Current trends of artificial intelligence and applications in digital pathology: A comprehensive review

被引：1

作者：

Goswami, Neelankit Gautam ^{[1
]}

Karnad, Shreyas ^{[1
]}

Sampathila, Niranjana ^{[1
]}

Bairy, G. Muralidhar ^{[1
]}

Chadaga, Krishnaraj ^{[2
]}

Swathi, K. S. ^{[3
]}

机构：

[1] Manipal Acad Higher Educ, Manipal Inst Technol, Dept Biomed Engn, Manipal, India

[2] Manipal Acad Higher Educ, Manipal Inst Technol, Dept Comp Sci & Engn, Manipal, India

[3] Manipal Acad Higher Educ, Prasanna Sch Publ Hlth, Manipal, India

来源：

INTERNATIONAL JOURNAL OF ADVANCED AND APPLIED SCIENCES | 2023年 / 10卷 / 12期

关键词：

Artificial intelligence; Digital pathology; Object detection; Digital health;

D O I：

10.21833/ijaas.2023.12.004

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

Digital pathology is a field that blends various techniques for obtaining, analyzing, sharing, and saving information about pathology. This information often comes from digitized microscope slides. Digital pathology also uses artificial intelligence (AI) to help reduce errors made by humans. This review talks about digital pathology and the new techniques linked to it. Instead of traditional microscopes, digital pathology employs virtual microscopy and whole-slide imaging. It marks a major improvement over old pathology methods, which had several problems. Digital methods use computers and machines to solve these issues. The basic process of digital pathology has three parts: the input stage, the analysis stage, and the output stage, which includes storing the information. This review focuses on two main techniques: object detection and its smaller methods, and the use of AI and its specific approaches like explainable AI (XAI) and deep learning. The paper also discusses various deep learning methods, mainly used to detect different types of cancer. It also acknowledges that not every method is perfect, so we discuss various challenges and limitations of digital pathology techniques that need to be solved before these methods can be widely used. (c) 2023 The Authors. Published by IASE.

引用

页码：29 / 41

页数：13

共 72 条

[1] Aeffner Famke, 2019, J Pathol Inform, V10, P9, DOI 10.4103/jpi.jpi_82_18
[2] Alake R., 2022, Deep learning: GoogLeNet explained: One of the initial convolutional neural network that dared to go deeper
[3] Doing diagnosis: Whether and how clinicians use a diagnostic tool of uncertain clinical utility
Armstrong, Natalie
Hilton, Paul
[J]. SOCIAL SCIENCE & MEDICINE, 2014, 120 : 208 - 214
[4] Network medicine: a network-based approach to human disease
Barabasi, Albert-Laszlo
Gulbahce, Natali
Loscalzo, Joseph
[J]. NATURE REVIEWS GENETICS, 2011, 12 (01) : 56 - 68
[5] Beitzel S M., 2009, Encyclopedia of database systems, P1691, DOI [10.1007/978-0-387-39940-9 _492, DOI 10.1007/978-0-387-39940-9_492, 10.1007/978-0-387-39940-9492]
[6] BenTaieb A, 2019, Arxiv, DOI arXiv:1910.12329
[7] Bisong E., 2019, BUILDING MACHINE LEA, V1, P59, DOI [DOI 10.1007/978-1-4842-4470-8_7, 10.1007/978-1-4842-4470-8_19, DOI 10.1007/978-1-4842-4470-8_19, DOI 10.1007/978-1-4842-4470-8]
[8] Body fluid analysis: Clinical utility and applicability of published studies to guide interpretation of today's laboratory testing in serous fluids
Block, Darci R.
Algeciras-Schimnich, Alicia
[J]. CRITICAL REVIEWS IN CLINICAL LABORATORY SCIENCES, 2013, 50 (4-5) : 107 - 124
[9] Bochkovskiy A, 2020, Arxiv, DOI [arXiv:2004.10934, 10.48550/arXiv.2004.10934, DOI 10.48550/ARXIV.2004.10934]
[10] Deep learning based tissue analysis predicts outcome in colorectal cancer
Bychkov, Dmitrii
Linder, Nina
Turkki, Riku
Nordling, Stig
Kovanen, Panu E.
Verrill, Clare
Walliander, Margarita
Lundin, Mikael
Haglund, Caj
Lundin, Johan
[J]. SCIENTIFIC REPORTS, 2018, 8

← 1 2 3 4 5 6 7 8 →