PMID- 34359320
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20210810
IS  - 2075-4418 (Print)
IS  - 2075-4418 (Electronic)
IS  - 2075-4418 (Linking)
VI  - 11
IP  - 7
DP  - 2021 Jul 11
TI  - An End-to-End Pipeline for Early Diagnosis of Acute Promyelocytic Leukemia Based 
      on a Compact CNN Model.
LID - 10.3390/diagnostics11071237 [doi]
LID - 1237
AB  - 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.
FAU - Qiao, Yifan
AU  - Qiao Y
AUID- ORCID: 0000-0002-5909-1790
AD  - The College of Computer Science, Sichuan University, Chengdu 610065, China.
FAU - Zhang, Yi
AU  - Zhang Y
AUID- ORCID: 0000-0001-7201-2092
AD  - The College of Computer Science, Sichuan University, Chengdu 610065, China.
FAU - Liu, Nian
AU  - Liu N
AD  - The College of Electrical Engineering, Sichuan University, Chengdu 610065, China.
FAU - Chen, Pu
AU  - Chen P
AD  - The Department of Laboratory Medicine, Zhongshan Hospital, Fudan University, 
      Shanghai 200032, China.
FAU - Liu, Yan
AU  - Liu Y
AUID- ORCID: 0000-0003-4881-8429
AD  - The College of Electrical Engineering, Sichuan University, Chengdu 610065, China.
LA  - eng
GR  - 61902264/National Science Foundation of China/
GR  - 2019YFS0125/Key Research and Development projects in Sichuan Province/
PT  - Journal Article
DEP - 20210711
PL  - Switzerland
TA  - Diagnostics (Basel)
JT  - Diagnostics (Basel, Switzerland)
JID - 101658402
PMC - PMC8304210
OTO - NOTNLM
OT  - acute promyelocytic leukemia
OT  - convolutional neural networks
OT  - early diagnosis
OT  - pipeline
OT  - real cases validation
COIS- The authors declare no conflict of interest.
EDAT- 2021/08/08 06:00
MHDA- 2021/08/08 06:01
PMCR- 2021/07/11
CRDT- 2021/08/07 01:02
PHST- 2021/05/31 00:00 [received]
PHST- 2021/07/06 00:00 [revised]
PHST- 2021/07/06 00:00 [accepted]
PHST- 2021/08/07 01:02 [entrez]
PHST- 2021/08/08 06:00 [pubmed]
PHST- 2021/08/08 06:01 [medline]
PHST- 2021/07/11 00:00 [pmc-release]
AID - diagnostics11071237 [pii]
AID - diagnostics-11-01237 [pii]
AID - 10.3390/diagnostics11071237 [doi]
PST - epublish
SO  - Diagnostics (Basel). 2021 Jul 11;11(7):1237. doi: 10.3390/diagnostics11071237.