https://github.com/clemkoa/tooth-detection

🦷 Detection of restorations and treatments on dental x-rays in Tensorflow, using Faster-RCNN
https://github.com/clemkoa/tooth-detection

deep-learning dental health neural-networks object-detection tensorflow x-ray

Last synced: 3 months ago
JSON representation

🦷 Detection of restorations and treatments on dental x-rays in Tensorflow, using Faster-RCNN

• Host: GitHub
• URL: https://github.com/clemkoa/tooth-detection
• Owner: clemkoa
• License: mit
• Created: 2018-05-22T14:13:05.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2021-10-21T23:17:58.000Z (about 3 years ago)
• Last Synced: 2024-05-15T04:37:03.583Z (6 months ago)
• Topics: deep-learning, dental, health, neural-networks, object-detection, tensorflow, x-ray
• Language: Python
• Homepage:
• Size: 55.3 MB
• Stars: 204
• Watchers: 25
• Forks: 80
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Teeth detector

![Image 1](public/images/1.png "Image 1")

![Image 2](public/images/2.png "Image 2")

![Image 3](public/images/3.png "Image 3")

⚠️ Dataset is private at the moment. For privacy reasons it can't be shared. We are trying to get approval from hospitals and patients included in this dataset but this a work in progress. For the same privacy reasons the trained model can't be shared at the moment.

The dataset was made with a stomatologist surgeon using VoTT for labeling. The export was made under the `Tensorflow Pascal VOC` format

The project is divided into two tasks:

1. Detect tooth restoration, endodontic treatment and implants (models/treatment)

2. Detect teeth and identify their ISO Dental Notation (models/index)

## Installation

- Download the datasets from the google drive (datasets are private at the moment)

- Install tensorflow object detection: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md

- Install Cloud SDK to run on google cloud https://cloud.google.com/sdk/

```

pip install -r requirements.txt

# Tensorflow Object Detection API

git clone [email protected]:tensorflow/models.git

git clone https://github.com/cocodataset/cocoapi.git

cd cocoapi/PythonAPI

make

cp -r pycocotools /models/research/

# From tensorflow/models/research/

export PYTHONPATH=$PYTHONPATH:`pwd`:`pwd`/slim

```

## Training

```

python /models/research/object_detection/model_main.py \

    --pipeline_config_path=/tooth-detection/models/treatment/faster_rcnn_resnet50_coco.config \

    --model_dir=/tooth-detection/models/treatment/model \

    --num_train_steps=100000 \

    --alsologtostderr

```

## Inference

```

python inference.py \

    --PATH_TO_FROZEN_GRAPH=//frozen_inference_graph.pb \

    --PATH_TO_TEST_IMAGES_DIR=/data/iran_index/JPEGImages \

    --PATH_TO_LABELS=/data/pascal_label_map_index.pbtxt

```