Case Studies

Artificial Intelligence & Deep Learning

ThetaTech was tasked to create software for brain navigation for a medical AI lab. We were responsible for taking baseline AI algorithms for detecting brain cancer and enhancing the system to meet production standards that would be used by neurosurgeons.

  • Ability to handle various medical image data types
  • Interface with existing hospital software
  • Employ modern deep learning and analysis frameworks
  • Ensure ease of use by clinician
  • Design algorithm to handle various data types
  • Scale up lab level software to production requirements
  • Add specifics
  • Add specifics
  • Add specifics
  • Add specifics
  • Python
  • Docker images
  • Deep learning and image analysis frameworks
  • Communicate with medical AI lab on requirements
  • Develop / Approach / how was this done?
  • Design system around existing hospital systems and with end user in mind

Biostatistics

ThetaTech has performed ongoing data analytics for a large, (??multi-country??) prostate cancer clinical trial. We worked directly with researchers and clinicians to fine tune the automatic DIAGNOSTIC report that our system generated.

  • Standardize various unique data formats and medical data streams
  • Analyze for correlations between multidimensional data
  • Utilize statistical software and algorithms (??) for predicting cancer recurrence and treatment efficacy
  • How was this data presented to the stakeholders? report? dashboard?
  • AI was a key element in predicting cancer recurrence in
  • TEXT 2
  • TEXT 3
  • PII medical data
  • Several unique data formats
  • Were MRI images used?
  • TBD
  • Intimate data familiarization and usage
  • TEXT 2
  • TEXT 3

Image Analysis

ThetaTech was tasked to create an image analysis system capable of processing 100,000 - 500,000 images per month. The end result was a system that allowed the user to run experiments to tune the parameters live and further enhance its accuracy.

  • Built custom AI that sent results to the client
  • Used AWS to host convolution neural network deep learning system
  • Full stack solution - WebApp frontend connected to C++ deep learning backend
  • Seemless integration with client's existing systems
  • Full user control over system with reported accuracy values (FP's, FN's, PPV, NPV, Total Accuracy)
  • Scalable and required minimal maintenance
  • Utilized custom convolution neural network deep learning system
  • AI was automatically retrained when new, human-labeled data was fed into the pipeline
  • Bridged together the AI system with the frontend interface
  • Images from a proprietary company database
  • Human-labeled training data
  • AWS (EC2, SQS, S3)
  • C++ with Caffe framework
  • Python
  • Spring framework written with Java
  • Intimate data familiarization and usage
  • TEXT 2
  • TEXT 3

Regulatory Navigation

ThetaTech has worked with the FDA, considered the insurance reimbursement landscape, and product development experts on various software and hardware client projects.

  • Regularly interfaced with the FDA for an engineering project
  • Determined best position for AI technology and associated clinical trials for FDA approval
  • Text 1 and we are seeing how this looks when it wraps. looks good nice.
  • TEXT 2
  • TEXT 3
  • Intimate data familiarization and usage
  • TEXT 2
  • TEXT 3