Early Breast Cancer Predictor Using Image Processing
Our system would read-in the mammograms of patients, process those images and detect the early symptoms of breast cancer. The system would produce a report identifying whether the patient is at the risk of developing breast cancer in future.
2025-06-28 16:32:17 - Adil Khan
Early Breast Cancer Predictor Using Image Processing
Project Area of Specialization Artificial IntelligenceProject SummaryOur system would read-in the mammograms of patients, process those images and detect the early symptoms of breast cancer. The system would produce a report identifying whether the patient is at the risk of developing breast cancer in future.
Project ObjectivesTo detect the types of cancer in breast: benign calcificaion, benign mass, malignant calcification, malignant mass
Project Implementation MethodConvolutional Neural Network -ResNet50 Architecture.
Keras with tensorflow back end
pydicom library to deal wit dicom images
Benefits of the ProjectIn Developed nations, the breast cancer rate is relatively high. Early detection of breast cancer can improve survival rates to a great extent. Inter-observer and intra-observer errors occur frequently in analysis of medical images, given the high variability between interpretations of different radiologists. The early diagnosis of breast cancer can improve the prognosis and chance of survival significantly.
Technical Details of Final DeliverableA program in python with UI interface that would take in memmogram and predict cancer and tell the stage if it is present
Final Deliverable of the Project Software SystemCore Industry ITOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Good Health and Well-Being for PeopleRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 25000 | |||
| Zong Device | Equipment | 1 | 3000 | 3000 |
| 6 month bundle | Equipment | 1 | 12000 | 12000 |
| cloud service | Equipment | 1 | 10000 | 10000 |