Co-occurrence feature learning for visual recognition of immature leukocytes

Abstract Accurate and timely diagnosis of leukemia, a cancer characterized by an excessive number of abnormal white blood cells (WBCs), is crucial for effective treatment. Manual examination of blood smear images for leukemia diagnosis is often laborious and costly. Computer-aided classification of...

Full description

Saved in:
Bibliographic Details
Main Authors: Yi-Ting Hsiao, Si-Wa Chan, Yen-Chieh Ouyang, Ju-Huei Chien
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-01791-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434169964232704
author Yi-Ting Hsiao
Si-Wa Chan
Yen-Chieh Ouyang
Ju-Huei Chien
author_facet Yi-Ting Hsiao
Si-Wa Chan
Yen-Chieh Ouyang
Ju-Huei Chien
author_sort Yi-Ting Hsiao
collection DOAJ
description Abstract Accurate and timely diagnosis of leukemia, a cancer characterized by an excessive number of abnormal white blood cells (WBCs), is crucial for effective treatment. Manual examination of blood smear images for leukemia diagnosis is often laborious and costly. Computer-aided classification of WBCs has the potential to assist hematologists in improving diagnostic accuracy. However, the subtle visual differences among the five types of immature neutrophils pose a significant challenge, even for experienced professionals. The study proposes a method called densely connected co-occurrence network (DCONN). The method first detects white blood cells in blood smear images using Yolact. Then, the images are pre-processed to minimize the correlation between image channels by transforming RGB color space to LAB color space. Finally, DCONN extracts spatial texture information using a co-occurrence matrix to improve classification accuracy. DCONN achieved 93.46% accuracy in classifying five types of immature neutrophils: myeloblast, promyelocyte, myelocyte, metamyelocyte, and band cells. The results indicate that using a combination of densely connected convolutional layers and a co-occurrence layer improves classification accuracy while using fewer trainable parameters than other deep learning methods such as ResNet and Inception. Additionally, the model is less demanding in terms of training hardware than attentional mechanism-based models that also have local feature representation. DCONN achieves advanced performance based on small-scale models without requiring much training time. The proposed method can be extended to other pathological image analyses in the future.
format Article
id doaj-art-fac310a1d2ec44e59ee494857faaf7b9
institution Kabale University
issn 2045-2322
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-fac310a1d2ec44e59ee494857faaf7b92025-08-20T03:26:44ZengNature PortfolioScientific Reports2045-23222025-06-0115111610.1038/s41598-025-01791-9Co-occurrence feature learning for visual recognition of immature leukocytesYi-Ting Hsiao0Si-Wa Chan1Yen-Chieh Ouyang2Ju-Huei Chien3Department of Computer Science and Engineering, National Chung Hsing UniversityRadiology Department Division Taichung Veterans General HospitalDepartment of Computer Science and Engineering, National Chung Hsing UniversityDepartment of Research, Taichung Tzu-Chi Hospital, Buddhist Tzu-Chi Medical FoundationAbstract Accurate and timely diagnosis of leukemia, a cancer characterized by an excessive number of abnormal white blood cells (WBCs), is crucial for effective treatment. Manual examination of blood smear images for leukemia diagnosis is often laborious and costly. Computer-aided classification of WBCs has the potential to assist hematologists in improving diagnostic accuracy. However, the subtle visual differences among the five types of immature neutrophils pose a significant challenge, even for experienced professionals. The study proposes a method called densely connected co-occurrence network (DCONN). The method first detects white blood cells in blood smear images using Yolact. Then, the images are pre-processed to minimize the correlation between image channels by transforming RGB color space to LAB color space. Finally, DCONN extracts spatial texture information using a co-occurrence matrix to improve classification accuracy. DCONN achieved 93.46% accuracy in classifying five types of immature neutrophils: myeloblast, promyelocyte, myelocyte, metamyelocyte, and band cells. The results indicate that using a combination of densely connected convolutional layers and a co-occurrence layer improves classification accuracy while using fewer trainable parameters than other deep learning methods such as ResNet and Inception. Additionally, the model is less demanding in terms of training hardware than attentional mechanism-based models that also have local feature representation. DCONN achieves advanced performance based on small-scale models without requiring much training time. The proposed method can be extended to other pathological image analyses in the future.https://doi.org/10.1038/s41598-025-01791-9LeukocytesCo-occurrence matrixDenseNetYolactLeukemia
spellingShingle Yi-Ting Hsiao
Si-Wa Chan
Yen-Chieh Ouyang
Ju-Huei Chien
Co-occurrence feature learning for visual recognition of immature leukocytes
Scientific Reports
Leukocytes
Co-occurrence matrix
DenseNet
Yolact
Leukemia
title Co-occurrence feature learning for visual recognition of immature leukocytes
title_full Co-occurrence feature learning for visual recognition of immature leukocytes
title_fullStr Co-occurrence feature learning for visual recognition of immature leukocytes
title_full_unstemmed Co-occurrence feature learning for visual recognition of immature leukocytes
title_short Co-occurrence feature learning for visual recognition of immature leukocytes
title_sort co occurrence feature learning for visual recognition of immature leukocytes
topic Leukocytes
Co-occurrence matrix
DenseNet
Yolact
Leukemia
url https://doi.org/10.1038/s41598-025-01791-9
work_keys_str_mv AT yitinghsiao cooccurrencefeaturelearningforvisualrecognitionofimmatureleukocytes
AT siwachan cooccurrencefeaturelearningforvisualrecognitionofimmatureleukocytes
AT yenchiehouyang cooccurrencefeaturelearningforvisualrecognitionofimmatureleukocytes
AT juhueichien cooccurrencefeaturelearningforvisualrecognitionofimmatureleukocytes