AI Intelligent Deep Learning-Driven Computational Pathology Framework for Automated Breast Cancer Detection from Histopathology Images
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
One of the major reasons for death among women is breast cancer, and early diagnosis is essential for survival. The proposed study is an AI Intelligent Deep Learning, Driven Computational Pathology Framework that can automatically detect breast cancer from histopathological images. This Framework uses advanced convolutional neural networks (CNNs) to analyze the microscopic images in detail and classify them as either benign or malignant automatically. Pre-processing methods like image normalization, augmentation, and noise reduction are utilized in order to enhance the quality of data and make the model more resistant to changes. Feature extraction is done by deep learning layers, which help in the accurate identification of complicated cellular patterns without requiring manual feature engineering. The system introduced here uses transfer learning and fine, tuning strategies for best results when working with very few medical datasets. Besides accuracy, precision, recall, and F1, score, the model assessment is carried out to be sure of reliable clinical applicability of the proposed model. Experimental findings show that this framework not only reaches high levels of diagnostic accuracy but also cuts down the time needed for pathological assessment. This is achieved by equipping pathologists with fast and steady analysis, thus lowering the chances of human error and enabling early, stage breast cancer detection. This smart computational pathology method is a step forward in AI, powered healthcare solutions, and thereby helps in better patient outcomes.
Fields of Study & Subjects
AI in cancer detection
Digital Imaging for Blood Diseases
Radiomics and Machine Learning in Medical Imaging
Publication details
- Journal / source
- Journal of Future Internet and Hyperconnectivity
- Volume
- 3
- Issue
- 1
- Pages
- 1–18
- Publication date
- 1 January 2026
- Language
- EN