Authors:
Marie Économidès
1
;
2
and
Pascal Desbarats
2
Affiliations:
1
GE Healthcare, F-78530 Buc, France
;
2
Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, F-33400 Talence, France
Keyword(s):
Deep Learning, Medical Imaging, MRI, Classification, Convolutional Neural Network.
Abstract:
Deep learning has become a key method in computer vision, and has seen an increase in the size of both the networks used and the databases. However, its application in medical imaging faces limitations due to the size of datasets, especially for larger networks. This article aims to answer two questions: How can we design a simple model without compromising classification performance, making training more efficient? And, how much data is needed for our network to learn effectively? The results show that we can find a minimalist CNN adapted to a dataset that gives results comparable to larger architectures. The minimalist CNN does not have a fixed architecture. Its architecture varies according to the dataset and various criteria such as overall performance, training stability, and visual interpretation of network predictions. We hope this work can serve as inspiration for others concerned with these challenges.