You are here

Imaging Informatics

 

Most health systems already have enough clinical data to make more useful primary observations than any group of humans could ever connect the proverbial dots on. The good news is that machines are here to help—and they’re getting better at it all the time.

 

A novel computer-aided diagnosis (CAD) algorithm has bested three un-aided thoracic radiologists at predicting malignancy in small lung nodules found on low-dose CT imaging, according to a study published online Aug. 5 in Radiology.

The radiology department at an urban academic medical center has cut its average outpatient CT wait times to a little over an hour, and that includes the scan. Prior to starting the project that took aim at streamlining CT processes, the department was averaging more than three hours in arrival-through-completion times.

Knowing the amyloid status of patients who have symptoms of mild cognitive impairment or dementia affects diagnosis and alters care management, according to the authors of a study running online in Dementia and Geriatric Cognitive Disorders.

Projections of radiology’s demise at the hands of algorithms have been greatly exaggerated. In fact, not only will machine learning not take rads’ jobs: It will become a routine component of their clinical practice, making their work more efficient, accurate, satisfying and valued.

 

Recent Headlines

MRI plays an important role in pregnancy-associated breast cancers

A recent study published in the American Journal of Roentgenology states that breast MRI may play an important role in the management of pregnancy-associated breast cancers (PABC).

RLI Summit 2017: What radiology can learn from pathology about AI

Most health systems already have enough clinical data to make more useful primary observations than any group of humans could ever connect the proverbial dots on. The good news is that machines are here to help—and they’re getting better at it all the time.

 

CAD algorithm proves its power in early diagnosis of lung cancer

A novel computer-aided diagnosis (CAD) algorithm has bested three un-aided thoracic radiologists at predicting malignancy in small lung nodules found on low-dose CT imaging, according to a study published online Aug. 5 in Radiology.

CT process mapping cuts outpatient wait times to 1/3 of earlier average

The radiology department at an urban academic medical center has cut its average outpatient CT wait times to a little over an hour, and that includes the scan. Prior to starting the project that took aim at streamlining CT processes, the department was averaging more than three hours in arrival-through-completion times.

Brain PET scans change management of patients with possible Alzheimer’s

Knowing the amyloid status of patients who have symptoms of mild cognitive impairment or dementia affects diagnosis and alters care management, according to the authors of a study running online in Dementia and Geriatric Cognitive Disorders.

AI will augment rather than replace radiologists: How and why

Projections of radiology’s demise at the hands of algorithms have been greatly exaggerated. In fact, not only will machine learning not take rads’ jobs: It will become a routine component of their clinical practice, making their work more efficient, accurate, satisfying and valued.

Many radiotherapy cases require elevated diligence for imaging

When there’s a near-miss or safety incident (NMSI) with a patient undergoing radiation therapy, and the incident was related to the disease or treatment itself, the lapse often involves imaging. But it’s not imaging per se that raises any particular risk.

Fujifilm’s PACS gets go-ahead from Defense Department

The U.S. Department of Defense has given Fujifilm’s Synapse PACS the green light to operate on the department’s networks, granting the company an Authority to Operate (ATO) and making it the first medical-imaging vendor to obtain such clearance since DoD switched to its Risk Management Framework (RMF), according to a press release sent by Fujifilm Medical Systems USA.

Netherlands medical-imaging AI startup attracts $2.5M funding boost

A European AI startup that has so far focused on deep-learning detection of lung cancers on imaging has raised around $2.5 million (2.25 million euros) in seed-round funding to refine its product and bring it to market.

‘RAD Women’ launch online resource center

Women with an interest in medical imaging informatics have a new online resource center thanks to RADxx, the women’s advancement initiative kicked off at last year’s RSNA by Geraldine McGinty, MD, and Mini Peiris of the healthcare software company Ambra Health. 

Pages