Show simple item record

dc.contributor.authorHussain, Nosheen*
dc.contributor.authorCooper, Patricia A.*
dc.contributor.authorShnyder, Steven*
dc.contributor.authorUgail, Hassan*
dc.contributor.authorBukar, Ali M.*
dc.contributor.authorConnah, David*
dc.date.accessioned2018-01-17T16:09:52Z
dc.date.available2018-01-17T16:09:52Z
dc.date.issued2017
dc.identifier.citationHussain N, Cooper PA, Shnyder SD et al (2017) A Non-invasive 2D Digital Imaging Method for Detection of Surface Lesions Using Machine Learning. In: Proceedings of the 2017 International Conference on Cyberworlds (CW). 20-22 Sep 2017, University of Chester, Chester, UK: 166-169.en_US
dc.identifier.urihttp://hdl.handle.net/10454/14543
dc.descriptionNoen_US
dc.description.abstractAs part of the cancer drug development process, evaluation in experimental subcutaneous tumour transplantation models is a key process. This involves implanting tumour material underneath the mouse skin and measuring tumour growth using calipers. This methodology has been proven to have poor reproducibility and accuracy due to observer variation. Furthermore the physical pressure placed on the tumour using calipers is not only distressing for the mouse but could also lead to tumour damage. Non-invasive digital imaging of the tumour would reduce handling stresses and allow volume determination without any potential tumour damage. This is challenging as the tumours sit under the skin and have the same colour pattern as the mouse body making them hard to differentiate in a 2D image. We used the pre-trained convolutional neural network VGG-16 and extracted multiple layers in an attempt to accurately locate the tumour. When using the layer FC7 after RELU activation for extraction, a recognition rate of 89.85% was achieved.en_US
dc.language.isoenen_US
dc.subjectImage processingen_US
dc.subjectSkin detection
dc.subjectMachine learing
dc.titleA Non-invasive 2D Digital Imaging Method for Detection of Surface Lesions Using Machine Learningen_US
dc.status.refereedYesen_US
dc.typeConference paperen_US
dc.type.versionNo full-text in the repositoryen_US
dc.identifier.doihttps://doi.org/10.1109/CW.2017.39


This item appears in the following Collection(s)

Show simple item record