Medical Applications

Medical datasets are large, usually unannotated, and come in many disparate formats. We ingest the data, normalize it and allow you to create your training sets quickly with powerful and flexible annotation tools as well as other flexible features allowing you to browse, search and filter all of your images based on your specific criteria.

We provide automatic cropping tools for small image datasets. Our random cropping tools can generate thousands of images using manual polygon crops to mark ROI, incorporating areas both inside and outside of the cell boundary. Random cropping balances the dataset, removes any bias and prevents over-fitting. Mark your own ROI with our automatic annotation tools.

Annotations can be used to generate binary mask images at the same resolution as the whole digital slides. In addition to the binary annotation mask, you can also generate binary tissue masks to separate background from tissue. Keypoint annotation allows you to identify cell anomalies without using polygonal annotation.

Flexible augmentations done in real-time and online. Metadata Query Language (MQL) allows for all kinds of metadata to be searched including data type, what machine was used, what angle the image was taken, what kind of lens, model number, classification of tumor, tumor stage, year of patient’s birth, type of equipment used to perform scan, name of hospital, etc. Create custom collections from metadata filters. Export only the selected annotated images. No need to download TB’s of data and save on storage space.

Deep learning can automatically differentiate between cancerous and healthy tissue on radiotherapy scans and assist clinicians in planning radiotherapy treatment. A general problem found in the preparation of large data sets is the arduous task of labeling ground truth categories of the clinical images. Our annotation tools are used for classification, segmentation and feature localization. Create collections based on ground truth data and export directly in the format of your machine learning library.


Our labeling system is highly configurable and multi-layer aware. This means whether you are cropping, labeling or producing segmentation maps you will have the ability to do this in multiple layers and select which one(s) to export in the end.

Related labels that are grouped together can be assigned as a whole to a single annotation layer. For example, you can produce a semantic segmentation map of a street view in one layer and have objects masses and direction vectors in the 2nd and 3rd layer.

Labels also serve as templates where you can pre-define additional attributes to be bestowed on an annotated image or polygon. During export, these values can be included as individual fields or combined to form multi-layer segmentation maps.

Segmentation Maps

Segmentation tools can be used to delineate a VOI. You can indicate a VOI by drawing a contour or by creating a mask. You can also calculate predefined statistics on the indicated VOI.

The easiest method for creating segmentation map annotations is through polygon partitioning. By drawing intersecting splines on top of your source imagery you are effectively cutting the predefined area into many sub-polygons (aka segments). This is a highly efficient method of generating Pixel-dense segmentation maps, as the class for every single pixel is defined from the start, meaning you will not have to manually align the polygons for 2 segments running parallel to each other.

Alternatively if you are not looking for Pixel-dense representations but instead want to annotate only certain types of objects, you will have the ability to draw closed polygons. Since these often encompass a whole object including its occluded parts (e.g. car behind a lamp post) we have added the ability to control the Z-index (depth) of the objects. The Z-index defines which segment is closer to the camera and should be rendered last when outputting segmentation map images.

Bounding Boxes

In many ways bounding boxes have similar traits to polygons found in segmentation maps. The main difference is the fact they are constrained to either rectangular or square shape. On export they become interchangeable and polygons can automatically be enclosed by a bounding box fitting the polygon's maximum extents. The residual area outside the polygon can be filled through various methods: gaussian noise, background, solid color, opacity etc.

2D bounding boxes are created by first setting the aspect ratio constraints (e.g. 1:1 for square) and dragging the box on top of your image. Multiple labels and attributes can be automatically assigned to a single bounding box by using the label templates or multi-selecting labels. The entire process can be performed in multiple freely definable layers.

Bounding boxes are treated by our system as unique new images and can therefore undergo the same annotation as the original source image. For example, a cropped bounding box on a satellite image or whole slide image can be used as a starting for a segmentation map.


Using our simple point-and-click interface you can assign landmarks to either source imagery or to crops created out of bounding boxes. The value, size and smoothness of the landmark is not set at annotation time, instead it is freely configurable as an augmentation during export allowing for maximum flexibility when experimenting. Additionally, the landmarks can be drawn onto a blank canvas serving as a ground truth or rendered directly on top of the source images.

An alternative way of using our landmark annotation tool is by predefining their count and order in which to be assigned. This enables the creation of facial landmarks and other annotations that require a fixed feature output size.

Pixel Wise Painting

When dealing with irregular shaped or tiny objects, polygons are not always the best solution. For these cases we offer various painting tools that let you easily mark areas based on color or edge detections. Like our landmark tools these resulting annotations can be drawn on top or onto a blank canvas with fully configurable intensity values.

You can apply deep learning to a wide variety of medical applications including digital pathology, radiology, robotics surgery, drug discovery, etc.

Please contact us for more information for tailored solutions.