HistoPath AI: An Edge-Powered Web Platform for Real-Time Lung Cancer Diagnosis

Abstract

Lung cancer remains a major cause of mortality worldwide, underscoring the importance of accurate and timely diagnosis. Manual evaluation of histopathology slides is labor-intensive and error-prone, particularly in resource-constrained settings. This work introduces HistoPath AI, an edge-based web application for real-time lung cancer detection. The system employs a fine-tuned EfficientNetB7 model to classify histopathology images into benign, adenocarcinoma, and squamous cell carcinoma, achieving 99.8% validation accuracy with strong precision and recall. A novel Computational Severity Index approach stratifies disease progression into four levels, supporting clinical decision-making. To ensure practical deployment, the model is optimized into FP32, FP16, and INT8 formats using TensorFlow Lite and integrated on a Raspberry Pi 4. The framework includes benchmarking of latency, resource utilization, and thermal stability, alongside a Flask-based role-driven interface for secure access, patient registration, and automated reporting. HistoPath AI demonstrates a scalable, privacy-preserving, and deployable solution for point-of-care cancer diagnostics. The proposed framework emphasizes offline inference and local data processing, enabling privacy-preserving operation without reliance on cloud infrastructure. The results highlight the feasibility of deploying deep learning-based histopathology analysis on low-cost embedded hardware for real-time use. This study establishes a strong engineering foundation for future extensions involving clinically informed validation and real-world deployment in resource-limited healthcare settings.



Received: 8 November 2025 | Revised: 5 February 2026 | Accepted: 25 May 2026



Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.



Data Availability Statement

The data that support the findings of this study are openly available at https://doi.org/10.48550/arXiv.1912.12142, reference number [25].



Author Contribution Statement

Rajkumar Maharaju: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration. Sai Prasad Ellaboina: Conceptualization, Methodology, Software, Validation, Resources. Rama Valupadasu: Conceptualization, Writing – review & editing, Supervision.