Shedding light on the black box of a neural network used to
detect prostate cancer in whole slide images by occlusion-based
explainability

J 2023

Shedding light on the black box of a neural network used to detect prostate cancer in whole slide images by occlusion-based explainability

GALLO, Matej, Vojtěch KRAJŇANSKÝ, Rudolf NENUTIL, Petr HOLUB, Tomáš BRÁZDIL et. al.

Basic information

Original name

Shedding light on the black box of a neural network used to detect prostate cancer in whole slide images by occlusion-based explainability

Authors

GALLO, Matej (703 Slovakia, belonging to the institution), Vojtěch KRAJŇANSKÝ (203 Czech Republic, belonging to the institution), Rudolf NENUTIL (203 Czech Republic), Petr HOLUB (203 Czech Republic, belonging to the institution) and Tomáš BRÁZDIL (203 Czech Republic, belonging to the institution)

Edition

NEW BIOTECHNOLOGY, NETHERLANDS, ELSEVIER, 2023, 1871-6784

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Netherlands

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 5.400 in 2022

RIV identification code

RIV/00216224:14330/23:00131902

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.1016/j.nbt.2023.09.008

UT WoS

001102047400001

Keywords in English

Artificial intelligence; Digital histopathology; Explainable AI; Machine learning; Occlusion sensitivity analysis; Prostate cancer

Abstract

V originále

• Saliency maps identified histomorphological features characterizing cancer. • VGG16 model utilized all the structures that are observable by the pathologist. • The method can identify standard patterns not used by the model. • The method can also identify new patterns not yet used by human pathologists.

Links

LM2018140, research and development project

Name: e-Infrastruktura CZ (Acronym: e-INFRA CZ)

Investor: Ministry of Education, Youth and Sports of the CR

MUNI/A/0854/2017, interní kód MU

Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace VII.

Investor: Masaryk University, Category A

MUNI/A/1195/2021, interní kód MU

Name: Aplikovaný výzkum v oblastech vyhledávání, analýz a vizualizací rozsáhlých dat, zpracování přirozeného jazyka a aplikované umělé inteligence

Investor: Masaryk University

MUNI/A/1339/2022, interní kód MU

Name: Rozvoj technik pro zpracování dat pro podporu vyhledávání, analýz a vizualizací rozsáhlých datových souborů s využitím umělé inteligence

Investor: Masaryk University, Development of data processing techniques to support search, analysis and visualization of large datasets using artificial intelligence

Citovat

GALLO, Matej, Vojtěch KRAJŇANSKÝ, Rudolf NENUTIL, Petr HOLUB and Tomáš BRÁZDIL. Shedding light on the black box of a neural network used to detect prostate cancer in whole slide images by occlusion-based explainability. NEW BIOTECHNOLOGY. NETHERLANDS: ELSEVIER, 2023, vol. 78, December, p. 52-67. ISSN 1871-6784. Available from: https://dx.doi.org/10.1016/j.nbt.2023.09.008.

@article{2326025,
   author = {Gallo, Matej and Krajňanský, Vojtěch and Nenutil, Rudolf and Holub, Petr and Brázdil, Tomáš},
   article_location = {NETHERLANDS},
   article_number = {December},
   doi = {http://dx.doi.org/10.1016/j.nbt.2023.09.008},
   keywords = {Artificial intelligence; Digital histopathology; Explainable AI; Machine learning; Occlusion sensitivity analysis; Prostate cancer},
   language = {eng},
   issn = {1871-6784},
   journal = {NEW BIOTECHNOLOGY},
   title = {Shedding light on the black box of a neural network used to detect prostate cancer in whole slide images by occlusion-based explainability},
   url = {https://www.sciencedirect.com/science/article/pii/S1871678423000511},
   volume = {78},
   year = {2023}
}

TY  - JOUR
ID  - 2326025
AU  - Gallo, Matej - Krajňanský, Vojtěch - Nenutil, Rudolf - Holub, Petr - Brázdil, Tomáš
PY  - 2023
TI  - Shedding light on the black box of a neural network used to detect prostate cancer in whole slide images by occlusion-based explainability
JF  - NEW BIOTECHNOLOGY
VL  - 78
IS  - December
SP  - 52-67
EP  - 52-67
PB  - ELSEVIER
SN  - 18716784
KW  - Artificial intelligence
KW  - Digital histopathology
KW  - Explainable AI
KW  - Machine learning
KW  - Occlusion sensitivity analysis
KW  - Prostate cancer
UR  - https://www.sciencedirect.com/science/article/pii/S1871678423000511
N2  - • Saliency maps identified histomorphological features characterizing cancer. • VGG16 model utilized all the structures that are observable by the pathologist. • The method can identify standard patterns not used by the model. • The method can also identify new patterns not yet used by human pathologists.
ER  -

GALLO, Matej, Vojtěch KRAJŇANSKÝ, Rudolf NENUTIL, Petr HOLUB and Tomáš BRÁZDIL. Shedding light on the black box of a neural network used to detect prostate cancer in whole slide images by occlusion-based explainability. \textit{NEW BIOTECHNOLOGY}. NETHERLANDS: ELSEVIER, 2023, vol.~78, December, p.~52-67. ISSN~1871-6784. Available from: https://dx.doi.org/10.1016/j.nbt.2023.09.008.

Detailed Information on Publication Record