A 61-year-old woman had extracardiac unruptured aneurysms of the right and noncoronary sinuses of Valsalva, detected incidentally on electrocardiogram taken for a physical checkup. Two-dimensional echocardiography revealed that the sizes of the aneurysm of the right and noncoronary sinuses were 41×40 and 38×28mm respectively, but the shape of left coronary sinus was almost normal. The aortic valve leaflet was normal and the diameter of the aortic annulus and sinotubular junction was 23 and 27mm respectively. The Doppler color-flow echocardiogram showed moderate aortic regurgitation which resulted in prolapse of the right aortic cusp due to deformity of the annulus. We performed modified aortic root remodeling using a tailored Dacron graft to preserve the native aortic valve. Right and noncoronary sinuses of Valsalva were all excised with a small button of the aortic wall around the ostia of the right coronary artery. The left coronary sinus was left as it was. Then each commissure received sub-commissural annuloplasty and was pulled up. The defect of Valsalva was reconstructed with a 26mm Dacron tube graft, the proximal end of which was tailored to a scallop shape and that correspond to left coronary sinus was excised. The right coronary artery was reimplanted utilizing the Carrel patch method. Although we needed additional CABG to the right coronary artery and IABP support due to vasospasm of the right coronary artery, the postoperative course was uneventful. Echocardiography of the aortic valve before discharge showed a normal function without regurgitation.

Objective: Human papillomavirus subtypes are predictive indicators of cervical intraepithelial neoplasia (CIN) progression. While colposcopy is also an essential part of cervical cancer prevention, its accuracy and reproducibility are limited because of subjective evaluation. This study aimed to develop an artificial intelligence (AI) algorithm that can accurately detect the optimal lesion associated with prognosis using colposcopic images of CIN2 patients by utilizing objective AI diagnosis. Methods: We identified colposcopic findings associated with the prognosis of patients with CIN2. We developed a convolutional neural network that can automatically detect the rate of high-grade lesions in the uterovaginal area in 12 segments. We finally evaluated the detection accuracy of our AI algorithm compared with the scores by multiple gynecologic oncologists. Results: High-grade lesion occupancy in the uterovaginal area detected by senior colposcopists was significantly correlated with the prognosis of patients with CIN2. The detection rate for high-grade lesions in 12 segments of the uterovaginal area by the AI system was 62.1% for recall, and the overall correct response rate was 89.7%. Moreover, the percentage of high-grade lesions detected by the AI system was significantly correlated with the rate detected by multiple gynecologic senior oncologists (r=0.61). Conclusion Our novel AI algorithm can accurately determine high-grade lesions associated with prognosis on colposcopic images, and these results provide an insight into the additional utility of colposcopy for the management of patients with CIN2.