Breast cancer screening

The need arise from the need to streamline the analysis of exams performed on patients who may present detectable pathologies through imaging studies, assisting the physician in making a faster and more accurate diagnosis.

Prototype

We trained the AI model with a total of 11,000 images (radiographs) published by the University of South Florida, previously classified by physicians as positive and negative.

Results

The model was able to detect and classify cancer with 85% efficiency based on actual confirmed cases. It grouped patient radiographs into two different classes (positive and negative, corresponding to the classes provided in its AI training).

we enhanced the model with an additional neural network to obtain the location of pathological tissue within the image

>