openPR Logo
Press release

Oxipit Receives Patent for Improved AI Lung Cancer Diagnostics

05-25-2020 09:33 AM CET | Health & Medicine

Press release from: Oxipit

Oxipit, creators of artificial intelligence based radiology imaging suite ChestEye, announces that the European Patent Office has approved their patent application. The innovation allows efficient use of high-resolution chest X-ray images for machine learning model training and is especially relevant for improving lung nodule detection.

Modern X-ray equipment produces large images with 16 Megapixel resolution being common. On the other hand, machine learning and artificial intelligence (AI) algorithms are typically optimized for working with lower resolution images of 0.1 Megapixel. The patent EP3651117 granted to the company addresses the challenge of efficiently training these algorithms for use on modern X-ray images.

"The granting of this important patent strengthens Oxipit's position as the leading artificial intelligence based chest X-ray reporting software provider," said Oxipit CEO Gediminas Peksys. "The invention enables further diagnostic accuracy improvements for our products especially when it comes to lung cancer detection."

One of the advances that enables solving this technical problem is related to eliminating irrelevant pixels captured in the radiograph in an intelligent manner. Such pixels may include anatomical regions of the patient not pertinent to the radiological findings.

In case of a chest X-ray image these might be, for example, arms of the patient, which are not relevant to lung pathology. Moreover, when processing the resulting image for machine learning purposes, it might also be necessary to divide it up into smaller regions.

However, this process cannot be arbitrary, since in that case a medically-relevant lesion might be split up, which in turn would hinder training of the algorithm.

In 2017 Oxipit was founded by 5 scientists coming from diverse academic backgrounds including machine learning, medical sciences, and theoretical physics. The patent further underlines Oxipit's innovative approach towards advancing AI applications in medical care.

Recently Oxipit ChestEye radiology imaging suite received medical device certification in Australia. In early 2019 ChestEye received CE mark paving the way for clinical solution deployment in 32 European markets.

Sauletekio al. 15, LT-10224 Vilnius
Mantas Miksys


Oxipit is a computer vision software startup specialized in medical imaging. With a team of award-winning data scientists and medical doctors, the company aims to introduce innovative Artificial Intelligence/Deep Learning breakthroughs to everyday clinical practice. Oxipit is the authors of CE certified multi-award winning ChestEye radiology imaging suite.

This release was published on openPR.

Permanent link to this press release:

Please set a link in the press area of your homepage to this press release on openPR. openPR disclaims liability for any content contained in this release.

You can edit or delete your press release Oxipit Receives Patent for Improved AI Lung Cancer Diagnostics here

News-ID: 2056155 • Views: 579

More Releases from Oxipit

03-05-2020 | Health & Medicine
Oxipit ChestEye secures medical device certification in Australia
The AI medical imaging company has received an Australian Register of Therapeutic Goods Class IIa medical device certificate for ChestEye AI imaging service. Medical device certification paves the way for clinical use of ChestEye in the Australian market. ChestEye imaging suite is already certified by the CE mark. Oxipit received CE certification last February, enabling clinical ChestEye deployment in 32 European countries. "Australia presents a very advanced, well developed healthcare landscape.
01-29-2020 | Health & Medicine
New Oxipit service to aid large scale chest X-ray screening projects
The AI medical imaging company will showcase ChestEye Negative service at Arab Health 2020 conference in Dubai. ChestEye Negative produces preliminary reports for chest X-rays with no abnormality. The service aims to reduce the workload of radiologists, especially in clinical environments, where only a fraction of all studies features an abnormality. It also significantly simplifies large-scale medical screening projects. "Large scale medical surveys - such as tuberculosis screening in migrant populations
11-26-2019 | Health & Medicine
AI vs Radiologists: can AI surpass doctors in reporting accuracy?
A study by the Centre for Advanced Research in Imaging, Neuroscience and Genomics (CARING) found that nearly 80% of AI generated chest X-ray case reports were as accurate as produced by a radiology specialist. Furthermore, AI reports were more accurate in 5% of analyzed patient cases. The study was undertaken using Oxipit ChestEye AI imaging suite. The full study titled The full study titled “Judging the Accuracy and Clinical Validity
07-23-2019 | Health & Medicine
Medical Imaging Company Oxipit raises $1.7M Seed Round to bring AI into Clinical …
Oxipit are the authors of ChestEye AI-powered radiology software suite. Automated AI-based diagnosis and reporting by ChestEye enables radiologists to improve productivity, reduce error-rate, discover overlooked secondary findings and address the shortage and ever-increasing workload of radiology specialists. The round marks the largest investment for medical AI solutions in the Baltic states. It is also one of the largest seed rounds among Baltic startups. In February ChestEye software received CE

All 5 Releases

More Releases for ChestEye

02-04-2019 | Health & Medicine
Oxipit’s AI ChestEye imaging suite receives CE certification
Leading AI-based medical imaging solutions provider Oxipit received CE certification for ChestEye radiology imaging suite. Oxipit ChestEye provides analysis and preliminary reports for 75 most common radiological findings - the largest scope of diagnosis currently available on the market - with an average area under curve metric of 93%. CE mark ensures that the software complies with medical device regulations and paves the way for commercial deployments in 32