東華大學圖書館 |

Automated Longitudinal Assessment of CT Cancer Lesions.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Automated Longitudinal Assessment of CT Cancer Lesions./
作者:	Rister, Blaine Burton.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	120 p.
附註:	Source: Dissertations Abstracts International, Volume: 84-01, Section: B.
Contained By:	Dissertations Abstracts International84-01B.
標題:	Cancer. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29176534
ISBN:	9798835540891

Automated Longitudinal Assessment of CT Cancer Lesions.
Rister, Blaine Burton.

Automated Longitudinal Assessment of CT Cancer Lesions. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 120 p.

Source: Dissertations Abstracts International, Volume: 84-01, Section: B.

Thesis (Ph.D.)--Stanford University, 2022.

This item must not be sold to any third party vendors.

Objective assessment of cancer imaging studies remains a gap in patient care. Although lesion assessment is a critical part of assessing cancer treatment response, in current clinical practice it is mostly done qualitatively through free-text reports. Quantitative lesion assessment is usually only done in clinical trials, representing a small fraction of all cancer cases.To address this need, this thesis presents an automated pipeline for longitudinal assessment of cancer lesions. Given an annotated baseline exam, the system automatically detects, segments and measures the corresponding target lesions in one or more follow-up exams. It also learns from prior time points by training on partial lesion annotations made by physicians.The core components of this system are neural networks for organ and lesion segmentation, image registration from 3D SIFT-like keypoints, and a method for combining all of these into an end-to-end system that learns from prior time points. This thesis presents several contributions to each of these technical areas.For organ segmentation, we present a new dataset labeling six organs in a variety of CT scans. Despite the relative ease of locating organs in the human body, automated organ segmentation has been hindered by the scarcity of labeled training data. Due to the tedium of labeling organ boundaries, most datasets are limited to either a small number of cases or a single organ. Furthermore, many are restricted to specific imaging conditions unrepresentative of clinical practice. To address this need, we developed a diverse dataset of 140 CT scans containing six organ classes: liver, lungs, bladder, kidney, bones and brain. For the lungs and bones, we expedited annotation using unsupervised morphological segmentation algorithms, which were accelerated by 3D Fourier transforms. We trained a deep neural network which requires only 4.3 s to simultaneously segment all the organs in a CT exam. We also show how to efficiently augment the data to improve model generalization, providing a GPU library for doing so. The dataset and code are available through The Cancer Imaging Archive.For lesion segmentation, we show how the same neural network architecture can be generalized to segment lesions using public datasets with CT scans of two different organs: the liver and the lungs. For our ultimate goal of longitudinal segmentation, we also show how to train these models on partially labeled CT scans from prior timepoints in the clinical record.For image registration, we present a method based on 3D scale- and rotation-invariant keypoints. The method extends the Scale Invariant Feature Transform (SIFT) to arbitrary dimensions by making key modifications to orientation assignment and gradient histograms. Rotation invariance is proven mathematically. Additional modifications are made to extrema detection and keypoint matching based on the demands of image registration. Our experiments suggest that the choice of neighborhood in discrete extrema detection has a strong impact on image registration accuracy. In head MR images, the brain is registered to a labeled atlas with an average Dice coefficient of 92%, outperforming registration from mutual information as well as an existing 3D SIFT implementation. In abdominal CT images, the spine is registered with an average error of 4.82 mm.

ISBN: 9798835540891Subjects--Topical Terms:

634186
Cancer.

Automated Longitudinal Assessment of CT Cancer Lesions.
LDR:04462nmm a2200361 4500 001 2352098
005 20221111121017.5
008 241004s2022 ||||||||||||||||| ||eng d
020 $a 9798835540891
035 $a (MiAaPQ)AAI29176534
035 $a (MiAaPQ)STANFORDyx087mh5697
035 $a AAI29176534
040 $a MiAaPQ $c MiAaPQ
100 1 $a Rister, Blaine Burton. $3 3691718
245 1 0 $a Automated Longitudinal Assessment of CT Cancer Lesions.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 120 p.
500 $a Source: Dissertations Abstracts International, Volume: 84-01, Section: B.
500 $a Advisor: Rubin, Daniel;Duchi, John;Horowitz, Mark.
502 $a Thesis (Ph.D.)--Stanford University, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Objective assessment of cancer imaging studies remains a gap in patient care. Although lesion assessment is a critical part of assessing cancer treatment response, in current clinical practice it is mostly done qualitatively through free-text reports. Quantitative lesion assessment is usually only done in clinical trials, representing a small fraction of all cancer cases.To address this need, this thesis presents an automated pipeline for longitudinal assessment of cancer lesions. Given an annotated baseline exam, the system automatically detects, segments and measures the corresponding target lesions in one or more follow-up exams. It also learns from prior time points by training on partial lesion annotations made by physicians.The core components of this system are neural networks for organ and lesion segmentation, image registration from 3D SIFT-like keypoints, and a method for combining all of these into an end-to-end system that learns from prior time points. This thesis presents several contributions to each of these technical areas.For organ segmentation, we present a new dataset labeling six organs in a variety of CT scans. Despite the relative ease of locating organs in the human body, automated organ segmentation has been hindered by the scarcity of labeled training data. Due to the tedium of labeling organ boundaries, most datasets are limited to either a small number of cases or a single organ. Furthermore, many are restricted to specific imaging conditions unrepresentative of clinical practice. To address this need, we developed a diverse dataset of 140 CT scans containing six organ classes: liver, lungs, bladder, kidney, bones and brain. For the lungs and bones, we expedited annotation using unsupervised morphological segmentation algorithms, which were accelerated by 3D Fourier transforms. We trained a deep neural network which requires only 4.3 s to simultaneously segment all the organs in a CT exam. We also show how to efficiently augment the data to improve model generalization, providing a GPU library for doing so. The dataset and code are available through The Cancer Imaging Archive.For lesion segmentation, we show how the same neural network architecture can be generalized to segment lesions using public datasets with CT scans of two different organs: the liver and the lungs. For our ultimate goal of longitudinal segmentation, we also show how to train these models on partially labeled CT scans from prior timepoints in the clinical record.For image registration, we present a method based on 3D scale- and rotation-invariant keypoints. The method extends the Scale Invariant Feature Transform (SIFT) to arbitrary dimensions by making key modifications to orientation assignment and gradient histograms. Rotation invariance is proven mathematically. Additional modifications are made to extrema detection and keypoint matching based on the demands of image registration. Our experiments suggest that the choice of neighborhood in discrete extrema detection has a strong impact on image registration accuracy. In head MR images, the brain is registered to a labeled atlas with an average Dice coefficient of 92%, outperforming registration from mutual information as well as an existing 3D SIFT implementation. In abdominal CT images, the spine is registered with an average error of 4.82 mm.
590 $a School code: 0212.
650 4 $a Cancer. $3 634186
650 4 $a Tomography. $3 836553
650 4 $a Deep learning. $3 3554982
650 4 $a Clinical medicine. $3 804916
650 4 $a Liver. $3 3564653
650 4 $a Neural networks. $3 677449
650 4 $a Medical research. $2 bicssc $3 1556686
650 4 $a Clinical trials. $3 724498
650 4 $a Registration. $3 3682192
650 4 $a Annotations. $3 3561780
650 4 $a Tumors. $3 893964
650 4 $a Performance evaluation. $3 3562292
650 4 $a Reproducibility. $3 3683754
650 4 $a Morphology. $3 591167
650 4 $a Artificial intelligence. $3 516317
650 4 $a Biology. $3 522710
650 4 $a Medical imaging. $3 3172799
650 4 $a Medicine. $3 641104
650 4 $a Pharmacology. $3 634543
690 $a 0287
690 $a 0800
690 $a 0306
690 $a 0574
690 $a 0564
690 $a 0419
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 84-01B.
790 $a 0212
791 $a Ph.D.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29176534