Engineered feature embeddings meet deep learning: A novel strategy to improve bone marrow cell classification and model transparency

Cytomorphology evaluation of bone marrow cell is the initial step to diagnose different hematological diseases. This assessment is still manually performed by trained specialists, who may be a bottleneck within the clinical process. Deep learning algorithms are a promising approach to automate this...

Full description

Saved in:
Bibliographic Details
Main Authors: Jonathan Tarquino, Jhonathan Rodríguez, David Becerra, Lucia Roa-Peña, Eduardo Romero
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Journal of Pathology Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2153353924000294
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850257571481387008
author Jonathan Tarquino
Jhonathan Rodríguez
David Becerra
Lucia Roa-Peña
Eduardo Romero
author_facet Jonathan Tarquino
Jhonathan Rodríguez
David Becerra
Lucia Roa-Peña
Eduardo Romero
author_sort Jonathan Tarquino
collection DOAJ
description Cytomorphology evaluation of bone marrow cell is the initial step to diagnose different hematological diseases. This assessment is still manually performed by trained specialists, who may be a bottleneck within the clinical process. Deep learning algorithms are a promising approach to automate this bone marrow cell evaluation. These artificial intelligence models have focused on limited cell subtypes, mainly associated to a particular disease, and are frequently presented as black boxes. The herein introduced strategy presents an engineered feature representation, the region-attention embedding, which improves the deep learning classification performance of a cytomorphology with 21 bone marrow cell subtypes. This embedding is built upon a specific organization of cytology features within a squared matrix by distributing them after pre-segmented cell regions, i.e., cytoplasm, nucleus, and whole-cell. This novel cell image representation, aimed to preserve spatial/regional relations, is used as input of the network. Combination of region-attention embedding and deep learning networks (Xception and ResNet50) provides local relevance associated to image regions, adding up interpretable information to the prediction. Additionally, this approach is evaluated in a public database with the largest number of cell subtypes (21) by a thorough evaluation scheme with three iterations of a 3-fold cross-validation, performed in 80% of the images (n = 89,484), and a testing process in an unseen set of images composed by the remaining 20% of the images (n = 22,371). This evaluation process demonstrates the introduced strategy outperforms previously published approaches in an equivalent validation set, with a f1-score of 0.82, and presented competitive results on the unseen data partition with a f1-score of 0.56.
format Article
id doaj-art-38685f3df52a4fb2a64f035d77c7d936
institution OA Journals
issn 2153-3539
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Journal of Pathology Informatics
spelling doaj-art-38685f3df52a4fb2a64f035d77c7d9362025-08-20T01:56:23ZengElsevierJournal of Pathology Informatics2153-35392024-12-011510039010.1016/j.jpi.2024.100390Engineered feature embeddings meet deep learning: A novel strategy to improve bone marrow cell classification and model transparencyJonathan Tarquino0Jhonathan Rodríguez1David Becerra2Lucia Roa-Peña3Eduardo Romero4Computer Imaging and Medical Application Laboratory, Universidad Nacional de Colombia, Bogotá 111321, ColombiaComputer Imaging and Medical Application Laboratory, Universidad Nacional de Colombia, Bogotá 111321, ColombiaDepartment of Pathology, School of Medicine, Universidad Nacional de Colombia, Bogotá, ColombiaDepartment of Pathology, School of Medicine, Universidad Nacional de Colombia, Bogotá, ColombiaComputer Imaging and Medical Application Laboratory, Universidad Nacional de Colombia, Bogotá 111321, Colombia; Corresponding author:Cytomorphology evaluation of bone marrow cell is the initial step to diagnose different hematological diseases. This assessment is still manually performed by trained specialists, who may be a bottleneck within the clinical process. Deep learning algorithms are a promising approach to automate this bone marrow cell evaluation. These artificial intelligence models have focused on limited cell subtypes, mainly associated to a particular disease, and are frequently presented as black boxes. The herein introduced strategy presents an engineered feature representation, the region-attention embedding, which improves the deep learning classification performance of a cytomorphology with 21 bone marrow cell subtypes. This embedding is built upon a specific organization of cytology features within a squared matrix by distributing them after pre-segmented cell regions, i.e., cytoplasm, nucleus, and whole-cell. This novel cell image representation, aimed to preserve spatial/regional relations, is used as input of the network. Combination of region-attention embedding and deep learning networks (Xception and ResNet50) provides local relevance associated to image regions, adding up interpretable information to the prediction. Additionally, this approach is evaluated in a public database with the largest number of cell subtypes (21) by a thorough evaluation scheme with three iterations of a 3-fold cross-validation, performed in 80% of the images (n = 89,484), and a testing process in an unseen set of images composed by the remaining 20% of the images (n = 22,371). This evaluation process demonstrates the introduced strategy outperforms previously published approaches in an equivalent validation set, with a f1-score of 0.82, and presented competitive results on the unseen data partition with a f1-score of 0.56.http://www.sciencedirect.com/science/article/pii/S2153353924000294Deep learningBone marrow cell subtypesCytomorphologyInterpretabilityBiomedical image processing
spellingShingle Jonathan Tarquino
Jhonathan Rodríguez
David Becerra
Lucia Roa-Peña
Eduardo Romero
Engineered feature embeddings meet deep learning: A novel strategy to improve bone marrow cell classification and model transparency
Journal of Pathology Informatics
Deep learning
Bone marrow cell subtypes
Cytomorphology
Interpretability
Biomedical image processing
title Engineered feature embeddings meet deep learning: A novel strategy to improve bone marrow cell classification and model transparency
title_full Engineered feature embeddings meet deep learning: A novel strategy to improve bone marrow cell classification and model transparency
title_fullStr Engineered feature embeddings meet deep learning: A novel strategy to improve bone marrow cell classification and model transparency
title_full_unstemmed Engineered feature embeddings meet deep learning: A novel strategy to improve bone marrow cell classification and model transparency
title_short Engineered feature embeddings meet deep learning: A novel strategy to improve bone marrow cell classification and model transparency
title_sort engineered feature embeddings meet deep learning a novel strategy to improve bone marrow cell classification and model transparency
topic Deep learning
Bone marrow cell subtypes
Cytomorphology
Interpretability
Biomedical image processing
url http://www.sciencedirect.com/science/article/pii/S2153353924000294
work_keys_str_mv AT jonathantarquino engineeredfeatureembeddingsmeetdeeplearninganovelstrategytoimprovebonemarrowcellclassificationandmodeltransparency
AT jhonathanrodriguez engineeredfeatureembeddingsmeetdeeplearninganovelstrategytoimprovebonemarrowcellclassificationandmodeltransparency
AT davidbecerra engineeredfeatureembeddingsmeetdeeplearninganovelstrategytoimprovebonemarrowcellclassificationandmodeltransparency
AT luciaroapena engineeredfeatureembeddingsmeetdeeplearninganovelstrategytoimprovebonemarrowcellclassificationandmodeltransparency
AT eduardoromero engineeredfeatureembeddingsmeetdeeplearninganovelstrategytoimprovebonemarrowcellclassificationandmodeltransparency