MultiCaReClassifier for Medical Image Classification

The MultiCaReClassifier is a model ensemble used for multilabel medical image classification. It includes classes such as:

  • image_type: 'radiology', 'pathology', 'endoscopy', 'ophthalmic_imaging', 'medical_photograph', 'electrography', 'chart'.
  • image_subtype: 'ultrasound', 'x_ray', 'ct', 'mri', 'h&e', 'immunostaining', 'fundus_photograph', 'ekg', 'eeg', etc.
  • radiology_region: 'thorax', 'head', 'abdomen', 'upper_limb', 'lower_limb', etc.
  • radiology_view: 'frontal', 'sagittal', 'axial', 'oblique', etc.
  1. Clone this repo:
!git clone https://huggingface.co/mauro-nievoff/MultiCaReClassifier
  1. Change the directory:
%cd /content/MultiCaReClassifier
  1. Import the MultiCaReClassifier class:
from MultiCaReClassifier.pipeline import *
  1. Get the predictions for a given image folder:
predictions = MultiCaReClassifier(image_folder = '/content/img')
predictions.data.head()
  • Model Training by: Facundo Roffet
  • Data Curation and Postprocessing by: Mauro Nievas Offidani
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Dataset used to train mauro-nievoff/MultiCaReClassifier