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 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.

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

• Original language: English
• Type of outcome: Article in a journal
• Field of Study: 10201 Computer sciences, information science, bioinformatics
• Country of publisher: Netherlands
• Confidentiality degree: is not subject to a state or trade secret
• WWW: 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

• 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