Two radiologists reviewing results on computer with orange preset.

Diagnostic Reading #6: Five “Must Read” Articles on HIT and Radiology

Reading Time: 3 minutes read

New developments this week: AI for chest X-rays; improved radiology reporting; and 3D printed implants.

This week’s articles in Diagnostic Reading include: AI outperforms physicians at recognizing cancer; the future of radiology reporting – and improvements that are available today; AI triages abnormal chest X-rays; ‘outpatients’ more likely to complete follow-up imaging; and 3D-printed implants may help spinal cord injuries.

AI algorithm outperforms doctors at finding cervical cancer – AI in Healthcare

AI might be better at spotting cervical cancer and precancer after a study found a deep-learning algorithm was more accurate at recognizing the disease than human doctors. The study’s promising results—published in the Journal of the National Cancer Institute—could possibly lead to a more reliable way of detecting signs of cervical cancer and precancer at an early stage in low-resource areas.

Image of Radiologists looking at images on a workstation
Diagnostic reading helps radiologists, healthcare IT and others in the medical imaging profession stay up to date.

The future of radiology reporting – Everything Rad

Interactive, multi-media reporting is readily available within radiology workstations today – yet many diagnostic imaging reports remain text based. In fact, the format of medical imaging reports created by most radiology departments has not changed much in over 100 years. However, in the short and long term, reporting will undergo a considerable transformation. Read the blog to learn about reporting improvements you can use today; and AI’s role in the future.

Artificial intelligence shows potential for triaging chest X-rays – Imaging Technology News

An artificial intelligence (AI) system can interpret and prioritize abnormal chest X-rays with critical findings, according to a study appearing in the journal Radiology. This could potentially reduce the backlog of exams and bring urgently-needed care to patients more quickly. Deep learning (DL), a type of AI capable of being trained to recognize subtle patterns in medical images, has been proposed as an automated means to reduce backlog and identify exams that merit immediate attention, particularly in publicly-funded healthcare systems.

Patients in the outpatient setting most likely to complete follow-up imaging – Radiology Business

Patients receiving care in the outpatient setting are more likely to complete relevant follow-up imaging than patients in the inpatient or emergency department (ED) settings, according to recent research published in the Journal of the American College of Radiology. The findings, the researchers noted, show the need for increased efforts to redesign care processes to improve imaging follow-up for findings with undefined malignant potential.

3D-printed implant created from MRIs might help treat spinal cord injuries – Health Imaging

Using 3D printing, researchers from the University of California San Diego created spinal cord implants modeled from MRI scans that support nerve cell growth in spinal cord injuries and help restore lost physical mobility. Detailed in a study recently published in Nature Medicine, the researchers found their four-centimeter-sized implants could support tissue regrowth, stem cell survival and the expansion of neural stem cell axons—long extensions on nerve cells that connect to other cells—from the scaffolding of the implants into the injured spinal cords of immobile rats.

#diagnosticreading #AI #reporting #everythingrad

POST A COMMENT

This site uses Akismet to reduce spam. Learn how your comment data is processed.