Harvard Pathology Lab Develops Cancer-Detecting AI NVIDIA Blog

#artificialintelligence

Pathologists agreed just three-quarters of the time when diagnosing breast cancer from biopsy specimens, according to a recent study. The difficult, time-consuming process of analyzing tissue slides is why pathology is one of the most expensive departments in any hospital. Faisal Mahmood, assistant professor of pathology at Harvard Medical School and the Brigham and Women's Hospital, leads a team developing deep learning tools that combine a variety of sources -- digital whole slide histopathology data, molecular information, and genomics -- to aid pathologists and improve the accuracy of cancer diagnosis. Mahmood, who heads his eponymous Mahmood Lab in the Division of Computational Pathology at Brigham and Women's Hospital, spoke this week about this research at GTC DC, the Washington edition of our GPU Technology Conference. The variability in pathologists' diagnosis "can have dire consequences, because an uncertain determination can lead to more biopsies and unnecessary interventional procedures," he said in a recent interview.


Machine learning model provides rapid prediction of C. difficile infection risk: Model successfully applied to data from medical centers with different patient populations, electronic health record systems

#artificialintelligence

"Despite substantial efforts to prevent C. difficile infection and to institute early treatment upon diagnosis, rates of infection continue to increase," says Erica Shenoy, MD, PhD, of the MGH Division of Infectious Diseases, co-senior author of the study and assistant professor of Medicine at Harvard Medical School. "We need better tools to identify the highest risk patients so that we can target both prevention and treatment interventions to reduce further transmission and improve patient outcomes." The authors note that most previous models of C. difficile infection risk were designed as "one size fits all" approaches and included only a few risk factors, which limited their usefulness. Co-lead authors Jeeheh Oh, a U-M graduate student in Computer Science and Engineering, and Maggie Makar, MS, of MIT's Computer Science and Artificial Intelligence Laboratory and their colleagues took a "big data" approach that analyzed the whole electronic health record (EHR) to predict a patient's C. difficile risk throughout the course of hospitalization. Their method allows the development of institution-specific models that could accommodate different patient populations, different EHR systems and factors specific to each institution.


Where Does Consciousness Come From? Researchers Pinpoint The Physical Seat Of Sentience

International Business Times

For cognitive scientists, neurobiologists, and even some physicists, consciousness presents a unique and alluring problem. Although we know we are conscious, we know almost nothing about how it arises out of inanimate matter, and from where in the brain it comes from. Now, a team of researchers led by neurologists at Harvard Medical School's Beth Israel Deaconess Medical Center (BIDMC) believe it has discovered the physical foundations of consciousness. In a study published in the latest edition of the journal Neurology, the researchers pinpointed regions of the brain that appear to work together to create consciousness. "For the first time, we have found a connection between the brainstem region involved in arousal and regions involved in awareness, two prerequisites for consciousness," lead researcher Michael Fox from BIDMC, said in a statement.


AI achieves near-human efficiency in detecting cancer - CyberPsychology

#artificialintelligence

A research team from Beth Israel Deaconess Medical Center (BIDMC) and Harvard Medical School (HMS) has developed an artificial intelligence (AI) method, aimed at training computers to interpret pathology images. The team trained the computer to distinguish between cancerous tumor regions and normal regions based on a deep multi-layer convolutional network. In an objective evaluation in which researchers were given slides of lymph node cells and asked to determine whether or not they contained cancer, the team's automated diagnostic method proved accurate approximately 92 per cent of the time. One of the researchers, Aditya Khosla, said, "This nearly matched the success rate of a human pathologist, whose results were 96 percent accurate." "In our approach, we started with hundreds of training slides for which a pathologist has labeled regions of cancer and regions of normal cells," said Dayong Wang.


Paralyzed woman controls robot arm with mind

AITopics Original Links

Using only her thoughts, a Massachusetts woman paralyzed for 15 years directed a robotic arm to pick up a bottle of coffee and bring it to her lips, researchers report in the latest advance in harnessing brain waves to help disabled people. In the past year, similar stories have included a quadriplegic man in Pennsylvania who made a robotic arm give a high-five and stroke his girlfriend's hand, and a partially paralyzed man who remotely controlled a small robot that scooted around in a Swiss lab. But will the experimental brain-controlled technology ever help paralyzed people in everyday life? Experts in the technology and in rehabilitation medicine say they are optimistic that it will, once technology improves and the cost comes down. The latest report, which was published online Wednesday in the journal Nature, comes from scientists at Brown University, the Providence VA Medical Center in Rhode Island, Harvard Medical School and elsewhere.