Methods for detecting Acute Lymphoblastic (or Lymphocytic) Leukemia (ALL) based on the analysis of blood images are being increasingly researched in the context of Computer Aided Diagnosis (CAD) systems, which help the pathologist in performing in the diagnosis. Within CAD systems, approaches using Deep Learning (DL) and Convolutional Neural Networks (CNN) currently exhibit the highest accuracy in detecting the presence of lymphoblasts, which indicate the possible presence of ALL. Recently, approaches based on histopathological transfer learning have been proposed to increase the accuracy of ALL detection in the presence of databases with a small number of samples, by pretraining the CNN on histopathological data instead of using general-purpose datasets such as ImageNet. However, all the approaches in the literature consider CNN architectures with an extremely high number of parameters, with a learning procedure that is often impractical using mobile devices or without CUDA-enabled architectures. To compensate for these drawbacks, in this paper we propose ALLNet, the first approach in the literature for ALL detection using a lightweight architecture based on fixed binary kernels that replicate the Local Binary Patterns and that uses only ≈1.6% of the parameters of a traditional CNN, at the same time achieving better results in terms of classification accuracy.

ALLNet: Acute Lymphoblastic Leukemia Detection using lightweight convolutional networks / A. Genovese (... IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND VIRTUAL ENVIRONMENTS FOR MEASUREMENT SYSTEMS AND APPLICATIONS). - In: 2022 IEEE 9th International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)[s.l] : IEEE, 2022. - ISBN 978-1-6654-3445-4. - pp. 1-6 (( Intervento presentato al 9. convegno CIVEMSA tenutosi a Chemnitz nel 2022 [10.1109/CIVEMSA53371.2022.9853691].

ALLNet: Acute Lymphoblastic Leukemia Detection using lightweight convolutional networks

A. Genovese
2022

Abstract

Methods for detecting Acute Lymphoblastic (or Lymphocytic) Leukemia (ALL) based on the analysis of blood images are being increasingly researched in the context of Computer Aided Diagnosis (CAD) systems, which help the pathologist in performing in the diagnosis. Within CAD systems, approaches using Deep Learning (DL) and Convolutional Neural Networks (CNN) currently exhibit the highest accuracy in detecting the presence of lymphoblasts, which indicate the possible presence of ALL. Recently, approaches based on histopathological transfer learning have been proposed to increase the accuracy of ALL detection in the presence of databases with a small number of samples, by pretraining the CNN on histopathological data instead of using general-purpose datasets such as ImageNet. However, all the approaches in the literature consider CNN architectures with an extremely high number of parameters, with a learning procedure that is often impractical using mobile devices or without CUDA-enabled architectures. To compensate for these drawbacks, in this paper we propose ALLNet, the first approach in the literature for ALL detection using a lightweight architecture based on fixed binary kernels that replicate the Local Binary Patterns and that uses only ≈1.6% of the parameters of a traditional CNN, at the same time achieving better results in terms of classification accuracy.
Acute Lymphoblastic Leukemia (ALL); Deep Learning (DL); Convolutional Neural Networks (CNN)
Settore INF/01 - Informatica
2022
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
civemsa22all.pdf

accesso aperto

Tipologia: Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione 2.36 MB
Formato Adobe PDF
2.36 MB Adobe PDF Visualizza/Apri
ALLNet_Acute_Lymphoblastic_Leukemia_Detection_Using_Lightweight_Convolutional_Networks.pdf

accesso riservato

Tipologia: Publisher's version/PDF
Dimensione 2.25 MB
Formato Adobe PDF
2.25 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/924698
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? 3
social impact