Skip to main content
100%

Gist fb72ad147c42cdb900ded0f4b433b0f5

✓ Published0🌍 Public
Aakeshavan
Last edited Jan 18, 2017
Created on Jan 18, 2017

This visualization evaluates lesion segmentation results by plotting false positives (FP) against false negatives (FN) for each exam. It retrieves subject data from a MongoDB collection, filters entries reviewed by a specific clinician, and aggregates counts of FP and FN annotations into a pandas DataFrame. The notebook uses matplotlib through `%pylab inline` for plotting, with a custom `remove_crap` function to clean chart spines and ticks. Data comes from the `subjects` collection in a local MongoDB instance.

AI-generated description

Similar vizzes

Loading thumbnail…

Gist 39800f8b9a6191fff320

This visualization demonstrates the relationship between brain scan variables and subject metadata across a multi-site study. It uses pandas for data loading, seaborn for statistical plotting, and matplotlib for inline rendering within a Jupyter notebook. The code reads a FreeSurfer CSV dataset, applies LeaveOneOut cross-validation from scikit-learn, and fits models with statsmodels formula API. It displays sample rows of the dataframe to show the structure of the neuroimaging data.

Aakeshavan
68% match
Loading thumbnail…

Gist 8e62843a6ffa1dfd7293

This visualization shows how brain tissue volumes (CSF, WM, GM, and total brain) change across multiple time points and scanner types, with each subject’s measurements pivoted into a comparative table. The code uses pandas for data wrangling, including `pivot_table` and column aggregation, and relies on `seaborn` and matplotlib’s `%pylab inline` for plotting. Data comes from SIENAX report files parsed into a DataFrame, then normalized to cubic centimeters. The final table displays time point and scanner metadata alongside the computed tissue volumes.

Aakeshavan
66% match
Loading thumbnail…

Gist acc818edc967714bcbb49613956eb4cb

The dashboard displays MRI volumes alongside scalar summary metrics, linking clinical or behavioral data to brain images for quality control. Users select subjects by histogram brushing to view corresponding volume slices, annotate findings, and edit voxels directly in the browser. The web app uses Python-generated JSON configurations to define database entries and UI elements, with images referenced as pointers. The notebook embeds the live dashboard via an iframe pointing to a local server, demonstrating modular pipeline integration.

Aakeshavan
66% match
Loading thumbnail…

Gist 1ac505c846b09faa7bc4

This visualization demonstrates the variability of FreeSurfer-derived brain structure measurements across different MRI scanner models and sites. It plots the volume values for anatomical regions like the lateral ventricle and cerebellum, revealing distribution patterns and potential batch effects. Built with a Vue framework, the notebook uses pandas for data manipulation, matplotlib and seaborn for statistical plotting, and processes a CSV file containing subject-level neuroimaging metrics. The display emphasizes comparative analysis of brain region volumes across scanning conditions.

Aakeshavan
65% match
Loading thumbnail…

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.

Aakeshavan
65% match
Loading thumbnail…

Gist 5dd4cc899220d90a2606a1f3376b5f6f

This visualization demonstrates signal-to-noise ratio (SNR) calculation from ADNI phantom MRI data using a Jupyter notebook. It loads NIfTI images with nibabel, applies Otsu thresholding and histogram-based binning to segment structures, then labels connected components with scipy.ndimage. The workflow includes FOV validation, quaternion-based RAS coordinate transformation, and voxel volume checks using custom functions like `bin_data` and `clean_labels`, with matplotlib and prettyplotlib used for plotting. The notebook processes phantom scans to identify regions meeting required volume thresholds.

Aakeshavan
65% match
Loading thumbnail…

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.

Aakeshavan
64% match
Loading thumbnail…

Gist 9678802

This interactive visualization simulates MRI brain volume data from two scanner sites, comparing healthy controls and multiple sclerosis patients across age and disease severity. It applies linear calibration transformations between sites and tests statistical models, including OLS for controls and robust linear regression for patients. Built with Vue and WebGL, the notebook uses Python with matplotlib, seaborn, and pandas to generate and analyze the synthetic datasets, displaying distributions and regression fits interactively.

Aakeshavan
64% match