Mammography Image Annotation Using Thermal Lesion Pixel Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mammography and thermography techniques face challenges in accurately correlating high thermal regions on thermal images with high-density regions on mammography images, particularly for breast cancer detection, due to differences in imaging modalities and the need for expert interpretation, which is scarce in developing countries like India.
Innovation Solution
A system and method that uses a thermal imaging device and mammography imaging device, combined with machine learning models, to identify and annotate high temperature regions on mammography images by determining corresponding blocks of pixels, enabling automated lesion identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If mammography imaging is used to detect breast cancer, then structural details of breast tissue can be visualized, but accuracy drops to about 50% for women with dense breasts and requires high expertise for interpretation
Solution Approach 1:
The patent introduces thermal imaging as an intermediary modality that captures metabolic activity (heat patterns) from breast tissue. This thermal information serves as a complementary mediator that highlights suspicious regions, making them more apparent on mammography images and reducing dependence on expert interpretation skills.
Solution Approach 2:
The patent merges thermal imaging data with mammography images by overlaying heat map patterns onto structural breast images. This combination allows radiologists to simultaneously view both anatomical structure and metabolic activity, improving detection accuracy particularly for dense breast tissue where mammography alone is less effective.
2Ease of manufacture
If thermal imaging is used to detect breast cancer, then it provides irradiation-free and low-cost screening, but the reference systems of thermal imaging and mammography imaging are different making correlation difficult
Solution Approach 1:
The patent uses mammography images as a spatial reference framework (mediator) to which thermal imaging data is aligned. By using the anatomical structure from mammography as the reference system, the patent simplifies the correlation process between the two different imaging modalities while maintaining the safety and cost advantages of thermal imaging.
Solution Approach 2:
The patent adds a thermal dimension (temperature/metabolic activity) to the existing spatial dimension of mammography images. This multi-dimensional approach allows correlation of thermal regions with anatomical structures by overlaying thermal data as an additional layer of information on the mammography reference framework.
3Reliability
If early-stage breast cancer detection is pursued, then survival rates improve significantly, but detection accuracy decreases for dense breasts and requires expert interpretation that is scarce in developing countries
Solution Approach 1:
The patent enables the imaging system to partially perform diagnostic functions automatically by using thermal patterns to highlight suspicious regions and annotate mammography images. This self-service capability reduces the burden on expert radiologists, allowing them to focus on complex cases and increasing overall diagnostic throughput in resource-limited settings.
Solution Approach 2:
Thermal imaging serves as an intermediary screening tool that can be deployed in resource-limited settings without requiring expert interpretation. The automated analysis of thermal patterns and their correlation with mammography images enables early detection capability to extend to areas with scarce radiologist resources.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances the accuracy of breast cancer detection by correlating thermal and mammography images, allowing for early-stage cancer detection and improving diagnostic capabilities in resource-limited settings.
Implementation Method 1
Thermography captures the amount of heat radiating from the surface of the body
Implementation Method 2
Mammography captures the cross-section density information of the breast
Data Source
AI summary
A system for annotating mammography images of a subject using thermal images and mammography images of the subject using thermal and mammography images of the subject by (i) identifying a first breast region in the thermal image and a second breast region in the mammography image, (ii) identifying a block of pixels (Pt) with a high temperature region associated with a breast lesion within the first breast region, (iii) estimating a location (l) of the breast lesion corresponding to the identified block of pixels (Pt), (iv) determining a block of pixels (Pm) corresponding to the location (l) of the block of pixels (Pt) within the second breast region and (v) generating a report with an annotated mammography image with markings of a determined block of pixels (Pm) on the mammography image of the subject corresponding to the block of pixels (Pt) on the thermal image.