Název:
Lung Data Analysis With Deep Learning
Autoři:
KESAVAN VIJAYAKUMAR, Harikrishnan Typ dokumentu: Bakalářské práce
Rok:
2021
Jazyk:
eng
Abstrakt: [eng][cze] Medical images can have extremely high resolutions which cannot be handled properly by typical stateofart machine learning models. In this thesis, I compared the performance of two approaches of multiple instance learning models where the high resolution images are downscaled into smaller patches and low dimensional embedding are calculated using Resnet. Then low dimensional embedding are aggregated using multiple instance learning to attain class labels. The data set for this thesis consisted of high resolution histological slides of human lung which were classified to contain cancer or not.Medical images can have extremely high resolutions which cannot be handled properly by typical stateofart machine learning models. In this thesis, I compared the performance of two approaches of multiple instance learning models where the high resolution images are downscaled into smaller patches and low dimensional embedding are calculated using Resnet. Then low dimensional embedding are aggregated using multiple instance learning to attain class labels. The data set for this thesis consisted of high resolution histological slides of human lung which were classified to contain cancer or not.
Klíčová slova:
CLAM; Lung data analysis; Multiple instance learning Citace: KESAVAN VIJAYAKUMAR, Harikrishnan. Lung Data Analysis With Deep Learning. České Budějovice, 2021. bakalářská práce (Bc.). JIHOČESKÁ UNIVERZITA V ČESKÝCH BUDĚJOVICÍCH. Přírodovědecká fakulta
Instituce: Jihočeská univerzita v Českých Budějovicích
(web)
Informace o dostupnosti dokumentu:
Plný text je dostupný v digitálním repozitáři JČU. Původní záznam: http://www.jcu.cz/vskp/66708