Faculty duo from the Department of Electronics and Communication Engineering, Dr Anirban Ghosh and Dr Sunil Chinnadurai, along with their research cohort, Phanindra Rayapudi Venkata, Baswala Srujana, Gadde Saranya, and Abburi Sowgandhi (B.Tech. ECE students) have published their patent titled “A System and Method for Breast Cancer Diagnosis” (Application number: 202441088356). Their cutting-edge research presents a system to help diagnose breast cancer more accurately and efficiently using advanced image analysis techniques.

Abstract

The present disclosure discloses a system for diagnosing breast cancer that utilizes topological data analysis to transform mammogram images into meaningful diagnostic insights. It includes a data preprocessing module for image standardization and enhancement and a feature extraction module to create histograms for topological analysis. The topological data analysis module converts these histograms into Persistent Homology Diagrams (PHDs) representing topological features. An Earth Mover’s Distance (EMD) matrix is generated by a similarity metric module to compare PHDs. Representative PHDs are identified using a representative selection module, enabling accurate classification by the classification module. The system’s performance is assessed through various metrics by a performance analysis module, and a web service module provides an intuitive interface for users to upload images and receive diagnostic results. This approach enhances breast cancer detection by focusing on persistent topological features, offering improved precision and interpretability.

Figure 1. Conversion of mammograms into PHDs

Explanation of the Research in Layperson’s Terms

Here’s how the system works in simple terms:

1. Preparing the Images: Mammogram images are cleaned and adjusted to ensure they’re clear and easy to analyse. The focus is on areas that might show signs of cancer.

2. Extracting Patterns: The system looks for patterns in the images that could indicate healthy or unhealthy tissue. It turns these patterns into a visual map that represents the shape and structure of the tissue.

3. Analysing Shapes: The system uses math to study how these shapes appear and disappear as the image details change. The most persistent shapes (important ones) are kept, and random noise is ignored.

4. Comparing Images: A tool measures how similar or different these patterns are between images. This helps the system group them into healthy or cancerous categories.

5. Making a Decision: The system compares a new mammogram to its library of known patterns to decide whether it’s likely healthy or shows signs of cancer.

6. Easy to Use: Doctors can upload an image to a web-based tool and quickly get results, complete with visual explanations.

This system helps doctors by making the diagnosis process faster, more reliable, and easier to understand, which can lead to earlier and better treatment for breast cancer.

Figure 2. Flow diagram of normal method

Figure 3. Flow diagram of hybrid method

Practical Implementation/Social Implications of the Research

This research enhances breast cancer detection by enabling earlier, more accurate diagnoses and improving survival rates. Its web-based tool ensures access to advanced diagnostics in remote and underserved areas, reducing disparities in healthcare. Supporting radiologists with objective insights minimizes errors and workload, especially in resource-limited settings. Patients benefit from faster, clearer results, leading to timely and cost-effective treatment. Additionally, the innovative methods could inspire advancements in diagnosing other diseases, driving broader medical progress and improving global health outcomes.

Future Research Plans

Future research could expand this system to detect other diseases like lung or liver cancer, improve diagnostic accuracy by reducing false results, and integrate multimodal data for comprehensive analysis. Incorporating patient-specific information for personalized risk assessments, creating self-learning models, and optimizing computational efficiency could enhance its adaptability. Large-scale global trials and user-friendly interfaces would ensure effective implementation across diverse populations and healthcare systems, making the technology more versatile, accessible, and impactful.