Gist 1ec7d82931c03d4134419af0ccfdd985

Gist 895545c65773a661a6035d5ebc9d1313

This notebook demonstrates a TensorFlow/Keras implementation of the Hausdorff distance metric, visualized with synthetic image data. It uses `skimage.draw.circle` to generate a ground-truth circle image, then computes and displays the Hausdorff distance between predicted and actual binary masks via matplotlib. The visualization includes an inline image plot of the mask, rendered as an interactive matplotlib axes image, alongside the execution of the metric computation within the Keras backend.

90% match

Gist 51ee3c0f179008ff4a15

This visualization demonstrates white-stripe normalization of a T1-weighted brain MRI, overlaying a colored white-stripe mask on the normalized anatomical image. The notebook imports nipy’s `plot_map` for rendering, and uses scikit-image’s `threshold_otsu` to mask background voxels. It processes a control subject’s N4-corrected, rigidly aligned image via an R script (WhiteStripe package) called through rpy2, then visualizes the mask at the stripe’s centroid coordinates derived from the affine transform. The rendering uses a HSV colormap for the stripe overlay.

Gist 98636bb57280e38492740cdbe9c4901c

This example demonstrates a deep learning workflow for classifying brain images using TensorFlow and Keras. It loads CSV data from the braindr dataset, displaying a pandas DataFrame with vote counts, rater identities, and mean ratings for each image. The code builds a convolutional neural network with layers like Conv2D, MaxPooling2D, Dropout, and LeakyReLU, using Keras' Sequential API. It configures the model for GPU execution, imports optimizers such as RMSprop and Adam, and prepares callbacks like ModelCheckpoint for training.

Gist 1c87e6026e22589f1729

This visualization tracks the misclassification rate of a stochastic gradient descent classifier over 5,000 iterations, with separate lines for training and test datasets. The code uses Python with NumPy, Pandas, and Seaborn’s `color_palette` for styling, while Matplotlib’s `plot` and `legend` functions render the two curves. The y-axis shows misclassification rate and the x-axis shows iteration counter, revealing how the model’s performance evolves during a single pass through the data with a constant step size.

Gist 237fa77ce0984eaedbfd

A Vue-based visualization of brain MRI segmentation data, this example loads anatomical and labeled brain volumes using nibabel and renders them with nipy's OrthoSlicer. The notebook applies a threshold to isolate specific cortical regions, remaps label values, and displays the result as a colored overlay on the anatomical scan using an HSV colormap, producing a single axial slice visualization of segmented brain structures.

Gist dd6562218ed80aaca786

This example demonstrates a spectral clustering workflow for neuroimaging data, using scikit-learn’s `SpectralClustering` to segment thalamus voxels into distinct clusters based on correlation matrices. It processes fMRI time-series data via Nipype pipelines, nibabel for image I/O, and matplotlib with `%pylab inline` for visualization. The notebook shows how clustering results are saved as NIfTI files, with parameters like subject ID, region of interest, and cluster count varied across runs.

66% match

Gist 5c36e7318dd5c85aa743

This visualization displays a 16-slice mosaic of brain MRI scans across three orthogonal planes (x, y, z), with yellow contour lines outlining anatomical labels from a segmentation. The code loads NIfTI brain images and masks via nibabel, masks background data with NumPy masked arrays, and uses nipy’s `plot_anat` and `contour_map` to render slices with matplotlib subplots. It computes bounding boxes from the affine transformation to select meaningful cut coordinates, then arranges the slices in 4×4 grids per plane. The function supports optional contouring and saving each mosaic as a PNG image.

66% match

Gist d8aa62e81e12e25d45a3

This visualization presents statistical calculations for brain imaging data, comparing reliability metrics across different analysis methods. The notebook uses Python with rpy2 to bridge R and Python, calling the `psych` package for intraclass correlation coefficients and `statsmodels` for additional statistical modeling. It generates plots with matplotlib and seaborn, applying custom chart-cleaning functions to remove unnecessary axes and gridlines. The code also leverages pandas for data manipulation and NumPy for z-score normalization, with output rendered inline through IPython’s `%pylab` magic.