no code implementations • 10 Nov 2023 • Fabi Prezja, Leevi Annala, Sampsa Kiiskinen, Timo Ojala
Our study underscores the need for careful technique selection for improved model performance and identifying and managing potential confounding regions in radiographic KOA deep learning.
no code implementations • 10 Nov 2023 • Fabi Prezja, Leevi Annala, Sampsa Kiiskinen, Suvi Lahtinen, Timo Ojala
This approach led to two key outcomes: an increase in the initial accuracy of the pre-trained KOA models and a 60-fold reduction in the NAS input vector space, thus facilitating faster inference speed and a more efficient hyperparameter search.
no code implementations • 10 Nov 2023 • Fabi Prezja, Leevi Annala, Sampsa Kiiskinen, Suvi Lahtinen, Timo Ojala
Knee Osteoarthritis (KOA), a leading cause of disability worldwide, is challenging to detect early due to subtle radiographic indicators.
no code implementations • 25 Oct 2023 • Fabi Prezja, Leevi Annala, Sampsa Kiiskinen, Suvi Lahtinen, Timo Ojala, Pekka Ruusuvuori, Teijo Kuopio
However, recent research highlights the potential of convolutional neural networks (CNNs) in facilitating the extraction of clinically relevant biomarkers from these readily available images.