Saved in:
Bibliographic Details
Main Author: Chusy0211
Format: Recurso digital
Language:
Published: Zenodo 2026
Online Access:https://doi.org/10.5281/zenodo.19478253
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866902254455357440
author Chusy0211
author_facet Chusy0211
contents <h1>AI_Based_Image_Analysis_for_Organoid_Microscopy_Images</h1> <h2>Overview</h2> <p>This repository provides the dataset and source code developed for our study on automated abnormality detection in organoid microscopy images.</p> <h2>Directory Structure</h2> <pre><code>datasets/ ├── train/ ├───── *.[jpg|png] src/ ├── model_pool.py ├── train.py ├── validate.py </code></pre> <h2>Dataset Description</h2> <p>The dataset consists of grayscale images in JPG and PNG format.</p> <ul> <li>Total samples: 254</li> <li>Normal samples: 203</li> <li>Abnormal samples: 51 (including false positives)</li> <li>Image format: JPG, PNG</li> <li>Resolution: [e.g., 224*224]</li> </ul> <h2>Code Description</h2> <p>This repository includes Python code for training and inference.</p> <h3>Main Files</h3> <ul> <li><code>train.py</code> – training pipeline</li> <li><code>validate.py</code> – validate script</li> <li><code>model_pool.py</code> – model_pool definition</li> </ul> <h2>Installation</h2> <pre><code>conda create -n cv python=3.12 -y conda activate cv pip3 install torch torchvision --index-url https://download.pytorch.org/whl/cu126 pip install opencv-python </code></pre> <h3>Usage</h3> <h4>Training</h4> <pre><code>cd src && python train.py </code></pre> <h4>Inference</h4> <pre><code>cd src && python validate.py </code></pre> <h2>Reproducibility</h2> <p>To ensure reproducibility:</p> <ul> <li>Validation threshold: 0.5</li> <li>Inference threshold: 0.70</li> </ul> <p>Hardware: [optional, e.g., NVIDIA 4090, NVIDIA 4060ti]</p> <h2>License</h2> <p>This project is licensed under the MIT License.</p> <h2>Contact</h2> <p>For questions, please contact: [xiangyf@shanghaitech.edu.cn]</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19478253
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Chusy0211/AI_Based_Image_Analysis_for_Organoid_Microscopy_Images: v0.0.1
Chusy0211
<h1>AI_Based_Image_Analysis_for_Organoid_Microscopy_Images</h1> <h2>Overview</h2> <p>This repository provides the dataset and source code developed for our study on automated abnormality detection in organoid microscopy images.</p> <h2>Directory Structure</h2> <pre><code>datasets/ ├── train/ ├───── *.[jpg|png] src/ ├── model_pool.py ├── train.py ├── validate.py </code></pre> <h2>Dataset Description</h2> <p>The dataset consists of grayscale images in JPG and PNG format.</p> <ul> <li>Total samples: 254</li> <li>Normal samples: 203</li> <li>Abnormal samples: 51 (including false positives)</li> <li>Image format: JPG, PNG</li> <li>Resolution: [e.g., 224*224]</li> </ul> <h2>Code Description</h2> <p>This repository includes Python code for training and inference.</p> <h3>Main Files</h3> <ul> <li><code>train.py</code> – training pipeline</li> <li><code>validate.py</code> – validate script</li> <li><code>model_pool.py</code> – model_pool definition</li> </ul> <h2>Installation</h2> <pre><code>conda create -n cv python=3.12 -y conda activate cv pip3 install torch torchvision --index-url https://download.pytorch.org/whl/cu126 pip install opencv-python </code></pre> <h3>Usage</h3> <h4>Training</h4> <pre><code>cd src && python train.py </code></pre> <h4>Inference</h4> <pre><code>cd src && python validate.py </code></pre> <h2>Reproducibility</h2> <p>To ensure reproducibility:</p> <ul> <li>Validation threshold: 0.5</li> <li>Inference threshold: 0.70</li> </ul> <p>Hardware: [optional, e.g., NVIDIA 4090, NVIDIA 4060ti]</p> <h2>License</h2> <p>This project is licensed under the MIT License.</p> <h2>Contact</h2> <p>For questions, please contact: [xiangyf@shanghaitech.edu.cn]</p>
title Chusy0211/AI_Based_Image_Analysis_for_Organoid_Microscopy_Images: v0.0.1
url https://doi.org/10.5281/zenodo.19478253