News | Artificial Intelligence | September 30, 2020

AI Algorithm Detects Difficult to Read Medical Images

A new artificial intelligence (AI) algorithm can identify when medical images are likely to be difficult for either a radiologist or AI to make an effective diagnosis.

September 30, 2020 — A new artificial intelligence (AI) algorithm can identify when medical images are likely to be difficult for either a radiologist or AI to make an effective diagnosis. The algorithm can potentially be used to triage medical scans and highlight cases that warrant further in-depth clinical evaluation or additional tests to support a definitive clinical diagnosis.

The algorithm, called UDC by AI healthcare company Presagen, was originally designed to automatically detect errors in medical data, particularly data that cannot be reliably verified by experts.

When applied to images of X-rays to detect pneumonia, errors by radiologists were rare when the X-ray images had clear features. However, UDC found the diagnosis (or label) for several X-ray images to be neither correct nor an error. Verification of these images by an independent radiologist also agreed that they were indeed difficult images to diagnose, with their independent assessment often disagreeing with the original diagnosis provided in the public dataset. Similarly, AI that was trained to diagnose pneumonia also found the assessment difficult for these images.

Removal of poor-quality (difficult) images identified by UDC from the training dataset improved AI accuracy for diagnosing pneumonia in X-rays images by over 10% as measured on a hold out blind test set, and the AI was shown to be more scalable (generalizable). The accuracy also exceeded benchmarks set by the current literature for that public dataset.

The AI scientist that led the project, Milad Dakka, Ph.D., said "Our results suggest these poor-quality images are uninformative, counter-productive or confusing when used in training AI. The ability to identify when new images are poor-quality is important to prevent an inaccurate AI clinical assessment, but also to alert the radiologist when the scan is likely to be difficult to diagnose or when a new scan should be taken."

Presagen Co-Founder and Chief Strategy Officer, Don Perugini, Ph.D., said "Many AI practitioners believe that AI performance and scalability can be solved with more data. This is not true, and we call it the AI data fallacy. Even 1% poor-quality data can impact the performance of the AI. Building accurate and scalable AI is about using the right data."

Presagen has recently developed a range of patent-pending AI technologies that drive a fundamental paradigm shift in developing commercially scalable AI products for real-world problems, which apply beyond healthcare and to AI more generally.

Michelle Perugini, Ph.D., said "We are excited to present to the world the suite of technologies, which we believe advance the field of AI. These technologies will allow Presagen to build scalable 'out of the box' AI products that are more commercially viable and technically superior, and thus market dominating. This is vital in Presagen's journey to become world-leaders in AI Enhanced Healthcare and a dominant player in the AI-in-Femtech market globally. More importantly, we see it as an opportunity to change, lead, and dominate the AI industry."

For more information: www.presagen.com

Related Content

Agfa announced the launch of its SmartXR portfolio at RSNA, being held virtually. SmartXR uses a unique combination of hardware and AI-powered software to lighten radiographers’ workloads and provide image acquisition support.
News | Artificial Intelligence | November 29, 2020
November 29, 2020 — Agfa announced the launch of its SmartXR portfolio at...
James P. Borgstede, M.D.

James P. Borgstede, M.D.

News | Radiology Business | November 29, 2020
November 29, 2020 — RSNA President...
During the virtual 106th Scientific Assembly and Annual Meeting of the Radiological Society of North America (RSNA), Nov. 29 to Dec. 5, Siemens Healthineers debuts the MULTIX Impact C,¹ a new ceiling-mounted digital radiography (DR) system.
News | Digital Radiography (DR) | November 29, 2020
November 29, 2020 — During the virtual 106th Scientific Assembly and Annual Meeting of the...
Chest CT images in a 34-year-old man with fever for 4 days. Positive result of reverse-transcription polymerase chain reaction assay for severe acute respiratory syndrome coronavirus 2 using a swab sample was obtained on February 8, 2020. Dates of examination are shown on images. A, Chest CT scan with magnification of lesions in coronal and sagittal planes shows a nodule with reversed halo sign in left lower lobe (box) at the early stage of the pneumonia. B, Chest CT scans in different axial planes and coro

Chest CT images in a 34-year-old man with fever for 4 days. Positive result of reverse-transcription polymerase chain reaction assay for severe acute respiratory syndrome coronavirus 2 using a swab sample was obtained on February 8, 2020. Dates of examination are shown on images. A, Chest CT scan with magnification of lesions in coronal and sagittal planes shows a nodule with reversed halo sign in left lower lobe (box) at the early stage of the pneumonia. B, Chest CT scans in different axial planes and coronal reconstruction show bilateral multifocal ground-glass opacities. The nodular opacity resolved.

News | Coronavirus (COVID-19) | November 29, 2020
November 29, 2020 — The Radiological Society of North America (...
Videos | Remote Viewing Systems | November 28, 2020
Konica Minolta’s theme for RSNA 2020 is Depth of Vision. ITN
Videos | X-Ray | November 28, 2020
Agfa is looking to transform...
Study conducted by medical AI startup Lunit and Massachusetts General Hospital, published in JAMA Network Open - When used as a second reader, the AI algorithm may help detect lung cancer
News | Artificial Intelligence | November 26, 2020
November 26, 2020 — A recent study published in ...
Vital is hosting demonstrations and educational content from industry experts
News | Enterprise Imaging | November 26, 2020
November 26, 2020 — Vital, a Canon Group company, alongside