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

Increasing the Depth and Quality of ...

Border, Samuel P.,

FindBook

Google Book

Amazon

博客來

Increasing the Depth and Quality of Computational Pathology Research Through Interactive Tools and Multi-Modal Data /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Increasing the Depth and Quality of Computational Pathology Research Through Interactive Tools and Multi-Modal Data // Samuel P Border.
作者:	Border, Samuel P.,
面頁冊數:	1 electronic resource (146 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
Contained By:	Dissertations Abstracts International86-12B.
標題:	Biomedical engineering. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32042445
ISBN:	9798280781344

Increasing the Depth and Quality of Computational Pathology Research Through Interactive Tools and Multi-Modal Data /
Border, Samuel P.,

Increasing the Depth and Quality of Computational Pathology Research Through Interactive Tools and Multi-Modal Data /Samuel P Border. - 1 electronic resource (146 pages)

Source: Dissertations Abstracts International, Volume: 86-12, Section: B.

In the last decade, the field of computational histology has grown by great leaps and bounds. Aided by increases in the accessibility and power of computational hardware and widespread pushes for whole slide image (WSI) digitization, the application and design of machine learning (ML) algorithms for use in diagnostics and prognostics has expanded to cover a wide variety of different use-cases specific to pathology. Accompanying this increase in Artificial Intelligence (AI) and ML algorithms popularity is an increase in demand for quantification and assessment of robustness of algorithms in preparation for regulatory approval. As opposed to classical ML problems, such as cat vs. dog image classification, all problems which have direct influence on decisions which could impact a patient's health must be extensively validated to ensure applied models are appropriately analyzing a given set of data. Furthermore, researchers in the field of computational histology must also account for the much more granular distinctive characteristics which are present between different diagnostic grades compared to other classification tasks. Finally, successful pipelines which have a potential for integration into a clinical setting must build off hundreds of years of pathological research in order to provide a supplement, not replacement, for an experienced pathologist.The great number of challenges which are presented for new researchers in the field of computational histology may also lead to new opportunities to design robust algorithms and techniques which are applicable to many other problems in biological and biomedical research. In the following document, I will provide an extensive look into the design and usage of computational image analysis algorithms for the quantification and analysis of patterns found in histology WSIs. Additionally, I will demonstrate the incorporation of complex algorithms into user-friendly tools that encourage direct interaction and interrogation of large amounts of data. Finally, I will illustrate how computational image analysis can also be integrated into multi-modal spatial -omics data to uncover linked insights into underlying pathological mechanisms.

English

ISBN: 9798280781344Subjects--Topical Terms:

535387
Biomedical engineering.
Subjects--Index Terms:

Computational pathology

Increasing the Depth and Quality of Computational Pathology Research Through Interactive Tools and Multi-Modal Data /
LDR:03760nmm a22004573i 4500 001 2432725
005 20250731101920.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798280781344
035 $a (MiAaPQD)AAI32042445
035 $a AAI32042445
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Border, Samuel P., $e author. $0 (orcid)0000-0002-8806-6965 $3 3822057
245 1 0 $a Increasing the Depth and Quality of Computational Pathology Research Through Interactive Tools and Multi-Modal Data / $c Samuel P Border.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (146 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: 86-12, Section: B.
500 $a Advisors: Tomaszewski, John E. Committee members: Tutino, Vincent; Doyle, Scott.
502 $b Ph.D. $c State University of New York at Buffalo $d 2025.
520 $a In the last decade, the field of computational histology has grown by great leaps and bounds. Aided by increases in the accessibility and power of computational hardware and widespread pushes for whole slide image (WSI) digitization, the application and design of machine learning (ML) algorithms for use in diagnostics and prognostics has expanded to cover a wide variety of different use-cases specific to pathology. Accompanying this increase in Artificial Intelligence (AI) and ML algorithms popularity is an increase in demand for quantification and assessment of robustness of algorithms in preparation for regulatory approval. As opposed to classical ML problems, such as cat vs. dog image classification, all problems which have direct influence on decisions which could impact a patient's health must be extensively validated to ensure applied models are appropriately analyzing a given set of data. Furthermore, researchers in the field of computational histology must also account for the much more granular distinctive characteristics which are present between different diagnostic grades compared to other classification tasks. Finally, successful pipelines which have a potential for integration into a clinical setting must build off hundreds of years of pathological research in order to provide a supplement, not replacement, for an experienced pathologist.The great number of challenges which are presented for new researchers in the field of computational histology may also lead to new opportunities to design robust algorithms and techniques which are applicable to many other problems in biological and biomedical research. In the following document, I will provide an extensive look into the design and usage of computational image analysis algorithms for the quantification and analysis of patterns found in histology WSIs. Additionally, I will demonstrate the incorporation of complex algorithms into user-friendly tools that encourage direct interaction and interrogation of large amounts of data. Finally, I will illustrate how computational image analysis can also be integrated into multi-modal spatial -omics data to uncover linked insights into underlying pathological mechanisms.
546 $a English
590 $a School code: 0656
650 4 $a Biomedical engineering. $3 535387
650 4 $a Pathology. $3 643180
650 4 $a Cellular biology. $3 3172791
653 $a Computational pathology
653 $a Histology
653 $a Interactive analysis
653 $a Interactive tools
653 $a Machine learning
653 $a Spatial omics
690 $a 0541
690 $a 0571
690 $a 0379
690 $a 0800
710 2 $a State University of New York at Buffalo. $b Pathology and Anatomical Sciences. $e degree granting institution. $3 3822058
720 1 $a Tomaszewski, John E. $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-12B.
790 $a 0656
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32042445