Ultra high-resolution segmentation of biological images using reduced-memory convolutional neural networks with inter-tile communication
Advances in imaging technology continue to outpace the innovations in computing hardware. For some tasks such as object classification this gap presents almost no problem, given that the results are largely unaffected if some pixel data is missing. This task can produce accurate results by shrinking...
| Main Author: | |
|---|---|
| Format: | Thesis (University of Nottingham only) |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/68434/ |
| _version_ | 1848800487368818688 |
|---|---|
| author | Benson, Ezenwoko |
| author_facet | Benson, Ezenwoko |
| author_sort | Benson, Ezenwoko |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Advances in imaging technology continue to outpace the innovations in computing hardware. For some tasks such as object classification this gap presents almost no problem, given that the results are largely unaffected if some pixel data is missing. This task can produce accurate results by shrinking the image since not all pixel information is required. As such, currently available hardware can be used to complete this task. Tasks like segmentation produce dense per-pixel classifications and benefit greatly from processing all of the pixels in an image, unchanged. In this task only a small amount of image shrinking can take place before the results are affected. Small images can be segmented however, the computational cost becomes prohibitive when applying the same methods to high resolution images. This hasn’t been adequately addressed by current research because of the focus on performance on low resolution benchmark datasets. This thesis presents a novel solution which builds upon the commonly used technique of image tiling. Image tiling is where an image is divided into smaller sub-images called tiles. Processing tiles reduces the memory burden therefore, allowing for the segmentation of larger images. Segmenting a single tile only allows the method to view the context within a tile, which results in inaccurate segmentations when a wider context is required. In this work, context is shared between tiles using global filters. This allows corrections to be made to predictions based on the wider context of the image. The method is shown to be competitive on low resolution datasets against a baseline. It is also shown to outperform high resolution segmentation techniques on high resolution datasets. |
| first_indexed | 2025-11-14T20:52:20Z |
| format | Thesis (University of Nottingham only) |
| id | nottingham-68434 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T20:52:20Z |
| publishDate | 2022 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-684342025-02-28T15:14:46Z https://eprints.nottingham.ac.uk/68434/ Ultra high-resolution segmentation of biological images using reduced-memory convolutional neural networks with inter-tile communication Benson, Ezenwoko Advances in imaging technology continue to outpace the innovations in computing hardware. For some tasks such as object classification this gap presents almost no problem, given that the results are largely unaffected if some pixel data is missing. This task can produce accurate results by shrinking the image since not all pixel information is required. As such, currently available hardware can be used to complete this task. Tasks like segmentation produce dense per-pixel classifications and benefit greatly from processing all of the pixels in an image, unchanged. In this task only a small amount of image shrinking can take place before the results are affected. Small images can be segmented however, the computational cost becomes prohibitive when applying the same methods to high resolution images. This hasn’t been adequately addressed by current research because of the focus on performance on low resolution benchmark datasets. This thesis presents a novel solution which builds upon the commonly used technique of image tiling. Image tiling is where an image is divided into smaller sub-images called tiles. Processing tiles reduces the memory burden therefore, allowing for the segmentation of larger images. Segmenting a single tile only allows the method to view the context within a tile, which results in inaccurate segmentations when a wider context is required. In this work, context is shared between tiles using global filters. This allows corrections to be made to predictions based on the wider context of the image. The method is shown to be competitive on low resolution datasets against a baseline. It is also shown to outperform high resolution segmentation techniques on high resolution datasets. 2022-08-02 Thesis (University of Nottingham only) NonPeerReviewed application/pdf en cc_by_nc https://eprints.nottingham.ac.uk/68434/1/Ezenwoko%20Benson%20Thesis%20%281%29.pdf Benson, Ezenwoko (2022) Ultra high-resolution segmentation of biological images using reduced-memory convolutional neural networks with inter-tile communication. PhD thesis, University of Nottingham. deep learning high-resolution images convolutional neural networks global context |
| spellingShingle | deep learning high-resolution images convolutional neural networks global context Benson, Ezenwoko Ultra high-resolution segmentation of biological images using reduced-memory convolutional neural networks with inter-tile communication |
| title | Ultra high-resolution segmentation of biological images using reduced-memory convolutional neural networks with inter-tile communication |
| title_full | Ultra high-resolution segmentation of biological images using reduced-memory convolutional neural networks with inter-tile communication |
| title_fullStr | Ultra high-resolution segmentation of biological images using reduced-memory convolutional neural networks with inter-tile communication |
| title_full_unstemmed | Ultra high-resolution segmentation of biological images using reduced-memory convolutional neural networks with inter-tile communication |
| title_short | Ultra high-resolution segmentation of biological images using reduced-memory convolutional neural networks with inter-tile communication |
| title_sort | ultra high-resolution segmentation of biological images using reduced-memory convolutional neural networks with inter-tile communication |
| topic | deep learning high-resolution images convolutional neural networks global context |
| url | https://eprints.nottingham.ac.uk/68434/ |