{"id":15553578,"url":"https://github.com/dana-farber-aios/pathml","last_synced_at":"2025-09-16T13:25:53.089Z","repository":{"id":37949538,"uuid":"199872628","full_name":"Dana-Farber-AIOS/pathml","owner":"Dana-Farber-AIOS","description":"Tools for computational pathology","archived":false,"fork":false,"pushed_at":"2024-08-19T19:37:16.000Z","size":228215,"stargazers_count":390,"open_issues_count":52,"forks_count":84,"subscribers_count":13,"default_branch":"master","last_synced_at":"2024-10-22T09:48:54.053Z","etag":null,"topics":["biomedical-image-processing","computational-pathology","deep-learning","digital-pathology","fluorescence-microscopy-imaging","histopathology","image-analysis","machine-learning","microscopy","pathml","pathology","python","pytorch","research","spatial-transcriptomics"],"latest_commit_sha":null,"homepage":"https://pathml.org","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Dana-Farber-AIOS.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.rst","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-07-31T14:30:22.000Z","updated_at":"2024-10-09T03:32:08.000Z","dependencies_parsed_at":"2023-01-29T15:31:06.048Z","dependency_job_id":"9112baa2-6222-47b9-8305-21474ded5e10","html_url":"https://github.com/Dana-Farber-AIOS/pathml","commit_stats":{"total_commits":772,"total_committers":19,"mean_commits":40.63157894736842,"dds":0.5246113989637305,"last_synced_commit":"15a64698baeafc9bdcddfe5558775ff6e2f73be6"},"previous_names":[],"tags_count":19,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dana-Farber-AIOS%2Fpathml","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dana-Farber-AIOS%2Fpathml/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dana-Farber-AIOS%2Fpathml/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dana-Farber-AIOS%2Fpathml/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Dana-Farber-AIOS","download_url":"https://codeload.github.com/Dana-Farber-AIOS/pathml/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":236261753,"owners_count":19120768,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["biomedical-image-processing","computational-pathology","deep-learning","digital-pathology","fluorescence-microscopy-imaging","histopathology","image-analysis","machine-learning","microscopy","pathml","pathology","python","pytorch","research","spatial-transcriptomics"],"created_at":"2024-10-02T14:38:58.218Z","updated_at":"2025-09-16T13:25:53.061Z","avatar_url":"https://github.com/Dana-Farber-AIOS.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"🤖🔬 **PathML: Tools for computational pathology**\n\n[![Downloads](https://static.pepy.tech/badge/pathml)](https://pepy.tech/project/pathml)\n[![Documentation Status](https://readthedocs.org/projects/pathml/badge/?version=latest)](https://pathml.readthedocs.io/en/latest/?badge=latest)\n[![codecov](https://codecov.io/gh/Dana-Farber-AIOS/pathml/branch/master/graph/badge.svg?token=UHSQPTM28Y)](https://codecov.io/gh/Dana-Farber-AIOS/pathml)\n[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)\n[![PyPI version](https://img.shields.io/pypi/v/pathml)](https://pypi.org/project/pathml/)\n![tests](https://github.com/Dana-Farber-AIOS/pathml/actions/workflows/tests-linux.yml/badge.svg?branch=master)\n![dev-tests](https://github.com/Dana-Farber-AIOS/pathml/actions/workflows/tests-linux.yml/badge.svg?branch=dev)\n\n⭐ **PathML objective is to lower the barrier to entry to digital pathology**\n\nImaging datasets in cancer research are growing exponentially in both quantity and information density. These massive datasets may enable derivation of insights for cancer research and clinical care, but only if researchers are equipped with the tools to leverage advanced computational analysis approaches such as machine learning and artificial intelligence. In this work, we highlight three themes to guide development of such computational tools: scalability, standardization, and ease of use. We then apply these principles to develop PathML, a general-purpose research toolkit for computational pathology. We describe the design of the PathML framework and demonstrate applications in diverse use cases. \n\n🚀 **The fastest way to get started?**\n\n    docker pull pathml/pathml \u0026\u0026 docker run -it -p 8888:8888 pathml/pathml\n\nDone, what analyses can I write now? 👉 \u003ca href=\"https://chat.openai.com/g/g-L1IbnIIVt-digital-pathology-assistant-v3-0\" target=\"_blank\"\u003e\u003cimg src=\"https://github.com/Dana-Farber-AIOS/pathml/assets/25375373/7fdc35b4-fede-431b-a8d5-324bea1873e4\" width=\"30%\"/\u003e\u003c/a\u003e\n\n\u003ctable\u003e \n\u003ctr\u003e\n    \u003ctd\u003e \u003cimg src=\"https://github.com/Dana-Farber-AIOS/pathml/assets/25375373/7b1b7293-03cd-4ef1-91d3-8f2efde0899a\"/\u003e \u003c/td\u003e\n    \u003ctd\u003e\n        \nThis AI will:\n        \n- 🤖 write digital pathology analyses for you\n- 🔬 walk you through the code, step-by-step\n- 🎓 be your teacher, as you embark on your digital pathology journey ❤️\n\nMore information [here](./ai-digital-pathology-assistant-v3) and usage examples [here](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/talk_to_pathml.ipynb)\n  \n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n\n📖 **Official PathML Documentation**\n\nView the official [PathML Documentation on readthedocs](https://pathml.readthedocs.io/en/latest/)\n\n🔥 **Examples! Examples! Examples!**\n\n[↴ Jump to the gallery of examples below](#3-examples)\n\n\u003cbr\u003e\n\n\u003cimg src=https://raw.githubusercontent.com/Dana-Farber-AIOS/pathml/master/docs/source/_static/images/logo.png width=\"300\"\u003e \n\n\u003cimg src=https://raw.githubusercontent.com/Dana-Farber-AIOS/pathml/master/docs/source/_static/images/overview.png width=\"750\"\u003e\n\n# 1. Installation\n\n`PathML` is an advanced tool for pathology image analysis. Below are simplified instructions to help you install PathML on your system. Whether you're a user or a developer, follow these steps to get started.\n\n## 1.1 Prerequisites\n\nWe recommend using [Micromamba](https://mamba.readthedocs.io/en/latest/index.html) for managing your environments. We provide instructions on how to install PathML via Micromamba below. In addition, we also provide instructions on how to install via [Miniconda](https://docs.conda.io/en/latest/miniconda.html) should you have a license. \n\n#### Installation \n\nIf you don't have Miniconda installed, you can download Miniconda [here](https://docs.conda.io/en/latest/miniconda.html).\n\n\n#### Upating Micromamba\n\nMake sure you have the recent version of Micromamba by using the following command:\n```\nmicromamba update \n```\n\n####  Updating Conda and Using libmamba (Optional)\n\n**If you are using Micromamba, you can skip to the next [section](#Platform-Specific-External-Dependencies).** \n\n We recommend that Anaconda/Microconda users complete the following steps to update your Conda version and use `libmamba` to resolve dependency conflicts. \n\nRecent versions of Conda have integrated `libmamba`, a faster dependency solver. To benefit from this improvement, first ensure your Conda is updated:\n\n````\nconda update -n base conda\n````\n\nThen, to install and set the new `libmamba` solver, run:\n\n````\nconda install -n base conda-libmamba-solver\nconda config --set solver libmamba\n````\n*Note: these instructions are for Linux. Commands may be different for other platforms.*\n\n#### Platform-Specific External Dependencies\n\nFor installation methods [1)](#2.1-Install-with-Micromamba-and-pip-(Recommended-for-Users)) and [2)](#2.2-Install-from-Source-(Recommended-for-Developers)), you will need to install the following platform-specific packages. \n\n* Linux: Install external dependencies with [Apt](https://ubuntu.com/server/docs/package-management):\n````\nsudo apt-get install openslide-tools g++ gcc libblas-dev liblapack-dev\n````\n\n* MacOS: Install external dependencies with [Brew](www.brew.sh):\n````\nbrew install openslide\n````\n\n* Windows:\n\n 1. Option A: Install with [vcpkg](https://vcpkg.io/en/):\n````\nvcpkg install openslide\n````\n\n 2. Option B: Using Pre-built OpenSlide Binaries (Alternative)\nFor Windows users, an alternative to using `vcpkg` is to download and use pre-built OpenSlide binaries. This method is recommended if you prefer a quicker setup.\n\n  - Download the OpenSlide Windows binaries from the [OpenSlide Downloads](https://openslide.org/download/) page.\n  - Extract the archive to your desired location, e.g., `C:\\OpenSlide\\`.\n\n\n## 1.2 PathML Installation Methods\n\n### 1.2.1 Install with Micromamba and pip (Recommended for Users)\n\n#### Create and Activate Micromamba Environment and install openjdk\n````\nmicromamba create -n pathml  'openjdk\u003c=18.0' -c conda-forge python=3.9\nmicromamba activate pathml\n````\n\n#### Install `PathML` from PyPI\n````\npip install pathml\n````\n\n### 1.2.2 Install with Anaconda and pip \n\n#### Create and Activate Conda Environment\n````\nconda create --name pathml python=3.9\nconda activate pathml\n````\n#### Install OpenJDK \n````\nconda install -c conda-forge 'openjdk\u003c=18.0'\n````\n\n#### Install `PathML` from PyPI\n````\npip install pathml\n````\n\n### 1.2.3 Install from Source (Recommended for Developers)\n\n#### Clone repository\n````\ngit clone https://github.com/Dana-Farber-AIOS/pathml.git\ncd pathml\n````\n\n#### Create conda environment \n\n* Linux and Windows:\n\n````\nconda env create -f environment.yml\nconda activate pathml\n````\nTo use GPU acceleration for model training or other tasks, you must install CUDA. The default CUDA version in our environment file is 11.6. To install a different CUDA version, refer to the instructions [here](#CUDA)). \n\n* MacOS:\n\n````\nconda env create -f requirements/environment_mac.yml\nconda activate pathml\n````\n\n#### Install `PathML` from source: \n````\npip install -e .\n````\n\n### 1.2.4 Use Docker Container\n\nFirst, download or build the PathML Docker container:\n\n![pathml-docker-installation](https://user-images.githubusercontent.com/25375373/191053363-477497a1-9804-48f3-91f9-767dc7f859ed.gif)\n\n- Option A: download PathML container from Docker Hub\n   ````\n   docker pull pathml/pathml:latest\n   ````\n  Optionally specify a tag for a particular version, e.g. `docker pull pathml/pathml:2.0.2`. To view possible tags, \n  please refer to the [PathML DockerHub page](https://hub.docker.com/r/pathml/pathml).\n  \n- Option B: build docker container from source\n   ````\n   git clone https://github.com/Dana-Farber-AIOS/pathml.git\n   cd pathml\n   docker build -t pathml/pathml .\n   ````\n\nThen connect to the container:\n````\ndocker run -it -p 8888:8888 pathml/pathml\n````\n\nThe above command runs the container, which is configured to spin up a jupyter lab session and expose it on port 8888. \nThe terminal should display a URL to the jupyter lab session starting with `http://127.0.0.1:8888/lab?token=\u003c.....\u003e`. \nNavigate to that page and you should connect to the jupyter lab session running on the container with the pathml \nenvironment fully configured. If a password is requested, copy the string of characters following the `token=` in the \nurl.\n\nNote that the docker container requires extra configurations to use with GPU.  \nNote that these instructions assume that there are no other processes using port 8888.\n\nPlease refer to the `Docker run` [documentation](https://docs.docker.com/engine/reference/run/) for further instructions\non accessing the container, e.g. for mounting volumes to access files on a local machine from within the container.\n\n### 1.2.5 Use Google Colab\n\nTo get PathML running in a Colab environment:\n\n````\nimport os\n!pip install openslide-python\n!apt-get install openslide-tools\n!apt-get install openjdk-17-jdk-headless -qq \u003e /dev/null\nos.environ[\"JAVA_HOME\"] = \"/usr/lib/jvm/java-17-openjdk-amd64\"\n!update-alternatives --set java /usr/lib/jvm/java-17-openjdk-amd64/bin/java\n!java -version\n!pip install pathml\n````\n\n*Thanks to all of our open-source collaborators for helping maintain these installation instructions!*  \n*Please open an issue for any bugs or other problems during installation process.*\n\n## 1.3. Import PathML\n\nAfter you have installed all necessary dependencies and PathML itself, import it using the following command:\n\n````\nimport pathml\n````\n\nFor Windows users, insert the following code snippet at the beginning of your Python script or Jupyter notebook before importing PathML. This code sets up the DLL directory for OpenSlide, ensuring that the library is properly loaded:\n\n```python\n\n# The path can also be read from a config file, etc.\nOPENSLIDE_PATH = r'c:\\path\\to\\openslide-win64\\bin'\n\nimport os\nif hasattr(os, 'add_dll_directory'):\n    # Windows-specific setup\n    with os.add_dll_directory(OPENSLIDE_PATH):\n        import openslide\nelse:\n    # For other OSes, this step is not needed\n    import openslide\n\n# Now you can proceed with using PathML\nimport pathml\n```\nThis code snippet ensures that the OpenSlide DLLs are correctly found by Python on Windows systems. Replace c:\\path\\to\\openslide-win64\\bin with the actual path where you extracted the OpenSlide binaries.\n\nIf you encounter any DLL load failures, verify that the OpenSlide `bin` directory is correctly added to your `PATH`.\n\n\n## 1.4 CUDA\n\nTo use GPU acceleration for model training or other tasks, you must install CUDA. \nThis guide should work, but for the most up-to-date instructions, refer to the [official PyTorch installation instructions](https://pytorch.org/get-started/locally/).\n\nCheck the version of CUDA:\n````\nnvidia-smi\n````\n\nReplace both instances of 'cu116' in `requirements/requirements_torch.txt` with the CUDA version you see. For example, for CUDA 11.7, 'cu116' becomes 'cu117'. \n\nThen create the environment:\n\n````\nconda env create -f environment.yml\nconda activate pathml\n````\n\nAfter installing PyTorch, optionally verify successful PyTorch installation with CUDA support: \n````\npython -c \"import torch; print(torch.cuda.is_available())\"\n````\n\n# 2. Using with Jupyter (optional)\n\nJupyter notebooks are a convenient way to work interactively. To use `PathML` in Jupyter notebooks: \n\n## 2.1 Set JAVA_HOME environment variable\n\nPathML relies on Java to enable support for reading a wide range of file formats.\nBefore using `PathML` in Jupyter, you may need to manually set the `JAVA_HOME` environment variable \nspecifying the path to Java. To do so:\n\n1. Get the path to Java by running `echo $JAVA_HOME` in the terminal in your pathml conda environment (outside of Jupyter)\n2. Set that path as the `JAVA_HOME` environment variable in Jupyter:\n    ````\n    import os\n    os.environ[\"JAVA_HOME\"] = \"/opt/conda/envs/pathml\" # change path as needed\n    ````\n\n## 2.2 Register environment as an IPython kernel\n````\nconda activate pathml\nconda install ipykernel\npython -m ipykernel install --user --name=pathml\n````\nThis makes the pathml environment available as a kernel in jupyter lab or notebook.\n\n# 3. Examples\n\nNow that you are all set with ``PathML`` installation, let's get started with some analyses you can easily replicate:\n\n\u003ctable style=\"border: 0px !important;\"\u003e\n    \u003ctr\u003e\n    \u003ctd\u003e \n        \n1. [Load over 160+ different types of pathology images using PathML](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/loading_images_vignette.ipynb)\n2. [H\u0026E Stain Deconvolution and Color Normalization](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/stain_normalization.ipynb)\n3. [Brightfield imaging pipeline: load an image, preprocess it on a local cluster, and get it read for machine learning analyses in PyTorch](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/workflow_HE_vignette.ipynb)\n4. [Multiparametric Imaging: Quickstart \u0026 single-cell quantification](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/multiplex_if.ipynb)\n5. [Multiparametric Imaging: CODEX \u0026 nuclei quantization](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/codex.ipynb)\n6. [Train HoVer-Net model to perform nucleus detection and classification, using data from PanNuke dataset](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/train_hovernet.ipynb)\n7. [Gallery of PathML preprocessing and transformations](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/pathml_gallery.ipynb)\n8. [Use the new Graph API to construct cell and tissue graphs from pathology images](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/construct_graphs.ipynb)\n9. [Train HACTNet model to perform cancer sub-typing using graphs constructed from the BRACS dataset](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/train_hactnet.ipynb)\n10. [Perform reconstruction of tiles obtained from pathology images using Tile Stitching](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/tile_stitching.ipynb)\n11. [Create an ONNX model in HaloAI or similar software, export it, and run it at scale using PathML](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/InferenceOnnx_tutorial.ipynb)\n12. [Step-by-step process used to analyze the Whole Slide Images (WSIs) of Non-Small Cell Lung Cancer (NSCLC) samples as published in the Journal of Clinical Oncology](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/Graph_Analysis_NSCLC.ipynb)\n13. [Talk to the PathML Digital Pathology Assistant](https://github.com/Dana-Farber-AIOS/pathml/blob/master/examples/talk_to_pathml.ipynb)\n\n\u003c/td\u003e                                                                                                                             \n        \u003ctd\u003e\n\u003cimg src=\"https://github.com/Dana-Farber-AIOS/pathml/assets/25375373/502c9e69-e988-4d61-b50f-0d6bfc8af251\" width=\"1000px\" /\u003e\n\n   \u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n# 4. Citing \u0026 known uses\n\nIf you use ``PathML`` please cite:\n\n- [**J. Rosenthal et al., \"Building tools for machine learning and artificial intelligence in cancer research: best practices and a case study with the PathML toolkit for computational pathology.\" Molecular Cancer Research, 2022.**](https://doi.org/10.1158/1541-7786.MCR-21-0665)\n\nSo far, **PathML** was referenced in 40+ manuscripts:\n\n-   [L. Heumos et al. **Nature Medicine**, 2024](https://www.nature.com/articles/s41591-024-03214-0)\n-   [M. Omar et al. **Lancet Digital Health**, 2024](https://www.thelancet.com/journals/landig/article/PIIS2589-7500(24)00114-6/fulltext)\n-   [H. Pakula et al. **Nature Communications**, 2024](https://www.nature.com/articles/s41467-023-44210-1)\n-   [B. Ricciuti et al. **Journal of Clinical Oncology**, 2024](https://ascopubs.org/doi/full/10.1200/JCO.23.00580)\n-   [DT. Hoang et al. **Nature Cancer**, 2024](https://www.nature.com/articles/s43018-024-00793-2)\n-   [A. Song et al. **Nature Reviews Bioengineering**, 2023](https://www.nature.com/articles/s44222-023-00096-8)\n-   [I. Virshup et al. **Nature Bioengineering**, 2023](https://www.nature.com/articles/s41587-023-01733-8)\n-   [A. Karargyris et al. **Nature Machine Intelligence**, 2023](https://www.nature.com/articles/s42256-023-00652-2)\n-   [S. Pati et al. **Nature Communications Engineering**, 2023](https://www.nature.com/articles/s44172-023-00066-3)\n-   [C. Gorman et al. **Nature Communications**, 2023](https://www.nature.com/articles/s41467-023-37224-2)\n-   [J. Nyman et al. **Cell Reports Medicine**, 2023](https://doi.org/10.1016/j.xcrm.2023.101189)\n-   [A. Shmatko et al. **Nature Cancer**, 2022](https://www.nature.com/articles/s43018-022-00436-4)\n-   [J. Pocock et al. **Nature Communications Medicine**, 2022](https://www.nature.com/articles/s43856-022-00186-5)\n-   [S. Orsulic et al. **Frontiers in Oncology**, 2022](https://www.frontiersin.org/articles/10.3389/fonc.2022.924945/full)\n-   [J. Linares et al. **Molecular Cell**, 2021](https://doi.org/10.1016/j.molcel.2021.08.039)\n-   the list continues [**here** **🔗**](https://scholar.google.com/scholar?oi=bibs\u0026hl=en\u0026cites=1157052756975292108)\n\n# 5. Users\n\n\u003ctable style=\"border: 0px !important;\"\u003e\u003ctr\u003e\u003ctd\u003eThis is where in the world our most enthusiastic supporters are located:\n   \u003cbr/\u003e\u003cbr/\u003e\n\u003cimg src=\"https://github.com/user-attachments/assets/18fdaf1c-5ee0-48db-b0d4-99698184c93e\" width=\"722px\"\u003e\n   \u003c/td\u003e\u003ctd\u003e   \nand this is where they work:\n   \u003cbr/\u003e\u003cbr/\u003e\n\u003cimg src=\"https://github.com/user-attachments/assets/0ce73bb5-a722-4dc8-8846-824757e45f0c\" width=\"400px\"\u003e\n\u003c/td\u003e                                                                                                                             \n\u003c/tr\u003e\n\u003c/table\u003e\n\nSource: https://ossinsight.io/analyze/Dana-Farber-AIOS/pathml#people\n\n# 6. Contributing\n\n``PathML`` is an open source project. Consider contributing to benefit the entire community!\n\nThere are many ways to contribute to `PathML`, including:\n\n* Submitting bug reports\n* Submitting feature requests\n* Writing documentation and examples\n* Fixing bugs\n* Writing code for new features\n* Sharing workflows\n* Sharing trained model parameters\n* Sharing ``PathML`` with colleagues, students, etc.\n\nSee [contributing](https://github.com/Dana-Farber-AIOS/pathml/blob/master/CONTRIBUTING.rst) for more details.\n\n\n# 7. License\n\nThe GNU GPL v2 version of PathML is made available via Open Source licensing. \nThe user is free to use, modify, and distribute under the terms of the GNU General Public License version 2.\n\nCommercial license options are available also.\n\n# 8. Contact\n\nQuestions? Comments? Suggestions? Get in touch!\n\n[innovation@dfci.harvard.edu](mailto:innovation@dfci.harvard.edu)\n\n\u003cimg src=https://raw.githubusercontent.com/Dana-Farber-AIOS/pathml/master/docs/source/_static/images/dfci_cornell_joint_logos.png width=\"750\"\u003e \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdana-farber-aios%2Fpathml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdana-farber-aios%2Fpathml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdana-farber-aios%2Fpathml/lists"}