Deep learning for estimation of fetal weight throughout the pregnancy from fetal abdominal ultrasound.

BACKGROUND: Fetal weight is currently estimated from fetal biometry parameters using heuristic mathematical formulas. Fetal biometry requires measurements of the fetal head, abdomen, and femur. However, this examination is prone to inter- and intraobserver variability because of factors, such as the experience of the operator, image quality, maternal characteristics, or fetal movements. Our study tested the hypothesis that a deep learning method can estimate fetal weight based on a video scan of the fetal abdomen and gestational age with similar performance to the full biometry-based estimations provided by clinical experts. OBJECTIVE: This study aimed to develop and test a deep learning method to automatically estimate fetal weight from fetal abdominal ultrasound video scans. STUDY DESIGN: A dataset of 900 routine fetal ultrasound examinations was used. Among those examinations, 800 retrospective ultrasound video scans of the fetal abdomen from 700 pregnant women between 15 6/7 and 41 0/7 weeks of gestation were used to train the deep learning model. After the training phase, the model was evaluated on an external prospectively acquired test set of 100 scans from 100 pregnant women between 16 2/7 and 38 0/7 weeks of gestation. The deep learning model was trained to directly estimate fetal weight from ultrasound video scans of the fetal abdomen. The deep learning estimations were compared with manual measurements on the test set made by 6 human readers with varying levels of expertise. Human readers used standard 3 measurements made on the standard planes of the head, abdomen, and femur and heuristic formula to estimate fetal weight. The Bland-Altman analysis, mean absolute percentage error, and intraclass correlation coefficient were used to evaluate the performance and robustness of the deep learning method and were compared with human readers. RESULTS: Bland-Altman analysis did not show systematic deviations between readers and deep learning. The mean and standard deviation of the mean absolute percentage error between 6 human readers and the deep learning approach was 3.75%±2.00%. Excluding junior readers (residents), the mean absolute percentage error between 4 experts and the deep learning approach was 2.59%±1.11%. The intraclass correlation coefficients reflected excellent reliability and varied between 0.9761 and 0.9865. CONCLUSION: This study reports the use of deep learning to estimate fetal weight using only ultrasound video of the fetal abdomen from fetal biometry scans. Our experiments demonstrated similar performance of human measurements and deep learning on prospectively acquired test data. Deep learning is a promising approach to directly estimate fetal weight using ultrasound video scans of the fetal abdomen.

Embolization of a large, symptomatic splenic artery pseudoaneurysm.

BACKGROUND: Splenic artery aneurysm is the third most common abdominal aneurysm. Most often it is due to pancreatitis. There were only 19 cases of aneurysms larger than 5 cm in diameter described in the literature. Management of splenic artery aneurysms depends on the size and symptoms. Invasive treatment modalities involve open procedures and interventional radiology methods (endovascular). CASE REPORTS: A 44-years-old male with chronic pancreatitis, in a gradually worsening general condition due to a large splenic artery aneurysm, was subjected to the procedure. Blood flow through the aneurysm was cut-off by implanting a covered stent between celiac trunk and common hepatic artery. Patient's general condition rapidly improved, allowing discharge home in good state soon after the procedure. CONCLUSIONS: Percutaneous embolization appears to be the best method of treatment of large splenic artery aneurysms. Complications of such treatment are significantly less dangerous than those associated with surgery.

Torsion of the uterus with myomas in a postmenopausal woman - case study and review of the literature.

INTRODUCTION: Torsion of the uterus is defined as a rotation of more than 45° around the long axis of the uterus; 2/3 of cases are dextrorotations. The extent of rotation usually ranges from 45° to 180°. OBJECTIVE: The purpose of the article was to present a case study of a postmenopausal woman with uterine torsion and myomas and to review the articles discussing the problem of rotated non-pregnant uterus. MATERIAL AND METHODS: The article analyses the course of an extremely uncommon pathology, i.e. uterine torsion in a 67-year-old patient. Laparotomy exposed the uterus with myomas and numerous hemorrhages, rotated by 180° to the right side, size of 350 × 300 × 200 mm and bilateral necrosis of the ovaries. Moreover, we present a review of articles discussing surgical management in case of rotated non-pregnant uterus. RESULTS AND DISCUSSION: The patient was operated on by a team of gynecologists and surgeons. The uterus was derotated and total hysterectomy with salpingoophorectomy was performed. A fragment of the hepatic oval ligament was excised and periumbilical hernioplasty was performed. The patient was released home on the 10(th) day following the operation. CONCLUSIONS: If women complain of pain located within the small pelvis and abdominal cavity it is necessary to remember that it might result from the torsion of reproductive organs which is an uncommon condition but poses a health or life threat to patients. Surgical treatment of uterine torsion is successful if promptly implemented; in certain cases it is even possible to spare the patient's fertility.