Image Processing for Tumor Detection

I developed this project as part of my Stanford undergraduate coursework in Bioengineering 103: Systems Physiology and Design.

PART 1: For the first half of the project, I analyzed lung CT scans. CT scans are more likely to show lung abnormalities, including infections and tumors, than routine chest X-rays. This is partially due to the fact that we can use CT scans to create detailed 3D reconstructions of the lungs composed from multiple cross-sectional slices, allowing for comprehensive visualization.

I started by taking in a set of lung CT scans and applying K-means clustering from Scikit-learn to segment the images by tissue type:

Then, I utilized OpenCV image processing functions to further isolate the lung tissue in the image segmentation:

Finally, I applied these image masks to all of the CT scans in the collection, and was able to make a 3D reconstruction of the lungs:

PART 2:

You can also put regular text between your rows of images, even citations (Einstein & Taub, 1950). Say you wanted to write a bit about your project before you posted the rest of the images. You describe how you toiled, sweated, bled for your project, and then… you reveal its glory in the next row of images.

The code is simple. Just wrap your images with <div class="col-sm"> and place them inside <div class="row"> (read more about the Bootstrap Grid system). To make images responsive, add img-fluid class to each; for rounded corners and shadows use rounded and z-depth-1 classes. Here’s the code for the last row of images above:

<div class="row justify-content-sm-center">
  <div class="col-sm-8 mt-3 mt-md-0">
    {% include figure.liquid path="assets/img/6.jpg" title="example image" class="img-fluid rounded z-depth-1" %}
  </div>
  <div class="col-sm-4 mt-3 mt-md-0">
    {% include figure.liquid path="assets/img/11.jpg" title="example image" class="img-fluid rounded z-depth-1" %}
  </div>
</div>