Cargando…

An End-to-End Pipeline for Early Diagnosis of Acute Promyelocytic Leukemia Based on a Compact CNN Model

Timely microscopy screening of peripheral blood smears is essential for the diagnosis of acute promyelocytic leukemia (APL) due to the occurrence of early death (ED) before or during the initial therapy. Screening manually is time-consuming and tedious, and may lead to missed diagnosis or misdiagnos...

Descripción completa

Detalles Bibliográficos
Autores principales: Qiao, Yifan, Zhang, Yi, Liu, Nian, Chen, Pu, Liu, Yan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8304210/
https://www.ncbi.nlm.nih.gov/pubmed/34359320
http://dx.doi.org/10.3390/diagnostics11071237
_version_ 1783727278702723072
author Qiao, Yifan
Zhang, Yi
Liu, Nian
Chen, Pu
Liu, Yan
author_facet Qiao, Yifan
Zhang, Yi
Liu, Nian
Chen, Pu
Liu, Yan
author_sort Qiao, Yifan
collection PubMed
description Timely microscopy screening of peripheral blood smears is essential for the diagnosis of acute promyelocytic leukemia (APL) due to the occurrence of early death (ED) before or during the initial therapy. Screening manually is time-consuming and tedious, and may lead to missed diagnosis or misdiagnosis because of subjective bias. To address these problems, we develop a three-step pipeline to help in the early diagnosis of APL from peripheral blood smears. The entire pipeline consists of leukocytes focusing, cell classification and diagnostic opinions. As the key component of the pipeline, a compact classification model based on attention embedded convolutional neural network blocks is proposed to distinguish promyelocytes from normal leukocytes. The compact classification model is validated on both the combination of two public datasets, APL-Cytomorphology_LMU and APL-Cytomorphology_JHH, as well as the clinical dataset, to yield a precision of 96.53% and 99.20%, respectively. The results indicate that our model outperforms the other evaluated popular classification models owing to its better accuracy and smaller size. Furthermore, the entire pipeline is validated on realistic patient data. The proposed method promises to act as an assistant tool for APL diagnosis.
format Online
Article
Text
id pubmed-8304210
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83042102021-07-25 An End-to-End Pipeline for Early Diagnosis of Acute Promyelocytic Leukemia Based on a Compact CNN Model Qiao, Yifan Zhang, Yi Liu, Nian Chen, Pu Liu, Yan Diagnostics (Basel) Article Timely microscopy screening of peripheral blood smears is essential for the diagnosis of acute promyelocytic leukemia (APL) due to the occurrence of early death (ED) before or during the initial therapy. Screening manually is time-consuming and tedious, and may lead to missed diagnosis or misdiagnosis because of subjective bias. To address these problems, we develop a three-step pipeline to help in the early diagnosis of APL from peripheral blood smears. The entire pipeline consists of leukocytes focusing, cell classification and diagnostic opinions. As the key component of the pipeline, a compact classification model based on attention embedded convolutional neural network blocks is proposed to distinguish promyelocytes from normal leukocytes. The compact classification model is validated on both the combination of two public datasets, APL-Cytomorphology_LMU and APL-Cytomorphology_JHH, as well as the clinical dataset, to yield a precision of 96.53% and 99.20%, respectively. The results indicate that our model outperforms the other evaluated popular classification models owing to its better accuracy and smaller size. Furthermore, the entire pipeline is validated on realistic patient data. The proposed method promises to act as an assistant tool for APL diagnosis. MDPI 2021-07-11 /pmc/articles/PMC8304210/ /pubmed/34359320 http://dx.doi.org/10.3390/diagnostics11071237 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Qiao, Yifan
Zhang, Yi
Liu, Nian
Chen, Pu
Liu, Yan
An End-to-End Pipeline for Early Diagnosis of Acute Promyelocytic Leukemia Based on a Compact CNN Model
title An End-to-End Pipeline for Early Diagnosis of Acute Promyelocytic Leukemia Based on a Compact CNN Model
title_full An End-to-End Pipeline for Early Diagnosis of Acute Promyelocytic Leukemia Based on a Compact CNN Model
title_fullStr An End-to-End Pipeline for Early Diagnosis of Acute Promyelocytic Leukemia Based on a Compact CNN Model
title_full_unstemmed An End-to-End Pipeline for Early Diagnosis of Acute Promyelocytic Leukemia Based on a Compact CNN Model
title_short An End-to-End Pipeline for Early Diagnosis of Acute Promyelocytic Leukemia Based on a Compact CNN Model
title_sort end-to-end pipeline for early diagnosis of acute promyelocytic leukemia based on a compact cnn model
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8304210/
https://www.ncbi.nlm.nih.gov/pubmed/34359320
http://dx.doi.org/10.3390/diagnostics11071237
work_keys_str_mv AT qiaoyifan anendtoendpipelineforearlydiagnosisofacutepromyelocyticleukemiabasedonacompactcnnmodel
AT zhangyi anendtoendpipelineforearlydiagnosisofacutepromyelocyticleukemiabasedonacompactcnnmodel
AT liunian anendtoendpipelineforearlydiagnosisofacutepromyelocyticleukemiabasedonacompactcnnmodel
AT chenpu anendtoendpipelineforearlydiagnosisofacutepromyelocyticleukemiabasedonacompactcnnmodel
AT liuyan anendtoendpipelineforearlydiagnosisofacutepromyelocyticleukemiabasedonacompactcnnmodel
AT qiaoyifan endtoendpipelineforearlydiagnosisofacutepromyelocyticleukemiabasedonacompactcnnmodel
AT zhangyi endtoendpipelineforearlydiagnosisofacutepromyelocyticleukemiabasedonacompactcnnmodel
AT liunian endtoendpipelineforearlydiagnosisofacutepromyelocyticleukemiabasedonacompactcnnmodel
AT chenpu endtoendpipelineforearlydiagnosisofacutepromyelocyticleukemiabasedonacompactcnnmodel
AT liuyan endtoendpipelineforearlydiagnosisofacutepromyelocyticleukemiabasedonacompactcnnmodel