Connect with us

Bioengineer

Computers predict people’s tastes in art

New study offers insight into how people make aesthetic judgmentsCredit: Smithsonian American Art Museum, Gift of Mrs. Joseph Schillinger Do

Published

on

Credit: Smithsonian American Art Museum, Gift of Mrs. Joseph Schillinger

Do you like the thick brush strokes and soft color palettes of an impressionist painting such as those by Claude Monet? Or do you prefer the bold colors and abstract shapes of a Rothko? Individual art tastes have a certain mystique to them, but now a new Caltech study shows that a simple computer program can accurately predict which paintings a person will like.

The new study, appearing in the journal Nature Human Behaviour, utilized Amazon’s crowdsourcing platform Mechanical Turk to enlist more than 1,500 volunteers to rate paintings in the genres of impressionism, cubism, abstract, and color field. The volunteers’ answers were fed into a computer program and then, after this training period, the computer could predict the volunteers’ art preferences much better than would happen by chance.

“I used to think the evaluation of art was personal and subjective, so I was surprised by this result,” says lead author Kiyohito Iigaya, a postdoctoral scholar who works in the laboratory of Caltech professor of psychology John O’Doherty.

The findings not only demonstrated that computers can make these predictions but also led to a new understanding about how people judge art.

“The main point is that we are gaining an insight into the mechanism that people use to make aesthetic judgments,” says O’Doherty. “That is, that people appear to use elementary image features and combine over them. That’s a first step to understanding how the process works.”

In the study, the team programmed the computer to break a painting’s visual attributes down into what they called low-level features–traits like contrast, saturation, and hue–as well as high-level features, which require human judgment and include traits such as whether the painting is dynamic or still.

“The computer program then estimates how much a specific feature is taken into account when making a decision about how much to like a particular piece of art,” explains Iigaya. “Both the low- and high-level features are combined together when making these decisions. Once the computer has estimated that, then it can successfully predict a person’s liking for another previously unseen piece of art.”

The researchers also discovered that the volunteers tended to cluster into three general categories: those who like paintings with real-life objects, such as an impressionist painting; those who like colorful abstract paintings, such as a Rothko; and those who like complex paintings, such as Picasso’s cubist portraits. The majority of people fell into the first “real-life object” category. “Many people liked the impressionism paintings,” says Iigaya.

What is more, the researchers found that they could also train a deep convolutional neural network (DCNN) to learn to predict the volunteer’s art preferences with a similar level of accuracy. A DCNN is a type of machine-learning program, in which a computer is fed a series of training images so that it can learn to classify objects, such as cats versus dogs. These neural networks have units that are connected to each other like neurons in a brain. By changing the strength of the connection of one unit to another, the network can “learn.”

In this case, the deep-learning approach did not include any of the selected low- or high-level visual features used in the first part of the study, so the computer had to “decide” what features to analyze on its own.

“In deep-neural-network models, we do not actually know exactly how the network is solving a particular task because the models learn by themselves much like real brains do,” explains Iigaya. “It can be very mysterious, but when we looked inside the neural network, we were able to tell that it was constructing the same feature categories we selected ourselves.” These results hint at the possibility that features used for determining aesthetic preference might emerge naturally in a brain-like architecture.

“We are now actively looking at whether this is indeed the case by looking at people’s brains while they make these same types of decisions,” says O’Doherty.

In another part of the study, the researchers also demonstrated that their simple computer program, which had already been trained on art preferences, could accurately predict which photos volunteers would like. They showed the volunteers photographs of swimming pools, food, and other scenes, and saw similar results to those involving paintings. Additionally, the researchers showed that reversing the order also worked: after first training volunteers on photos, they could use the program to accurately predict the subjects’ art preferences.

While the computer program was successful at predicting the volunteers’ art preferences, the researchers say there is still more to learn about the nuances that go into any one individual’s taste.

“There are aspects of preferences unique for a given individual that we have not succeeded in explaining using this method,” says O’Doherty. “This more idiosyncratic component may relate to semantic features, or the meaning of a painting, past experiences, and other individual personal traits that might influence valuation. It still may be possible to identify and learn about those features in a computer model, but to do so will involve a more detailed study of each individual’s preferences in a way that may not generalize across individuals as we found here.”

###

The study, titled, “Aesthetic preference for art can be predicted from a mixture of low- and high-level visual features,” was funded by the National Institute of Mental Health (through Caltech’s Conte Center for the Neurobiology of Social Decision Making), the National Institute on Drug Abuse, the Japan Society for Promotion of Science, the Swartz Foundation, the Suntory Foundation, and the William H. and Helen Lang Summer Undergraduate Research Fellowship. Other Caltech authors include Sanghyun Yi, Iman A. Wahle (BS ’20), and Koranis Tanwisuth, who is now a graduate student at UC Berkeley.

“I used to think the evaluation of art was personal and subjective, so I was surprised by this result,” says lead author Kiyohito Iigaya, a postdoctoral scholar who works in the laboratory of Caltech professor of psychology John O’Doherty.

Source: https://bioengineer.org/computers-predict-peoples-tastes-in-art/

Bioengineer

Healing skin ischemia-reperfusion injuries with interleukin-36 receptor antagonists

Ischemia, which in modern Latin means, “staunching of blood,” is a medical condition in which the blood supply is cut

Published

on

Ischemia, which in modern Latin means, “staunching of blood,” is a medical condition in which the blood supply is cut off to different parts of the body. In patients who are bed-ridden, ischemia can manifest as pressure ulcers. Else, it could be the Raynaud’s phenomenon in someone under severe stress. This condition can be rescued by blood reperfusion to the affected areas. However, the latter carries the risk of injuries known medically as ischemia-reperfusion (I/R) injuries.

Ischemia, which in modern Latin means, “staunching of blood,” is a medical condition in which the blood supply is cut off to different parts of the body. In patients who are bed-ridden, ischemia can manifest as pressure ulcers. Else, it could be the Raynaud’s phenomenon in someone under severe stress. This condition can be rescued by blood reperfusion to the affected areas. However, the latter carries the risk of injuries known medically as ischemia-reperfusion (I/R) injuries.

Skin-based I/R injuries can be exacerbated by inherited immunological mechanisms, for instance in patients who are otherwise showing signs of slow wound healing. To understand the immunological mechanisms underlying the development of this condition better, scientists from Japan, building on previous studies, decided to narrow down their investigation to interleukin-36 receptor antagonist (IL-36Ra), a protein that plays a pivotal immunomodulatory role in wound healing.

Speaking about the motivation behind their research, Mr. Yoshihito Tanaka from Fujita Health University School of Medicine, Japan, who led the team of scientists in the investigation, explains, “We wanted to understand the immunological mechanisms involved in the healing of wounds from cutaneous ischemia-reperfusion injuries, such as pressure ulcers and Raynaud’s phenomenon, to narrow down possible therapeutic targets. Drawing from experience, IL-36Ra appeared to be a promising candidate for kickstarting our investigation.”

Accordingly, Mr. Tanaka worked with his team to understand how deficiency of IL-36Ra affects wound healing in cutaneous I/R injuries. For this, the scientists used mice knocked out for the receptor. Also, they induced cutaneous I/R injuries in knockout and wildtype control mice. Subsequently, they studied corresponding immunological responses in both groups of animals, including the time required for wound healing, infiltration of neutrophils/macrophages (key immune cells) to the site of the wounds, apoptotic skin cells, and activation of other unwanted immunological defense mechanisms. Their findings have been published as a research article in the Journal of The European Academy of Dermatology and Venereology.

The team, comprising Dr. Kazumitsu Sugiura and Dr. Yohei Iwata from Fujita Health University School of Medicine, among others, was able to pinpoint important results. The scientists found that the absence of IL-36Ra, indeed, significantly slows down wound healing in cutaneous I/R injuries, through increased apoptosis, or ‘suicide’ of useful skins cells, excessive recruitment of inflammatory cells, and employment of unnecessary proinflammatory mechanisms. Additionally, they demonstrated the role of Cl-amidine, a protein-arginine deiminase inhibitor as effective in normalizing exacerbated I/R injury in IL-36Ra mice. Based on these observations, the scientists assert their findings are the first conclusive report of the involvement of IL-36Ra in cutaneous I/R injury.

The scientists are positive that they have identified a stalwart therapeutic candidate against cutaneous I/R injuries in IL-36Ra. As Mr. Tanaka optimistically adds, “Our research may lead to the development of therapeutic agents for wound healing of various other refractory skin diseases too.”

The quest for novel therapeutic targets in skin wound healing might just have been empowered by these findings of the team and the future indeed looks brighter for alleviating the painful burden of cutaneous I/R injuries.

***

Reference

DOI: https://doi.org/10.1111/jdv.17767

About Fujita Health University

Fujita Health University is a private university situated in Toyoake, Aichi, Japan. It was founded in 1964 and houses one of the largest teaching university hospitals in Japan in terms of the number of beds. With over 900 faculty members, the university is committed to providing various academic opportunities to students internationally. Fujita Health University has been ranked eighth among all universities and second among all private universities in Japan in the 2020 Times Higher Education (THE) World University Rankings. THE University Impact Rankings 2019 visualized university initiatives for sustainable development goals (SDGs). For the “good health and well-being” SDG, Fujita Health University was ranked second among all universities and number one among private universities in Japan. The university will also be the first Japanese university to host the “THE Asia Universities Summit” in June 2021. The university’s founding philosophy is “Our creativity for the people (DOKUSOU-ICHIRI),” which reflects the belief that, as with the university’s alumni and alumnae, current students also unlock their future by leveraging their creativity.

Website: https://www.fujita-hu.ac.jp/en/index.html

About Mr. Yoshihito Tanaka from Fujita Health University

Mr. Yoshihito Tanaka is a graduate student at the Department of Dermatology of Fujita Health University School of Medicine. Mr. Tanaka extensively studies the immunological mechanisms behind dermatological conditions, specifically with animal models. He has over 11 publications to his credit, in reputed international journals, with over 16 citations.

Journal

Journal of the European Academy of Dermatology and Venereology

Method of Research

Experimental study

Subject of Research

Animals

Article Title

Cutaneous ischemia-reperfusion injury is exacerbated by IL-36 receptor antagonist deficiency

Article Publication Date

26-Oct-2021

COI Statement

The authors declare none.

Source: https://bioengineer.org/healing-skin-ischemia-reperfusion-injuries-with-interleukin-36-receptor-antagonists/

Continue Reading

Bioengineer

Social inequities perpetuate breastfeeding disparities for Black women

Philadelphia, November 8, 2021 – As Black women continue to have the lowest breastfeeding initiation and duration rates in the

Published

on

Philadelphia, November 8, 2021 – As Black women continue to have the lowest breastfeeding initiation and duration rates in the United States, researchers examined factors associated with breastfeeding disparities and inequities through the lens of critical race theory and the social-ecological model in a new Perspective in the Journal of Nutrition Education and Behavior, published by Elsevier.

Philadelphia, November 8, 2021 – As Black women continue to have the lowest breastfeeding initiation and duration rates in the United States, researchers examined factors associated with breastfeeding disparities and inequities through the lens of critical race theory and the social-ecological model in a new Perspective in the Journal of Nutrition Education and Behavior, published by Elsevier.

In the United States, there has been a heightened recognition of the health and social disparities that continuously impact Black, Indigenous, and People of Color (BIPOC) communities. Among these health disparities is the low rate of breastfeeding among Black mothers, despite the association between positive health outcomes and breastfeeding. A general lack of acceptance about breastfeeding within the Black American culture and American culture; lack of neighborhood resources like primary care, social cohesion, and safety; and experiences of racism and implicit bias by healthcare providers have been identified as contributing factors to the low breastfeeding rates among Black women.

“The reality is that right now the breastfeeding rates in the United States are not improving, and [Black women] have the lowest rates of breastfeeding for any race or ethnicity in the US. Unfortunately, the breastfeeding rates between Black infants and White infants are widening, so what we’re doing right now is not working,” said Melissa Petit, MN PH, BA, RN, IBCLC, College of Nursing, Washington State University, Spokane, WA, USA.

This Perspective encourages healthcare providers and nurses to address breastfeeding disparities among Black women in the US from the individual level to the societal level.

“In clinical practice, we need to examine the roadblocks or barriers to fostering inclusion and equity in healthcare for all women. We need to identify our own assumptions about race, understand and acknowledge our own biases and perceptions, and challenge our own thoughts to identify our own microaggressions by reading about microinequities and microaggressions. We need to be active practitioners of trauma informed care. We need to realize trauma impacts patients and recognize the signs and symptoms of trauma whether it be historical or structural or personal, and we need to respond by implementing care structures for all women by acknowledging our shared humanity and challenges in that shared humanity,” commented coauthor Denise Smart, DrPH, MPH, BSN, RN, College of Nursing, Washington State University, Spokane, WA, USA.

Journal

Journal of Nutrition Education and Behavior

DOI

10.1016/j.jneb.2021.08.013

Subject of Research

People

Article Title

Examination of Factors That Contribute to Breastfeeding Disparities and Inequities for Black Women in the US

Article Publication Date

8-Nov-2021

Source: https://bioengineer.org/social-inequities-perpetuate-breastfeeding-disparities-for-black-women/

Continue Reading

Bioengineer

SNMMI Image of the Year: PET imaging measures cognitive impairment in COVID-19 patients

Credit: G Blazhenets et al., Department of Nuclear Medicine, Medical Center – University of Freiburg, Faculty of Medicine, University of

Published

on

Credit: G Blazhenets et al., Department of Nuclear Medicine, Medical Center – University of Freiburg, Faculty of Medicine, University of Freiburg.

Reston, VA–The effects of COVID-19 on the brain can be accurately measured with positron emission tomography (PET), according to research presented at the Society of Nuclear Medicine and Molecular Imaging (SNMMI) 2021 Annual Meeting. In the study, newly diagnosed COVID-19 patients, who required inpatient treatment and underwent PET brain scans, were found to have deficits in neuronal function and accompanying cognitive impairment, and in some, this impairment continued six months after their diagnosis. The detailed depiction of areas of cognitive impairment, neurological symptoms and comparison of impairment over a six-month time frame has been selected as SNMMI’s 2021 Image of the Year.

Each year, SNMMI chooses an image that best exemplifies the most promising advances in the field of nuclear medicine and molecular imaging. The state-of-the-art technologies captured in these images demonstrate the capacity to improve patient care by detecting disease, aiding diagnosis, improving clinical confidence, and providing a means of selecting appropriate treatments. This year, the SNMMI Henry N. Wagner, Jr., Image of the Year was chosen from more than 1,280 abstracts submitted to the meeting and voted on by reviewers and the society leadership.

“As the SARS-CoV-2 pandemic proceeds, it has become increasingly clear that neurocognitive long-term consequences occur not only in severe COVID-19 cases, but in mild and moderate cases as well. Neurocognitive deficits like impaired memory, disturbed concentration and cognitive problems may persist well beyond the acute phase of the disease,” said Ganna Blazhenets, PhD, a post-doctoral researcher in Medical Imaging at the University Medical Center Freiburg, in Freiburg, Germany.

To study cognitive impairment associated with COVID-19, researchers carried out a prospective study on recently diagnosed COVID-19 patients who required inpatient treatment for non-neurological complaints. A cognitive assessment was performed, followed by imaging with 18F-FDG PET if at least two new neurological symptoms were present. By comparing COVID-19 patients to controls, the Freiburg group established a COVID-19-related covariance pattern of brain metabolism with most prominent decreases in cortical regions. Across patients, the expression of this pattern showed a very high correlation with the patients’ cognitive performance.

Follow-up PET imaging was performed six months after the initial COVID-19 diagnosis. Imaging results showed a significant improvement in the neurocognitive deficits in most patients, accompanied by an almost complete normalization of the brain metabolism.

“We can clearly state that a significant recovery of regional neuronal function and cognition occurs for most COVID-19 patients based on the results of this study. However, it is important to recognize the evidence of longer-lasting deficits in neuronal function and accompanying cognitive deficits is still measurable in some patients six months after manifestation of disease,” noted Blazhenets. “As a result, post-COVID-19 patients with persistent cognitive complaints should be presented to a neurologist and possibly allocated to cognitive rehabilitation programs.”

“18F-FDG PET is an established biomarker of neuronal function and neuronal injury,” stated SNMMI’s Scientific Program Committee chair, Umar Mahmood, MD, PhD. “As shown the Image of the Year, it can be applied to unravel neuronal correlates of the cognitive decline in patients after COVID-19. Since 18F-FDG PET is widely available, it may therefore aid in the diagnostic work-up and follow-up in patients with persistent cognitive impairment after COVID-19.”

###

Abstract 41. “Altered regional cerebral function and its association with cognitive impairment in COVID 19: A prospective FDG PET study.” Ganna Blazhenets, Johannes Thurow, Lars Frings and Philipp Meyer, Department of Nuclear Medicine, Medical Center – University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany; Nils Schroeter, Tobias Bormann, Cornelius Weiller, Andrea Dressing and Jonas Hosp; Department of Neurology and Clinical Neuroscience, Medical Center – University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany; and Dirk Wagner, Department of Internal Medicine, Medical Center – University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany.

All 2021 SNMMI Annual Meeting abstracts can be found online at https://jnm.snmjournals.org/content/62/supplement_1.

About the Society of Nuclear Medicine and Molecular Imaging

The Society of Nuclear Medicine and Molecular Imaging (SNMMI) is an international scientific and medical organization dedicated to advancing nuclear medicine and molecular imaging, vital elements of precision medicine that allow diagnosis and treatment to be tailored to individual patients in order to achieve the best possible outcomes.

SNMMI’s members set the standard for molecular imaging and nuclear medicine practice by creating guidelines, sharing information through journals and meetings and leading advocacy on key issues that affect molecular imaging and therapy research and practice. For more information, visit http://www.snmmi.org.

Source: https://bioengineer.org/snmmi-image-of-the-year-pet-imaging-measures-cognitive-impairment-in-covid-19-patients/

Continue Reading

Trending