Deep Clustering for Blood Cell Classification and Quantification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Macarie-Ancau, Mihaela, Groza, Adrian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911172294344704
author Macarie-Ancau, Mihaela
Groza, Adrian
author_facet Macarie-Ancau, Mihaela
Groza, Adrian
contents Accurate classification of blood cells plays a key role in improving automated blood analysis for both medical and veterinary applications. This work presents a two-stage deep clustering method for classifying blood cells from high-dimensional signal data. In the first stage, red blood cells (RBCs) and platelets (PLTs) are separated using a combination of an improved autoencoder and the IDEC algorithm. The second stage further classifies RBC subtypes, pure RBCs, reticulocytes, and clumped RBCs, through a variational deep embedding (VaDE) approach. Due to the lack of detailed cell-level labels, soft classification probabilities are generated from sample-level data to approximate the true distributions. The aim is to contribute to the development of low-cost, automated blood analysis systems suitable for veterinary and biomedical use. Initial results indicate this method shows promise in effectively distinguishing different blood cell populations, even with limited supervision.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19399
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Clustering for Blood Cell Classification and Quantification
Macarie-Ancau, Mihaela
Groza, Adrian
Quantitative Methods
Accurate classification of blood cells plays a key role in improving automated blood analysis for both medical and veterinary applications. This work presents a two-stage deep clustering method for classifying blood cells from high-dimensional signal data. In the first stage, red blood cells (RBCs) and platelets (PLTs) are separated using a combination of an improved autoencoder and the IDEC algorithm. The second stage further classifies RBC subtypes, pure RBCs, reticulocytes, and clumped RBCs, through a variational deep embedding (VaDE) approach. Due to the lack of detailed cell-level labels, soft classification probabilities are generated from sample-level data to approximate the true distributions. The aim is to contribute to the development of low-cost, automated blood analysis systems suitable for veterinary and biomedical use. Initial results indicate this method shows promise in effectively distinguishing different blood cell populations, even with limited supervision.
title Deep Clustering for Blood Cell Classification and Quantification
topic Quantitative Methods
url https://arxiv.org/abs/2509.19399