Pulmonary Nodule Detection by a Team of Medical Practitioners

  • Client Profile

    Industry: Medical Software
    Location: Israel
    Size: 50-100 employees

  • Company Bio

    Our client provides artificial intelligence software for full body imaging. With the help of deep learning and AI algorithms, this software analyzes medical images and patient data to help radiologists detect critical anomalies.

Overview

To create advanced healthcare-grade AI-based decision support software, massive amounts of unsorted and encrypted lung scans needed to be annotated. These scans had to be sorted, grouped, and checked for pulmonary nodules. Pulmonary nodules then had to be marked as prominent, non-prominent, borderline, or granuloma.

  • Target Time for Each CT scan

    25 min

  • Volume of CT scans

    500

  • Amount of Nodules to be Detected

    10k+

Challenge

Our main challenge was that no specific instructions nor any annotation tools were provided to our team. The output format was not standard, so the conversion took more time and effort than anticipated.

Human Resources

Mindy Support worked with three radiologists each who had 5+ years of experience and were also members of the Radiologist’s Association of Ukraine, and one was also a member of the European Society of Radiology. A dedicated project manager was also provided.

Solution Process

  • We sorted studies and matched them with their descriptions.

  • We researched different annotation tools, selected the ones which suited our needs, and set them up.

  • Radiologists labelled pulmonary nodules in the CT scans with polygons and added special tags for each type of nodule: prominent, non-prominent, borderline, and granuloma. If nodules could not be detected, image artifacts were applied: breathing movement, lung disease, metastatic disease.

  • For our client’s convenience, we sent the data in two separate formats — JSON and PKL. In order to convert JSON into PKL, we developed a special script.

Mindy Support is ISO 9001 certified. Our information security management system (ISMS) is built on the basis of ISO 27001:2013 international standards that helps organizations keep information assets secure.
We are committed to respecting all rights of the data subjects under the General Data Protection Regulation (GDPR) (EU) 2016/679. According to the Article 28 of the GDPR, the relationship between the controller and the processor are regulated by Data Processing Agreement, which we put in place with every Client.

Results

Our dedicated team of 3 radiologists and 1 project manager delivered the following results:

  • 10k+ nodules detected

  • 99% annotation accuracy

  • 65% cost efficiency

  • 25 min

    Target time for each CT

  • 500

    CT Scans

  • 10k+

    nodules to be detected