Proceedings of the International Conference on Intelligent Information Systems Design and Indian Knowledge System Applications (ICISDIKSA 2026)

<Previous Article In Volume
Next Article In Volume>

Capturing Subtle Morphological Differences in Blood Cells with Involution-Based Networks

Authors
Saikiran Gogineni1, *, Yuvaraju Chinnam1, Kanaka Durga Returi2, Vaka Murali Mohan3, G. Suryanarayana4
1Department of Computer Science and Engineering, Malla Reddy (MR) Deemed to Be University, Hyderabad, India
2Department of Computer Science and Engineering, Malla Reddy Vishwavidyapeeth (Deemed to Be University), Hyderabad, India
3Department of Computer Science and Engineering, Malla Reddy College of Engineering and Technology, Hyderabad, India
4Department of Computer Science and Engineering, Symbiosis Institute of Technology, Hydera-bad Campus, Symbiosis International (Deemed University), Pune, India
*Corresponding author. Email: goginenisaikiran31677@gmail.com
Corresponding Author
Saikiran Gogineni
Available Online 29 December 2025.
DOI
10.2991/978-94-6463-976-6_13How to use a DOI?
Keywords
Involution; CNNS; ResNet; Rednet; VGG; GoogleNet; INN-50; fine-grained image classification; blood cell classification; hematology; medical image analysis; deep learning; morphological feature learning; diagnostic automation; biomedical imaging; pattern recognition
Abstract

Accurate classification of blood cells is required when diagnosing blood-related illnesses. But classifying very fine-grained blood cells is a complex task. Due to subtle differences between classes that are clinically significant, categorizing blood cells is more complex than classifying Stanford Cars or CUB-200 bird species. Traditional convolutional neural networks (CNNs) often struggle to capture nuanced patterns. Involution, an emerging approach, possesses capabilities to capture location-specific and fine-grained features. In this paper, we evaluate the performance of involution-based architectures against CNNs while classifying blood cells. Overall, we found that involution consistently outperformed CNNs in distinguishing very fine morphological patterns between images, making it an effective model for fully automated hematologic diagnostics.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Intelligent Information Systems Design and Indian Knowledge System Applications (ICISDIKSA 2026)
Series
Advances in Intelligent Systems Research
Publication Date
29 December 2025
ISBN
978-94-6463-976-6
ISSN
1951-6851
DOI
10.2991/978-94-6463-976-6_13How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Saikiran Gogineni
AU  - Yuvaraju Chinnam
AU  - Kanaka Durga Returi
AU  - Vaka Murali Mohan
AU  - G. Suryanarayana
PY  - 2025
DA  - 2025/12/29
TI  - Capturing Subtle Morphological Differences in Blood Cells with Involution-Based Networks
BT  - Proceedings of the International Conference on Intelligent Information Systems Design and Indian Knowledge System Applications (ICISDIKSA 2026)
PB  - Atlantis Press
SP  - 184
EP  - 197
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-976-6_13
DO  - 10.2991/978-94-6463-976-6_13
ID  - Gogineni2025
ER  -