Input-Enhanced Dual-Scale Network for Immunofixation Electrophoresis Image Classification

doi:10.13438/j.cnki.jdzk.2026.03.007

Abstract

Abstract: To address the clinical challenges of immunofixation electrophoresis images,such as background fluctuations,noise interference,and faint bands leading to missed detections and misdiagnoses,we propose a DGDB-IE2FNet model.The model features a dynamically gated dual-branch residual block and an IFE input enhancement dual-scale branch.The former adaptively fuses complementary convolutional branches,while the latter suppresses background noise and enhances directional information of bands.We formulate the classification of positive/negative results for ELP,G,A,M,K,and L lanes as a multi-label prediction task and conduct comparative experiments with several mainstream models using 20 000 real-world cases.Results show that the DGDB-IE2FNet achieves an accuracy of 99.63%,negative predictive value of 99.74%,sensitivity of 98.07%,and F1 score of 98.56% on the test set,outperforming other compared models in overall prediction performance.

Key words: immunofixation electrophoresis, deep learning, convolutional neural networks, dual-scale

FU Xiaotian, XIE Jianyu, TAN Zihan, LI Shu. Input-Enhanced Dual-Scale Network for Immunofixation Electrophoresis Image Classification[J]. Journal of Jishou University(Natural Sciences Edition), 2026, 47(3): 41-49.

References

[1] ZHUGE Linmin,LIN Xiaowu,FAN Ziwei,et al.Global,Regional and National Epidemiological Trends of Multiple Myeloma from 1990 to 2021:A Systematic Analysis of the Global Burden of Disease Study 2021[J].Frontiers in Public Health,2025,13:1527198.
[2] ZHU Shanshan,LI Wei,LIN Meilin,et al.Serum Protein Electrophoresis and Immunofixation Electrophoresis Detection in Multiple Myeloma[J].Journal of the College of Physicians and Surgeons Pakistan,2021,30(7):864-867.
[3] FADILI HAJAR,OUAZZANI HAMZA,RHALEB IKRAME,et al.Relevance of Prescribing Serum Immunofixation Electrophoresis in the Diagnosis of Monoclonal Gammopathies[J].Cureus,2025,17(6):e86339.
[4] SHASTRI MALVIKA,MALHOTRA PANKAJ,KAUR HARVINDER,et al.Understanding the Constraints and Optimization of Serum Immunofixation Electrophoresis and Serum Free Light Chains for Detecting Monoclonal Proteins:A Single-Center Experience[J].Journal of Laboratory Physicians,2023,15(4):518-523.
[5] 中国医师协会血液科医师分会,中华医学会血液学分会.中国多发性骨髓瘤诊治指南（2024年修订）[J].中华内科杂志,2024,63(12):1186-1195.
[6] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Deep Residual Learning for Image Recognition[C]//IEEE/CVF.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016:770-778.
[7] CHEN Yinpeng,DAI Xiyang,LIU Mengchen,et al.Dynamic Convolution:Attention over Convolution Kernels[C]//IEEE/CVF.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle:IEEE,2020:11030-11039.
[8] LI Jiaqi,WEN Yingming,HE Lin.SCConv:Spatial and Channel Reconstruction Convolution for Feature Redundancy[C]//IEEE/CVF.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver:IEEE,2023:6153-6162.
[9] HU Jie,SHEN Li,SUN Gang.Squeeze-and-Excitation Networks[C]//IEEE/CVF.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:7132-7141.
[10] RAINIO OSKARI,TEUHO JUHANI,KLN RIKU.Evaluation Metrics and Statistical Tests for Machine Learning[J].Scientific Reports,2024,14(1):6086.
[11] CUBUK EKIN DOGUS,ZOPH BARRET,MANE DANDAN,et al.AutoAugment:Learning Augmentation Strategies from Data[C]//IEEE/CVF.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE,2019:113-123.
[12] TAN Mingxing,LE QUOC V.EfficientNetV2:Smaller Models and Faster Training[C]//International Machine Learning Society.International Conference on Machine Learning.New York:PMLR,2021:10096-10106.
[13] LIU Zhuang,MAO Hanzi,WU Chaoyuan,et al.A ConvNet for the 2020s[C]//IEEE/CVF.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans:IEEE,2022:11976-11986.
[14] WOO SANGHYUN,DEBNATH SHOUBHIK,HU Ronghang,et al.ConvNeXt V2:Co-Designing and Scaling ConvNets with Masked Autoencoders[C]//IEEE/CVF.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver:IEEE,2023:16133-16142.
[15] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Deep Residual Learning for Image Recognition[C]//IEEE/CVF.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016:770-778.