Extracting Knowledge from Medical Data with Machine-Learning

We develop novel machine learning and artificial intelligence approaches to retrieve knowledge of medical data including images, text and voice.

  • Project Scope

    Development and evaluation of workflows and algorithms to extract multi-modal information from medical data. Medical data can encompass time series from intensive care units, images from optical coherence tomography or ultra-sound or simple text documents.

    Note: Raw and labeled data are available in sufficient quantity

  • Project Plan

    1. Bootstrapping & familiarize with state-of-the-art approaches
    2. Develop promising approaches, e.g.
      1. generative models: GANs, VAE
      2. object classification, segmentation and detection in images
      3. causality models: PGMs
      4. anomaly detection
      5. Sentiment analysis
      6. Network pruning
    3. Establish simple workflow including data collection, pre-processing, analysis, benchmarking and optimizing
    4. Evaluate developed models w.r.t. benchmarking metrics

  • Further Information

    • 30% theory, 70% software engineering
    • Master’s thesis, 1-2 students
    • Prior knowledge recommended in Python, AI and ML required

Haben wir dein Interesse geweckt?

Ich möchte mich auf die Stelle als Extracting Knowledge from Medical Data with Machine-Learning bewerben.