DL4ALL: Multi-task cross-dataset transfer learning for Acute Lymphoblastic Leukemia detection
Articolo
Data di Pubblicazione:
2023
Citazione:
DL4ALL: Multi-task cross-dataset transfer learning for Acute Lymphoblastic Leukemia detection / A. Genovese, V. Piuri, K.N. Plataniotis, F. Scotti. - In: IEEE ACCESS. - ISSN 2169-3536. - 11:(2023), pp. 65222-65237. [10.1109/ACCESS.2023.3289219]
Abstract:
Methods for the detection of Acute Lymphoblastic (or Lymphocytic) Leukemia (ALL)
are increasingly considering Deep Learning (DL) due to its high accuracy in several elds, including
medical imaging. In most cases, such methods use transfer learning techniques to compensate for
the limited availability of labeled data. However, current methods for ALL detection use traditional
transfer learning, which requires the models to be fully trained on the source domain, then ne-
tuned on the target domain, with the drawback of possibly over tting the source domain and
reducing the generalization capability on the target domain. To overcome this drawback and
increase the classi cation accuracy that can be obtained using transfer learning, in this paper
we propose our method named Deep Learning for Acute Lymphoblastic Leukemia (DL4ALL),
a novel multi-task learning DL model for ALL detection, trained using a cross-dataset transfer
learning approach. The method adapts an existing model into a multi-task classi cation problem,
then trains it using transfer learning procedures that consider both source and target databases
at the same time, interleaving batches from the two domains even when they are signi cantly
di erent. The proposed DL4ALL represents the rst work in the literature using a multi-task
cross-dataset transfer learning procedure for ALL detection. Results on a publicly-available ALL
database con rm the validity of our approach, which achieves a higher accuracy in detecting ALL
with respect to existing methods, even when not using manual labels for the source domain.
Tipologia IRIS:
01 - Articolo su periodico
Keywords:
Acute Lymphoblastic Leukemia (ALL); Deep Learning (DL); Convolutional Neural Networks (CNN);
Elenco autori:
A. Genovese, V. Piuri, K.N. Plataniotis, F. Scotti
Link alla scheda completa:
Link al Full Text: