Streamlined Imaging Workflows for Advanced Analysis

A laptop screen shows Layar’s Retina app analyzing images of breast cancer pathology samples.

Retina is a scalable image analytics application that enhances the abilities of our core Layar data fabric. Deep learning models within Retina accelerate image workflows related to file management, model training and image classification. 

Retina allows users to classify, annotate, integrate, manage and search for image assets. 

Key Features

Retina makes it easy for organizations to manage and pull insights from imagery. Using built-in, pre-trained models, Retina enables users to streamline imaging workflows and conduct a number of deep learning tasks including model training and management, dataset curation, image annotations, preprocessing pipelines, model training and inferencing.

Additional features and benefits include the ability to:

1. Simplified Image Management

Users can access images without the burden of time-consuming file migrations.


2. Normalize and Augment Images

Reduce artifacts and accentuate natural features in images to improve precision with image analysis.


3. Protect Sensitive Image Data

Facilitate de-identification tasks, such as blurring, censoring or redaction of sensitive information embedded in images.


4. Optimize Deep Learning

Tiling and Multi-Instance Learning (MIL) techniques minimize your network and memory footprint to facilitate training on large images.


5. Streamline Model Training

Retina’s model management dashboard allows users to easily monitor, train and deploy learning models both internally within Retina and externally across other analytics platforms.

Applications for Retina
Image Analysis

Healthcare & Life Sciences

By supplementing the work of human research and medical teams, Retina can help triage cases, speed mammography results and more effectively classify and manage image libraries.

Classification accuracy now stands at 90 percent for tissue diagnostics, while reducing manual input time for radiologists, pathologists and oncologists.

Uses for Retina include:

  • Reading additional types of scans, whether for screening or diagnosis
  • Predicting disease progression
  • Reading medical record images submitted for health insurance claims
  • Analyzing assay images for drug research and development
  • Training deep learning models for image identification and classification

Use Cases


The adage “a picture is worth a thousand words” isn’t just a reflection on traditional photographs. In fact, as much as 90% of healthcare data comes from imagery.1 Within each image hides key insights from disease type to patient demographics to dimensions, voxel size and repetition time. This data can influence diagnoses from healthcare providers, […]

Vyasa features a suite of application interfaces
for exploring your data fabric.