(Press-News.org) OAK BROOK, Ill. – A deep learning model performs at the level of an abdominal radiologist in the detection of clinically significant prostate cancer on MRI, according to a study published today in Radiology, a journal of the Radiological Society of North America (RSNA). The researchers hope the model can be used as an adjunct to radiologists to improve prostate cancer detection.
Prostate cancer is the second most common cancer in men worldwide. Radiologists typically use a technique that combines different MRI sequences (called multiparametric MRI) to diagnose clinically significant prostate cancer. Results are expressed through the Prostate Imaging-Reporting and Data System version 2.1 (PI-RADS), a standardized interpretation and reporting approach. However, lesion classification using PI-RADS has limitations.
“The interpretation of prostate MRI is difficult,” said study senior author Naoki Takahashi, M.D., from the Department of Radiology at the Mayo Clinic in Rochester, Minnesota. “More experienced radiologists tend to have higher diagnostic performance.”
Applying artificial intelligence (AI) algorithms to prostate MRI has shown promise for improving cancer detection and reducing observer variability, which is the inconsistency in how people measure or interpret things that can lead to errors. However, a major drawback of existing AI approaches is that the lesion needs to be annotated (adding a note or explanation) by a radiologist or pathologist at the time of initial model development and again during model re-evaluation and retraining after clinical implementation.
“Radiologists annotate suspicious lesions at the time of interpretation, but these annotations are not routinely available, so when researchers develop a deep learning model, they have to redraw the outlines,” Dr. Takahashi said. “Additionally, researchers have to correlate imaging findings with the pathology report when preparing the dataset. If multiple lesions are present, it may not always be feasible to correlate lesions on MRI to their corresponding pathology results. Also, this is a time-consuming process.”
Dr. Takahashi and colleagues developed a new type of deep learning model to predict the presence of clinically significant prostate cancer without requiring information about lesion location. They compared its performance with that of abdominal radiologists in a large group of patients without known clinically significant prostate cancer who underwent MRI at multiple sites of a single academic institution. The researchers trained a convolutional neural network (CNN)—a sophisticated type of AI that is capable of discerning subtle patterns in images beyond the capabilities of the human eye—to predict clinically significant prostate cancer from multiparametric MRI.
Among 5,735 examinations in 5,215 patients, 1,514 examinations showed clinically significant prostate cancer. On both the internal test set of 400 exams and an external test set of 204 exams, the deep learning model’s performance in clinically significant prostate cancer detection was not different from that of experienced abdominal radiologists. A combination of the deep learning model and the radiologist’s findings performed better than radiologists alone on both the internal and external test sets.
Since the output from the deep learning model does not include tumor location, the researchers used something called a gradient-weighted class activation map (Grad-CAM) to localize the tumors. The study showed that for true positive examinations, Grad-CAM consistently highlighted the clinically significant prostate cancer lesions.
Dr. Takahashi sees the model as a potential assistant to the radiologist that can help improve diagnostic performance on MRI through increased cancer detection rates with fewer false positives.
“I do not think we can use this model as a standalone diagnostic tool,” Dr. Takahashi said. “Instead, the model’s prediction can be used as an adjunct in our decision-making process.”
The researchers have continued to expand the dataset, which is now twice the number of cases used in the original study. The next step is a prospective study that examines how radiologists interact with the model’s prediction.
“We’d like to present the model’s output to radiologists and assess how they use it for interpretation and compare the combined performance of radiologist and model to the radiologist alone in predicting clinically significant prostate cancer,” Dr. Takahashi said.
###
“Fully Automated Deep Learning Model to Detect Clinically Significant Prostate Cancer at MRI.” Collaborating with Dr. Takahashi were Jason C. Cai, M.D., Hirotsugu Nakai, M.D., Ph.D., Shiba Kuanar, Ph.D., Adam T. Froemming, M.D., Candice W. Bolan, M.D., Akira Kawashima, M.D., Ph.D., Hiroaki Takahashi, M.D., Ph.D., Lance A. Mynderse, M.D., Chandler D. Dora, M.D., Mitchell R. Humphreys, M.D., Panagiotis Korfiatis, Ph.D., Pouria Rouzrokh, M.D., M.P.H., M.H.P.E., Alexander K. Bratt, M.D., Gian Marco Conte, M.D., Ph.D., and Bradley J. Erickson, M.D., Ph.D.
Radiology is edited by Linda Moy, M.D., New York University, New York, N.Y., and owned and published by the Radiological Society of North America, Inc. (https://pubs.rsna.org/journal/radiology)
RSNA is an association of radiologists, radiation oncologists, medical physicists and related scientists promoting excellence in patient care and health care delivery through education, research and technologic innovation. The Society is based in Oak Brook, Illinois. (RSNA.org)
For patient-friendly information on MRI and prostate imaging, visit RadiologyInfo.org.
END
CHICAGO – Nearly 100 wildfires are currently raging throughout the country, burning more than 2 million acres. The rising frequency of these fires poses a special concern for anesthesiologists – the potential for increased rates of adverse outcomes from anesthesia and surgery among patients exposed to wildfire smoke, according to a special article in the Online First edition of Anesthesiology, the peer-reviewed journal of the American Society of Anesthesiologists (ASA).
"Wildfire smoke causes inflammation and is known to worsen heart and lung disease and pregnancy outcomes," said senior author Vijay Krishnamoorthy, M.D., M.P.H., Ph. D., chief of the Critical Care ...
A new study by an international team of collaborators led by researchers at the University of Vienna, and in collaboration with the Dom Museum Wien, aimed to address the questions of whether art exhibitions can make us more empathic or even change our attitudes and behaviors? The researchers were able to show that, indeed, looking through the exhibition reduced xenophobia and increased acceptance of immigration. Even more, by employing a new cellphone-based experience sampling method, they could track how long ...
Some believe the future of fusion in the U.S. lies in compact, spherical fusion vessels. A smaller tokamak, it is thought, could offer a more economical fusion option. The trick is squeezing everything into a small space. New research suggests eliminating one major component used to heat the plasma, freeing up much-needed space.
Scientists at the U.S. Department of Energy’s (DOE) Princeton Plasma Physics Laboratory (PPPL), the private company Tokamak Energy and Kyushu University in Japan have proposed a design for a compact, spherical fusion pilot plant ...
One popular strategy to motivate people to get vaccinated is the nudge—a message designed to take advantage of human tendencies to conform to social norms, seek to protect loved ones or community, and to prefer treatments with high efficacy rates. Jiseon Chang and colleagues sought to assess the efficacy of such nudges in real world contexts during the COVID-19 pandemic. The authors paid for ads to appear on Facebook between October 2021 and January 2022, reaching almost 15 million users in Brazil, Russia, South Africa, Taiwan, ...
More than 1 in 4 people age 50 and older helps take care of at least one family member or friend who has a health problem or disability, a new poll finds.
And among those caregivers, the new results from the University of Michigan National Poll on Healthy Aging reveal a lot about who they are and who they’re caring for.
In all, 30% of all people in their 50s and early 60s provide care to at least one person with a health issue or disability, compared with 23% of people over 65. And 1 in 10 caregivers in their 50s and early 60s are juggling taking care of three or more people.
In ...
To Predict Tax Revenue, Look at Corporate Earnings
States can make more accurate budget forecasts and avoid midyear cuts if they include growth in corporate earnings
AUSTIN, Texas -- In the complex task of building a state budget, much rides on the accuracy of its fiscal crystal ball: its forecast of how much tax revenue will come in to fund services during the year ahead. Forecasting errors have increased since 2001 due to revenue volatility, such as wider swings in personal income and consumer spending.
New research from Texas ...
MINNEAPOLIS / ST. PAUL (08/06/2024) — Researchers at the University of Minnesota, have developed a new visual diagnostic technique that can be used to advance early detection for neurodegenerative diseases like Parkinson's disease and similar diseases that affect animals, including Chronic Wasting Disease in deer.
The research is published in npj Biosensing, a peer-reviewed scientific journal published by Nature.
Named Cap-QuIC (Capillary-enhanced Quaking-Induced Conversion), researchers will now be able to distinguish infected samples with the naked eye, which makes testing ...
People with higher levels of metals found in their blood and urine may be more likely to be diagnosed with — and die from — amyotrophic lateral sclerosis, or ALS, a University of Michigan-led study suggests.
Researchers have known that ALS, a rare but fatal neurodegenerative condition, is influenced by genetic and environmental factors, including exposure to pesticides and metals.
This latest study examined the levels of metals in the blood and urine of people with and without ALS, finding that exposure to individual and mixtures of metals is associated with a greater risk for ALS and shorter survival.
The ...
PULLMAN, Wash. – It may be possible to turn anxiety into a superpower in some scenarios, recent research with entrepreneurs indicates.
A Washington State University-led study found that if entrepreneurs preparing to make a funding pitch connected their pitch anxiety to their passion for their venture, judges ranked their performance higher. Perhaps even more importantly, the judges were also more likely to recommend them for funding.
This emotion reframing involved the entrepreneurs recognizing that they were feeling anxious partly because the project means so much to them. Entrepreneurs who tried other strategies ...
The findings of the randomized crossover clinical trial, available online now and slated to appear in an upcoming issue of the Journal of Nutrition, reveal simply swapping in foods made from refined corn flour + corn bran can lower LDL cholesterol concentrations by anywhere from 5% - 13.3% in just four weeks.
The trial compared the impact of whole-grain corn meal, refined corn meal, and a blend (refined corn meal plus corn bran) and found that 70% of the participants saw significant reductions in LDL cholesterol concentrations when consuming the blend. For the other corn flours, participants did not see a decrease in their LDL or total cholesterol ...