Search

Purpose: This study aims to share the experience of minimally invasive ultrasound-guided methotrexate intervention in the treatment of heterotopic interstitial pregnancy (HIP) with good pregnancy outcomes, and to review the treatment, pregnancy outcomes, and impact on the future fertility of HIP patients. Methods: The paper describes the medical history, clinical manifestations, treatment history, and clinical prognosis of a 31-year-old woman with HIP, and reviews cases of HIP from 1992 to 2021 published in the PubMed database. Results: The patient was diagnosed with HIP by transvaginal ultrasound (TVUS) at 8 weeks after assisted reproductive technology. The interstitial gestational sac was inactivated by ultrasound-guided methotrexate injection. The intrauterine pregnancy was successfully delivered at 38 weeks of gestation. Twenty-five HIP cases in 24 studies published on PubMed from 1992 to 2021 were reviewed. Combined with our case, there were 26 cases in total. According to these studies, 84.6% (22/26) of these cases were conceived by in vitro fertilization embryo transfer, 57.7% (15/26) had tubal disorders, and 23.1% (6/26) had a history of ectopic pregnancy; 53.8% (14/26) of the patients presented with abdominal pain and 19.2% (5/26) had vaginal bleeding. All cases were confirmed by TVUS. In total, 76.9% (20/26) of intrauterine pregnancies had a good prognosis (surgery vs. ultrasound interventional therapy 1:1). All fetuses were born without abnormalities. Conclusions: The diagnosis and treatment of HIP remain challenging. Diagnosis mainly relies on TVUS. Interventional ultrasound therapy and surgery are equally safe and effective. Early treatment of concomitant heterotopic pregnancy is associated with high survival of the intrauterine pregnancy.

Objective: A non-invasive assessment of the risk of benign and malignant follicular thyroid cancer is invaluable in the choice of treatment options. The extraction and fusion of multidimensional features from ultrasound images of follicular thyroid cancer is decisive in improving the accuracy of identifying benign and malignant thyroid cancer. This paper presents a non-invasive preoperative benign and malignant risk assessment system for follicular thyroid cancer, based on the proposed deep feature extraction and fusion of ultrasound images of follicular thyroid cancer. Methods: First, this study uses a convolution neural network (CNN) to obtain a global feature map of the image, and the fusion of global features cropped to local features to identify tumor images. Secondly, this tumour image is also extracted by googleNet and ResNet respectively to extract features and recognize the image. Finally, we employ an averaging algorithm to obtain the final recognition results. Results: The experimental results show that the method proposed in this study achieved 89.95% accuracy, 88.46% sensitivity, 91.30% specificity and an AUC value of 96.69% in the local dataset obtained from Peking University Shenzhen Hospital, all of which are far superior to other models. Conclusion: In this study, a non-invasive risk prediction system is proposed for ultrasound images of thyroid follicular tumours. We solve the problem of unbalanced sample distribution by means of an image enhancement algorithm. In order to obtain enough features to differentiate ultrasound images, a three-branched feature extraction network was designed in this study, and a balance of sensitivity and specificity is ensured by an averaging algorithm. [ABSTRACT FROM AUTHOR]