Artificial intelligence for automatic diagnosis of biliary stricture malignancy status in single-operator cholangioscopy: a pilot study

Saraiva, Miguel Mascarenhas; Ribeiro, Tiago; Ferreira, João; Vilas-Boas, Filipe; Afonso, João; Santos, Ana Luísa; Parente, Marco; Jorge, Renato Natal; Pereira, Pedro; Macedo, Guilherme

doi:10.1016/j.gie.2021.08.027

Cited by 31 publications

(21 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For stage II, the x required neoplastic or nonneoplastic cases was calculated using the power.diagnostic.test function in the MKmisc (v1.6; Kohl M, 2019) package [18]. Assumption for the proportion of discordant pairs considered a 94.7% sensitivity for a CNN model, as estimated by Saraiva M et al [16].. A probabilistic sample was designed considering a 10% delta and a 50% prevalence (1:1 case vs. controls ratio, to recreate the same probability of neoplastic or non-neoplastic cases during DSOC videos assessment, as in Bernoulli trial). A 5% significance level was considered, along with a defined 5% and 20% alpha and beta error, respectively.…”

Section: Discussionmentioning

confidence: 99%

“…To date, despite the numerous advantages of DSOC, there is an ongoing discrepancy between the operators' visual impression using current classifications for indeterminate biliary lesions. To overcome this limitation, the application of new technologies to aid in image interpretation has been proposed; however, the proposed models could only be applied in images [15,16]. In the present study, we developed a new DSOC-based CNN for recognizing neoplasia in indeterminate biliary lesions in prerecorded videos and real-time DSOC procedures and compared the model with DSOC experts and nonexperts using the CRM and Mendoza classifications.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence for diagnosing neoplasia on digital cholangioscopy: development and multicenter validation of a convolutional neural network model

et al. 2023

View full text Add to dashboard Cite

Background and study aim: We aimed to develop a convolutional neural network (CNN) model for detecting neoplastic lesions during real-time digital single-operator cholangioscopy (DSOC) and clinically validated the model through comparisons with DSOC experts and nonexpert endoscopists. Patients and methods: In this two-stage study, we first developed and validated CNN1. Then, we performed a multicenter diagnostic trial to compare four DSOC experts and nonexperts against an improved model (CNN2). They classified the lesions in neoplastic and nonneoplastic in accordance with Carlos Robles-Medranda (CRM) and Mendoza disaggregated criteria. The final diagnosis of neoplasia was based on histopathology and twelve-month follow-up outcomes. Results: In stage I, CNN2 achieved a mAP of 0.88, an IoU of 83.24%, and a total loss of 0.0975. For clinical validation, a total of 170 videos from newly included patients were analyzed with the CNN2. 50% of cases had neoplastic lesions. This model achieved significant accuracy values for neoplastic diagnosis cases, with a 90.5% sensitivity, 68.2% specificity, and 74.0% and 87.8% positive and negative predictive values, respectively. CNN2 model outperformed nonexpert #2 ([ROC-CRM: 0.657 vs ROC-CNN2: 0.794, P<0.05 and ROC-Mendoza: 0.657 vs ROC-CNN2: 0.794, P<0.05]), nonexpert #4 (ROC-CRM: 0.683 vs ROC-CNN2: 0.791, P<0.05), and expert #4 ([ROC-CRM: 0.755 vs ROC-CNN2: 0.848, P<0,05 and ROC-Mendoza: 0.753 vs ROC-CNN2: 0.848, P<0,05]). Conclusions: The proposed CNN models distinguish neoplastic bile duct lesions with good accuracy and outperformed two nonexperts and one expert endoscopists.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Artificial intelligence for diagnosing neoplasia on digital cholangioscopy: development and multicenter validation of a convolutional neural network model

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In the last decade, we assisted the development of AI systems for application to several diagnostic modalities. Studies on the implementation of CNNs to several endoscopic modalities produced promising results [11][12][13][14][15]. In this retrospective study, we developed a pioneer deep learning algorithm for automatic detection of gastrointestinal angioectasia, with high sensitivity, specificity and overall accuracy.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning and Device-Assisted Enteroscopy: Automatic Detection of Gastrointestinal Angioectasia

et al. 2021

Self Cite

View full text Add to dashboard Cite

Background and Objectives: Device-assisted enteroscopy (DAE) allows deep exploration of the small bowel and combines diagnostic and therapeutic capacities. Suspected mid-gastrointestinal bleeding is the most frequent indication for DAE, and vascular lesions, particularly angioectasia, are the most common etiology. Nevertheless, the diagnostic yield of DAE for the detection of these lesions is suboptimal. Deep learning algorithms have shown great potential for automatic detection of lesions in endoscopy. We aimed to develop an artificial intelligence (AI) model for the automatic detection of angioectasia DAE images. Materials and Methods: A convolutional neural network (CNN) was developed using DAE images. Each frame was labeled as normal/mucosa or angioectasia. The image dataset was split for the constitution of training and validation datasets. The latter was used for assessing the performance of the CNN. Results: A total of 72 DAE exams were included, and 6740 images were extracted (5345 of normal mucosa and 1395 of angioectasia). The model had a sensitivity of 88.5%, a specificity of 97.1% and an AUC of 0.988. The image processing speed was 6.4 ms/frame. Conclusions: The application of AI to DAE may have a significant impact on the management of patients with suspected mid-gastrointestinal bleeding.

show abstract

“…Mascharenas et al developed a deep learning algorithm that can accurately differentiate malignant from non-malignant biliary stricture. 30 Radiofrequency ablation (RFA) of unresectable cholangiocarcinomas has been shown to improve stent patency and overall survival. There is an emerging role of cholangioscopes in the pre-procedure and post-procedure evaluation of the tumor after application of RFA.…”

Section: Future Directionsmentioning

confidence: 99%

Cholangioscopy: Has It Changed Management?

Chowdhury

Jaleel

2022

Journal of Digestive Endoscopy

View full text Add to dashboard Cite

The single operator per oral cholangioscope is a catheter-based system that allows for direct visualization of the bile duct and pancreatic duct. The instrument with its improved imaging technique and larger accessory channel allows for high-quality image acquisition and performance of therapeutic and diagnostic procedures within the bile duct and pancreatic duct. There has been an increase in the range of indications for the use of the cholangioscope. The current indications include management of difficult biliary stones, pancreatic calculi, assessment of indeterminate biliary stricture, pancreatic stricture, intra-ductal papillary mucinous neoplasms, and extractions of proximally migrated stents. The use of laser lithotripsy and electro-hydraulic lithotripsy has improved the management of difficult bile duct stones. Direct visualization of biliary and pancreatic duct strictures is helpful in the diagnosis of indeterminate strictures. In this review, we explore how cholangioscopy has changed management.

show abstract

Artificial intelligence for automatic diagnosis of biliary stricture malignancy status in single-operator cholangioscopy: a pilot study

Cited by 31 publications

References 24 publications

Artificial intelligence for diagnosing neoplasia on digital cholangioscopy: development and multicenter validation of a convolutional neural network model

Artificial intelligence for diagnosing neoplasia on digital cholangioscopy: development and multicenter validation of a convolutional neural network model

Deep Learning and Device-Assisted Enteroscopy: Automatic Detection of Gastrointestinal Angioectasia

Cholangioscopy: Has It Changed Management?

Contact Info

Product

Resources

About