dc.contributor.author | Henriksen, Fredrik Lund | |
dc.contributor.author | Jensen, Rune | |
dc.contributor.author | Stensland, Håkon Kvale | |
dc.contributor.author | Johansen, Dag | |
dc.contributor.author | Riegler, Michael | |
dc.contributor.author | Halvorsen, Pål | |
dc.date.accessioned | 2020-02-04T10:05:12Z | |
dc.date.accessioned | 2020-03-10T15:49:33Z | |
dc.date.available | 2020-02-04T10:05:12Z | |
dc.date.available | 2020-03-10T15:49:33Z | |
dc.date.issued | 2019 | |
dc.identifier.citation | Henriksen, Jensen, Stensland H, Johansen D, Riegler M, Halvorsen P. Performance of data enhancements and training optimization for neural network: A polyp detection case study. IEEE International Symposium on Computer-Based Medical Systems. 2019 | en |
dc.identifier.issn | 2372-9198 | |
dc.identifier.issn | 2372-9198 | |
dc.identifier.uri | https://hdl.handle.net/10642/8262 | |
dc.description.abstract | Deep learning using neural networks is becoming more and more popular. It is frequently used in areas like video analysis, image retrieval, traffic forecast and speech recognition. In this respect, the learning and training process usually requires a lot of data. However, in many areas, data is scarce which is definitely the case in our medical application scenario, i.e., polyp detection in the gastrointestinal tract. Here, colorectal cancer is on the list of most common cancer types, and often, the cancer arises from benign, adenomatous polyps containing dysplastic cells. Detection and removal of polyps can therefore prevent the development of cancer. Due to high cost, time consumption, patient discomfort and in-accuracy of existing procedures, researchers have started to explore systems for automatic polyp detection to assist and automate current examination procedures. Following the current gained traction for neural networks, and the typical lack of medical data, we explore how data enhancements affect the training and evaluation of the networks in terms of polyp detection accuracy and particularly if it can be used to increase the detection rate. We also experiment with how various training techniques can be used to increase performance. Our experimental results show how data enhancement and training optimization can be used to increase different aspects of the performance, but we also point out mechanisms that have no, and even a negative, effect. | en |
dc.language.iso | en | en |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en |
dc.relation.ispartofseries | IEEE International Symposium on Computer-Based Medical Systems; 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS) | |
dc.rights | © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | en |
dc.subject | Training | en |
dc.subject | Biological neural networks | en |
dc.subject | Cancer | en |
dc.subject | Brightness | en |
dc.subject | Biomedical imaging | en |
dc.subject | Colons | en |
dc.title | Performance of data enhancements and training optimization for neural network: A polyp detection case study | en |
dc.type | Conference object | en |
dc.date.updated | 2020-02-04T10:05:12Z | |
dc.description.version | acceptedVersion | en |
dc.identifier.doi | https://dx.doi.org/10.1109/CBMS.2019.00067 | |
dc.identifier.cristin | 1738613 | |
dc.source.journal | IEEE International Symposium on Computer-Based Medical Systems | |