Collaborating Authors


Artificial intelligence can boost power, efficiency of even the best microscopes


With the help of artificial intelligence, even already powerful microscopes can see better, faster and process more data. In a new study, published Friday in the journal Nature Methods, researchers used new machine learning algorithms to combine a pair of novel microscopy techniques. The marriage dramatically accelerated image processing and yielded crisp, accurate results. To capture speedy biological processes in 3D, like the beating heart of a fish larva, researchers rely on a method called light-field microscopy. The technique involves the collection of massive amounts data, and as a result, image processing can take days.

Thought Leadership Webcast -- AI Ethics


Amita Kapoor is an Associate Professor in the Department of Electronics, SRCASW, University of Delhi and has been actively teaching neural networks and artificial intelligence for the last 20 years. She completed her masters in Electronics in 1996 and Ph.D. in 2011, during Ph.D. she was awarded a prestigious DAAD fellowship to pursue a part of her research work in Karlsruhe Institute of Technology, Karlsruhe, Germany. She was awarded the Best Presentation Award at the Photonics 2008 international conference. She is an active member of ACM, AAAI, IEEE, and INNS. She has co-authored four books including the best-selling book "Deep learning with TensorFlow2 and Keras" with Packt Publications.

Algorithmic Architecture: Using A.I. to Design Buildings


Architecture designed and built in 1921 won't look the same as a building from 1971 or from 2021. Trends change, materials evolve, and issues like sustainability gain importance, among other factors. But what if this evolution wasn't just about the types of buildings architects design, but was, in fact, key to how they design? While designers have long since used tools like Computer Aided Design (CAD) to help conceptualize projects, proponents of generative design want to go several steps further. They want to use algorithms that mimic evolutionary processes inside a computer to help design buildings from the ground up.

The artificial intelligence technology that detects rip currents


The system uses cameras that help lifeguards keep swimmers away from a hazardous situation near the shoreline. Every year, rip currents, undertows, and rip tides kill around 100 beachgoers in the United States. These bodies of water seep away from the shore through deep channels and are very common on nearly any worldwide beach. They are often indistinguishable in the eyes of a swimmer and even an inexperienced water sports enthusiast. And most people don't know what to do to avoid and survive a rip current.

Submit Abstract - Pathology Utilitarian Conference


Do you have a latest findings on Pathology, Digital Pathology, submit your papers today to enroll & participate at the Pathology Utilitarian Conference & Digital Pathology Meetings.

Rapid antigen testing in COVID-19 responses


The value of rapid antigen testing of people (with or without COVID-19 symptoms) to reduce transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been discussed extensively ([ 1 ][1]–[ 5 ][2]) but remains a topic of policy debates ([ 6 ][3], [ 7 ][4]). Lateral flow devices (LFDs) to test for SARS-CoV-2 antigen are inexpensive, provide results in minutes, and are highly specific ([ 2 ][5]–[ 4 ][6]), and although less sensitive than reverse transcriptase polymerase chain reaction (RT-PCR) tests to detect viral RNA, they detect most cases with high viral load ([ 2 ][5], [ 3 ][7], [ 8 ][8]), which are likely the most infectious ([ 8 ][8], [ 9 ][9]). Successful mass testing relies on public trust, the social and organizational factors that support uptake, contact tracing, and adherence to quarantine. On page 635 of this issue, Pavelka et al. ([ 10 ][10]) report the substantial reduction in transmission that population-wide rapid antigen testing had, in combination with other measures, in Slovakia. Slovakia ran mass testing interventions from the last week of October to the second week of November 2020, with 65% of the target populations taking rapid antigen tests. Testing started in the four counties with the highest rates of infection, continued with national mass testing, then was followed up with more testing in high-prevalence areas. Nasopharyngeal swabs for the LFDs were taken by clinical staff, not self-administered. Sample quality and test accuracy are higher with tests taken by health professionals ([ 3 ][7]). Although the specific impact of Slovakia's mass testing could not be disentangled from the contribution of other concurrent control measures (including closure of secondary schools and restrictions on hospitality and indoor leisure activities), statistical modelling by Pavelka et al. estimated a 70% reduction in the prevalence of COVID-19 cases compared with unmitigated growth. The UK piloted mass testing in Liverpool in November 2020 after the city experienced the highest COVID-19 prevalence in the country. Slovakia applied more pressure on its citizens to get tested than did Liverpool, by requiring anyone not participating in mass testing to quarantine. The Liverpool testing uptake was consequently lower than Slovakia's, involving 25% of the population in 4 weeks. Liverpool's public health service valued the testing as an additional control measure, but impacts were limited by lack of support for those in socioeconomically deprived areas facing income loss from quarantine after a positive test ([ 2 ][5]): Test positivity rates were highest and testing uptake lowest in the most deprived areas ([ 2 ][5], [ 11 ][11]). Similar socioeconomic barriers were reported for test uptake among care home staff ([ 12 ][12]). This highlights the importance of addressing public perceptions of testing and support for low-income workers to quarantine when implementing mass testing. ![Figure][13] Predictive value of testing changes with prevalence When testing 100,000 individuals with a lateral flow device with 80% sensitivity and 99.9% specificity, the proportion of false-positive and false-negative test results will vary according to the prevalence of infection. GRAPHIC: V. ALTOUNIAN/ SCIENCE The predictive value of testing varies with the population prevalence of infection and phase of the epidemic curve ([ 7 ][4]). As the prevalence of SARS-CoV-2 infections decreases, the proportion of false-positive test results increases, whereas the number of false-negative test results decreases. For example, with 99.9% specificity (proportion of noninfections that the test rejects) and 80% sensitivity (proportion of infections that the test detects), the positive predictive value (proportion of people with a positive test result who are infected) is 89% when the prevalence is 1%, and it drops to 44% at 0.1% prevalence (55 in 100 positive test results are false). In absolute terms, however, if testing 100,000 people, these scenarios would result in 99 false positives (out of 899 positive results) and 100 false positives (out of 180 positive results) for 1% and 0.1% prevalence, respectively (see the figure). Confirmatory RT-PCR tests after a positive LFD test result was recently reintroduced by Public Health England because of both the low positive predictive values of testing at low prevalence of infection and the utility of reusing PCR samples for viral genetic sequencing in variant surveillance ([ 13 ][14]). The pilot in Slovakia was conducted while the prevalence was still high (3.9% in areas with the highest rate of infection). Rapid antigen testing was used as an additional tool to identify a substantial proportion of asymptomatic SARS-CoV-2–infected individuals, who were required to quarantine. Additionally, those who did not agree to take part in testing were required to quarantine, thus reducing the chance of transmission among those who were permitted to mix. At higher prevalence, more SARS-CoV-2 infections can be identified, but the proportion of false-negative tests is also higher, so the reliance on other control measures is greater. No matter what the prevalence, mass testing regimes can only properly be considered amid other health protection measures. By the end of the mass testing program in Slovakia, rapid antigen tests had identified more than 50,000 people without COVID-19 symptoms who were likely contagious with SARS-CoV-2. UK mass testing pilots in Liverpool and also in Wales that started at a similar time as the pilot in Slovakia, but with fewer pressures to take part, identified more than 4000 asymptomatic cases in the Cheshire and Merseyside region around Liverpool ([ 14 ][15]) and more than 700 in Wales ([ 15 ][16]). Although the testing technology was equivalent across Slovakia, England, and Wales, the interventions were different, spanning a variety of population prevalence, phases of the epidemic curve, surges of new variants, periods of lockdown, periods of reopening of large-scale social mixing, and targeting of testing. For example, the Liverpool project shifted in public messaging from “Let's All Get Tested” to “Test Before You Go” to “Testing Our Front Line” (for anyone having to leave home to go to work in lockdown). In places with low SARS-CoV-2 prevalence, mindful of the cumulative harms from COVID-19 restrictions, the emphasis is on restarting social and economic activities while minimizing infections. As research continues to clarify the impact of vaccines on SARS-CoV-2 transmission, there is a need to use rapid antigen testing as a part of comprehensive public health measures that reduce the risk of the virus escaping vaccine or natural immunity through avoidable transmission—for example, testing to secure workplaces and large events as societies reopen after lockdowns. Successful implementation, however, depends on public participation in testing and adequate support to quarantine. 1. [↵][17]1. Z. Kmietowicz , BMJ 372, n81 (2021). 10.1136/bmj.n81 [OpenUrl][18][FREE Full Text][19] 2. [↵][20]1. I. Buchan et al ., Liverpool COVID-19 community testing pilot. Interim evaluation report. 2020 (University of Liverpool, 2020); [][21]. 3. [↵][22]1. T. Peto et al ., medRxiv 10.1101/2021.01.13.21249563 (2021). 4. [↵][23]1. A. Crozier, 2. S. Rajan, 3. I. Buchan, 4. M. McKee , BMJ 372, 208 (2021). [OpenUrl][24] 5. [↵][25]1. M. J. Mina, 2. T. E. Peto, 3. M. García-Fiñana, 4. M. G. Semple, 5. I. E. Buchan , Lancet 397, 1425 (2021). [OpenUrl][26] 6. [↵][27]1. L. Y. W. Lee et al ., medRxiv 10.1101/2021.03.31.21254687 (2021). 7. [↵][28]1. R. W. Peeling, 2. P. Olliaro , Lancet 10.1016/S1473-3099(21)00152-3 (2021). 8. [↵][29]1. L. Y. W. Lee et al ., medRxiv 10.1101/2021.03.31.21254687 (2021). 9. [↵][30]1. M. Marks et al ., Lancet Infect. Dis. (2021). 10.1016/S1473-3099(20)30985-3 10. [↵][31]1. M. Pavelka et al ., Science 372, 635 (2021). [OpenUrl][32][Abstract/FREE Full Text][33] 11. [↵][34]1. M. A. Green et al ., medRxiv 10.1101/2021.02.10.21251256 (2021). 12. [↵][35]1. J. Tulloch et al ., SSRN 10.2139/ssrn.3822257 (2021). 13. [↵][36]1. S. Hopkins , Gov.UK 30 March 2021); . 14. [↵][37]NHS Cheshire and Merseyside, Combined Intelligence for Population Health Action (2021): [][38]. 15. [↵][39]1. K. Nnoaham , Evaluation of the lateral flow device testing pilot for COVID-19 in Merthyr Tydfil and the lower Cynon Valley (2021); [\_V2\_Whole%20Area%20Testing%20Evaluation%20Full%20Report%2020210325.pdf][40]. Acknowledgments: I. E.B. and M.G.-F. received grant funding from the UK Department of Health and Social Care to evaluate the Liverpool community testing pilot. I.E.B. reports fees from AstraZeneca as chief data scientist adviser through Liverpool University and a senior investigator grant from the National Institute for Health Research (NIHR) outside the submitted work. [1]: #ref-1 [2]: #ref-5 [3]: #ref-6 [4]: #ref-7 [5]: #ref-2 [6]: #ref-4 [7]: #ref-3 [8]: #ref-8 [9]: #ref-9 [10]: #ref-10 [11]: #ref-11 [12]: #ref-12 [13]: pending:yes [14]: #ref-13 [15]: #ref-14 [16]: #ref-15 [17]: #xref-ref-1-1 "View reference 1 in text" [18]: {openurl}?query=rft.jtitle%253DBMJ%26rft_id%253Dinfo%253Adoi%252F10.1136%252Fbmj.n81%26rft_id%253Dinfo%253Apmid%252F33436413%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [19]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiRlVMTCI7czoxMToiam91cm5hbENvZGUiO3M6MzoiYm1qIjtzOjU6InJlc2lkIjtzOjE1OiIzNzIvamFuMTJfNy9uODEiO3M6NDoiYXRvbSI7czoyMjoiL3NjaS8zNzIvNjU0Mi81NzEuYXRvbSI7fXM6ODoiZnJhZ21lbnQiO3M6MDoiIjt9 [20]: #xref-ref-2-1 "View reference 2 in text" [21]: [22]: #xref-ref-3-1 "View reference 3 in text" [23]: #xref-ref-4-1 "View reference 4 in text" [24]: {openurl}?query=rft.jtitle%253DBMJ%26rft.volume%253D372%26rft.spage%253D208%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [25]: #xref-ref-5-1 "View reference 5 in text" [26]: {openurl}?query=rft.jtitle%253DLancet%26rft.volume%253D397%26rft.spage%253D1425%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [27]: #xref-ref-6-1 "View reference 6 in text" [28]: #xref-ref-7-1 "View reference 7 in text" [29]: #xref-ref-8-1 "View reference 8 in text" [30]: #xref-ref-9-1 "View reference 9 in text" [31]: #xref-ref-10-1 "View reference 10 in text" [32]: {openurl}?query=rft.jtitle%253DScience%26rft.stitle%253DScience%26rft.aulast%253DPavelka%26rft.auinit1%253DM.%26rft.volume%253D372%26rft.issue%253D6542%26rft.spage%253D635%26rft.epage%253D641%26rft.atitle%253DThe%2Bimpact%2Bof%2Bpopulation-wide%2Brapid%2Bantigen%2Btesting%2Bon%2BSARS-CoV-2%2Bprevalence%2Bin%2BSlovakia%26rft_id%253Dinfo%253Adoi%252F10.1126%252Fscience.abf9648%26rft_id%253Dinfo%253Apmid%252F33758017%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [33]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6Mzoic2NpIjtzOjU6InJlc2lkIjtzOjEyOiIzNzIvNjU0Mi82MzUiO3M6NDoiYXRvbSI7czoyMjoiL3NjaS8zNzIvNjU0Mi81NzEuYXRvbSI7fXM6ODoiZnJhZ21lbnQiO3M6MDoiIjt9 [34]: #xref-ref-11-1 "View reference 11 in text" [35]: #xref-ref-12-1 "View reference 12 in text" [36]: #xref-ref-13-1 "View reference 13 in text" [37]: #xref-ref-14-1 "View reference 14 in text" [38]: [39]: #xref-ref-15-1 "View reference 15 in text" [40]:

Insights into black box of artificial intelligence


At many banks, insurance companies and online retailers, self-learning computer algorithms are used to make decisions that have major consequences for customers. However, just how algorithms in artificial intelligence (AI) represent and process their input data internally is largely unknown. They have published their results in the journal Neural Networks. 'What we call artificial intelligence today is based on deep artificial neural networks that roughly mimic human brain functions,' explains Dr. Patrick Krauss from the Cognitive Computational Neuroscience Group at FAU. As is the case in children learning their native language without being aware of the rules of grammar, AI algorithms can learn to make the right choice by independently comparing a large amount of input data.

Shift Technology raises $220M at a $1B+ valuation to fight insurance fraud with AI – TechCrunch


While incumbent insurance providers continue to get disrupted by startups like Lemonade, Alan, Clearcover, Pie and many others applying tech to rethink how to build a business around helping people and companies mitigate against risks with some financial security, one issue that has not disappeared is fraud. Today, a startup out of France is announcing some funding for AI technology that it has built for all insurance providers, old and new, to help them detect and prevent it. Shift Technology, which provides a set of AI-based SaaS tools to insurance companies to scan and automatically flag fraud scenarios across a range of use cases -- they include claims fraud, claims automation, underwriting, subrogation detection and financial crime detection -- has raised $220 million, money that it will be using both to expand in the property and casualty insurance market, the area where it is already strong, as well as to expand into health, and to double down on growing its business in the U.S. It also provides fraud detection for the travel insurance sector. This Series D is being led Advent International, via Advent Tech, with participation from Avenir and others. Accel, Bessemer Venture Partners, General Catalyst, and Iris Capital -- who were all part of Shift's Series C led by Bessemer in 2019 -- also participated.

Artificial intelligence to monitor water quality more effectively


Environmental protection agencies and industry bodies currently monitor the'trophic state' of water -- its biological productivity -- as an indicator of ecosystem health. Large clusters of microscopic algae, or phytoplankton, is called eutrophication and can turn into HABs, an indicator of pollution and which pose risk to human and animal health. HABs are estimated to cost the Scottish shellfish industry £1.4 million per year, and a single HAB event in Norway killed eight million salmon in 2019, with a direct value of over £74 million. Lead author Mortimer Werther, a PhD Researcher in Biological and Environmental Sciences at Stirling's Faculty of Natural Sciences, said: "Currently, satellite-mounted sensors, such as the Ocean and Land Instrument (OLCI), measure phytoplankton concentrations using an optical pigment called chlorophyll-a. However, retrieving chlorophyll-a across the diverse nature of global waters is methodologically challenging. "We have developed a method that bypasses the chlorophyll-a retrieval and enables us to estimate water health status directly from the signal measured at the remote sensor." Eutrophication and hypereutrophication is often caused by excessive nutrient input, for example from agricultural practices, waste discharge, or food and energy production. In impacted waters, HABs are common, and cyanobacteria may produce cyanotoxins which affect human and animal health. In many locations, these blooms are of concern to the finfish and shellfish aquaculture industries. Mr Werther said: "To understand the impact of climate change on freshwater aquatic environments such as lakes, many of which serve as drinking water resources, it is essential that we monitor and assess key environmental indicators, such as trophic status, on a global scale with high spatial and temporal frequency.

Scientists develop £2,700 'shoe camera' that detects obstacles

Daily Mail - Science & tech

Computer scientists have created an'intelligent' shoe that helps blind and visually-impaired people avoid multiple obstacles. The £2,700 (€3,200) product, called InnoMake, has been developed by Austrian company Tec-Innovation, backed by Graz University of Technology (TU Graz). The product consists of waterproof ultrasonic sensors attached to the tip of each shoe, which vibrate and make noises near obstacles. The closer the wearer gets to an obstacle, the faster the vibration becomes, much like a parking sensor on the back of a vehicle. Tec-Innovation is now working on embedding an AI-powered camera as part of a new iteration of the product.