Time filter

Source Type

News Article | April 25, 2017
Site: www.rdmag.com

Artificial intelligence models may be the new tool to help screen and evaluate efforts in tuberculosis-prevalent areas that often are plagued by limited access to radiologists. In TB-prone areas, there is a lack of trained radiologists qualified to screen and diagnose TB, which can be done using chest imaging techniques. However, the researchers used deep learning, a type of artificial intelligence that allows computers to complete tasks based on existing relationships of data. They modeled a deep convolutional neural network (DCNN) after brain structure to employ multiple hidden layers and patterns to classify images. “There is a tremendous interest in artificial intelligence, both inside and outside the field of medicine,” Dr. Paras Lakhani, study co-author and assistant professor of Radiology at Thomas Jefferson University Hospital (TJUH) in Philadelphia, said in a statement. “An artificial intelligence solution that could interpret radiographs for presence of TB in a cost-effective way could expand the reach of early identification and treatment in developing nations.” The researchers obtained 1,007 X-rays of patients with and without active TB, using multiple chest X-ray datasets from the National Institute of Health, the Belarus Tuberculosis Portal and TJUH. The datasets were split into three categories—training (68 percent), validation (17.1 percent) and test (14.9 percent). A pair of DCNN models—AlexNet and GoogLeNet—were used to learn from TB-positive and TB-negative X-rays. However, the best performance was a combination of the two models, which saw a 96 percent net accuracy. “The relatively high accuracy of the deep learning models is exciting,” Lakhani said. “The applicability for TB is important because it's a condition for which we have treatment options. It's a problem that can be solved.” The two models disagreed on 13 of the 150 test cases that were excluded from the training and validation datasets. For these 13 cases the researchers evaluated a workflow with an expert radiologist who was able to interpret the images and accurately diagnose 100 percent of the cases. “Application of deep learning to medical imaging is a relatively new field,” Lakhani said. “In the past, other machine learning approaches could only get to a certain accuracy level of around 80 percent. “However, with deep learning, there is potential for more accurate solutions, as this research has shown,” he added. TB is considered one of the 10 most common causes of death worldwide, according to the World Health Organization. In 2016, 1.8 million people died from TB, while 10.4 million total people fell ill from the disease. TB is particularly prevalent in sub-Saharan Africa and Southeast Asia. The research team now plans on improving the models with more training cases and other deep learning methods. “We hope to prospectively apply this in a real world environment,” Lakhani said. “An artificial intelligence solution using chest imaging can play a big role in tackling TB.” The study was published in Radiology.


News Article | April 22, 2017
Site: hosted2.ap.org

Scientists leave labs, take to streets to defend research (AP) — Scientists worldwide left their labs to take to the streets Saturday along with students and research advocates in pushing back against what they say are mounting attacks on science. The March for Science, coinciding with Earth Day, was set for more than 500 cities, anchored in Washington and to be joined by dozens of nonpartisan scientific professional societies in a turnout intended to combine political and how-to science demonstrations. Marchers in Geneva carried signs that said, "Science — A Candle in the Dark" and "Science is the Answer." In Berlin, several thousand people participated in a march from the one of the city's universities to the Brandenburg Gate landmark. "We need to make more of our decision based on facts again and less on emotions," said Meike Weltin, a doctorate student at an environmental institute near the capital. In London, physicists, astronomers, biologists and celebrities gathered for a march past the city's most celebrated research institutions. Supporters carried signs showing images of a double helix and chemical symbols. The protest was putting scientists, who generally shy away from advocacy and whose work depends on objective experimentation, into a more public position. Organizers portrayed the march as political but not partisan, promoting the understanding of science as well as defending it from various attacks, including proposed U.S. government budget cuts under President Donald Trump, such as a 20 percent slice of the National Institute of Health. Signs and banners readied for the Washington rally reflected anger, humor and obscure scientific references, such as a 7-year-old's "No Taxation Without Taxonomy." Taxonomy is the science of classifying animals, plants and other organisms. The sign that 9-year-old Sam Klimas held was red, handmade and personal: "Science saved my life." He had a form of brain cancer and has been healthy for eight years now. His mother, grandmother and brother traveled with him from Parkersburg, West Virginia. "I have to do everything I can to oppose the policies of this administration," said his grandmother, Susan Sharp. Scientists involved in the march said they were anxious about political and public rejection of established science such as climate change and the safety of vaccine immunizations. "Scientists find it appalling that evidence has been crowded out by ideological assertions," said Rush Holt, a former physicist and Democratic congressman who runs the American Association for the Advancement of Science. "It is not just about Donald Trump, but there is also no question that marchers are saying 'when the shoe fits." Judy Twigg, a public health professor at Virginia Commonwealth University, was aiming one of her signs at the president. The sign showed the periodic table of chemical elements and said: "You're out of your element Donny (Trump)." For Twigg, who was wearing a T-shirt that said "Science is not a liberal conspiracy," research is a matter of life and death on issues such as polio and child mortality. Despite saying the march was not partisan, Holt acknowledged it was only dreamed up at the Women's March on Washington, a day after Trump's inauguration on Jan. 20. "It's not about the current administration. The truth is we should have been marching for science 30 years ago, 20 years, 10 years ago," said co-organizer and public health researcher Caroline Weinberg. "The current (political) situation took us from kind of ignoring science to blatantly attacking it. And that seems to be galvanizing people in a way it never has before. ... It's just sort of relentless attacks on science." "The scientific method was developed to be nonpartisan and objective," Weinberg said. "It should be embraced by both parties." Christine McEntee, executive director of the American Geophysical Union, a global professional organization of earth and space scientists, cited concerns by scientists and threats to research as a result of elections in the U.S. and other countries. Threats to science are heightened in Turkey and elsewhere in Europe, said McEntee, who planned to march with geophysical scientists in Vienna, Austria. Dr. Mona Hanna-Attisha, who exposed the dangerous lead levels in the drinking water and children's blood in Flint, Michigan, planned to march in Washington and speak to the crowd. "It's risky, but that's when we make advancements when we take risks ... for our heart rates to go up, to be a little anxious and scared and uncomfortable," she said before the event. Associated Press writer Markus Schreiber in Berlin contributed to this report.


News Article | May 2, 2017
Site: www.cnet.com

Technically Incorrect offers a slightly twisted take on the tech that's taken over our lives. President Trump has been tweeting about how his version of health insurance will cover everyone, even those with pre-existing conditions. Jimmy Kimmel thinks it's insane that a parent has to worry whether they have enough money to save their child's life. Indeed, he wept through a 13-minute monologue on Monday as he told the story of his newborn son, Billy. Very soon after he was born on April 21, Billy turned a little purple. At first, Kimmel himself didn't notice. It took a nurse at Cedar-Sinai Hospital in LA to declare that something might be wrong. What followed was a series of doctors getting involved and surgery for Billy at the Children's Hospital in Los Angeles. Kimmel recounted the story of his son's life being saved -- with all the emotion of a parent. He tried to find space for humor. Referring to a long-time meme involving his (fake) feud with Matt Damon, he said: "Even that son of a bitch Matt Damon sent flowers." After minutes of thanks, Kimmel turned to the political nuances of his experience. "President Trump last month proposed a $6 billion cut in funding to the National Institute of Health and thank God our congressmen made a deal last night to not go along with that. They actually increased funding by $2 billion." He continued: "More than 40 percent of those who would have been affected by those cuts are children." "We were brought up to believe that we live in the greatest country in the world, but until a few years ago millions and millions of us had no access to health insurance at all," he said. "Before 2014, if you were born with congenital heart disease, like my son was, there was a good chance you'd never be able to get health insurance because you had a pre-existing condition." At this point, he began to break down. He said this was above politics. This was something all Americans should agree on. The states are supposed to be united. ABC released video of Kimmel's emotional monologue to YouTube, even before it aired on the west coast. Soon, it had amassed more than 100,000 viewers. As the battle for universal healthcare continues, and as scientists march to protest against any cuts in their funding, it's a fight for what some might see as basic humanity. It's harder for a society that has individualism at its core to accept the notion of anything universal. For Kimmel, however, the argument is simple: "No parent should ever have to decide if they can afford to save their child's life." Tech Enabled: CNET chronicles tech's role in providing new kinds of accessibility. Technically Literate: Original works of short fiction with unique perspectives on tech, exclusively on CNET.


News Article | April 24, 2017
Site: globenewswire.com

NEW YORK, April 24, 2017 (GLOBE NEWSWIRE) -- Dr. Matilde Inglese, Associate Professor of Neurology, Radiology and Neuroscience at the Icahn School of Medicine at Mount Sinai has been selected to join the Education Board at the American Health Council. She will be sharing her knowledge and expertise on Neuroscience, Neuroimaging and Multiple Sclerosis.   As an Internationally recognized expert in the field of neuroimaging in demyelinating disorders, Dr. Matilde Inglese offers valuable insight in her role as the Associate Professor of Neurology, Radiology and Neuroscience at the Icahn School of Medicine at Mount Sinai for over fifteen years, Dr. Inglese’s day-to-day responsibilities include clinical research of Multiple Sclerosis patients using neuroimaging techniques. With support from the National Institute of Health, her research is geared towards the development and application of new structural and functional magnetic resonance imaging techniques at high and ultra-high field strength to analyze neurological diseases. Upon receipt of a medical degree magna cum laude from the University of Genoa, Italy in 1992, Dr. Inglese completed her residency at the University of Genoa in 1998.  In 1999, she completed a post-doctoral fellowship in Neuroimaging at San Raffaele Hospital, Milan, Italy. To further develop her professional career, she completed a fellowship in Radiology at the New York University in 2002. In 2004, Dr. Inglese obtained her PhD from the University of Genoa. Prior to her role as an Associate Professor of Neurology, Radiology and Neuroscience, at the Icahn School of Medicine at Mount Sinai in New York, Dr. Inglese joined the NYU faculty as an Associate Professor of Radiology, Neurology and Biomedical Imaging at New York University in 2011. Her interest in the field of Neurology began while in Italy, when she felt that very little was known about the pathophysiology of multiple sclerosis and the available treatments were only partially efficacious or not efficacious at all in subgroups of patients. Dr. Inglese thought that understanding how the disease progressed and why some patients have benefit from treatment and other not would eventually lead to improvement of patients’ care and quality of life. Dr. Inglese has authored over a hundred and fifty publications and received multiple grant funding from the National Institute for Neurological Disorders and Stroke, the National Multiple Sclerosis Society and the Congressionally Directed Medical Research Program in Multiple Sclerosis. Her publications have been featured in peer-reviewed journals such as the Lancet, Lancet Neurology, Annals of Neurology, Brain and Neurology. She has served on the editorial board of peer-reviewed journals and on grant advisory panels for the National Institute of Health, the National Multiple Sclerosis Society and for several international funding agencies. Dr. Inglese maintains affiliations with The American Academy of Neurology, International Society of Magnetic Resonance in Medicine, and the National Institute of Health study sections. In her free time, Dr. Inglese enjoys reading, bicycling and swimming. Her charitable organizations involvement includes participating in marathons for Multiple Sclerosis, completing peer reviews for the MS Foundation, and volunteering with MS Hope for a Cure. Considering the future, Dr. Inglese hopes to understand the pathophysiology of Multiple Sclerosis progression and contribute to provide new and effective biomarkers to monitor disease progression and response to treatment.


News Article | April 24, 2017
Site: globenewswire.com

NEW YORK, April 24, 2017 (GLOBE NEWSWIRE) -- Dr. Matilde Inglese, Associate Professor of Neurology, Radiology and Neuroscience at the Icahn School of Medicine at Mount Sinai has been selected to join the Education Board at the American Health Council. She will be sharing her knowledge and expertise on Neuroscience, Neuroimaging and Multiple Sclerosis.   As an Internationally recognized expert in the field of neuroimaging in demyelinating disorders, Dr. Matilde Inglese offers valuable insight in her role as the Associate Professor of Neurology, Radiology and Neuroscience at the Icahn School of Medicine at Mount Sinai for over fifteen years, Dr. Inglese’s day-to-day responsibilities include clinical research of Multiple Sclerosis patients using neuroimaging techniques. With support from the National Institute of Health, her research is geared towards the development and application of new structural and functional magnetic resonance imaging techniques at high and ultra-high field strength to analyze neurological diseases. Upon receipt of a medical degree magna cum laude from the University of Genoa, Italy in 1992, Dr. Inglese completed her residency at the University of Genoa in 1998.  In 1999, she completed a post-doctoral fellowship in Neuroimaging at San Raffaele Hospital, Milan, Italy. To further develop her professional career, she completed a fellowship in Radiology at the New York University in 2002. In 2004, Dr. Inglese obtained her PhD from the University of Genoa. Prior to her role as an Associate Professor of Neurology, Radiology and Neuroscience, at the Icahn School of Medicine at Mount Sinai in New York, Dr. Inglese joined the NYU faculty as an Associate Professor of Radiology, Neurology and Biomedical Imaging at New York University in 2011. Her interest in the field of Neurology began while in Italy, when she felt that very little was known about the pathophysiology of multiple sclerosis and the available treatments were only partially efficacious or not efficacious at all in subgroups of patients. Dr. Inglese thought that understanding how the disease progressed and why some patients have benefit from treatment and other not would eventually lead to improvement of patients’ care and quality of life. Dr. Inglese has authored over a hundred and fifty publications and received multiple grant funding from the National Institute for Neurological Disorders and Stroke, the National Multiple Sclerosis Society and the Congressionally Directed Medical Research Program in Multiple Sclerosis. Her publications have been featured in peer-reviewed journals such as the Lancet, Lancet Neurology, Annals of Neurology, Brain and Neurology. She has served on the editorial board of peer-reviewed journals and on grant advisory panels for the National Institute of Health, the National Multiple Sclerosis Society and for several international funding agencies. Dr. Inglese maintains affiliations with The American Academy of Neurology, International Society of Magnetic Resonance in Medicine, and the National Institute of Health study sections. In her free time, Dr. Inglese enjoys reading, bicycling and swimming. Her charitable organizations involvement includes participating in marathons for Multiple Sclerosis, completing peer reviews for the MS Foundation, and volunteering with MS Hope for a Cure. Considering the future, Dr. Inglese hopes to understand the pathophysiology of Multiple Sclerosis progression and contribute to provide new and effective biomarkers to monitor disease progression and response to treatment.


News Article | April 25, 2017
Site: www.rdmag.com

Artificial intelligence models may be the new tool to help screen and evaluate efforts in tuberculosis-prevalent areas that often are plagued by limited access to radiologists. In TB-prone areas, there is a lack of trained radiologists qualified to screen and diagnose TB, which can be done using chest imaging techniques. However, the researchers used deep learning, a type of artificial intelligence that allows computers to complete tasks based on existing relationships of data. They modeled a deep convolutional neural network (DCNN) after brain structure to employ multiple hidden layers and patterns to classify images. “There is a tremendous interest in artificial intelligence, both inside and outside the field of medicine,” Dr. Paras Lakhani, study co-author and assistant professor of Radiology at Thomas Jefferson University Hospital (TJUH) in Philadelphia, said in a statement. “An artificial intelligence solution that could interpret radiographs for presence of TB in a cost-effective way could expand the reach of early identification and treatment in developing nations.” The researchers obtained 1,007 X-rays of patients with and without active TB, using multiple chest X-ray datasets from the National Institute of Health, the Belarus Tuberculosis Portal and TJUH. The datasets were split into three categories—training (68 percent), validation (17.1 percent) and test (14.9 percent). A pair of DCNN models—AlexNet and GoogLeNet—were used to learn from TB-positive and TB-negative X-rays. However, the best performance was a combination of the two models, which saw a 96 percent net accuracy. “The relatively high accuracy of the deep learning models is exciting,” Lakhani said. “The applicability for TB is important because it's a condition for which we have treatment options. It's a problem that can be solved.” The two models disagreed on 13 of the 150 test cases that were excluded from the training and validation datasets. For these 13 cases the researchers evaluated a workflow with an expert radiologist who was able to interpret the images and accurately diagnose 100 percent of the cases. “Application of deep learning to medical imaging is a relatively new field,” Lakhani said. “In the past, other machine learning approaches could only get to a certain accuracy level of around 80 percent. “However, with deep learning, there is potential for more accurate solutions, as this research has shown,” he added. TB is considered one of the 10 most common causes of death worldwide, according to the World Health Organization. In 2016, 1.8 million people died from TB, while 10.4 million total people fell ill from the disease. TB is particularly prevalent in sub-Saharan Africa and Southeast Asia. The research team now plans on improving the models with more training cases and other deep learning methods. “We hope to prospectively apply this in a real world environment,” Lakhani said. “An artificial intelligence solution using chest imaging can play a big role in tackling TB.” The study was published in Radiology.


News Article | April 24, 2017
Site: globenewswire.com

NEW YORK, April 24, 2017 (GLOBE NEWSWIRE) -- Dr. Matilde Inglese, Associate Professor of Neurology, Radiology and Neuroscience at the Icahn School of Medicine at Mount Sinai has been selected to join the Education Board at the American Health Council. She will be sharing her knowledge and expertise on Neuroscience, Neuroimaging and Multiple Sclerosis.   As an Internationally recognized expert in the field of neuroimaging in demyelinating disorders, Dr. Matilde Inglese offers valuable insight in her role as the Associate Professor of Neurology, Radiology and Neuroscience at the Icahn School of Medicine at Mount Sinai for over fifteen years, Dr. Inglese’s day-to-day responsibilities include clinical research of Multiple Sclerosis patients using neuroimaging techniques. With support from the National Institute of Health, her research is geared towards the development and application of new structural and functional magnetic resonance imaging techniques at high and ultra-high field strength to analyze neurological diseases. Upon receipt of a medical degree magna cum laude from the University of Genoa, Italy in 1992, Dr. Inglese completed her residency at the University of Genoa in 1998.  In 1999, she completed a post-doctoral fellowship in Neuroimaging at San Raffaele Hospital, Milan, Italy. To further develop her professional career, she completed a fellowship in Radiology at the New York University in 2002. In 2004, Dr. Inglese obtained her PhD from the University of Genoa. Prior to her role as an Associate Professor of Neurology, Radiology and Neuroscience, at the Icahn School of Medicine at Mount Sinai in New York, Dr. Inglese joined the NYU faculty as an Associate Professor of Radiology, Neurology and Biomedical Imaging at New York University in 2011. Her interest in the field of Neurology began while in Italy, when she felt that very little was known about the pathophysiology of multiple sclerosis and the available treatments were only partially efficacious or not efficacious at all in subgroups of patients. Dr. Inglese thought that understanding how the disease progressed and why some patients have benefit from treatment and other not would eventually lead to improvement of patients’ care and quality of life. Dr. Inglese has authored over a hundred and fifty publications and received multiple grant funding from the National Institute for Neurological Disorders and Stroke, the National Multiple Sclerosis Society and the Congressionally Directed Medical Research Program in Multiple Sclerosis. Her publications have been featured in peer-reviewed journals such as the Lancet, Lancet Neurology, Annals of Neurology, Brain and Neurology. She has served on the editorial board of peer-reviewed journals and on grant advisory panels for the National Institute of Health, the National Multiple Sclerosis Society and for several international funding agencies. Dr. Inglese maintains affiliations with The American Academy of Neurology, International Society of Magnetic Resonance in Medicine, and the National Institute of Health study sections. In her free time, Dr. Inglese enjoys reading, bicycling and swimming. Her charitable organizations involvement includes participating in marathons for Multiple Sclerosis, completing peer reviews for the MS Foundation, and volunteering with MS Hope for a Cure. Considering the future, Dr. Inglese hopes to understand the pathophysiology of Multiple Sclerosis progression and contribute to provide new and effective biomarkers to monitor disease progression and response to treatment.


News Article | April 24, 2017
Site: globenewswire.com

NEW YORK, April 24, 2017 (GLOBE NEWSWIRE) -- Dr. Matilde Inglese, Associate Professor of Neurology, Radiology and Neuroscience at the Icahn School of Medicine at Mount Sinai has been selected to join the Education Board at the American Health Council. She will be sharing her knowledge and expertise on Neuroscience, Neuroimaging and Multiple Sclerosis.   As an Internationally recognized expert in the field of neuroimaging in demyelinating disorders, Dr. Matilde Inglese offers valuable insight in her role as the Associate Professor of Neurology, Radiology and Neuroscience at the Icahn School of Medicine at Mount Sinai for over fifteen years, Dr. Inglese’s day-to-day responsibilities include clinical research of Multiple Sclerosis patients using neuroimaging techniques. With support from the National Institute of Health, her research is geared towards the development and application of new structural and functional magnetic resonance imaging techniques at high and ultra-high field strength to analyze neurological diseases. Upon receipt of a medical degree magna cum laude from the University of Genoa, Italy in 1992, Dr. Inglese completed her residency at the University of Genoa in 1998.  In 1999, she completed a post-doctoral fellowship in Neuroimaging at San Raffaele Hospital, Milan, Italy. To further develop her professional career, she completed a fellowship in Radiology at the New York University in 2002. In 2004, Dr. Inglese obtained her PhD from the University of Genoa. Prior to her role as an Associate Professor of Neurology, Radiology and Neuroscience, at the Icahn School of Medicine at Mount Sinai in New York, Dr. Inglese joined the NYU faculty as an Associate Professor of Radiology, Neurology and Biomedical Imaging at New York University in 2011. Her interest in the field of Neurology began while in Italy, when she felt that very little was known about the pathophysiology of multiple sclerosis and the available treatments were only partially efficacious or not efficacious at all in subgroups of patients. Dr. Inglese thought that understanding how the disease progressed and why some patients have benefit from treatment and other not would eventually lead to improvement of patients’ care and quality of life. Dr. Inglese has authored over a hundred and fifty publications and received multiple grant funding from the National Institute for Neurological Disorders and Stroke, the National Multiple Sclerosis Society and the Congressionally Directed Medical Research Program in Multiple Sclerosis. Her publications have been featured in peer-reviewed journals such as the Lancet, Lancet Neurology, Annals of Neurology, Brain and Neurology. She has served on the editorial board of peer-reviewed journals and on grant advisory panels for the National Institute of Health, the National Multiple Sclerosis Society and for several international funding agencies. Dr. Inglese maintains affiliations with The American Academy of Neurology, International Society of Magnetic Resonance in Medicine, and the National Institute of Health study sections. In her free time, Dr. Inglese enjoys reading, bicycling and swimming. Her charitable organizations involvement includes participating in marathons for Multiple Sclerosis, completing peer reviews for the MS Foundation, and volunteering with MS Hope for a Cure. Considering the future, Dr. Inglese hopes to understand the pathophysiology of Multiple Sclerosis progression and contribute to provide new and effective biomarkers to monitor disease progression and response to treatment.

Loading National Institute of Health collaborators
Loading National Institute of Health collaborators