1. Lernen
    2. /
  2. Kurse
    3. /
  3. Biomedical Image Analysis in Python
  • 1

    Exploration

    Kostenlos

    Prepare to conquer the Nth dimension! To begin the course, you'll learn how to load, build and navigate N-dimensional images using a CT image of the human chest. You'll also leverage the useful ImageIO package and hone your NumPy and matplotlib skills.

  • 2

    Masks and Filters

    Cut image processing to the bone by transforming x-ray images. You'll learn how to exploit intensity patterns to select sub-regions of an array, and you'll use convolutional filters to detect interesting features. You'll also use SciPy's ndimage module, which contains a treasure trove of image processing tools.

  • 3

    Measurement

    In this chapter, you'll get to the heart of image analysis: object measurement. Using a 4D cardiac time series, you'll determine if a patient is likely to have heart disease. Along the way, you'll learn the fundamentals of image segmentation, object labeling, and morphological measurement.

  • 4

    Image Comparison

    For the final chapter, you'll need to use your brain... and hundreds of others! Drawing data from more than 400 open-access MR images, you'll learn the basics of registration, resampling, and image comparison. Then, you'll use the extracted measurements to evaluate the effect of Alzheimer's Disease on brain structure.

Initializing

Ubung

Filter convolutions

Filters are an essential tool in image processing. They allow you to transform images based on intensity values surrounding a pixel, rather than globally.

2D array convolution. By Michael Plotke [CC BY-SA 3.0 (https://creativecommons.org/licenses/by-sa/3.0)], from Wikimedia Commons

For this exercise, smooth the foot radiograph. First, specify the weights to be used. (These are called "footprints" and "kernels" as well.) Then, convolve the filter with im and plot the result.

Anweisungen 1/3

undefined XP
    1
    2
    3

Create a three by three array of filter weights. Set each element to 0.11 to perform mean filtering (also called "uniform filtering").