dc.contributor.author |
Mabaso, Matsilele A
|
|
dc.contributor.author |
Withey, Daniel J
|
|
dc.contributor.author |
Twala, B
|
|
dc.date.accessioned |
2018-03-14T12:57:42Z |
|
dc.date.available |
2018-03-14T12:57:42Z |
|
dc.date.issued |
2018-01 |
|
dc.identifier.citation |
Mabaso, M.A., Withey, D.J. and Twala, B. 2018. Spot detection in microscopy images using Convolutional Neural Network with sliding-window approach. Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies, 19-21 January 2018, Funchal, Madeira, Portugal |
en_US |
dc.identifier.isbn |
978-989-758-278-3 |
|
dc.identifier.uri |
http://www.scitepress.org/DigitalLibrary/ProceedingsDetails.aspx?ID=yyXCnk8kL6s=&t=1
|
|
dc.identifier.uri |
http://hdl.handle.net/10204/10100
|
|
dc.description |
This is the accepted version of the paper. The published version can be obtained via the publisher's website. |
en_US |
dc.description.abstract |
Robust spot detection in microscopy image analysis serves as a critical prerequisite in many biomedical applications. Various approaches that automatically detect spots have been proposed to improve the analysis of biological images. In this paper, we propose an approach based on Convolutional Neural Network (conv-net) that automatically detects spots using sliding-window approach. In this framework, a supervised CNN is trained to identify spots in image patches. Then, a sliding window is applied on testing images containing multiple spots where each window is sent to a CNN classifier to check if it contains a spot or not. This gives results for multiple windows which are then post-processed to remove overlaps by overlap suppression. The proposed approach was compared to two other popular conv-nets namely, GoogleNet and AlexNet using two types of synthetic images. The experimental results indicate that the proposed methodology provides fast spot detection with precision, recall and F score values that are comparable with the other state-of-the-art pre-trained conv-nets methods. This demonstrates that, rather than training a conv-net from scratch, fine-tuned pre-trained conv-net models can be used for the task of spot detection. |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
SCITEPRESS |
en_US |
dc.relation.ispartofseries |
Worklist;20271 |
|
dc.subject |
Microscopy images |
en_US |
dc.subject |
Convolutional Neural Network |
en_US |
dc.subject |
Spot Detection |
en_US |
dc.title |
Spot detection in microscopy images using Convolutional Neural Network with sliding-window approach |
en_US |
dc.type |
Conference Presentation |
en_US |
dc.identifier.apacitation |
Mabaso, M. A., Withey, D. J., & Twala, B. (2018). Spot detection in microscopy images using Convolutional Neural Network with sliding-window approach. SCITEPRESS. http://hdl.handle.net/10204/10100 |
en_ZA |
dc.identifier.chicagocitation |
Mabaso, Matsilele A, Daniel J Withey, and B Twala. "Spot detection in microscopy images using Convolutional Neural Network with sliding-window approach." (2018): http://hdl.handle.net/10204/10100 |
en_ZA |
dc.identifier.vancouvercitation |
Mabaso MA, Withey DJ, Twala B, Spot detection in microscopy images using Convolutional Neural Network with sliding-window approach; SCITEPRESS; 2018. http://hdl.handle.net/10204/10100 . |
en_ZA |
dc.identifier.ris |
TY - Conference Presentation
AU - Mabaso, Matsilele A
AU - Withey, Daniel J
AU - Twala, B
AB - Robust spot detection in microscopy image analysis serves as a critical prerequisite in many biomedical applications. Various approaches that automatically detect spots have been proposed to improve the analysis of biological images. In this paper, we propose an approach based on Convolutional Neural Network (conv-net) that automatically detects spots using sliding-window approach. In this framework, a supervised CNN is trained to identify spots in image patches. Then, a sliding window is applied on testing images containing multiple spots where each window is sent to a CNN classifier to check if it contains a spot or not. This gives results for multiple windows which are then post-processed to remove overlaps by overlap suppression. The proposed approach was compared to two other popular conv-nets namely, GoogleNet and AlexNet using two types of synthetic images. The experimental results indicate that the proposed methodology provides fast spot detection with precision, recall and F score values that are comparable with the other state-of-the-art pre-trained conv-nets methods. This demonstrates that, rather than training a conv-net from scratch, fine-tuned pre-trained conv-net models can be used for the task of spot detection.
DA - 2018-01
DB - ResearchSpace
DP - CSIR
KW - Microscopy images
KW - Convolutional Neural Network
KW - Spot Detection
LK - https://researchspace.csir.co.za
PY - 2018
SM - 978-989-758-278-3
T1 - Spot detection in microscopy images using Convolutional Neural Network with sliding-window approach
TI - Spot detection in microscopy images using Convolutional Neural Network with sliding-window approach
UR - http://hdl.handle.net/10204/10100
ER -
|
en_ZA |