OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Training Set Class Distribution Analysis for Deep Learning Model - Application to Cancer Detection

Reshma, Ismat Ara and Gaspard, Margot and Franchet, Camille and Brousset, Pierre and Faure, Emmanuel and Mejbri, Sonia and Mothe, Josiane Training Set Class Distribution Analysis for Deep Learning Model - Application to Cancer Detection. (2019) In: 1st International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI 2019), 20 March 2019 - 22 March 2019 (Barcelona, Spain).

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
417kB

Abstract

Deep learning models specifically CNNs have been used successfully in many tasks including medical image classification. CNN effectiveness depends on the availability of large training data set to train which is generally costly to obtain for new applications or new cases. However, there is a little concrete recommendation about training set creation. In this research, we analyze the impact of different class distributions in the training data to a CNN model. We consider the case of cancer detection task from histopathological images for cancer diagnosis and derive some useful hypotheses about the distribution of classes in the training data. We found that using all the training data leads to the best recall-precision trade-off, while training with a reduced number of examples from some classes, it is possible to inflect the model toward a desired accuracy on a given class.

Item Type:Conference or Workshop Item (Paper)
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Other partners > Centre Hospitalier Universitaire de Toulouse - CHU Toulouse (FRANCE)
Laboratory name:
Statistics:download
Deposited On:22 Jun 2020 11:56

Repository Staff Only: item control page