Skip to content
View anupbagale's full-sized avatar

Block or report anupbagale

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
anupbagale/README.md

Anup Bagale

Biomedical engineer working on medical imaging, mostly brain MRI, in Python.

A lot of my projects start with a doubt about a good-looking result. Is the X-ray model actually looking at the lungs? Does the heart disease model still work at another hospital? How would you know a classifier got worse at a new site without labelling everything again? I'd rather find out than report the number and move on.

Research

Teaching

Small tools

segmentation-volumes · segmentation-colormap · csv-data-to-image

Python, PyTorch, MONAI, TensorFlow, scikit-learn, NumPy, nibabel

Google Scholar · LinkedIn

Pinned Loading

  1. brain-age-prediction-ixi brain-age-prediction-ixi Public

    Predicting brain age from T1 MRI with a 3D CNN, with bias correction and scanner analysis (IXI dataset)

    Jupyter Notebook 5

  2. covid-xray-shortcut-learning covid-xray-shortcut-learning Public

    Does a COVID-19 chest X-ray classifier look at the lungs? A DenseNet121 scores 0.994 AUC, but still reaches 0.983 with the central lung region hidden, and file metadata alone reaches 0.989. A short…

    Jupyter Notebook 7

  3. breast-ultrasound-performance-monitoring breast-ultrasound-performance-monitoring Public

    Label-free and label-efficient performance monitoring of breast-ultrasound classifiers across five public datasets from five countries.

    Jupyter Notebook 4

  4. Heart_disease_prediction Heart_disease_prediction Public

    Heart disease prediction using UCI dataset

    Jupyter Notebook 4

  5. ssl-brain-parcellation ssl-brain-parcellation Public

    In-domain masked-volume self-supervised pretraining for label-efficient whole-brain MRI parcellation. 3D U-Net on OASIS-3, tested with 10, 25, 50 and 104 labeled scans under 5-fold cross-validation…

    Jupyter Notebook 4

  6. Whole-Brain-Segmentation Whole-Brain-Segmentation Public

    3D U-Net (MONAI) that segments T1 brain MRI into 44 FreeSurfer structures on OASIS-3, compares a full and a reduced label set, and checks volume agreement with FreeSurfer.

    Jupyter Notebook 4