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. |
Other formats:
BibTeX
LaTeX
RIS
@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.
|