東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Advancing Precision Medicine Through...

Lee, Dong Neuck,

Linked to FindBook

Google Book

Amazon

博客來

Advancing Precision Medicine Through Machine Learning /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Advancing Precision Medicine Through Machine Learning // Dong Neuck Lee.
Author:	Lee, Dong Neuck,
Description:	1 electronic resource (164 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
Subject:	Biostatistics. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31147259
ISBN:	9798382719504

Advancing Precision Medicine Through Machine Learning /
Lee, Dong Neuck,

Advancing Precision Medicine Through Machine Learning /Dong Neuck Lee. - 1 electronic resource (164 pages)

Source: Dissertations Abstracts International, Volume: 85-11, Section: B.

Precision medicine adapts medical treatments to individuals. Machine learning is an integral part of this field. Our research focuses on extending and developing machine learning methods in two key areas: image analysis for breast cancer and the development of a novel precision medicine approach.Breast cancer's inherent heterogeneity often requires genetic-based precision medicine, which entails high costs. We explore whether readily available hematoxylin and eosin (H&E)- stained biopsy slides can replace genetics-based information. To achieve this goal, we explore methods for controlling unwanted variation during image acquisition and segmenting H&E stained images into major tissue types. We aim to uncover meaningful information for each type. Additionally, we examine the relationship between H&E stained images and 48 genes closely associated with the immune response, and evaluate the potential for machine learning models based on images to replace genetic-based diagnostics.Another facet of our research involves developing a reinforcement learning method applicable to the general treatment goals of precision medicine. While existing methods often focus on maximizing the expected value of a univariate outcome, our proposed method offers a more versatile approach. It is well-suited for scenarios involving multivariate rewards and the optimization of any real-valued utility function, rather than being limited to optimizing the expectation of a univariate outcome. Our approach is supported by robust theoretical foundations.

English

ISBN: 9798382719504Subjects--Topical Terms:

1002712
Biostatistics.
Subjects--Index Terms:

Image analysis

Advancing Precision Medicine Through Machine Learning /
LDR:03036nmm a22004333i 4500 001 2430738
005 20250603111607.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798382719504
035 $a (MiAaPQD)AAI31147259
035 $a AAI31147259
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Lee, Dong Neuck, $e author. $3 3819212
245 1 0 $a Advancing Precision Medicine Through Machine Learning / $c Dong Neuck Lee.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (164 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
500 $a Advisors: Kosorok, Michael R.; Marron, J. S. Committee members: Li, Yao; Li, Didong; Troester, Melissa.
502 $b Ph.D. $c The University of North Carolina at Chapel Hill $d 2024.
520 $a Precision medicine adapts medical treatments to individuals. Machine learning is an integral part of this field. Our research focuses on extending and developing machine learning methods in two key areas: image analysis for breast cancer and the development of a novel precision medicine approach.Breast cancer's inherent heterogeneity often requires genetic-based precision medicine, which entails high costs. We explore whether readily available hematoxylin and eosin (H&E)- stained biopsy slides can replace genetics-based information. To achieve this goal, we explore methods for controlling unwanted variation during image acquisition and segmenting H&E stained images into major tissue types. We aim to uncover meaningful information for each type. Additionally, we examine the relationship between H&E stained images and 48 genes closely associated with the immune response, and evaluate the potential for machine learning models based on images to replace genetic-based diagnostics.Another facet of our research involves developing a reinforcement learning method applicable to the general treatment goals of precision medicine. While existing methods often focus on maximizing the expected value of a univariate outcome, our proposed method offers a more versatile approach. It is well-suited for scenarios involving multivariate rewards and the optimization of any real-valued utility function, rather than being limited to optimizing the expectation of a univariate outcome. Our approach is supported by robust theoretical foundations.
546 $a English
590 $a School code: 0153
650 4 $a Biostatistics. $3 1002712
650 4 $a Statistics. $3 517247
653 $a Image analysis
653 $a Machine learning
653 $a Precision medicine
653 $a Reinforcement learning method
690 $a 0308
690 $a 0463
690 $a 0800
710 2 $a The University of North Carolina at Chapel Hill. $b Biostatistics. $e degree granting institution. $3 3817171
720 1 $a Kosorok, Michael R. $e degree supervisor.
720 1 $a Marron, J. S. $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 85-11B.
790 $a 0153
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31147259