Stamford, United Kingdom
Stamford, United Kingdom

Time filter

Source Type

News Article | April 24, 2017
Site: www.eurekalert.org

An artificial intelligence image detection method has the potential to outperform PAP and HPV tests in screening for cervical cancer; Low-cost technique could be used in less-developed countries, where 80 percent of cervical cancer deaths occur Artificial intelligence--commonly known as A.I.--is already exceeding human abilities. Self-driving cars use A.I. to perform some tasks more safely than people. E-commerce companies use A.I. to tailor product ads to customers' tastes quicker and with more precision than any breathing marketing analyst. And, soon, A.I. will be used to "read" biomedical images more accurately than medical personnel alone--providing better early cervical cancer detection at lower cost than current methods. However, this does not necessarily mean radiologists will soon be out of business. "Humans and computers are very complementary," says Sharon Xiaolei Huang, associate professor of computer science and engineering at Lehigh University in Bethlehem, PA. "That's what A.I. is all about." Huang directs the Image Data Emulation & Analysis Laboratory at Lehigh where she works on artificial intelligence related to vision and graphics, or, as she says: "creating techniques that enable computers to understand images the way humans do." Among Huang's primary interests is training computers to understand biomedical images. Now, as a result of 10 years work, Huang and her team have created a cervical cancer screening technique that, based on an analysis of a very large dataset, has the potential to perform as well or better than human interpretation on other traditional screening results, such as Pap tests and HPV tests--at a much lower cost. The technique could be used in less-developed countries, where 80% of deaths from cervical cancer occur. The researchers are currently seeking funding for the next step in their project, which is to conduct clinical trials using this data-driven detection method. Huang's screening system is built on image-based classifiers (an algorithm that classifies data) constructed from a large number of Cervigram images. Cervigrams are images taken by digital cervicography, a noninvasive visual examination method that takes a photograph of the cervix. The images, when read, are designed to detect cervical intraepithelial neoplasia (CIN), which is the potentially precancerous change and abnormal growth of squamous cells on the surface of the cervix. "Cervigrams have great potential as a screening tool in resource-poor regions where clinical tests such as Pap and HPV are too expensive to be made widely available," says Huang. "However, there is concern about Cervigrams' overall effectiveness due to reports of poor correlation between visual lesion recognition and high-grade disease, as well as disagreement among experts when grading visual findings." Huang thought that computer algorithms could help improve accuracy in grading lesions using visual information--a suspicion that, so far, is proving correct. Because Huang's technique has been shown, via an analysis of the very large dataset, to be both more sensitive--able to detect abnormality--as well as more specific (fewer false positives), it could be used to improve cervical cancer screening in developed countries like the U.S. "Our method would be an effective low-cost addition to a battery of tests helping to lower the false positive rate since it provides 10% better sensitivity and specificity than any other screening method, including Pap and HPV tests," says Huang. To identify the characteristics that are most helpful in screening for cancer, the team created hand-crafted pyramid features (basic components of recognition systems)--as well as investigated the performance of a common deep learning framework known as convolutional neural networks (CNN) for cervical disease classification. They describe their results in an article in the March issue of Pattern Recognition called: "Multi-feature base benchmark for cervical dysplasia classification." The researchers have also released the multi-feature dataset and extensive evaluations using seven classic classifiers here. To build the screening tool, Huang and her team used data from 1,112 patient visits, where 345 of the patients were found to have lesions that were positive for moderate or severe dysplasia (considered high-grade and likely to develop into cancer) and 767 had lesions that were negative (considered low-grade with mild dysplasia typically cleared by the immune system). These data were selected from a large medical archive collected by the U.S. National Cancer Institute consisting of information from 10,000 anonymized women who were screened using multiple methods, including Cervigrams, over a number of visits. The data also contains the diagnosis and outcome for each patient. "The program we've created automatically segments tissue regions seen in photos of the cervix, correlating visual features from the images to the development of precancerous lesions," says Huang. "In practice, this could mean that medical staff analyzing a new patient's Cervigram could retrieve data about similar cases--not only in terms of optics, but also pathology since the dataset contains information about the outcomes of women at various stages of pathology." From the study: "...with respect to accuracy and sensitivity, our hand-crafted PLBP-PLAB-PHOG feature descriptor with random forest classifier (RF.PLBP-PLAB-PHOG) outperforms every single Pap test or HPV test, when achieving a specificity of 90%. When not constrained by the 90% specificity requirement, our image-based classifier can achieve even better overall accuracy. For example, our fine-tuned CNN features with Softmax classifier can achieve an accuracy of 78.41% with 80.87% sensitivity and 75.94% specificity at the default probability threshold 0.5. Consequently, on this dataset, our lower-cost image-based classifiers can perform comparably or better than human interpretation based on widely-used Pap and HPV tests..." According to the researchers, their classifiers achieve higher sensitivity in a particularly important area: detecting moderate and severe dysplasia--or cancer. Among Huang's other projects is a collaboration with Chao Zhou, assistant professor of electrical and computer engineering at Lehigh. They are working on the use of an established medical imaging technique called optical coherence microscopy (OCM)--most commonly used in ophthalmology--to analyze breast tissue to produce computer-aided diagnoses. Their analysis is designed to help surgeons minimize the tissue removed while operating on cancer patients by providing highly accurate, real-time information about the health of the excised tissue. They recently conducted a feasibility study with promising results that have been published in an article in Medical Image Analysis called: "Integrated local binary pattern texture features for classification of breast tissue imaged by optical coherence microscopy." Huang and Zhou used multi-scale and integrated image features to improve classification accuracy and were able to achieve high sensitivity (100%) and specificity (85.2%) for cancer detection using OCM images. "Chao has done a lot of work in new instrumentation--improving the quality of biomedical images," says Huang. "Since he works on the images--or data inputs--and I work on the results of the data analysis--or outputs, our collaboration is a natural fit."


A2iA and ACHeck21 Announce Partnership for Mobile ACH and Check Deposit Services ACHeck21 Open Standard API to include offline data recognition for iOS and Android SDK. New York, NY, April 27, 2017 --( The ACHeck21 Mobile SDK integrates capabilities from a2ia Mobility™, an offline and client-side mobile SDK powered by artificial intelligence and machine learning, dedicated to the image analysis and data extraction from checks, IDs, bills and other forms. The new combined offering delivers cross platform functionality for iOS and Android, and offers a white label, REST-based API and SDK. As with all ACHeck21 FinTech Cloud services, ACHeck21 Mobile will incorporate both ACH and check deposit, along with verification and ancillary services such as ID recognition, in a single work flow and simple user interface. The service will also allow licensees to customize the user interface and branding to meet business requirements. “This new service offers fintech companies and mobile application developers a complete service that will support all ACH entry classes, mobile deposit, fraud detection, and verification,” said Sam Ackley, CEO of DCS Holdings Group, LLC, the owner of ACHeck21. “With the inclusion of a2ia Mobility, developers can incorporate document and check capture in an offline manner that increases conversion rates, straight through processing, and decreases operating costs.” ACHeck21 Mobile SDK is available from ACheck21. For more information contact Ralph Martinez at 314-282-3666, email sales@dcsdeposits.com or visit www.acheck21.com About A2iA Award-winning with research and development at its core, A2iA, Artificial Intelligence and Image Analysis (www.a2ia.com), is a science and R&D driven software company with deep roots in artificial intelligence, machine learning and neural networks. With simple, easy to use and intuitive toolkits, A2iA delivers add-on features to speed automation, simplify customer engagement and quickly capture all types of printed and handwritten data from documents – whether captured by a desktop scanner or mobile device. By enhancing solutions from systems integrators and independent software vendors, A2iA allows complex and cursive data from all types of documents to become part of a structured database, making it searchable and reportable, with the same level of flexibility as printed or digital data. For more information, visit www.a2ia.com or call +1 917-237-0390 within the Americas, or +33 1 44 42 00 80 within EMEA, India or Asia. About ACHeck21 ACHeck21 is an intelligent private financial cloud that combines ACH (Automatic Clearing House) entry classes and Check21 (Remote Deposit Capture) along with ancillary services and features into a single hosted work flow. ACH21℠ Payment Gateway offers a fully integrated management console that puts you in the driver’s seat. ACHeck21 software is designed to improve efficiency and reduce complexity for any user, organization or business processing ACH, Checks or verifying account information from point of sale, the internet, mobile devices, laptops, desktops or scanners. If you would like more information about ACHeck21 and the services we offer, please visit www.acheck21.com. Media Inquiries: A2iA Communications Marketing@a2ia.com Americas: + 1 917.237.0390 EMEA, India, APAC: +33 (0)1 44 42 00 80 New York, NY, April 27, 2017 --( PR.com )-- A2iA (@A2iA), a trusted name in the worldwide data capture, document processing, and payment systems markets, today announced that it has extended its 15 year partnership with ACHeck21®, an intelligent private financial cloud that combines ACH (Automatic Clearing House) entry classes and Check21 (Remote Deposit Capture), along with ancillary services and features into a single hosted work flow. ACHeck21will debut its new open standard API that includes both mobile payments and mobile deposit this week at NACHA’s Payments show, Booth 518.The ACHeck21 Mobile SDK integrates capabilities from a2ia Mobility™, an offline and client-side mobile SDK powered by artificial intelligence and machine learning, dedicated to the image analysis and data extraction from checks, IDs, bills and other forms. The new combined offering delivers cross platform functionality for iOS and Android, and offers a white label, REST-based API and SDK. As with all ACHeck21 FinTech Cloud services, ACHeck21 Mobile will incorporate both ACH and check deposit, along with verification and ancillary services such as ID recognition, in a single work flow and simple user interface. The service will also allow licensees to customize the user interface and branding to meet business requirements.“This new service offers fintech companies and mobile application developers a complete service that will support all ACH entry classes, mobile deposit, fraud detection, and verification,” said Sam Ackley, CEO of DCS Holdings Group, LLC, the owner of ACHeck21. “With the inclusion of a2ia Mobility, developers can incorporate document and check capture in an offline manner that increases conversion rates, straight through processing, and decreases operating costs.”ACHeck21 Mobile SDK is available from ACheck21. For more information contact Ralph Martinez at 314-282-3666, email sales@dcsdeposits.com or visit www.acheck21.comAbout A2iAAward-winning with research and development at its core, A2iA, Artificial Intelligence and Image Analysis (www.a2ia.com), is a science and R&D driven software company with deep roots in artificial intelligence, machine learning and neural networks. With simple, easy to use and intuitive toolkits, A2iA delivers add-on features to speed automation, simplify customer engagement and quickly capture all types of printed and handwritten data from documents – whether captured by a desktop scanner or mobile device. By enhancing solutions from systems integrators and independent software vendors, A2iA allows complex and cursive data from all types of documents to become part of a structured database, making it searchable and reportable, with the same level of flexibility as printed or digital data. For more information, visit www.a2ia.com or call +1 917-237-0390 within the Americas, or +33 1 44 42 00 80 within EMEA, India or Asia.About ACHeck21ACHeck21 is an intelligent private financial cloud that combines ACH (Automatic Clearing House) entry classes and Check21 (Remote Deposit Capture) along with ancillary services and features into a single hosted work flow. ACH21℠ Payment Gateway offers a fully integrated management console that puts you in the driver’s seat.ACHeck21 software is designed to improve efficiency and reduce complexity for any user, organization or business processing ACH, Checks or verifying account information from point of sale, the internet, mobile devices, laptops, desktops or scanners. If you would like more information about ACHeck21 and the services we offer, please visit www.acheck21.com.Media Inquiries:A2iA CommunicationsMarketing@a2ia.comAmericas: + 1 917.237.0390EMEA, India, APAC: +33 (0)1 44 42 00 80 Click here to view the list of recent Press Releases from A2iA


The global ultrasound image analysis software market is expected to reach USD 1.2 billion by 2025 The growing prevalence of chronic diseases is a high impact rendering growth driver for the ultrasound image analysis software market. The increasing prevalence is presumed to be driving the clinical urgency to adopt ultrasound image analysis software in order to improve the existing poor patient diagnostic imaging measures and reduce long-term cost associated with the conventional diagnostics. In addition, a widening geriatric population base, possessing high susceptibility toward development of chronic diseases is expected to upsurge the demand for ultrasound image analysis software in the future. According to a research published in Medscape, chronic diseases, which predominantly include cardiovascular diseases, are responsible for high mortality rate in the U.S. Consequentially; presence of these highly prevalent cardiovascular diseases raises the demand to utilize advanced diagnostic and imaging alternatives. The aforementioned factor is anticipated to widen the potential for growth throughout the forecast period. Further Key Findings From the Study Suggest: 3 Ultrasound Image Analysis Software Market Variables, Trends & Scope 3.1 Market Segmentation & Scope 3.2 Market Driver Analysis 3.2.1 Technological advancements 3.2.2 Increasing incidences of chronic diseases 3.3 Market Restraint Analysis 3.3.1 Unavailability of skilled professionals 3.3.2 Absence of stringent cyber security 3.4 Penetration &Growth Prospect Mapping 3.5 Ultrasound Image Analysis Software Market - SWOT Analysis, by Factor (Political & legal, economic and technological) 3.6 Industry Analysis - Porter's For more information about this report visit http://www.researchandmarkets.com/research/t69bxd/ultrasound_image To view the original version on PR Newswire, visit:http://www.prnewswire.com/news-releases/research-and-markets---ultrasound-image-analysis-software-integrated-standalone-market-2014-2017-to-2025-key-players-are-ge-healthcare-philips-healthcare-siemens-healthineers--merge-health-300444270.html


DUBLIN, Apr. 25, 2017 /PRNewswire/ -- Research and Markets has announced the addition of the "Ultrasound Image Analysis Software Market Size & Forecast By Software Type (Integrated, Standalone), By Product (2D, 3D & 4D, Doppler), By Application (Cardiology, Obstetrics &...


Grant
Agency: GTR | Branch: Innovate UK | Program: | Phase: Smart - Development of Prototype | Award Amount: 250.00K | Year: 2011

MRI is a major tool in clinical routine since it enables early diagnosis and reliable assessment of treatment, especially in arthritis and oncology studies, where timely diagnosis can make a difference between a disability or even death and a recovery to a relatively normal lifestyle. However, the cost of MRI procedures limits its use, which impacts on patient outcomes. To limit costs and to increase use of MRI radiologists need the best tools to aid their diagnostic procedures. Computer Aided Detection (CAD) solutions automate clinical routine, optimise treatment pathways, and enable earlier diagnosis, leading to overall costs savings in healthcare organisations and improvement of patient outcomes. However, CAD originates in academia and rarely finds its way to clinical routine. This project will extend functionality of IA’s proprietary solution Dynamika, widely deployed in rheumatoid arthritis into detection of prostate and breast cancer. We will further to deliver a prototype of an infrastructure for a faster deployment of this first multi-disease comprehensive MRI CAD solution in clinical routine. Centres of excellence (Oxford, Imperial, UCLH) will be used for R&D guidance, development of this innovative solution and its validation. IA will partner with key service providers (Agfa, Accenture) to build up the infrastructure, enabling academics to transfer their research into clinical practice and clinicians to have access to the latest cutting edge scientific findings. The grant will aid the significant technical development required to build and validate this infrastructure. IA has a track record of successful collaborative work with academia and hands on experience in developing innovative CAD tools. The output of the project will be a UK-wide deployment of MRI CAD solutions for better clinical diagnosis in rheumatoid arthritis, breast, and prostate cancer. The grant will facilitate intense R&D and to allow rapid development and growth of the company.


Grant
Agency: European Commission | Branch: FP7 | Program: CP | Phase: ICT-2009.4.3 | Award Amount: 3.51M | Year: 2010

The goal of the Dicode project is to facilitate and augment collaboration and decision making in data-intensive and cognitively-complex settings. To do so, it will exploit and build on the most prominent high-performance computing paradigms and large data processing technologies - such as cloud computing, MapReduce, Hadoop, Mahout, and column databases to meaningfully search, analyze and aggregate data existing in diverse, extremely large, and rapidly evolving sources.Building on current advancements, the solution foreseen in the Dicode project will bring together the reasoning capabilities of both the machine and the humans. It can be viewed as an innovative workbench incorporating and orchestrating a set of interoperable services that reduce the data-intensiveness and complexity overload at critical decision points to a manageable level, thus permitting stakeholders to be more productive and concentrate on creative activities. Services to be developed are: (i) scalable data mining services (including services for text mining and opinion mining), (ii) collaboration support services, and (iii) decision making support services.The achievement of the Dicode projects goal will be validated through three use cases addressing clearly established problems. These cases were chosen to test the transferability of Dicode solution in different collaboration and decision making settings, associated with diverse types of data and data sources, thus covering the full range of the foreseen solutions features and functionalities. They concern: (i) scientific collaboration supported by integrated large-scale knowledge discovery in clinico-genomic research, (ii) delivering pertinent information from heterogeneous data to communities of doctors and patients in medical treatment decision making, and (iii) capturing tractable, commercially valuable high-level information from unstructured Web 2.0 data for opinion mining.


Grant
Agency: GTR | Branch: Innovate UK | Program: | Phase: European | Award Amount: 172.80K | Year: 2015

Awaiting Public Project Summary


Patent
Image Analysis | Date: 2014-04-09

A computer-implemented method and apparatus for quantifying inflammation in tissue or anatomy. The method includes analysing Dynamic Contrast Enhanced MRI data. The analysis comprises determining a value quantifying inflammation in the tissue. The value is a continuous score value and small changes in the inflammation result in a change in the determined value.


News Article | February 17, 2017
Site: www.marketwired.com

ORLANDO, FL--(Marketwired - February 17, 2017) - TeraRecon (www.terarecon.com), a leader in advanced visualization and enterprise medical image viewing solutions, releases support for virtualization of their iNtuition™ platform. All new customer systems include the Volume Pro® (VP) CUDA® interface layer as standard, readying the platform for nVidia CUDA® GPUs and eliminating the need for previously required proprietary hardware. Today, TeraRecon is the only enterprise advanced visualization company in the world that leverages the CUDA interface. Its pristine legacy of high performance rendering servers made the use of this new technology a near drop-in. With 4 to 20-times improved performance of its industry leading Volume Pro ASIC-based rendering technology, the company has just begun offering its customers VP CUDA interface as a remarkably affordable way to achieve even higher performance from the same iNtuition solution. With a technology upgrade program for install base customers, TeraRecon is easing the transition to the virtual computing environment. Existing customers can purchase TeraRecon's VP CUDA interface layer and upgrade their own hardware to bring their entire viewing architecture to a new level of unmatched performance. TeraRecon customer, Josh Tan, of Wake Forest University's Baptist Medical Center stated, "Our testing has shown a 30% faster load time for images in addition to better bandwidth and memory utilization. We have observed faster rotation, scrolling, and segmenting through 2D and 3D images, as well as faster 3D reconstruction." VP CUDA also supports expansion as an AI-ready platform by providing a future-thinking architecture for the TeraRecon Within Image Analysis (WIA™) Cloud prototype. With the demands of running multiple machine learning application engines simultaneously, WIA Cloud will be fully supported by the processing power of VP CUDA. Visit TeraRecon at HIMSS17 this week in Orlando, Florida in Booth #1475 to experience their full suite of advanced medical image viewing solutions. About TeraRecon (www.terarecon.com) TeraRecon is the largest independent, vendor neutral medical image viewing solution provider with a focus on advanced image processing innovation. TeraRecon iNtuition and iNteract+ solutions advance the accessibility, performance, clinical functionality and medical imaging workflow throughout many areas of the healthcare ecosystem. The company provides world class advanced visualization 3D post-processing tools, as well as a spectrum of enterprise medical image viewing, diagnostic interpretation, image sharing, interoperability and collaboration solutions. TeraRecon is a privately-held company with its world headquarters in Foster City, California with major offices in Acton, MA, Durham, NC, Frankfurt, Germany and Tokyo, Japan.


PARIS & NEW YORK--(BUSINESS WIRE)--A2iA (@A2iA), a world leading developer of artificial intelligence and machine-learning based text recognition, information extraction and intelligent document classification toolkits, today announced the availability of a2ia TextReader™ V5.0. A software toolkit, a2ia TextReader enables full lines of printed and handwritten text to be transcribed without prior segmentation into characters or words. With this new version, global enterprises and business processing organizations can address additional languages, including Simplified and Traditional Chinese, as well as Russian, with the support for Cyrillic characters. Currently supported Western languages - English, French, Spanish, Portuguese, German and Italian – also see an increase in performance, boasting on average 14% higher accuracy rates for cursive handwriting. “A2iA is committed to addressing global market demands, including the growing need to process mixed workflows in multiple languages,” said Jean-Louis Fages, A2iA President and Chairman of the Board. “a2ia TextReader’s simple plug-and-play features enable organizations to gain access to all data quickly and with the highest levels of accuracy.” Award-winning with research and development at its core, A2iA, Artificial Intelligence and Image Analysis (www.a2ia.com), is a science and R&D driven software company with deep roots in artificial intelligence, machine learning and neural networks. With simple, easy to use and intuitive toolkits, A2iA delivers add-on features to speed automation, simplify customer engagement and quickly capture all types of printed and handwritten data from documents – whether captured by a desktop scanner or mobile device. By enhancing solutions from systems integrators and independent software vendors, A2iA allows complex and cursive data from all types of documents to become part of a structured database, making it searchable and reportable, with the same level of flexibility as printed or digital data. For more information, visit www.a2ia.com or call +1 917-237-0390 within the Americas, or +33 1 44 42 00 80 within EMEA, India or Asia.

Loading Image Analysis collaborators
Loading Image Analysis collaborators