Classification of Serum Protein and Immunofixation Electrophoresis Images by Computer Vision-Based Deep Learning Models: A Single- and Dual-Modality Study

Maide Hacer Alagöz; Simge Erdem; Poyraz Doğan; İbrahim Utku Derman; Mehmet Güven Günver; Özlem Çakır Madenci; Evin Ademoğlu

doi:10.1177/00045632261454299

May 13, 2026Annals of Clinical Biochemistry International Journal of Laboratory Medicine

Classification of Serum Protein and Immunofixation Electrophoresis Images by Computer Vision-Based Deep Learning Models: A Single- and Dual-Modality Study

View at Publisher

Ask AI

Bookmark

Share

Key Points

The aim is to evaluate deep learning models for categorizing serum electrophoresis images into various diagnostic groups.
Deep learning models were developed for image classification of serum protein electrophoresis (SPE) and immunofixation electrophoresis (IFE).
Images were classified into oncologic, non-oncologic, and healthy categories.
The study emphasized the combination of SPE and IFE for enhanced diagnostic performance.
Deep learning models accurately classified images with improved diagnostics for oncologic and non-oncologic conditions.
Combining SPE and IFE resulted in significantly better performance in diagnosing borderline cases, although specific metrics were not provided.
The necessity for validation in larger, multicenter cohorts was identified prior to clinical application.

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Reveals improved classification of electrophoresis images in healthcare, suggesting enhanced diagnostic accuracy.

Abstract

Deep learning models can reliably classify electrophoresis images into oncologic, non-oncologic, and healthy categories. Combining SPE and IFE improves diagnostic performance and may assist laboratory specialists and hematologists in reducing subjectivity, particularly in borderline cases. Validation in larger, multicenter cohorts is warranted prior to clinical implementation.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Alagöz et al. (2026) studied this question.

synapsesocial.com/papers/6a06b971e7dec685947ac255 https://doi.org/10.1177/00045632261454299

View at Publisher

Ask AI

Bookmark

Share

Classification of Serum Protein and Immunofixation Electrophoresis Images by Computer Vision-Based Deep Learning Models: A Single- and Dual-Modality Study

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Classification of Serum Protein and Immunofixation Electrophoresis Images by Computer Vision-Based Deep Learning Models: A Single- and Dual-Modality Study

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading