Open Access

ARTICLE

Lightweight Residual Multi-Head Convolution with Channel Attention (ResMHCNN) for End-to-End Classification of Medical Images

Sudhakar Tummala^1,2,*, Sajjad Hussain Chauhdary³, Vikash Singh⁴, Roshan Kumar⁵, Seifedine Kadry⁶, Jungeun Kim^7,*

1 Department of Radiology, Huzhou Wuxing People’s Hospital, Huzhou Wuxing Maternity and Child Health Hospital, Huzhou, 313000, China
2 Department of Electronics and Communication Engineering, School of Engineering and Sciences, SRM University—AP, Amaravati, 522240, India
3 College of Information Engineering, Huzhou Normal University, Huzhou, 313000, China
4 Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Udupi, 576104, India
5 Department of Electronic and Information Technology, Miami College, Henan University, Kaifeng, 475004, China
6 Department of Computer Science and Mathematics, Lebanese American University, Beirut, 13-5053, Lebanon
7 Department of Computer Engineering, Inha University, Incheon, 22212, Republic of Korea

* Corresponding Authors: Sudhakar Tummala. Email: ; Jungeun Kim. Email:

(This article belongs to the Special Issue: Machine Learning and Deep Learning-Based Pattern Recognition)

Computer Modeling in Engineering & Sciences 2025, 144(3), 3585-3605. https://doi.org/10.32604/cmes.2025.069731

Received 29 June 2025; Accepted 18 August 2025; Issue published 30 September 2025

Abstract

Lightweight deep learning models are increasingly required in resource-constrained environments such as mobile devices and the Internet of Medical Things (IoMT). Multi-head convolution with channel attention can facilitate learning activations relevant to different kernel sizes within a multi-head convolutional layer. Therefore, this study investigates the capability of novel lightweight models incorporating residual multi-head convolution with channel attention (ResMHCNN) blocks to classify medical images. We introduced three novel lightweight deep learning models (BT-Net, LCC-Net, and BC-Net) utilizing the ResMHCNN block as their backbone. These models were cross-validated and tested on three publicly available medical image datasets: a brain tumor dataset from Figshare consisting of T1-weighted magnetic resonance imaging slices of meningioma, glioma, and pituitary tumors; the LC25000 dataset, which includes microscopic images of lung and colon cancers; and the BreaKHis dataset, containing benign and malignant breast microscopic images. The lightweight models achieved accuracies of 96.9% for 3-class brain tumor classification using BT-Net, and 99.7% for 5-class lung and colon cancer classification using LCC-Net. For 2-class breast cancer classification, BC-Net achieved an accuracy of 96.7%. The parameter counts for the proposed lightweight models—LCC-Net, BC-Net, and BT-Net—are 0.528, 0.226, and 1.154 million, respectively. The presented lightweight models, featuring ResMHCNN blocks, may be effectively employed for accurate medical image classification. In the future, these models might be tested for viability in resource-constrained systems such as mobile devices and IoMT platforms.

---

Keywords

---