2019
DOI: 10.1002/path.5331
|View full text |Cite
|
Sign up to set email alerts
|

Computational pathology definitions, best practices, and recommendations for regulatory guidance: a white paper from the Digital Pathology Association

Abstract: In this white paper, experts from the Digital Pathology Association (DPA) define terminology and concepts in the emerging field of computational pathology, with a focus on its application to histology images analyzed together with their associated patient data to extract information. This review offers a historical perspective and describes the potential clinical benefits from research and applications in this field, as well as significant obstacles to adoption. Best practices for implementing computational pa… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
316
0
18

Year Published

2019
2019
2024
2024

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 317 publications
(334 citation statements)
references
References 60 publications
0
316
0
18
Order By: Relevance
“…Tissue atlases are envisioned to be spatially resolved counterparts of well-established genomefocused atlases such as The Cancer Genome Atlas (TCGA) 22 and Encyclopedia of DNA Elements (ENCODE) 23 . Unfortunately, algorithms, software, and standards for high-dimensional image data 24 remain under-developed relative to almost all types of genomic information. Moreover, with sequencing data, almost all of the information present in primary data files (e.g., FASTQ files) is retained (or enhanced) when reads are aligned and count tables are generated; it is rarely necessary to re-access the primary fastq files.…”
Section: Accessing and Sharing Imaging Datamentioning
confidence: 99%
“…Tissue atlases are envisioned to be spatially resolved counterparts of well-established genomefocused atlases such as The Cancer Genome Atlas (TCGA) 22 and Encyclopedia of DNA Elements (ENCODE) 23 . Unfortunately, algorithms, software, and standards for high-dimensional image data 24 remain under-developed relative to almost all types of genomic information. Moreover, with sequencing data, almost all of the information present in primary data files (e.g., FASTQ files) is retained (or enhanced) when reads are aligned and count tables are generated; it is rarely necessary to re-access the primary fastq files.…”
Section: Accessing and Sharing Imaging Datamentioning
confidence: 99%
“…8,9 Günümüzde sıkça duyduğumuz "yapay zekâ", insanlar tarafından makinelere kazandırılan, deneyimleri hatırlama, bunlardan öğrenme, düşünme, oluşturma, yargılama ve karar verme becerisi olarak tanımlanmaktadır. [4][5][6]10 Bir makinenin, insan tarafından belli bir göreve yönelik olarak yüklenen çok sayıda veriyi çeşitli yöntemler ile "öğrenmesi" ve insanın istediği bu görevi gerçekleştirebilmesi amaçlanır. Makinenin bu amaçla kullandığı "öğrenme" yöntemlerinden biri ML'dir.…”
Section: Di̇ji̇tal Patoloji̇ Ve Yapay Zekâ İle İlgi̇li̇ Teknoloji̇ler Ve Teunclassified
“…Makinenin bu amaçla kullandığı "öğrenme" yöntemlerinden biri ML'dir. [3][4][5][6] En popüler ML biçimlerinden biri olan derin öğrenme [deep learning (DL)] ise bilgisayarların, insan görsel algılama işlemini, kabaca nöronlara benzeyen, tabakalanmış ve bağlantılandırılmış bir dizi bilgisayar ünitesi, yani evrişimli sinir ağı [convolutional neural network (CNN)] yar-dımı ile taklit etmesini sağlar. [3][4][5][6] İstenen görev ne kadar zorsa karmaşıklık o kadar artar; yani, o kadar fazla tabaka ve tabaka içi ünite işlevi söz konusu olur.…”
Section: Di̇ji̇tal Patoloji̇ Ve Yapay Zekâ İle İlgi̇li̇ Teknoloji̇ler Ve Teunclassified
See 1 more Smart Citation
“…This ready availability of whole slide images raises many issues, from the ethics of using such images for research, through the use of digital images to add quantitation to diagnostic assessment, to the stratification of images based solely on computational assessment. In another recent paper in the Journal, the current position of computational pathology is reviewed and summarized by Abels et al . In addition to providing a very useful glossary of terms, they discuss the various issues facing the implementation of computational pathology approaches in diagnostic and research practice.…”
Section: Computational Pathologymentioning
confidence: 99%