Comparison of abdominal radiographs and sonography in prognostic prediction of infants with necrotizing enterocolitis

Chen, Shuai; Hu, Yuanchen; Liu, Qinghua; Li, Xiaoying; Wang, Hefeng; Wang, Kelai

doi:10.1007/s00383-018-4256-y

Cited by 30 publications

(43 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The recognized AR visualized pathology in NEC have a good positive predictive value but low sensitivity [25], [26]. Frequently in clinical practice, however, the changes may be subtle and difficult to interpret.…”

Section: Need For Cam In Neonatal Radiologymentioning

confidence: 99%

See 1 more Smart Citation

A Deep Learning Based Suggested Model to Detect Necrotising Enterocolitis in Abdominal Radiography Images

Druten

Sharif

Chan

et al. 2019

2019 International Conference on Computing, Electronics &Amp; Communications Engineering (iCCECE)

View full text Add to dashboard Cite

Despite decades of exploration into necrotising enterocolitis (NEC), we still lack the capacity to accurately diagnose the disease to improve outcomes in its management. Existing diagnostics struggle to delineate NEC from other neonatal intestinal diseases; it is also unable to highlight those likely to deteriorate to needing emergency life-saving surgery before it is too late. The diagnosis of NEC is heavily dependent on interpretation of radiological findings, especially abdominal radiography (AR) and abdominal ultrasound (AUS). Interexpert variability in interpreting AR imaging, and in the case of AUS, performing and interpreting the test, remains an unresolved challenge. With the compounding impact of the shrinking radiology workforce, a novel approach is imperative. Computer assisted detection (CAD) and classification of abnormal pathology in medical imaging is a rapidly evolving field of clinical and biomedical research. This technology is widely used as a preliminary screening tool. This research paper proposes a deep learning-based model to classify AR images in an automated manner, generating class activation maps (CAM) from various imaging features consistent with NEC pathology, as agreed by expert consensus papers (in neonatology and paediatric radiology). It also compares it with conventional machine learning methods. The suggested model aims to produce heatmaps for various imaging features to highlight NEC pathology in AR (or in future AUS). Once the model is trained, validation is done through quantitative measures and visually by the attending radiologist (clinician) reviewing the validity of the colour maps highlighting the pathology of the AR image (future extension to AUS). As the volume of imaging data is increasing year by year, CAD can be a key strategy to assist radiology departments meet service needs. This technology can greatly assist in screening for NEC, improving the detection of NEC and potentially aid in the earlier identification of disease. Furthermore, it can fast track research cost effectively by creating big data through the automatic labeling of imaging data to create big-data for NEC databases.

show abstract

Section: Need For Cam In Neonatal Radiologymentioning

confidence: 99%

“…Furthermore, novel imaging modalities like AUS remains underutilised due to the lack of expertise in its use and reporting [36], [37]. Highlighting a further area for CAM to assist the integration of new point of care ultrasound (POCUS) to overcome underutilisation [26], [36], [37].…”

Section: Need For Cam In Neonatal Radiologymentioning

confidence: 99%

A Deep Learning Based Suggested Model to Detect Necrotising Enterocolitis in Abdominal Radiography Images

Druten

Sharif

Chan

et al. 2019

2019 International Conference on Computing, Electronics &Amp; Communications Engineering (iCCECE)

View full text Add to dashboard Cite

show abstract

“…It is possible to differentiate between normal, increased, and absent peristalsis on the moving image. Peristalsis is often absent in the affected bowel segments in NEC [5,7,10]. It must be determined whether the entire bowel or only parts are affected.…”

Section: Evaluation Of Peristalsismentioning

confidence: 99%

“…Im bewegten Bild kann zwischen normaler, gesteigerter oder fehlender Peristaltik unterschieden werden. Die betroffenen Darmabschnitte bei NEK weisen oft eine fehlende Peristaltik auf [5,7,10]. Dabei muss differenziert werden, ob der gesamte Darm oder nur Teile desselben betroffen sind.…”

Section: Beurteilung Der Peristaltikunclassified

“…Comparison of ultrasound with plain abdominal radiography ▶ Table 6 Only a few signs suspicious for NEC can be found using abdominal radiography, the gold standard of NEC diagnosis: Gas bubbles in the intestinal wall and portal vein as well as free intraabdominal gas [7,10]. Dilated, gasfilled bowel loops and bowel loops with greater distance between them can also be visualized on radiography [5,7].…”

Section: Focal Intestinal Perforation (Fip)mentioning

confidence: 99%

See 1 more Smart Citation

Sonographic and Doppler Sonographic Diagnosis of Necrotizing Enterocolitis in Preterm Infants and Newborns

Deeg

2019

Ultraschall in Med

View full text Add to dashboard Cite

Necrotizing enterocolitis (NEC) occurs primarily in immature preterm infants with low birth weight. It has a prevalence of 7 – 11 % with a poor prognosis and a mortality rate of 20 – 40 %. Plain abdominal radiography is still considered the diagnostic method of first choice even though ultrasound can visualize significantly more findings suspicious for NEC. Such as thickened bowel walls, dilated fluid-filled bowel loops, and gas bubbles in the intestinal wall, portal vein. Moreover, it is possible to assess intestinal peristalsis, to differentiate between intraluminal and extraluminal fluid and to assess the location of fluid accumulations and their internal echo pattern. In addition, free intraabdominal gas can be visualized on ultrasound. Increased flow rates in the mesenteric arteries and decreased flow in the portal vein can be detected on Doppler ultrasound in NEC. Color-coded Doppler ultrasound can be used to differentiate between bowel loops with increased and decreased perfusion and thus at risk for perforation. Ultrasound is therefore superior to conventional radiography in many regards and should replace it as the diagnostic method of first choice not least because of its noninvasive nature.

show abstract

Association between the dynamic movement of hyperechoic foci and patients'/sonographic outcomes among pediatric patients with portal venous gas following a cardiac event

Hosokawa

Tanami

Sato

et al. 2023

J of Clinical Ultrasound

View full text Add to dashboard Cite

Objectives To demonstrate the association between the dynamic movements of hyperechoic foci in portal venous gas (PVG) and patients'/sonographic outcomes after congenital heart disease or cardiac events. Methods Thirty‐one pediatric patients requiring management of congenital heart diseases or cardiac events who had PVG on ultrasound were included in this retrospective study. The patient outcome was prognosis: dead or alive. The sonographic outcome was recovery from PVG, measured as days from PVG detection to when it diminished on ultrasound. The following sonographic findings of hyperechoic foci in PVG were compared between patients: detection within the mesenteric vein, having to‐and‐fro movements within the intrahepatic portal vein, distribution (left segment or both left and right segments) and shape (line or punctate) in the liver, and detection within the portal and hepatic veins. Comparisons were made using Fisher's exact/Mann–Whitney U test. Results Four patients died without having recovered from PVG. A significant difference was observed in terms of the to‐and‐fro movement (with/without to‐and‐fro movement in dead vs. alive patients: 3/1 vs. 1/26, respectively; P = 0.003). Furthermore, a significant difference in sonographic outcomes was observed regarding patients with/without hyperechoic foci within the mesenteric vein (days with vs. without this finding: 2.0 ± 1.24(1–5) vs.1 ± 0(1), respectively; P = 0.011). Conclusions In our small limited cohort, when PVG was visualized on ultrasound, close evaluation of the dynamic movement of hyperechoic foci, especially their to‐and‐fro movement within the intrahepatic portal vein and detection of hyperechoic foci within the mesenteric vein, were useful in predicting patients' outcomes and the time to PVG diminishment.

show abstract

Comparison of abdominal radiographs and sonography in prognostic prediction of infants with necrotizing enterocolitis

Abstract: In conclusion, we found that several radiographic and sonographic parameters were associated with the prognosis of patients with NEC. The AUS model based on the logistic regression analysis was significant superior to the AR model in the prognostic prediction of NEC.

Cited by 30 publications

References 35 publications

A Deep Learning Based Suggested Model to Detect Necrotising Enterocolitis in Abdominal Radiography Images

A Deep Learning Based Suggested Model to Detect Necrotising Enterocolitis in Abdominal Radiography Images

Sonographic and Doppler Sonographic Diagnosis of Necrotizing Enterocolitis in Preterm Infants and Newborns

Association between the dynamic movement of hyperechoic foci and patients'/sonographic outcomes among pediatric patients with portal venous gas following a cardiac event

Contact Info

Product

Resources

About