DIAGNOS Announces Industry Leading Performance of its Automated Dark Lesion Detection for Diabetic Retinopathy Screening
(firmenpresse) - BROSSARD, QUEBEC -- (Marketwired) -- 06/16/15 -- DIAGNOS Inc. ("DIAGNOS" or "the Corporation") (TSX VENTURE: ADK), a leader in healthcare technical services including screening, software and algorithm development, data analysis, and image processing, is pleased to announce the leading results for the automated detection of dark lesions (microaneurysms and bleeding) related to the presence of diabetic retinopathy.
Innovative algorithms for detecting retinal microaneurysms and bleeding were developed at Diagnos and integrated into its CARA platform. Their validation on a public database of 1,200 images () demonstrated, on the one hand, performance results exceeding all other similar platforms reported in the literature on the same set of images (1, 2, 3, 4) CARA also generated results similar to those of two human experts. Of the 1,200 images, the new version of CARA detected 92% of the images with indicators of referable diabetic retinopathy.
Moreover, based on an assessment of 1,000 images acquired in an actual telemedicine setting, with a heterogeneic set of fundus cameras, CARA detected 95% of diabetic retinopathy cases, thereby demonstrating the robustness of the new algorithms in the face of image and source variability.
Finally, assessed on the public basis of the Retinopathy Online Challenge (), the CARA lesion detection algorithm demonstrated performance results exceeding those obtained by our competitors (IDX, LLC and Hubble Telemedical Inc.) for the same set of images (5, 6).
(1) C. I. Sanchez, M. Niemeijer, A. V Dumitrescu, M. S. A. Suttorp-Schulten, M. D. Abramoff, and B. van Ginneken, "Evaluation of a computer-aided diagnosis system for diabetic retinopathy screening on public data," Invest. Ophthalmol. Vis. Sci., vol. 52, no. 7, pp. 4866-4871, Jun. 2011.
(2) B. Antal and A. Hajdu, "An ensemble-based system for microaneurysm detection and diabetic retinopathy grading," IEEE Trans. Biomed. Eng., vol. 59, no. 6, pp. 1720-6, Jun. 2012.
(3) C. Agurto, V. Murray, E. Barriga, S. Murillo, M. Pattichis, H. Davis, S. Russell, M. Abramoff, and P. Soliz, "Multiscale AM-FM methods for diabetic retinopathy lesion detection.," IEEE Trans. Med. Imaging, vol. 29, no. 2, pp. 502-12, Feb. 2010.
(4) G. Quellec, M. Lamard, M. D. Abramoff, E. Decenciere, B. Lay, A. Erginay, B. Cochener, and G. Cazuguel, "A multiple-instance learning framework for diabetic retinopathy screening.," Med. Image Anal., vol. 16, no. 6, pp. 1228-40, Aug. 2012.
(5) M. Niemeijer, B. van Ginneken, J. Staal, M. S. A. Suttorp-Schulten, and M. D. Abramoff, "Automatic detection of red lesions in digital color fundus photographs," IEEE Trans. Med. Imaging, vol. 24, no. 5, pp. 584-592, May 2005.
(6) L. Giancardo, F. Meriaudeau, T. P. Karnowski, Y. Li, K. W. Tobin, and E. Chaum, "Microaneurysm detection with the radon cliff operator in retinal fundus images," in IEEE International Conference on Image Processing, 2011, pp. 49-52.
About DIAGNOS
Founded in 1998, DIAGNOS is a publicly traded Canadian corporation with a mission to commercialize technologies combining contextual imaging and traditional data mining thereby improving decision making processes. DIAGNOS offers products, services, and solutions to clients in a variety of fields including healthcare and natural resources.
CARA is a tele-ophthalmology platform that integrates with existing equipment (hardware and software) and processes at the point of care (POC) and comprises: image upload, image enhancement automated pre-screening, grading by a specialist, and referral to a specialist. CARA's image enhancement algorithms make standard retinal images sharper, clearer, and easier to read. CARA is accessible securely over the internet, and is compatible with all recognized image formats and brands of fundus cameras, and is EMR compatible. CARA is a cost-effective tool for screening large numbers of patients, in real-time and has been approved by regulatory authorities including Health Canada, US Food and Drug Administration, and the European Union.
Forward-looking information
This document contains forward-looking information. There can be no assurance that forward-looking information will prove to be accurate, as actual results and future events could differ materially from those anticipated in these
statements.
Neither the TSX Venture Exchange nor its Regulation Service Provider (as that term is defined in the policies of the TSX Venture Exchange) accepts responsibility for the adequacy or accuracy of this release.
Contacts:
DIAGNOS Inc.
Andre Larente, President and CEO
1-877-678-8882 or (450) 678-8882, ext.: 224
Themen in dieser Pressemitteilung:
Unternehmensinformation / Kurzprofil:
Datum: 16.06.2015 - 13:29 Uhr
Sprache: Deutsch
News-ID 400819
Anzahl Zeichen: 5117
contact information:
Town:
BROSSARD, QUEBEC
Kategorie:
Software
Diese Pressemitteilung wurde bisher 194 mal aufgerufen.
Die Pressemitteilung mit dem Titel:
"DIAGNOS Announces Industry Leading Performance of its Automated Dark Lesion Detection for Diabetic Retinopathy Screening"
steht unter der journalistisch-redaktionellen Verantwortung von
DIAGNOS Inc. (Nachricht senden)
Beachten Sie bitte die weiteren Informationen zum Haftungsauschluß (gemäß TMG - TeleMedianGesetz) und dem Datenschutz (gemäß der DSGVO).
