Home

About ValidPath

The Whole Slide Image Processing and Machine Learning Performance Assessment Tool is a software program written in Python for analyzing whole slide images (WSIs), assisting pathologists in the assessment of machine learning (ML) results, and assessment of ML performance. The tool currently contains three modules that accept WSIs to generate image patches for AI/ML models, accept image patches (e.g., ML detected ROIs) to generate an Aperio ImageScope annotation file for validation of ML model results by pathologists, and accept outputs of ML models to generate performance results and their confidence intervals.

The Whole Slide Image Processing and Performance Assessment Tool code has been used in the following publications:

• Kahaki, Seyed, et al. “Weakly supervised deep learning for predicting the response to hormonal treatment of women with atypical endometrial hyperplasia: a feasibility study.” Medical Imaging 2023: Digital and Computational Pathology. Vol. 12471. SPIE, 2023.

• Kahaki, Seyed, et al. “Supervised deep learning model for ROI detection of atypical endometrial hyperplasia and endometrial cancer on histopathology whole slide images for predicting hormonal treatment response.” Medical Imaging 2024: Digital and Computational Pathology.

• Kahaki, Seyed, et al. “End-to-End Deep Learning Method for Predicting Hormonal Treatment Response in Women with Atypical Endometrial Hyperplasia or Endometrial Cancer.” Journal of Medical Imaging, Journal of Medical Imaging, Under Review

• Mariia Sidulova, et al. “Contextual unsupervised deep clustering of digital pathology dataset”, Submitted to ISBI 2024

Modules

There are several modules in this package including:

1. WSI handler: includes functions and classes for general WSI analysis such as read whole slide images, tissue segmentation, and normalization.

2. Annotation Extraction: this module includes several functions for processing annotations such as annotation extraction.

3. Patch Extraction: which assist pathologist and developers in extracting image patches from whole slide images region of interest.

4. Aperio ImageScope Annotation File Generator: to enable pathologist validation of the AI/ML results.

5. Performance Assessment: to assess the performance of ML models in classification tasks.

To see a demo of the functions in this toolbox, please refer to the Jupyter Notebooks files in the root folder of this package.

• 01_read_wsi.ipynb

• 02_annotation_extraction.ipynb

• 03_patch_extraction.ipynb

• 4_annotation_generator.ipynb

• 05_performance_assessment.ipynb

• Installation
  • Required Packages
  • Installation Using Anaconda
  • Installing ValidPath using Anaconda
  • Direct Installation of ValidPath
  • From Source
• Data (Input/Output) Examples
  • WSI Handler
  • Annotation Extraction
  • Patch Extraction
  • Annotation File Generator
  • Performance Assessment
• Annotation Extraction
  • WSI.annotation module
    • AnnotationExtractor
      • AnnotationExtractor.extract_ann()
      • AnnotationExtractor.make_folder()
• Patch Extraction
  • WSI.patch module
    • PatchExtractor
      • PatchExtractor.find_between()
      • PatchExtractor.gen_patch()
    • WSIpatch_extractor
      • WSIpatch_extractor.patch_extraction()
      • WSIpatch_extractor.patch_extraction_of_tissue()
      • WSIpatch_extractor.patch_extraction_with_normalized_tiles()
• Annotation File Generator
  • assessment.annotation module
    • Annotation_Generator
      • Annotation_Generator.create_xml()
      • Annotation_Generator.generate_map_file()
      • Annotation_Generator.make_region()
• ML Assessment
  • assessment.uncertainty module
    • Uncertainty_Analysis
      • Uncertainty_Analysis.Delong_CI()
      • Uncertainty_Analysis.auc_keras_()
      • Uncertainty_Analysis.bootstrapping()
      • Uncertainty_Analysis.calc_pvalue()
      • Uncertainty_Analysis.ci_()
      • Uncertainty_Analysis.compute_ground_truth_statistics()
      • Uncertainty_Analysis.compute_midrank()
      • Uncertainty_Analysis.compute_midrank_weight()
      • Uncertainty_Analysis.delong_roc_variance()
      • Uncertainty_Analysis.fastDeLong()
      • Uncertainty_Analysis.fastDeLong_no_weights()
      • Uncertainty_Analysis.fastDeLong_weights()
      • Uncertainty_Analysis.get_report()

Indices and tables

• Index

• Module Index

• Search Page