EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MLFRNet: Multi-Scale Local Feature Refinement Network Using Multi-Scale Depthwise Convolution for HER2 Score Classification

Mohan Venkata Sai Valluru iD, Bala Venkateswarlu Isunuri, Sibendu Samanta

Diagnostics · 01.11.2026 · 16 (21) · 3614

DOI: 10.3390/diagnostics16213614 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 01.11.2026. Verfasst von Mohan Venkata Sai Valluru und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, School of Engineering and Sciences, SRM University-AP, Amaravati 522240, Andhra Pradesh, India. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: SRM University, SRM University-AP.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Human Epidermal Growth Factor Receptor 2 (HER2) is a key biomarker for selecting treatment strategies in breast cancer patients. In routine pathology workflows, HER2 assessment is performed by pathologists through examination of immunohistochemistry (IHC)-stained sections under a microscope. Manual IHC assessment requires expert interpretation and can be subject to inter-observer variability, which motivates the study of computer-assisted analysis in digital pathology.

Methods

MLFRNet uses a ConvNeXt-Tiny backbone with a Multi-scale Local Feature Refinement (MLFR) module that integrates Efficient Channel Attention (ECA), a multi-scale depthwise convolution block (MSB), and a residual refinement block (RB). ECA reweights channel representations without dimensionality reduction, after which MSB applies parallel depthwise convolutions with 3 × 3, 5 × 5, and 7 × 7 kernels to capture complementary spatial contexts. The resulting representation is further processed by RB before classification. Comprehensive experiments were conducted on the HER2-IHC-40× dataset across three prespecified stochastic runs.

Results

The mean test accuracy was 96.10 ± 0.22% and the macro-averaged F1-score was 95.30 ± 0.23%.

Conclusions

Because the public release does not provide patient or whole-slide identifiers, patient-level and slide-level independence of the partitions could not be independently verified. The reported results should therefore be interpreted as an exploratory patch-level benchmark rather than as patient-level or clinically validated HER2 scoring performance.

Schlagwörter

Stichwörter der Autor:innen

HER2 score classificationhistopathology image classificationmulti-scale depthwise convolutionmulti-scalelocal feature refinement network

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, School of Engineering and Sciences, SRM University-AP, Amaravati 522240, Andhra Pradesh, India.
  • Department of Electronics and Communication Engineering, School of Engineering and Sciences, SRM University-AP, Amaravati 522240, Andhra Pradesh, India.

ORCID-Profile: Mohan Venkata Sai Valluru

Förderung

  • SRM University
  • SRM University-AP

Zitieren

APA

Valluru, M. V. S., Isunuri, B. V., & Samanta, S. (2026). MLFRNet: Multi-Scale Local Feature Refinement Network Using Multi-Scale Depthwise Convolution for HER2 Score Classification. Diagnostics, 16(21), 3614. https://doi.org/10.3390/diagnostics16213614

Vancouver

Valluru MVS, Isunuri BV, Samanta S. MLFRNet: Multi-Scale Local Feature Refinement Network Using Multi-Scale Depthwise Convolution for HER2 Score Classification. Diagnostics. 2026;16(21):3614. doi:10.3390/diagnostics16213614

BibTeX
@article{Valluru2026,
  author = {Valluru, Mohan Venkata Sai and Isunuri, Bala Venkateswarlu and Samanta, Sibendu},
  title = {MLFRNet: Multi-Scale Local Feature Refinement Network Using Multi-Scale Depthwise Convolution for HER2 Score Classification},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {21},
  pages = {3614},
  doi = {10.3390/diagnostics16213614}
}
Kostenlos starten →