Quality control of fetal ultrasound images: Detection of abdomen anatomical landmarks using AdaBoost

AbstractHigh-quality medical ultrasound imaging is definitely concerning motion blur, while medical image analysis requires motionless and accurate data acquired by sonographers. The main idea of this paper is to establish some motion blur invariant in both frequency and moment domain to estimate the motion parameters of ultrasound images. We propose a discrete model of point spread function of motion blur convolution based on the Dirac delta function to simplify the analysis of motion invariant in frequency and moment domain. This model paves the way for estimating the motion angle and length in terms of the proposed invariant features. In this research, the performance of the proposed schemes is compared with other state-of-the-art existing methods of image deblurring. The experimental study performs using fetal phantom images and clinical fetal ultrasound images as well as breast scans. Moreover, to validate the accuracy of the proposed experimental framework, we apply two image quality assessment methods as no-reference and full-reference to show the robustness of the proposed algorithms compared to the well-known approaches.

Download Full-text

Postnatal ultrasound follow-up in neonates with prenatal hydronephrosis

Diagnosis ◽

10.1515/dx-2020-0109 ◽

2021 ◽

Vol 0 (0) ◽

Author(s):

Elham Kebriyaei ◽

Ali Davoodi ◽

Seyed Alinaghi Kazemi ◽

Zahra Bazargani

Keyword(s):

Ultrasound Imaging ◽

Maternal Education ◽

Left Kidney ◽

Ultrasound Images ◽

Fetal Ultrasound ◽

Renal Anomalies ◽

Cross Sectional ◽

Fetal Hydronephrosis ◽

Kidney Involvement

Abstract Objectives Renal anomalies are the most common fetal abnormalities that occur during prenatal development, and are typically detected by observing hydronephrosis on fetal ultrasound imaging. Follow-up with post-natal ultrasound is important to detect clinically-important obstruction, because many of the pre-natal abnormalities resolve spontaneously. This study aimed to evaluate the postnatal hydronephrosis follow-up rate, and reasons for non follow-up in affected neonates. Methods In this cross-sectional study all neonates born during a period of one year at Ayatollah Mousavi Hospital with hydronephrosis on fetal ultrasound imaging were recruited. All mothers were also given face-to-face information about fetal hydronephrosis and its postnatal outcomes, and follow-up with at least a postnatal ultrasound was recommended from the fourth day of their neonates’ birth until the end of the fourth week. The neonates were subsequently observed for one month to determine the postnatal ultrasound follow-up rate and to reflect on diagnostic test results, reasons for failure to follow-up, as well as causes of hydronephrosis. Results In this study, 71 cases (1.2%) out of 5,952 neonates had fetal hydronephrosis on prenatal ultrasound images. The postnatal ultrasound imaging showed kidney involvement in 18 neonates (25%), particularly in the left kidney (61.1%). Seven neonates had no follow-up at one month (10%). No significant relationship was found between lack of follow-up and the neonates’ place of residence (p=0.42), maternal education (p=0.90), number of siblings (p=0.33), or gender (p=0.64). Conclusions Postnatal ultrasound follow-up rate in these neonates with a history of fetal hydronephrosis was incomplete even though parents had been provided with education and advice at their birth time. Accordingly, it is recommended to perform postnatal ultrasound once neonates are discharged from hospitals.

Download Full-text

Value of Ultrasound Images and Reports Scoring System in Quality Control

ADVANCED ULTRASOUND IN DIAGNOSIS AND THERAPY ◽

10.37015/audt.2021.210003 ◽

2021 ◽

Vol 5 (3) ◽

pp. 245

Author(s):

Qiu, MD Li ◽

Peng, MD Yulan ◽

Lu, MD Qiang ◽

Luo, MD Yan

Keyword(s):

Quality Control ◽

Scoring System ◽

Ultrasound Images

Download Full-text

Automated Segmentation of Fetal Ultrasound Images Using Feature Attention Supervised Network

Ultrasound Quarterly ◽

10.1097/ruq.0000000000000532 ◽

2021 ◽

Vol 37 (3) ◽

pp. 278-286

Author(s):

Pengfei Liu ◽

Huaici Zhao ◽

Peixuan Li

Keyword(s):

Ultrasound Images ◽

Automated Segmentation ◽

Fetal Ultrasound ◽

Feature Attention

Download Full-text

Automatic and Efficient Standard Plane Recognition in Fetal Ultrasound Images via Multi-scale Dense Networks

Data Driven Treatment Response Assessment and Preterm, Perinatal, and Paediatric Image Analysis - Lecture Notes in Computer Science ◽

10.1007/978-3-030-00807-9_16 ◽

2018 ◽

pp. 160-168 ◽

Cited By ~ 3

Author(s):

Peiyao Kong ◽

Dong Ni ◽

Siping Chen ◽

Shengli Li ◽

Tianfu Wang ◽

...

Keyword(s):

Ultrasound Images ◽

Fetal Ultrasound ◽

Dense Networks ◽

Multi Scale

Download Full-text

Abstract 308: Cardiac Cycle Affects Ultrasound Measurements of Ascending Aortic Diameter in a Marfan Mouse Model

Arteriosclerosis Thrombosis and Vascular Biology ◽

10.1161/atvb.37.suppl_1.308 ◽

2017 ◽

Vol 37 (suppl_1) ◽

Author(s):

Zheying Chen ◽

Hisashi Sawada ◽

Debra Rateri ◽

Alan Daugherty ◽

Mary Sheppard

Keyword(s):

Cardiac Cycle ◽

Interobserver Variability ◽

Innominate Artery ◽

Aortic Diameter ◽

Ultrasound Images ◽

Anatomical Landmarks ◽

Wild Type ◽

Ultrasound Measurements ◽

Fibrillin 1 ◽

Ascending Aortic Diameter

Objective: Ultrasound measurements of aortic diameter are a common endpoint in preclinical studies. However, there is a lack of standardization in both image capture and analysis. For our study, we developed a standardized protocol for measuring ascending aortic diameter and examined effects of cardiac cycle in wild type and fibrillin-1 hypomorphic (FBN mgR/mgR ) mice. Methods and Results: Twelve week old male and female FBN mgR/mgR mice were anesthetized and maintained at a heart rate of 450-550 beats per minute. Ultrasound images were captured using a Vevo 2100 system with a 40MHz tranducer. Images captured were standardized according to two anatomical landmarks: the innominate artery branchpoint and aortic valves. The largest luminal ascending aortic diameter between the sinotubular junction and the innominate artery were measured in mid-systole and end-diastole by two blinded, independent observers. Aortic diameters were significantly different (p<0.05) when comparing systole and diastole within gender and genotype. Interestingly, wild-type male (n=4) and female (n=3) mice exhibited a 19% and 15% expansion of the ascending aorta respectively during systole compared to diastole. This difference was not recapitulated in either male (n=6) or female (n=5) FBN mgR/mgR mice (4% expansion in both; p<0.05 vs wild-type). Agreement between observers was excellent (R^2 = 0.99) but interobserver variability was a mean of .09 mm (%CV = 5%) Conclusion: As expected, there is a difference in aortic diameters between wild-type and FBN mgR/mgR mice. Luminal aortic diameters in FBN mgR/mgR vs wild-type mice of both genders are affected by cardiac cycle. Mid-systolic aortic expansion in wild-type vs FBN mgR/mgR mice were different. Error introduced by interobserver variability impacts ascending aortic measurements. Altogether, these phenomena may confound analyses of aortic dilation in FBN mgR/mgR mice, especially when studying interventions with modest effect sizes.

Download Full-text