Exploring Deep Learning and Transfer Learning for Colonic Polyp Classification

Computational and Mathematical Methods in Medicine
Eduardo RibeiroMichael Häfner

Abstract

Recently, Deep Learning, especially through Convolutional Neural Networks (CNNs) has been widely used to enable the extraction of highly representative features. This is done among the network layers by filtering, selecting, and using these features in the last fully connected layers for pattern classification. However, CNN training for automated endoscopic image classification still provides a challenge due to the lack of large and publicly available annotated databases. In this work we explore Deep Learning for the automated classification of colonic polyps using different configurations for training CNNs from scratch (or full training) and distinct architectures of pretrained CNNs tested on 8-HD-endoscopic image databases acquired using different modalities. We compare our results with some commonly used features for colonic polyp classification and the good results suggest that features learned by CNNs trained from scratch and the "off-the-shelf" CNNs features can be highly relevant for automated classification of colonic polyps. Moreover, we also show that the combination of classical features and "off-the-shelf" CNNs features can be a good approach to further improve the results.

References

Mar 5, 2019·Australasian Physical & Engineering Sciences in Medicine·Roopa B HegdeBrij Mohan Kumar Singh
Dec 19, 2019·Journal of Digital Imaging·Vidya KudvaShyamala Guruvare
Jun 28, 2019·Archives of Pathology & Laboratory Medicine·David R MartinDouglas P Clark
Sep 7, 2017·Biomedical Engineering Letters·Mustain Billah, Sajjad Waheed
Nov 30, 2018·Histochemistry and Cell Biology·K Shaga DevanC Read
Sep 29, 2020·World Journal of Gastroenterology : WJG·Ke-Wei Wang, Ming Dong
Mar 7, 2019·Journal of Medical Imaging·Georg WimmerAndreas Uhl
Mar 20, 2019·World Journal of Gastroenterology : WJG·Georg WimmerAndreas Uhl

Citations

Oct 1, 1994·Journal of Clinical Pathology·S KudoA Yagyuu
Mar 23, 2006·World Journal of Gastroenterology : WJG·Shigeharu KatoTakahiro Fujimori
Mar 1, 2012·IEEE Transactions on Bio-medical Engineering·Sun Young ParkYousif A-Rahim
May 1, 2012·IEEE Transactions on Bio-medical Engineering·M GanzG Slabaugh
Oct 15, 2013·IEEE Journal of Biomedical and Health Informatics·Yi WangPiet C de Groen
Mar 1, 2014·Medical Image Computing and Computer-assisted Intervention : MICCAI·Adhish PrasoonMads Nielsen
Mar 1, 2014·Medical Image Computing and Computer-assisted Intervention : MICCAI·Dan C CireşanJürgen Schmidhuber
Jul 17, 2014·IEEE Transactions on Cybernetics·Yongsheng DongJiexin Pu
May 9, 2015·Computer Methods and Programs in Biomedicine·Yi WangPiet C de Groen
Sep 20, 2015·Medical Image Analysis·Michael HäfnerShigeto Yoshida
Oct 7, 2015·IEEE Transactions on Medical Imaging·Holger R RothRonald M Summers
Oct 16, 2015·IEEE Transactions on Medical Imaging·Nima TajbakhshJianming Liang
Mar 8, 2016·Medical Image Analysis·Georg WimmerAndreas Uhl
Mar 16, 2016·IEEE Transactions on Medical Imaging·Nima Tajbakhsh Jianming Liang

Related Concepts

Hemodialysis
Endoscopy (Procedure)
Classification
Surgical Endoscopy
Computer Assisted Diagnosis
Reversal Learning
Colonoscopic Surgical Procedures
Optical Image Reconstruction
Computer Programs and Programming
Neural Network Simulation

Trending Feeds

COVID-19

Coronaviruses encompass a large family of viruses that cause the common cold as well as more serious diseases, such as the ongoing outbreak of coronavirus disease 2019 (COVID-19; formally known as 2019-nCoV). Coronaviruses can spread from animals to humans; symptoms include fever, cough, shortness of breath, and breathing difficulties; in more severe cases, infection can lead to death. This feed covers recent research on COVID-19.

Chronic Fatigue Syndrome

Chronic fatigue syndrome is a disease characterized by unexplained disabling fatigue; the pathology of which is incompletely understood. Discover the latest research on chronic fatigue syndrome here.

Synapse Loss as Therapeutic Target in MS

As we age, the number of synapses present in the human brain starts to decline, but in neurodegenerative diseases this occurs at an accelerated rate. In MS, it has been shown that there is a reduction in synaptic density, which presents a potential target for treatment. Here is the latest research on synapse loss as a therapeutic target in MS.

Artificial Intelligence in Cardiac Imaging

Artificial intelligence (ai) techniques are increasingly applied to cardiovascular (cv) medicine in cardiac imaging analysis. Here is the latest research.

Position Effect Variegation

Position Effect Variagation occurs when a gene is inactivated due to its positioning near heterochromatic regions within a chromosome. Discover the latest research on Position Effect Variagation here.

Social Learning

Social learning involves learning new behaviors through observation, imitation and modeling. Follow this feed to stay up to date on the latest research.

Cell Atlas of the Human Eye

Constructing a cell atlas of the human eye will require transcriptomic and histologic analysis over the lifespan. This understanding will aid in the study of development and disease. Find the latest research pertaining to the Cell Atlas of the Human Eye here.

Single Cell Chromatin Profiling

Techniques like ATAC-seq and CUT&Tag have the potential to allow single cell profiling of chromatin accessibility, histones, and TFs. This will provide novel insight into cellular heterogeneity and cell states. Discover the latest research on single cell chromatin profiling here.

Genetic Screens in iPSC-derived Brain Cells

Genetic screening is a critical tool that can be employed to define and understand gene function and interaction. This feed focuses on genetic screens conducted using induced pluripotent stem cell (iPSC)-derived brain cells.

Related Papers

IEEE Transactions on Cybernetics
Yunchao WeiShuicheng Yan
Conference Proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Yuehao Pan Zhongxiang Ding
© 2020 Meta ULC. All rights reserved