Medical Image Analysis

CuraCloud™ takes a multidisciplinary approach to medical image analysis.

Technological advantages:

  • Machine learning models built by experts in medical imaging
  • Comprehensive: Spans imaging, clinical notes, genomics



Radiology practices will be able to use CuraRad solutions to speed radiologist review of critical cases, introduce new kinds of exams, and increase the throughput of image review without increasing costs or reducing quality.

Examples of exams being explored by CuraCloud:

  • Intracranial Hemorrhage detection via CT
  • Measuring stenosis or occlusion in blood vessels
  • Pneumothorax detection via Xray
  • Pulmonary embolism identification via Xray
  • Pulmonary nodule detection


Smarter Worklists

This diagram shows how CuraCloud is developing AI-powered priority escalation to a radiologist’s worklist.

Once an image is acquired, an enterprise worklist can use standard DICOM commands to have the image copied to the CuraRad AI server for automated analysis.

CuraRad would then execute a deep learning model capable of detecting and measuring certain conditions for which it has been previously trained, and returns the results to the worklist, PACS, VNA, or other calling system.

With reporting integration, the AI results could be configured to pre-populate the image result report for the radiologist and add notes for the radiologist to consider (e.g., lung nodule measurement and description, etc).

The radiologist would use this information to prioritize and speed her image exams.

The findings could also be used by the calling application to perform smart worklist assignment, routing the right exam to the right clinician at the right time. This will be particularly helpful for telehealth, emergency medicine and oncology applications.  This functionality is currently under development. It is not available for sale in the US.


Image Analysis in Pathology

Cancer Metastasis Detection

CuraCloud is developing A.I. models that enhance pathologist accuracy and efficiency in staging a variety of cancers.

Detecting metastasis of lymph nodes is critical to judging cancer prognosis, particularly for breast cancer.  However, detection can be challenging for the pathologist because slide images are high resolution (e.g., 100k X 200k pixels) and tissue is highly variable. CuraCloud is developing a spatially structured deep network (Spatio-Net) that improves detection of metastases by more than 5% over current state-of-the-art for breast cancer.

The Spatio-Net research project achieved this advantage by taking spatial variation into account.  In contrast, other approaches divide slide images into small areas and analyze each individually, discarding spatial structure information that is vital to detection inference. Spatio-Net gains a further advantage from its rich training dataset, which includes over 1 million image patches from 300 patients.

This is a research project and is not available for sale in the USA.

Challenge 1: Large, High Resolution Images

Challenge 2: High Variance within Each Slide

Overview of Spatio-Net


Explore collaboration with CuraCloud today


Towards Better Healthcare