東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Generalizable and Explainable Deep L...

Lee, Hyunkwang.

FindBook

Google Book

Amazon

博客來

Generalizable and Explainable Deep Learning in Medical Imaging with Small Data.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Generalizable and Explainable Deep Learning in Medical Imaging with Small Data./
作者:	Lee, Hyunkwang.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	199 p.
附註:	Source: Dissertations Abstracts International, Volume: 82-10, Section: B.
Contained By:	Dissertations Abstracts International82-10B.
標題:	Biomedical engineering. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28444918
ISBN:	9798597054452

Generalizable and Explainable Deep Learning in Medical Imaging with Small Data.
Lee, Hyunkwang.

Generalizable and Explainable Deep Learning in Medical Imaging with Small Data. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 199 p.

Source: Dissertations Abstracts International, Volume: 82-10, Section: B.

Thesis (Ph.D.)--Harvard University, 2020.

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

Deep learning algorithms, such as those used for image recognition, holds promise for automated medical diagnosis and in guiding clinical decision-making. At the same time, there remain several important challenges to the development and clinical translation of medical deep learning systems. First, it is costly to develop large and well-annotated datasets. Second, it is necessary for medical image interpretation to identify subtle key features for lesions despite the wide range in physiologic appearance across the population. Third, it is challenging to transfer the performance of deep learning algorithms from one setting to another because of domain shift problems. Fourth, the outputs of deep learning systems need to be explainable in order to make the systems understandable to clinicians. This dissertation investigates how to address these challenges, building generalizable and explainable deep learning models from small datasets. The thesis studies the impact on model performance of transferring prior knowledge learned from a non-medical source - ImageNet - to medical applications, especially when the dataset size is not sufficient. Instead of direct transfer learning from ImageNet, GrayNet is proposed as a bridge dataset to create a pre-trained model enriched with medical image representations on top of the generic image features learned from ImageNet. Benefits of GrayNet are analyzed with regard to overall performance and generalization across different imaging scanners, in comparison with training from scratch with small data and transfer learning from ImageNet. Domain-specific techniques including window setting optimization and slice interpolation, inspired by how radiologists interpret images for a diagnosis, are also introduced and shown to further enhance model performance. A new visualization module is introduced, able to generate an atlas of images during training, and display this as the basis of model predictions made during testing, in order to justify model predictions and make them more understandable for clinicians. This thesis demonstrates the potential of deep learning for medical image interpretation through three different applications, including AI-assisted bone age assessment to improve human's accuracy and variability, finding previously unrecognized patterns to perform bone sex classification in hand radiographs, and processing raw computed tomography data without image reconstruction. The contributions of this thesis are expected to facilitate the development of generalizable and explainable deep learning algorithms for a variety of medical applications and consequently accelerate the adoption of AI systems into clinical practice.

ISBN: 9798597054452Subjects--Topical Terms:

535387
Biomedical engineering.
Subjects--Index Terms:

Deep Learning

Generalizable and Explainable Deep Learning in Medical Imaging with Small Data.
LDR:04108nmm a2200457 4500 001 2281948
005 20210927083437.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798597054452
035 $a (MiAaPQ)AAI28444918
035 $a (MiAaPQ)vireoharvard3260Lee
035 $a AAI28444918
040 $a MiAaPQ $c MiAaPQ
100 1 $a Lee, Hyunkwang. $3 3560660
245 1 0 $a Generalizable and Explainable Deep Learning in Medical Imaging with Small Data.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 199 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-10, Section: B.
500 $a Advisor: Parkes, David C.
502 $a Thesis (Ph.D.)--Harvard University, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a Deep learning algorithms, such as those used for image recognition, holds promise for automated medical diagnosis and in guiding clinical decision-making. At the same time, there remain several important challenges to the development and clinical translation of medical deep learning systems. First, it is costly to develop large and well-annotated datasets. Second, it is necessary for medical image interpretation to identify subtle key features for lesions despite the wide range in physiologic appearance across the population. Third, it is challenging to transfer the performance of deep learning algorithms from one setting to another because of domain shift problems. Fourth, the outputs of deep learning systems need to be explainable in order to make the systems understandable to clinicians. This dissertation investigates how to address these challenges, building generalizable and explainable deep learning models from small datasets. The thesis studies the impact on model performance of transferring prior knowledge learned from a non-medical source - ImageNet - to medical applications, especially when the dataset size is not sufficient. Instead of direct transfer learning from ImageNet, GrayNet is proposed as a bridge dataset to create a pre-trained model enriched with medical image representations on top of the generic image features learned from ImageNet. Benefits of GrayNet are analyzed with regard to overall performance and generalization across different imaging scanners, in comparison with training from scratch with small data and transfer learning from ImageNet. Domain-specific techniques including window setting optimization and slice interpolation, inspired by how radiologists interpret images for a diagnosis, are also introduced and shown to further enhance model performance. A new visualization module is introduced, able to generate an atlas of images during training, and display this as the basis of model predictions made during testing, in order to justify model predictions and make them more understandable for clinicians. This thesis demonstrates the potential of deep learning for medical image interpretation through three different applications, including AI-assisted bone age assessment to improve human's accuracy and variability, finding previously unrecognized patterns to perform bone sex classification in hand radiographs, and processing raw computed tomography data without image reconstruction. The contributions of this thesis are expected to facilitate the development of generalizable and explainable deep learning algorithms for a variety of medical applications and consequently accelerate the adoption of AI systems into clinical practice.
590 $a School code: 0084.
650 4 $a Biomedical engineering. $3 535387
650 4 $a Artificial intelligence. $3 516317
650 4 $a Medical imaging. $3 3172799
653 $a Deep Learning
653 $a Artificial Intelligence
653 $a Radiology
653 $a Medical Imaging
653 $a Convolutional Neural Network
653 $a Explainable AI
653 $a Generalization
653 $a Segmentation
653 $a Object Recognition
653 $a Healthcare
653 $a Transfer Learning
690 $a 0800
690 $a 0574
690 $a 0541
710 2 $a Harvard University. $b Engineering and Applied Sciences - Engineering Sciences. $3 3184097
773 0 $t Dissertations Abstracts International $g 82-10B.
790 $a 0084
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28444918