Diagnostic role of US for biliary atresia

Ensembled deep learning model outperforms human experts in diagnosing biliary atresia from sonographic gallbladder images

It is still challenging to make accurate diagnosis of biliary atresia (BA) with sonographic gallbladder images particularly in rural area without relevant expertise. To help diagnose BA based on sonographic gallbladder images, an ensembled deep learning model is developed. The model yields a patient-level sensitivity 93.1% and specificity 93.9% [with areas under the receiver operating characteristic curve of 0.956 (95% confidence interval: 0.928-0.977)] on the multi-center external validation dataset, superior to that of human experts. With the help of the model, the performances of human experts with various levels are improved. Moreover, the diagnosis based on smartphone photos of sonographic gallbladder images through a smartphone app and based on video sequences by the model still yields expert-level performances. The ensembled deep learning model in this study provides a solution to help radiologists improve the diagnosis of BA in various clinical application scenarios, particularly in rural and undeveloped regions with limited expertise.

Paediatric liver ultrasound: a pictorial essay

Ultrasound scan is a painless and radiation-free imaging modality and, therefore, it is widely considered the first-choice diagnostic tool in the setting of hepatopathies in paediatric patients. This article focuses on the normal ultrasound anatomy of the liver in neonatal and paediatric age and reviews the ultrasound appearance of the most common diffuse and focal liver affections.

Ultrasound findings in paediatric cholestasis: how to image the patient and what to look for

Paediatric biliary tract and gallbladder diseases include a variety of entities with a wide range of clinical presentations. Cholestasis represents an impaired secretion of bilirubin by hepatocytes, manifesting with high blood levels of conjugated bilirubin and jaundice. Various causes may be involved, which can be recognised analysing blood tests and hepatobiliary imaging, while sometimes liver biopsy or surgery may be necessary. High-resolution real-time ultrasonography is an important tool for differentiation of obstructive and non-obstructive causes of jaundice in infants and children. In this paper, we briefly review the normal anatomy and the ultrasound aspects of main pathologies affecting gallbladder and biliary tree in neonatal and paediatric age.

Incremental Value of MR Cholangiopancreatography in Diagnosis of Biliary Atresia

Purpose

To evaluate the incremental value of a combination of magnetic resonance cholangiopancreatography (MRCP) and ultrasonography (US), compared to US alone, for diagnosing biliary atresia (BA) in neonates and young infants with cholestasis.

Materials and Methods

The institutional review board approved this retrospective study. The US and MRCP studies were both performed on 64 neonates and young infants with BA (n = 41) or without BA (non-BA) (n = 23). Two observers reviewed independently the US alone set and the combined US and MRCP set, and graded them using a five-point scale. Diagnostic performance was compared using pairwise comparison of the receiver operating characteristics (ROC) curve. The sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value were assessed.

Results

The diagnostic performance (the area under the ROC curve [A_z]) for diagnosing BA improved significantly after additional review of MRCP images; A_z improved from 0.688 to 0.901 (P = .015) for observer 1 and from 0.676 to 0.901 (P = .011) for observer 2. The accuracy of MRCP combined with US (observer 1, 95% [61/64]; observer 2 92% [59/64]) and PPV (observer 1, 95% [40/42]; observer 2 91% [40/44]) were significantly higher than those of US alone for both observers (accuracy: observer 1, 73% [47/64], P = 0.003; observer 2, 72% [46/64], P = 0.004; PPV: observer 1, 76% [35/46], P = 0.016; observer 2, 76% [34/45], P = 0.013). Interobserver agreement of confidence levels was good for US alone (ĸ = 0.658, P < .001) and was excellent for the combined set of US and MRCP (ĸ = 0.929, P < .001).

Conclusion

Better diagnostic performance was achieved with the combination of US and MRCP than with US alone for the evaluation of BA in neonates and young infants with cholestasis.

Design and validation of a diagnostic score for biliary atresia

BACKGROUND & AIMS

The dilemma of early diagnosis of biliary Atresia (BA), particularly distinguishing it from other causes of neonatal cholestasis is challenging. The aim was to design and validate a scoring system for early discrimination of BA from other causes of neonatal cholestasis.

METHODS

A twelve-point scoring system was proposed according to clinical, laboratory, ultrasonographic, and histopathological parameters. A total of 135 patients with neonatal cholestasis in two sets were recruited to design (n=60) and validate (n=75) a scoring system. Parameters with significant statistical difference between BA (n=30) and non-BA (n=30) patients in the design set were analyzed by logistic regression to predict the presence or absence of BA then a scoring system was designed and validated.

RESULTS

The total score ranged from 0 to 37.18 and a cut-off value of >23.927 could discriminate BA from other causes of neonatal cholestasis with sensitivity and specificity of 100% each. By applying this score in the validation set, the accuracy was 98.83% in predicting BA. The diagnosis of BA was proposed correctly in 100% and the diagnosis of non-BA was proposed correctly in 97.67% of patients. By applying this model, unnecessary intraoperative cholangiography would be avoided in non-BA patients.

CONCLUSIONS

This scoring system accurately separates infants with BA and those with non-BA, rendering intraoperative cholangiography for confirming or excluding BA unnecessary in a substantial proportion of patients.

Accuracy of ultrasonography in the diagnosis of acute calculous cholecystitis: review of the literature

Background

To evaluate the accuracy of ultrasonography in the diagnosis of acute calculous cholecystitis in comparison with other imaging modalities.

Methods

The authors performed a search of the Medline/ PubMed (National Library of Medicine, Bethesda, Maryland) for original research and review publications examining the accuracy of ultrasonography in the diagnosis of acute calculous cholecystitis. The search design utilized a single or combination of the following terms : (1) acute cholecystitis, (2) ultrasonography, (3) computed tomography, (4) magnetic resonance cholangiopancreatography and (5) cholescintigraphy. This review was restricted to human studies and to English-language literature. Four authors reviewed all the titles and subsequent the abstract of 198 articles that appeared appropriate. Other articles were recognized by reviewing the reference lists of significant papers. Finally, the full text of 31 papers was reviewed.

Results

Sonography is still used as the initial imaging technique for evaluating patients with suspected acute calculous cholecystitis because of its high sensitivity at the detection of GB stones, its real-time character, and its speed and portability. Cholescintigraphy still has the highest sensitivity and specificity in patients who are suspected of having acute cholecystitis. However, due to a combination of reasons including logistic drawbacks, broad imaging capability and clinician referral pattern the use of cholescintigraphy is limited in clinical practice. CT is particularly useful for evaluating the many complications of acute calculous cholecystitis. The lack of widespread availability of MRI and the relatively high cost prohibits its primary use in patients with acute calculous cholecystitis.

Conclusions

US is currently considered the preferred initial imaging technique for patients who are clinically suspected of having acute calculous cholecystitis.

Diagnosis of Alagille syndrome-25 years of experience at King's College Hospital

OBJECTIVE

The aim of the study was to study the clinical and histological features of Alagille syndrome (AGS) at presentation comparing the value of the various modalities before the implementation of genetic diagnosis.

PATIENTS AND METHODS

We performed a retrospective analysis of the records of 117 children diagnosed as having AGS after referral to King's College Hospital between 1980 and 2005.

RESULTS

Cholestasis was seen in 104 of 117 (89%), characteristic facies in 91 of 117 (77%), posterior embryotoxon in 72 of 117 (61%), butterfly vertebrae in 44 of 117 (39%), heart disease (most often peripheral pulmonary stenosis) in 107 of 117 (91%), and renal disease in 27 of 117 (23%). Serum cholesterol levels of >5 mmol/L were seen in 52 of 86 (60.4%). Liver biopsy showed characteristic features of paucity of interlobular bile ducts in 59 of 77 (76.6%) children younger than 16 weeks of age, in 10 of 14 (71.4%) between 16 weeks and 1 year of age, and in 8 of 12 (66.66%) older than 1 year of age. Other biopsy findings were those of nonspecific hepatitis and biliary features. Iminodiacetic acid scans showed no excretion of isotope into the bowel after 24 hours in 21 of 35 (60%), and small/no gallbladder on ultrasound was seen in 29 of 104 (27.8%). Eleven of 117 (9.4%) had a diagnostic laparotomy and operative cholangiography, 2 proceeding to Kasai portoenterostomy before referral to our unit.

CONCLUSIONS

Clinical features of AGS are not as consistently informative as suggested in the literature. Hypercholesterolaemia is nonspecific but may be a helpful pointer. Histology is not characteristic in 25%; hepatobiliary iminodiacetic acid scan and ultrasound may suggest a false diagnosis of biliary atresia in 60% and 28%, respectively, supporting the concept that infants with liver disease warrant early referral to a specialist centre. The advent of genetic diagnosis will redefine the syndrome with likely effects on the prognosis of the defined group.