# mahmoodlab/CLAM

Open source tools for computational pathology - Nature BME

Repository: https://github.com/mahmoodlab/CLAM
Canonical: https://ross.abutalabs.com/products/clam
Homepage: http://clam.mahmoodlab.org
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: histopathology, pathology, weakly-supervised-learning, whole-slide-imaging, data-efficient, computational-pathology, mahmoodlab, bioimage-informatics, deep-learning, tcga-data, camelyon16, camelyon17, clam, digital-pathology, quantitative-pathology
Last push: 2025-04-14T19:42:01+00:00

## Health v2 (maintenance only)
Score: 39/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 16, release rhythm 35, longevity 100
- inputs: {"age_days": 2345, "days_push": 506, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_readme
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1728, forks 517 (observed 2026-08-28T04:05:28.433854+00:00)

## What it is
CLAM is an open-source Python toolkit for data-efficient, weakly supervised classification of whole-slide images (WSIs) in computational pathology. It converts slide-level labels into interpretable slide-level classifiers without ROI extraction or patch-level annotations, using attention-based multiple-instance learning.

## Use cases
- classify whole-slide pathology images with only slide-level labels
- subtype renal cell carcinoma or lung cancer from WSIs
- detect lymph node metastasis in breast cancer slides
- visualize attention heatmaps over histology slides
- train models on TCGA or Camelyon16/17 datasets
- process gigapixel WSIs into patches and embeddings

## When to choose
- you need interpretable WSI classification without patch-level annotations
- you work with gigapixel histopathology slides and limited labels
- you want a published, widely cited computational pathology pipeline

## When to avoid
- you need general-purpose medical imaging outside histopathology
- you require per-pixel segmentation annotations
- your project needs a permissive license (CLAM is GPL-3.0)

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: deep-learning, healthcare, image-processing
- platform: python, windows
- tags: whole-slide-imaging, histopathology, multiple-instance-learning, weakly-supervised-learning, digital-pathology, tcga, computational-pathology, linux, macos

## Member repositories
- mahmoodlab/CLAM (main) score 39

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:28.433854+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:32:10.258724+00:00, confidence not recorded.
  - homepage: http://clam.mahmoodlab.org (fetched 2026-08-29T11:08:54.203048+00:00, sha ce862543a239)
- Data as of 2026-08-30T08:39:29.467469+00:00.