2021 International Conference on E-Health and Bioengineering (EHB) 2021
DOI: 10.1109/ehb52898.2021.9657740
|View full text |Cite
|
Sign up to set email alerts
|

Experimental Deep Learning Object Detection in Real-time Colonoscopies

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
2
2

Relationship

1
8

Authors

Journals

citations
Cited by 12 publications
(5 citation statements)
references
References 11 publications
0
5
0
Order By: Relevance
“…Algorithms with low computational cost for medical image analysis have also been proposed [12]. Two detection and analysis studies in the edge computing context have been conducted for colonic neoplasia localization [13], and automated analysis of colonoscopies [14]. The latter utilized a Jetson Xavier NX development microsystem, demonstrating that it can host a real-time detection application in terms of computing power and speed.…”
Section: Ai-based Medical Image Assessmentmentioning
confidence: 99%
“…Algorithms with low computational cost for medical image analysis have also been proposed [12]. Two detection and analysis studies in the edge computing context have been conducted for colonic neoplasia localization [13], and automated analysis of colonoscopies [14]. The latter utilized a Jetson Xavier NX development microsystem, demonstrating that it can host a real-time detection application in terms of computing power and speed.…”
Section: Ai-based Medical Image Assessmentmentioning
confidence: 99%
“…Using CADe, AI is able to assist endoscopists in colon lesion detection, thereby increasing the adenoma detection rate (ADR). We present an example from our work of developing an AI system including a CADe module, in Figure 2 [24,25]. For this system, we used MobileNet1, a deep learning network with 4.2 million parameters already trained on the ImageNet dataset, retrained for detecting several types of polyps, lesions, water jet and endoscopic instruments [26].…”
Section: Artificial Intelligence-assisted Colonoscopy In Ibsmentioning
confidence: 99%
“…The accuracy for detection of Meckel's diverticulum is better (around 13%) than the existing work, but the accuracy for detecting polyp, ulcer, and bleeding is very similar with the others. MobileNet from the Jetson-inference software package [144] was used [145] to classify sessile polyps, pedunculated polyps, lipoma, diverticulum, bleeding, vascularized mucosa, water jet, multi-tool head, forceps, and snare) in colonoscopy frames. Accuracy was not reported.…”
Section: Detection Of Other Types Of Abnormalitymentioning
confidence: 99%