Navigation Links
Medical assessment in the blink of an eye
Date:6/17/2013

Have you ever thought that you knew something about the world in the blink of an eye? This restaurant is not the right place for dinner. That person could be The One. It turns out that radiologists can do this with mammograms, the x-ray images used for breast cancer screening. Cytologists, who screen micrographic images of cervical cells to detect cervical cancer, have a similar ability. A new study, published in Springer's journal Psychonomic Bulletin & Review, takes a closer look at the skill these specialists have.

There are many routes to making snap judgments (not all of them particularly useful). One of these is our ability to get the "gist" of an entire image by analyzing the whole scene at once, based on interpretation of global properties and image statistics, not focusing on specific details.

That seems to be what medical experts can do. They are not perfect in a fraction of a second but they do far better than random guessing when classifying medical images as normal or abnormal even though, in that blink of an eye, they cannot tell you where the problem might be located.

Karla Evans and colleagues, from Harvard Medical School and Brigham and Women's Hospital in the US, assessed medical experts' ability to categorize a breast cancer or cervical screening image as either normal or abnormal in a single glance. A total of 55 radiologists and 38 cytologists were shown either mammograms or images of cervical cells. Half the images were normal and half showed cancerous abnormalities.

Participants were shown the medical images briefly i.e., for 250 to 2000 milliseconds. They were asked to rate the abnormality of the image and then attempt to localize that abnormality on a subsequent screen showing only the outline of the original image.

Both groups of experts were able to detect subtle abnormalities more often than if they had simply guessed the answer; in other words, they showed above chance performance. Control groups, composed of non-expert observers who had no medical training, did no better than if they had guessed the answers on either the breast or cervical cancer images. Interestingly, neither expert group could localize the anomalies reliably in the second part of the experiment. The global gist of pathology might be detected in a flash. Localizing the problem would require a longer period of close scrutiny.

The authors conclude: "Our results show that, with specific training, an expert radiologist or cytologist learns the statistical regularities that distinguish normal from abnormal in the images in the realm of their expertise. They have the ability to feel that something is amiss, yet not know immediately where to find it. If the signal that helps with this initial decision could be identified by a computer, it could be used as a novel form of computer-aided detection."


'/>"/>

Contact: Joan Robinson
joan.robinson@springer.com
49-622-148-78130
Springer
Source:Eurekalert

Related medicine news :

1. Physician Groups Call for Fewer Medical Tests
2. Weill Cornell Medical College establishes Center for Healthcare Informatics and Policy
3. CAM therapy combined with conventional medical care may improve treatment of lower back pain
4. Image share project gives patients and physicians anytime, anywhere access to medical images
5. Researchers determine vitamin D blood level for reducing major medical risks in older adults
6. Biomedical researchers receive Hartwell Foundation awards
7. Columbia University Medical Center and NY-Presbyterian experts at APA meeting
8. Fitness in Middle Age Lowers Medical Costs Later: Study
9. Ben-Gurion U. and Cincinnati Childrens Hospital to develop pediatric-specific medical technologies
10. Gene Tests May Not Drive Patients to More Medical Care
11. University studies and career expectations of medical students
Post Your Comments:
*Name:
*Comment:
*Email:
(Date:2/8/2016)... ... 2016 , ... The Association of Home Care Coding & ... Health and Hospice ICD-10 Transition Workgroup are working closely with the American Hospital ... to address concerns over the use of 'A' as the seventh character indicating ...
(Date:2/8/2016)... ... 08, 2016 , ... Joshua Rosenthal, PhD, Chief Scientific Officer ... use newly released government data on populations and physicians to better calculate risk ... the value they create to succeed in new economic models for value based ...
(Date:2/8/2016)... ... , ... The schedule is now online for the largest and ... is being held May 25-29 at the Loews Chicago O’Hare Hotel, continues to give ... of chronic illness in children. , Very recent articles have cited 1 child in ...
(Date:2/7/2016)... Birmingham, Lake Orion, Clarkston, Metamora, Michigan (PRWEB) , ... ... ... the ability to correct pelvic organ prolapse with the latest techniques and the ... at greatest risk for pelvic organ prolapse, particularly after menopause. Other risk factors ...
(Date:2/7/2016)... ... February 07, 2016 , ... HealthSmart Holdings, Inc. announced today ... the tools and information to lower the costs, and increase the impact of ... providing employee healthcare benefits by as much as 22%:, + Price and ...
Breaking Medicine News(10 mins):
(Date:2/8/2016)... Calif. , Feb. 8, 2016  HemaFlo Therapeutics, Inc. ... (USPTO) has issued US Patent Number 9,119,880 covering the use ... Dale Peterson , PhD, HemaFlo,s founder, said, "We are ... --> Dale Peterson , PhD, HemaFlo,s founder, ... a powerful technology." --> Dale Peterson ...
(Date:2/8/2016)... Pharma Inc. President and Chief Executive Officer Yoshihiko Hatanaka ... as president, Americas Operations, for Astellas US LLC, with responsibility ... America , effective April 1, 2016.  Robinson previously served ... the United States -- a role ... who is retiring in June 2016.  --> ...
(Date:2/8/2016)... 8, 2016 --> ... by Allied Market Research titled, "World Synthetic ... 2014-2020", estimates the world synthetic biology market to ... sequencing technology segment would continue to lead the ... segment, collectively, held around half of the market ...
Breaking Medicine Technology: