Real-Time Gastrointestinal Tract Video Analysis on a Cluster Supercomputer

Blokus, Adam; Brzeski, Adam; Cychnerski, Jan; Dziubich, Tomasz; Jędrzejewski, Mateusz

doi:10.1007/978-3-642-30662-4_4

Cited by 3 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the MAYDAY 2012 project [23], carried out at the Gdansk University of Technology and the Medical University of Gdańsk (Clinic of Gastroenterology and Hepatology, GUMed), an attempt to create an ensemble of specialized classifiers of images from endoscopic videos was made. The aim of those classifiers, being a part of the MedEye application [24], was a multi-class classification and ROI detection to indicate places on the recording where the potential diseases occurred.…”

Section: Dataset Contentsmentioning

confidence: 99%

ERS: a novel comprehensive endoscopy image dataset for machine learning, compliant with the MST 3.0 specification

Cychnerski¹,

Dziubich²,

Brzeski³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The article presents a new multi-label comprehensive image dataset from flexible endoscopy, colonoscopy and capsule endoscopy, named ERS. The collection has been labeled according to the full medical specification of 'Minimum Standard Terminology 3.0' (MST 3.0), describing all possible findings in the gastrointestinal tract (104 possible labels), extended with an additional 19 labels useful in common machine learning applications.The dataset contains around 6000 precisely and 115,000 approximately labeled frames from endoscopy videos, 3600 precise and 22,600 approximate segmentation masks, and 1.23 million unlabeled frames from flexible and capsule endoscopy videos. The labeled data cover almost entirely the MST 3.0 standard. The data came from 1520 videos of 1135 patients.Additionally, this paper proposes and describes four exemplary experiments in gastrointestinal image classification task performed using the created dataset. The obtained results indicate the high usefulness and flexibility of the dataset in training and testing machine learning algorithms in the field of endoscopic data analysis.

show abstract

Section: Dataset Contentsmentioning

confidence: 99%

ERS: a novel comprehensive endoscopy image dataset for machine learning, compliant with the MST 3.0 specification

Cychnerski¹,

Dziubich²,

Brzeski³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…During previously performed experiments [12], the logical structure of the analyzed algorithm has been utilized for the parallelization in a pipeline-like scheme. In this experiments we present another two methods, applicable to a wider range of algorithms.…”

Section: Parallelization Optionsmentioning

confidence: 99%

“…It is capable of processing incoming data with the use of services created by the user and provides methods for an easy parallelization of the algorithms. During previous experiments on general classifying algorithms [12] complying to a similar scheme, the incorporation of the KASKADA platform into the system has allowed it to achieve the performance required for real-time usability.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Bleeding Detection in Gastrointestinal Tract Endoscopic Examinations Video

Blokus¹,

Brzeski²,

Cychnerski³

2013

IJDPS

Self Cite

View full text Add to dashboard Cite

The article presents a novel approach to medical video data analysis and recognition of bleedings.Emphasis has been put on adapting pre-existing algorithms dedicated to the detection of bleedings for realtimeusage in a medical doctor’s office during an endoscopic examination. A real-time system for analyzingendoscopic videos has been designed according to the most significant requirements of medical doctors.The main goal of the performed research was to establish the possibility of ensuring the necessaryperformance of a given class of algorithms to introduce the solution into real life diagnostics.The structures of two exemplary algorithms for bleeding detection have been analyzed to distinguish anddiscuss parallelization options. After applying them to the algorithms, the usage of a supercomputermultimedia processing platform allowed to acquire the throughput and latency values required for realtimeusage. Different configurations of the algorithms have been tested and their measured parametershave been provided and discussed

show abstract

Process of Medical Dataset Construction for Machine Learning - Multifield Study and Guidelines

Cychnerski

Dziubich

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Real-Time Gastrointestinal Tract Video Analysis on a Cluster Supercomputer

Cited by 3 publications

References 14 publications

ERS: a novel comprehensive endoscopy image dataset for machine learning, compliant with the MST 3.0 specification

ERS: a novel comprehensive endoscopy image dataset for machine learning, compliant with the MST 3.0 specification

Real-Time Bleeding Detection in Gastrointestinal Tract Endoscopic Examinations Video

Process of Medical Dataset Construction for Machine Learning - Multifield Study and Guidelines

Contact Info

Product

Resources

About