Koios Medical – Empowering physicians with the best possible solutions to improve diagnostic accuracy

The Silicon Review

Artificial Intelligence (AI) is becoming more common place in radiology practices, and emerging technologies are providing radiologists with sophisticated detection software to aid their reading and provide support for a busy workflow. With the progression of AI technology, vendors must look not only at what AI can do for the radiologist, but how the radiologist and the technician interact with that technology – the goal should be increasing accuracy while also positively improving workflow.

Koios Medical develops an ultrasound image analysis platform to offer early disease detection and diagnosis. The company focuses on providing software medical device products that meet or exceed customer and regulatory requirements. Koios Medical provides software solutions for radiologists diagnosing cancer. It uses artificial intelligence integrated algorithms trained on images combined with data from pathology results on breast and thyroid cancer diagnosis focusing on improving survival rates as well as workflow efficiency. Koios Medical was formerly known as Clearview Diagnostics. Koios Medical was founded in 2012 and is based in Chicago, Illinois. Koios Medical strives to deliver innovation via safe, reliable, high quality and clinical utility software medical device products. Koios meets or exceeds customer and regulatory requirements through a culture of quality, and maintains an effective quality management system (QMS) by managing risks and executing objectives.

The Koios Story: Innovation is in their DNA

In 2007, their engineers using radar technology and machine learning to help the U.S. Army catch bad guys figured out how to use that same technology to catch bad cancer cells. They have been hard at work for over 12 years experimenting, improving performance and developing software around the needs and workflow of interpreting physicians and technicians. In that time they have trained their proprietary algorithms on a dataset that now exceeds 500,000 ultrasound images of breast lesions all tied to pathology results or at least 1-year follow-up.

Powerful Cancer Diagnosis Software

Koios Smart Ultrasound software provides early and accurate breast and thyroid cancer diagnosis. Koios DS is built on an ensemble of algorithms trained by a proprietary dataset of over 2 million ultrasound images. By analyzing 17.9k features per image, the software uses artificial intelligence to accurately and successfully classify and render cancer risk assessment. The software’s ensemble of algorithms has been trained on hundreds of thousands of images from a variety of patient demographic profiles derived from a wide range of ultrasound system manufacturers, and customers have seen workflow improvements combined with a reduction in benign biopsies and avoidable, unnecessary follow-up appointments, while catching more cancers earlier. Koios Smart Ultrasound^® software reduces avoidable biopsy procedures and unnecessary follow-up appointments as well as decreases patient stress, unnecessary out-of-pocket expenses from false positives, over-treatment and human error. And more!

Koios DS Breast

It is the only FDA-cleared cancer diagnosis software using AI on breast ultrasound images, and works with the physician as an expert on-demand second opinion for classifying suspicious lesions and aligning to a BI-RADS category, while automatically prepopulating diagnostic reports. Koios DS is available directly on an ultrasound scanner and/or simply installed and connected to any PACS, and provides feedback useful for diagnosis and clinical decision making while streamlining workflow.

Koios decision support software integrates into most PACS workstations effectively taking malignancy risk assessment to the next level.

Select a region of interest for analysis.
In seconds, Koios DS analyzes and captures all nodule descriptors automatically and aligns to BI-RADS or ATA to dynamically calculate ratings.
Export the findings to a reporting system and save them as a secondary capture to PACS.

Using artificial intelligence (AI) to analyze breast ultrasound lesions reduced interpretation time by 49% at a healthcare center in Missouri. The software is particularly helpful for lesions classified as BI-RADS 2, 3, and 4A, attendees of the Society for Imaging Informatics in Medicine’s (SIIM) virtual meeting learned on June 24.

For almost a year, the women’s imaging department at Liberty Hospital in Liberty, MO, has used AI software developer Koios Medical’s DS breast tool. Image data passes from the ultrasound scanner to the AI software server and then back to the ultrasound scanner as well as the radiologist’s workstation. With the click of a button, a region of interest is analyzed within seconds and the AI software decides whether the lesion is suspicious or not and suggests a BI-RADS classification.

Koios DS^™ Thyroid

It is the Smart Ultrasound software providing early and accurate thyroid cancer diagnosis. Participants interpreted studies with higher accuracy, faster interpretation and with less variability when utilizing Koios DS Thyroid vs a reader alone. Across the full population of 15 readers and 650 cases (US + EU), results indicate a significant average relative improvement across multiple study end points with increased cancer detection and fewer benign biopsies.

With regulatory clearances from the U.S. Food and Drug Administration and CE Marks Koios develops AI-powered clinical decision support software for radiologists, endocrinologists, and other trained physicians and technicians, which are vendor agnostic solutions that can be integrated into most picture archiving and communication systems (PACS) workstations for breast and thyroid ultrasound analysis and reporting. Koios’s software aims to empower physicians in their decision-making process, and enhance the patient experience, identify cancers in earlier stages, reduce unnecessary procedures and minimize the stress associated with false positive findings.

Chad McClennan | President & Chief Executive Officer