Confocal Laser Endomicroscopy Image Analysis with Deep Convolutional Neural Networks
abstract: Rapid intraoperative diagnosis of brain tumors is of great importance for planning treatment and guiding the surgeon about the extent of resection. Currently, the standard for the preliminary intraoperative tissue analysis is frozen section biopsy that has major limitations such as tissue...
Other Authors: | |
---|---|
Format: | Doctoral Thesis |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | http://hdl.handle.net/2286/R.I.53650 |
id |
ndltd-asu.edu-item-53650 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-asu.edu-item-536502019-05-16T03:01:31Z Confocal Laser Endomicroscopy Image Analysis with Deep Convolutional Neural Networks abstract: Rapid intraoperative diagnosis of brain tumors is of great importance for planning treatment and guiding the surgeon about the extent of resection. Currently, the standard for the preliminary intraoperative tissue analysis is frozen section biopsy that has major limitations such as tissue freezing and cutting artifacts, sampling errors, lack of immediate interaction between the pathologist and the surgeon, and time consuming. Handheld, portable confocal laser endomicroscopy (CLE) is being explored in neurosurgery for its ability to image histopathological features of tissue at cellular resolution in real time during brain tumor surgery. Over the course of examination of the surgical tumor resection, hundreds to thousands of images may be collected. The high number of images requires significant time and storage load for subsequent reviewing, which motivated several research groups to employ deep convolutional neural networks (DCNNs) to improve its utility during surgery. DCNNs have proven to be useful in natural and medical image analysis tasks such as classification, object detection, and image segmentation. This thesis proposes using DCNNs for analyzing CLE images of brain tumors. Particularly, it explores the practicality of DCNNs in three main tasks. First, off-the shelf DCNNs were used to classify images into diagnostic and non-diagnostic. Further experiments showed that both ensemble modeling and transfer learning improved the classifier’s accuracy in evaluating the diagnostic quality of new images at test stage. Second, a weakly-supervised learning pipeline was developed for localizing key features of diagnostic CLE images from gliomas. Third, image style transfer was used to improve the diagnostic quality of CLE images from glioma tumors by transforming the histology patterns in CLE images of fluorescein sodium-stained tissue into the ones in conventional hematoxylin and eosin-stained tissue slides. These studies suggest that DCNNs are opted for analysis of CLE images. They may assist surgeons in sorting out the non-diagnostic images, highlighting the key regions and enhancing their appearance through pattern transformation in real time. With recent advances in deep learning such as generative adversarial networks and semi-supervised learning, new research directions need to be followed to discover more promises of DCNNs in CLE image analysis. Dissertation/Thesis Izady Yazdanabadi, Mohammadhassan (Author) Preul, Mark (Advisor) Yang, Yezhou (Advisor) Nakaji, Peter (Committee member) Vernon, Brent (Committee member) Arizona State University (Publisher) Medical imaging Computer science Surgery cancer detection confocal laser endomicroscopy convolutional neural networks deep learning digital pathology glioma eng 133 pages Doctoral Dissertation Neuroscience 2019 Doctoral Dissertation http://hdl.handle.net/2286/R.I.53650 http://rightsstatements.org/vocab/InC/1.0/ 2019 |
collection |
NDLTD |
language |
English |
format |
Doctoral Thesis |
sources |
NDLTD |
topic |
Medical imaging Computer science Surgery cancer detection confocal laser endomicroscopy convolutional neural networks deep learning digital pathology glioma |
spellingShingle |
Medical imaging Computer science Surgery cancer detection confocal laser endomicroscopy convolutional neural networks deep learning digital pathology glioma Confocal Laser Endomicroscopy Image Analysis with Deep Convolutional Neural Networks |
description |
abstract: Rapid intraoperative diagnosis of brain tumors is of great importance for planning treatment and guiding the surgeon about the extent of resection. Currently, the standard for the preliminary intraoperative tissue analysis is frozen section biopsy that has major limitations such as tissue freezing and cutting artifacts, sampling errors, lack of immediate interaction between the pathologist and the surgeon, and time consuming.
Handheld, portable confocal laser endomicroscopy (CLE) is being explored in neurosurgery for its ability to image histopathological features of tissue at cellular resolution in real time during brain tumor surgery. Over the course of examination of the surgical tumor resection, hundreds to thousands of images may be collected. The high number of images requires significant time and storage load for subsequent reviewing, which motivated several research groups to employ deep convolutional neural networks (DCNNs) to improve its utility during surgery. DCNNs have proven to be useful in natural and medical image analysis tasks such as classification, object detection, and image segmentation.
This thesis proposes using DCNNs for analyzing CLE images of brain tumors. Particularly, it explores the practicality of DCNNs in three main tasks. First, off-the shelf DCNNs were used to classify images into diagnostic and non-diagnostic. Further experiments showed that both ensemble modeling and transfer learning improved the classifier’s accuracy in evaluating the diagnostic quality of new images at test stage. Second, a weakly-supervised learning pipeline was developed for localizing key features of diagnostic CLE images from gliomas. Third, image style transfer was used to improve the diagnostic quality of CLE images from glioma tumors by transforming the histology patterns in CLE images of fluorescein sodium-stained tissue into the ones in conventional hematoxylin and eosin-stained tissue slides.
These studies suggest that DCNNs are opted for analysis of CLE images. They may assist surgeons in sorting out the non-diagnostic images, highlighting the key regions and enhancing their appearance through pattern transformation in real time. With recent advances in deep learning such as generative adversarial networks and semi-supervised learning, new research directions need to be followed to discover more promises of DCNNs in CLE image analysis. === Dissertation/Thesis === Doctoral Dissertation Neuroscience 2019 |
author2 |
Izady Yazdanabadi, Mohammadhassan (Author) |
author_facet |
Izady Yazdanabadi, Mohammadhassan (Author) |
title |
Confocal Laser Endomicroscopy Image Analysis with Deep Convolutional Neural Networks |
title_short |
Confocal Laser Endomicroscopy Image Analysis with Deep Convolutional Neural Networks |
title_full |
Confocal Laser Endomicroscopy Image Analysis with Deep Convolutional Neural Networks |
title_fullStr |
Confocal Laser Endomicroscopy Image Analysis with Deep Convolutional Neural Networks |
title_full_unstemmed |
Confocal Laser Endomicroscopy Image Analysis with Deep Convolutional Neural Networks |
title_sort |
confocal laser endomicroscopy image analysis with deep convolutional neural networks |
publishDate |
2019 |
url |
http://hdl.handle.net/2286/R.I.53650 |
_version_ |
1719183430252494848 |