The following projects showcase the professional service capabilities of our R&D team, illustrating possible applications for AI in radiology. These applications may be further developed in collaboration with our team for submission to regulatory agencies in the future.
These products are not for sale in the USA.

Clinical Use CasesAnnotation Services

Intracranial Hemorrhage Detection

CuraCloud has developed a software system that can detect intracranial hemorrhage (ICH) condition on non-contrast head CT images in just a few seconds based on a deep learning model. The software can be used to help radiologists to triage and prioritize reading of images for patients with ICH

Pulmonary Nodule Detection and Characterization

CuraCloud has developed a deep learning-based algorithm to process the thoracic CT image. The algorithm implements automatic highlighting, measuring and characterizing lung nodules within the workflow.

Chest X-Ray

In 2017, the NIH Clinical Center released over 100,000 anonymized chest X-ray images and their corresponding data to the scientific community. CuraCloud is one of the first AI companies to use this data to create computer-assisted diagnosis algorithms. Our algorithm accuracy is quite high and compares favorably with other industry  leaders.

Cardiovascular Structure Segmentation and Measurements

CuraCloud has extensive experience working with clinical collaboration partners in the field of interventional cardiology. One project that has been foundational to many projects in this area is the creation of a visual model of the heart and the surrounding blood vessels from radiology studies such as digital subtractive angiography. This model allows the automated segmentation, measurements, such as arterial stenosis, and the anatomical labeling of the vascular vessel structure.

Bone Age Prediction

Bone age is a predictor of the skeletal maturity of a child. It is usually assessed by pediatricians using an X-ray of the fingers and wrist with an atlas of X-rays to determine bone age. Our deep learning model is designed to accurately access the bone age from X-ray images. Our research paper “Residual Attention based Network for Hand Bone Age Assessment” has been invited to be presented at the 2019 IEEE International Symposium on Biomedical Imaging (ISB).

Metastasis Detection

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 and tissue is highly variable. CuraCloud has developed a spatially structured deep network (Spatio-Net), learning from a rich training dataset that includes over 1 million image patches from 300 patients to improve the detection of metastasis for breast cancer.

Breast Cancer Ultrasound Diagnosis

CuraCloud has developed a convolutional neural network algorithm to predict and classify breast cancer in ultrasound images following BI-RADS categories: malignant tumor, benign lump, or normal tissue. This study was presented at MICCAI 2018, one of the top international medical conferences.

NLP for Cancer Registry

CuraCloud has conducted a feasibility study in collaboration with a pediatric oncology research organization to partially automate the extraction, abstracting, and loading of patient data into a cancer registry for a consortium of institutions. The goal was to reduce the labor intensity of the manual process, improve quality and support the research mission.

Image Annotation Platform

CuraCloud has developed a cloud-based, zero-footprint annotation platform that allows users to navigate DICOM images, manually delineate structures and regions of interest in imaging data. This annotation tool effectively improves the efficiency of tedious annotation process by providing the essential interactions to quickly mark, measure, and manage their annotations consistently.

Let's start something new together.