patients. This study aimed to investigate whether DCE-MRI parameters (i.e., K^trans, k_ep, and IAUC) could predict ISUP grade and PSMs after RP. Method: Forty-five PCa patients underwent preoperative DCE-MRI. The clinical characteristics and DCE-MRI parameters of the 45 patients were compared between the low- and high-risk (i.e., ISUP grades III-V) groups and between patients with or without PSMs after RP. Multivariate logistic regression analysis was used to identify the significant predictors of placement in the high-risk group and PSMs. Results: The DCE parameter K^trans-max was significantly higher in the high-risk group than in the low-risk group (p = 0.028) and was also a significant predictor of placement in the high-risk group (odds ratio [OR] = 1.032, 95% confidence interval [CI] = 1.005–1.060, p = 0.021). Patients with PSMs had significantly higher prostate-specific antigen (PSA) titers, positive biopsy core percentages, K^trans-max, k_ep-median, and k_ep-max than others (all p < 0.05). Of these, positive biopsy core percentage (OR = 1.035, 95% CI = 1.003–1.068, p = 0.032) and k_ep-max (OR = 1.078, 95% CI = 1.012–1.148, p = 0.020) were significant predictors of PSMs. Conclusion: Preoperative DCE-MRI parameters, specifically K^trans-max and k_ep-max, could potentially serve as preoperative imaging biomarkers for postoperative PCa prognosis based on their predictability of PCa risk group and PSM on RP, respectively.