Publications by authors named "Hai-Man Song"
Objective: This study aimed to describe our experience of managing cesarean scar pregnancy (CSP) and outcomes depending on ultrasound imaging features.
Methods: A retrospective, cohort observational study was performed on 31 consecutive patients with CSP at 6 to 9 weeks of gestation from April 2015 to January 2021. All patients were evaluated for the residual myometrial thickness (RMT), growth direction of the gestational sac (GS), blood flow, and chorionic parenchyma using ultrasonography.
Article Synopsis
- A study aimed to develop a convolutional neural network (CNN) for classifying breast masses into four categories: inflammatory masses, adenosis, benign tumors, and malignant tumors, using ultrasound images.
- The study involved 3623 breast cancer patients, with data split into training and test groups, and compared different imaging models including 2D and color Doppler flow imaging.
- The 2D-CDFI model achieved the highest accuracy at 89.2% in classifying the types of masses, outperforming the other two models (2D at 87.9% and 2D-CDFI-PW at 88.7%).
This study aimed to explore the value of a real-time comparative observation method using contrast-enhanced ultrasound (CEUS) for discriminating between bronchial and pulmonary arterial phases in diagnosing lung diseases. Forty-nine patients with 50 pulmonary lesions (45 peripheral lesions and five central lesions with obstructive atelectasis, including 36 malignant tumors, five tuberculomas, four inflammatory pseudotumors and five pneumonia lesions) detected via computed tomography and visible on ultrasonography were enrolled in this study. The arterial phases were determined by comparing contrast agent arrival time (AT) in the peripheral lung lesion with that in adjacent lung tissue, referred to as a real-time comparative observation method.
View Article and Find Full Text PDF