ALL-IDB Patches: Whole slide imaging for Acute Lymphoblastic Leukemia detection using Deep Learning
Contributo in Atti di convegno
Data di Pubblicazione:
2023
Citazione:
ALL-IDB Patches: Whole slide imaging for Acute Lymphoblastic Leukemia detection using Deep Learning / A. Genovese, V. Piuri, F. Scotti - In: 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)[s.l] : IEEE, 2023 Jun 04. - ISBN 979-8-3503-0261-5. - pp. 1-5 (( convegno International Conference on Acoustics, Speech, and Signal Processing tenutosi a Rhodes Island nel 2023 [10.1109/ICASSPW59220.2023.10193429].
Abstract:
The detection of Acute Lymphoblastic (or Lymphocytic) Leukemia (ALL) is being increasingly performed using Deep Learning models (DL) that analyze each blood sample to detect the presence of lymphoblasts, possible indicators of the disease. However, current databases either contain too large images or images already segmented. In this paper, we introduce ALL-IDB Patches, a novel approach for processing Whole Slide Images (WSI) of ALL to take advantage of all the information available for ALL detection, by generating a larger number of samples, making the images usable by current DL models, and without any pre-performed segmentation. To evaluate the recognition accuracy, we consider the OrthoALLNet, obtained by imposing an additional orthogonality constraint on the filters learned by the CNN, with results confirming the validity of the approach.
Tipologia IRIS:
03 - Contributo in volume
Keywords:
Deep Learning; CNN; ALL; XAI
Elenco autori:
A. Genovese, V. Piuri, F. Scotti
Link alla scheda completa:
Link al Full Text:
Titolo del libro:
2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)