Mammogram Cancer Model Development
Budget: $250 – $750 USD
I am in the middle of my master’s thesis and need a capable partner to handle the coding side of a deep-learning project on mammogram images. The core task is to build a robust model for breast-cancer diagnosis; once the network architecture is in place I can take care of statistical write-ups and broader discussion, but I need you to get the codebase production-ready and well-documented.
Here’s what the collaboration will look like:
• Data: I will supply the curated mammography dataset and any preprocessing scripts I have so far.
• Model building: Using Python with either TensorFlow or PyTorch (whichever you work fastest with), you will design, train and fine-tune a CNN or transformer-based pipeline that targets breast-cancer detection specifically.
• Results and explainability: After training, you will generate performance metrics (AUC, sensitivity, specificity, confusion matrix) and incorporate visual-explainability tools such as Grad-CAM so we can interpret where the network is focusing.
• Knowledge transfer: Clear, step-by-step comments in the code plus a short walkthrough call so I can confidently explain the implementation in my defense.
Deliverables considered complete once:
– All scripts/notebooks run end-to-end on my machine without errors
– Model meets baseline diagnostic accuracy agreed upon during kickoff
– Documentation is concise and covers setup, training, inference and result interpretation
If you are fluent in computer-vision techniques, comfortable with medical-imaging conventions (DICOM, PNG), and eager to push a real-world breast-cancer diagnosis model over the finish line, let’s talk timelines and datasets and get started right away.
Here’s what the collaboration will look like:
• Data: I will supply the curated mammography dataset and any preprocessing scripts I have so far.
• Model building: Using Python with either TensorFlow or PyTorch (whichever you work fastest with), you will design, train and fine-tune a CNN or transformer-based pipeline that targets breast-cancer detection specifically.
• Results and explainability: After training, you will generate performance metrics (AUC, sensitivity, specificity, confusion matrix) and incorporate visual-explainability tools such as Grad-CAM so we can interpret where the network is focusing.
• Knowledge transfer: Clear, step-by-step comments in the code plus a short walkthrough call so I can confidently explain the implementation in my defense.
Deliverables considered complete once:
– All scripts/notebooks run end-to-end on my machine without errors
– Model meets baseline diagnostic accuracy agreed upon during kickoff
– Documentation is concise and covers setup, training, inference and result interpretation
If you are fluent in computer-vision techniques, comfortable with medical-imaging conventions (DICOM, PNG), and eager to push a real-world breast-cancer diagnosis model over the finish line, let’s talk timelines and datasets and get started right away.