Botkin.AI

What we do:
Cloud Platform for DICOM image analysis Early Disease prediction: Lung / Breast Cancer

What we achieved:
SLUSH Singapore Philips SEMI-finalist 5 pilot regions in Russia

Botkin.AI uses a unique technology to build mathematical models for patient representation. It performs domain-specific data preprocessing that depends on Data types (images, 3D images, video, 3D video, signals (time sequences), tables, text) and Data sources (EHR, X-ray, CT, MRI, ultrasound, mammography, ECG, EEG, blood/urine/stool/CSF tests, histology).
Even without manual labeling, the platform automatically prepares a machine learning dataset from different types of data, e.g. Medical images, Genomic data, Medical test results.
Botkin.AI automatically retrieves facts from the patient’s health records, highlights diagnoses and other relevant facts, places them on a timeline, sorts them by examination and forms diagnosis.
The platform automatically trains models on available selections of preset parametric model families for every type of data. Parametric families determine the general look of models with a certain selection of parameters, which are strictly defined by the model.
The Botkin.AI project is named after Sergey Botkin, one of the founders of modern clinical medicine.

OutfitMind

Manage User wardrobe | Recognize garment types | Combine outfits | Find the most suitable items in online shop | Buy online

With OutfitMind app you can create new stylish outfits using clothes from your personal wardrobe as well as items from online shops.

The app has the following features:

1. Recognition and arrangement of your clothes photos in the right categories.
2. Automatic stylish looks creation. We use trained neural networks to matchmake clothes.
3. Recommendations on what to buy to complement the look
4. You can save the looks you like
5. Wish list

With our application, you no longer have to waste time and nerves figuring out what to wear!
OutfitMind is what suits you! Download OutfitMind for your Android.

CV Projects

Our Clients:
TRA Robotics & LG

What we do:
Synthetic Image Generation | Data Science & Machine Learning | Integration

Technologies that we use: Python | C++ | Blender | Unreal Engine | TensorFlow | Nvidia Cuda & cuDNN | gRPC | Docker | SciPy | OpenCV | PointCloudLibrary | RobotOperationSystem (ROS)

Solving problems of World coordinates position for flexible factories based on The 4th Industrial Revolution principles.
Robot self-localization using video stream from camera

Artificial Art

What we do:
Style Generation | Style Transfer | High Resolution | Custom printed clothing | Paintings and prints on canvas | Posters & Interior painting
Technologies that we use:
Python | TensorFlow | SciPy | OpenCV

We developed Art Synthesising technology based on deep neural networks. All images are generated due to work of an artificial intelligence that has been taught to "paint" by best artists of the world. The key feature of our technology is an ability to generate high resolution images.