High School Student Using Artificial Intelligence to Fight Breast Cancer

What started as a tenth-grade class project, the high school senior believes his technology can take on potentially deadly breast tumors and non-cancerous…

NVIDIA logo
NVIDIA
•
Brad Nemire
•2 min read•intermediate•
--
•View Original
Artificial IntelligenceTensorFlow

Overview

A high school senior, Abu Qader, has developed a technology using artificial intelligence to assist in the diagnosis and classification of breast cancer. Partnering with entrepreneur Vedad Mesanovic, they created GliaLab, which leverages AI to analyze mammogram data, achieving high accuracy rates and improving diagnostic efficiency.

What You'll Learn

1

How to use AI to analyze medical imaging data for cancer diagnosis

2

Why leveraging real-time data processing improves diagnostic accuracy

3

When to utilize AI/ML tools in healthcare applications

Prerequisites & Requirements

  • Basic understanding of artificial intelligence and machine learning concepts(optional)
  • Familiarity with NVIDIA GPUs and TensorFlow framework(optional)

Key Questions Answered

How does GliaLab assist in breast cancer diagnosis?
GliaLab uses artificial intelligence to analyze mammogram images and fine-needle aspirations, providing a second-opinion diagnostic tool that enhances accuracy by building predictive models on tumor types and treatment outcomes. This technology aims to reduce human error and the costs associated with false-positive readings.
What technology does Abu Qader use for AI model training?
Abu Qader utilizes the NVIDIA GeForce GT 750M GPU and the cuDNN-accelerated TensorFlow deep learning framework to train their AI models. This setup allows them to achieve an impressive accuracy rate between 93% and 99%, while also providing real-time results.
What are the benefits of using NVIDIA GPUs in AI model training?
Using NVIDIA GPUs significantly enhances the speed and efficiency of training AI models. Abu Qader noted that without CUDA and NVIDIA GPUs, they would lose valuable time in training and testing their models, making these tools essential for their project.

Key Statistics & Figures

Model accuracy
93% to 99%
This accuracy rate is achieved through the use of AI in analyzing mammogram images.

Technologies & Tools

Some links below are affiliate links. We may earn a commission if you make a purchase.

Hardware
Nvidia Geforce Gt 750m GPU
Used for training AI models efficiently.
Software
Cudnn
Accelerates TensorFlow deep learning framework for faster model training.
Software
Tensorflow
Deep learning framework used to build and train AI models.

Key Actionable Insights

1
Implementing AI in medical diagnostics can drastically improve accuracy and efficiency.
By leveraging AI to analyze existing medical imaging data, healthcare professionals can reduce human error and enhance patient outcomes, making it a valuable tool in modern medicine.
2
Utilizing high-performance GPUs is crucial for real-time data processing in AI applications.
The speed provided by NVIDIA GPUs allows for quicker model training and testing, which is essential in time-sensitive fields like healthcare.
3
Building predictive models from existing data can provide significant insights into treatment outcomes.
By analyzing historical data on tumor types and treatment responses, AI can help predict future outcomes, aiding in better decision-making for patient care.

Common Pitfalls

1
Relying solely on traditional diagnostic methods without integrating AI can lead to missed opportunities for improved accuracy.
Many healthcare professionals may hesitate to adopt new technologies due to familiarity with existing methods. However, integrating AI can significantly enhance diagnostic capabilities.