MIT’s deep learning artificial intelligence algorithm demonstrates how similar new technologies and smartphones can be combined to give dermatologists and dermatopathologists valuable new ways to diagnose skin cancer from digital images
According to an MIT press release, “The paper describes the development of an SPL [Suspicious Pigmented Lesion] analysis system using DCNNs [Deep Convolutional Neural Networks] to more quickly and efficiently identify skin lesions that require more investigation, screenings that can be done during routine primary care visits, or even by the patients themselves. The system utilized DCNNs to optimize the identification and classification of SPLs in wide-field images.”
The MIT scientists believe their AI analysis system could aid dermatologists, dermatopathologists, and clinical laboratories detect melanoma, a deadly form of skin cancer, in its early stages using smartphones at the point-of-care.
Improving Melanoma Treatment and Patient Outcomes
Melanoma develops when pigment-producing cells called melanocytes start to grow out of control. The cancer has traditionally been diagnosed through visual inspection of SPLs by physicians in medical settings. Early-stage identification of SPLs can drastically improve the prognosis for patients and significantly reduce treatment costs. It is common to biopsy many lesions to ensure that every case of melanoma can be diagnosed as early as possible, thus contributing to better patient outcomes.
“Early detection of SPLs can save lives. However, the current capacity of medical systems to provide comprehensive skin screenings at scale are still lacking,” said Luis Soenksen, PhD, Venture Builder in Artificial Intelligence and Healthcare at MIT and first author of the study in the MIT press release.
The researchers trained their AI system by using 20,388 wide-field images from 133 patients at the Gregorio Marañón General University Hospital in Madrid, as well as publicly available images. The collected photographs were taken with a variety of ordinary smartphone cameras that are easily obtainable by consumers.
They taught the deep learning algorithm to examine various features of skin lesions such as size, circularity, and intensity. Dermatologists working with the researchers also visually classified the lesions for comparison.
“Our system achieved more than 90.3% sensitivity (95% confidence interval, 90 to 90.6) and 89.9% specificity (89.6 to 90.2%) in distinguishing SPLs from nonsuspicious lesions, skin, and complex backgrounds, avoiding the need for cumbersome individual lesion imaging,” the MIT researchers noted in their Science Translational Medicine paper.
In addition, the algorithm agreed with the consensus of experienced dermatologists 88% of the time and concurred with the opinions of individual dermatologists 86% of the time, Medgadget reported.
Modern Imaging Technologies Will Advance Diagnosis of Disease
According to the American Cancer Society, about 106,110 new cases of melanoma will be diagnosed in the United States in 2021. Approximately 7,180 people are expected to die of the disease this year. Melanoma is less common than other types of skin cancer but more dangerous as it’s more likely to spread to other parts of the body if not detected and treated early.
More research is needed to substantiate the effectiveness and accuracy of this new tool before it could be used in clinical settings. However, the early research looks promising and smartphone camera technology is constantly improving. Higher resolutions would further advance development of this type of diagnostic tool.
In addition, MIT’s algorithm enables in situ examination and possible diagnosis of cancer. Therefore, a smartphone so equipped could enable a dermatologist to diagnose and excise cancerous tissue in a single visit, without the need for biopsies to be sent to a dermatopathologist.
Currently, dermatologists refer a lot of skin biopsies to dermapathologists and anatomic pathology laboratories. An accurate diagnostic tool that uses modern smartphones to characterize suspicious skin lesions could become quite popular with dermatologists and affect the flow of referrals to medical laboratories.
DeepMind hopes its unrivaled collection of data, enabled by artificial intelligence, may advance development of precision medicines, new medical laboratory tests, and therapeutic treatments
‘Tis the season for giving, and one United Kingdom-based artificial intelligence (AI) research laboratory is making a sizeable gift. After using AI and machine learning to create “the most comprehensive map of human proteins,” in existence, DeepMind, a subsidiary of Alphabet Inc. (NASDAQ:GOOGL), parent company of Google, plans to give away for free its database of millions of protein structure predictions to the global scientific community and to all of humanity, The Verge reported.
Pathologists and clinical laboratory scientists developing proteomic assays understand the significance of this gesture. They know how difficult and expensive it is to determine protein structures using sequencing of amino acids. That’s because the various types of amino acids in use cause the [DNA] string to “fold.” Thus, the availability of this data may accelerate the development of more diagnostic tests based on proteomics.
“For decades, scientists have been trying to find a method to reliably determine a protein’s structure just from its sequence of amino acids. Attraction and repulsion between the 20 different types of amino acids cause the string to fold in a feat of ‘spontaneous origami,’ forming the intricate curls, loops, and pleats of a protein’s 3D structure. This grand scientific challenge is known as the protein-folding problem,” a DeepMind statement noted.
Enter DeepMind’s AlphaFold AI platform to help iron things out. “Experimental techniques for determining structures are painstakingly laborious and time consuming (sometimes taking years and millions of dollars). Our latest version [of AlphaFold] can now predict the shape of a protein, at scale and in minutes, down to atomic accuracy. This is a significant breakthrough and highlights the impact AI can have on science,” DeepMind stated.
Release of Data Will Be ‘Transformative’
In July, DeepMind announced it would begin releasing data from its AlphaFold Protein Structure Database which contains “predictions for the structure of some 350,000 proteins across 20 different organisms,” The Verge reported, adding, “Most significantly, the release includes predictions for 98% of all human proteins, around 20,000 different structures, which are collectively known as the human proteome. By the end of the year, DeepMind hopes to release predictions for 100 million protein structures.”
According to Edith Heard, PhD, Director General of the European Molecular Biology Laboratory (EMBL), the open release of such a dataset will be “transformative for our understanding of how life works,” The Verge reported.
Free Data about Proteins Will Accelerate Research on Diseases, Treatments
Research into how protein folds and, thereby, functions could have implications to fighting diseases and developing new medicines, according to DeepMind.
“This will be one of the most important datasets since the mapping of the human genome,” said Ewan Birney, PhD, Deputy Director General of the EMBL, in the DeepMind statement. EMBL worked with DeepMind on the dataset.
DeepMind protein prediction data are already being used by scientists in medical research. “Anyone can use it for anything. They just need to credit the people involved in the citation,” said Demis Hassabis, DeepMind CEO and Co-founder, in The Verge.
In a blog article, Hassabis listed several projects and organizations already using AlphaFold. They include:
“As researchers seek cures for diseases and pursue solutions to other big problems facing humankind—including antibiotic resistance, microplastic pollution, and climate change—they will benefit from fresh insights in the structure of proteins,” Hassabis wrote.
Because of the deep financial backing that Alphabet/Google can offer, it is reasonable to predict that DeepMind will make progress with its AI technology that regularly adds capabilities and accuracy, allowing AlphaFold to be effective for many uses.
This will be particularly true for the development of new diagnostic assays that will give clinical laboratories better tools for diagnosing disease earlier and more accurately.
Research could lead to clinical laboratory tests in service of precision medicine therapies to reduce a person’s susceptibility to being targeted by blood-sucking insects
Ever wonder why some people attract mosquitoes while others do not? Could biting insects pick their victims by smell? Scientists in California believe the answers to these questions could lead to new precision medicine therapies and clinical laboratory tests.
The research revealed evidence that some blood-sucking insects may identify their prey by homing in on the “scent” of chemicals produced by bacteria located in the skin microbiome of animals and humans.
This is yet another example of research into one area of the human microbiome that might someday lead to a new clinical laboratory test, in this case to determine if a person is more likely to attracts biting insects. If there were such a test, precision medicine therapies could be developed that change an individual’s microbiome to discourage insects from biting that individual.
Then, the clinical laboratory test would have value because it helped diagnose a health condition that is treatable.
“In these caves, I’d see all these different bat species or even taxonomic families roosting side by side. Some of them were loaded with bat flies, while others had none or only a few,” Lutz said in Phys.org. “And these flies are typically very specific to different kinds of bats—you won’t find a fly that normally feeds on horseshoe bats crawling around on a fruit bat. I started wondering why the flies are so particular. Clearly, they can crawl over from one kind of bat to another, but they don’t really seem to be doing that.”
The researchers suspected that the bacteria contained in the skin microbiomes of individual bats could be influencing which bats the flies selected to bite. The bacteria produce a distinctive odor which may make certain bats more attractive to the flies.
The type of fly assessed for the study are related to mosquitoes and most of them are incapable of flight.
“They have incredibly reduced wings in many cases and can’t actually fly,” Lutz explained. “And they have reduced eyesight, so they probably aren’t really operating by vision. So, some other sensory mechanisms must be at play, maybe a sense of smell or an ability to detect chemical cues.”
To test their hypothesis, the research team collected skin and fur samples from the bodies and wings of a variety of bat species located in various caves around Kenya and Uganda. They collected their samples at 14 field sites from August to October in 2016. They then examined the DNA of the bats as well as the microbes residing on the animals’ skin and searched for the presence of flies.
“The flies are exquisitely evolved to stay on their bat,” said Carl Dick, PhD, a professor of biology at Western Kentucky University and one of the study’s authors. “They have special combs, spines, and claws that hold them in place in the fur, and they can run quickly in any direction to evade the biting and scratching of the bats, or the efforts by researchers to capture them,” he told Phys.org.
“You brush the bats’ fur with your forceps, and it’s like you’re chasing the fastest little spider,” Lutz said. “The flies can disappear in a split second. They are fascinatingly creepy.”
Genetic Sequencing DNA of Bat Skin Bacteria
After collecting their specimens, the researchers extracted DNA from the collected bacteria and performed genetic sequencing on the samples. They created libraries of the bacteria contained in each skin sample and used bioinformatics methods to identify the bacteria and compare the samples from bats that had flies versus those that did not.
“How the flies actually locate and find their bats has previously been something of a mystery,” Dick noted. “But because most bat flies live and feed on only one bat species, it’s clear that they somehow find the right host.”
The scientists discovered that different bat families did have their own distinctive skin microbiome, even among samples collected from different locations. They found that differences in the skin microbiomes of certain bats does contribute to whether those bats have parasites. But not all their questions were answered.
“We weren’t able to collect the actual chemicals producing cue—secondary metabolites or volatile organic compounds—during this initial work. Without that information, we can’t definitively say that the bacteria are leading the flies to their hosts,” Lutz said.
Next Steps
“So, next steps will be to sample bats in a way that we can actually tie these compounds to the bacteria. In science, there is always a next step,” she added.
This research illustrates that there may be a reason why certain animals and humans tend to be more attractive to insects than others. It is also possible that an individual’s skin microbiome may explain why some people are more prone to mosquito and other types of insect bites.
More research and clinical studies on this topic are needed, but it could possibly lead to a clinical laboratory test to determine if an individual’s skin microbiome could contribute to his or her potential to being bitten by insects. Such a test would be quite beneficial, as insects can carry a variety of diseases that are harmful to humans.
Perhaps a precision medicine therapy could be developed to alter a person’s microbiome to make them invisible to blood-sucking insects. That would be a boon to regions of the world were diseases like malaria are spread by insect bites.
Determining how dogs do this may lead to biomarkers for new clinical laboratory diagnostics tests
Development of new diagnostic olfactory tools for prostate and other cancers is expected to result from research now being conducted by a consortium of researchers at different universities and institutes. To identify new biomarkers, these scientists are studying how dogs can detect the presence of prostate cancer by sniffing urine specimens.
Funded by a grant from the Prostate Cancer Foundation, the pilot study demonstrated that dogs could identify prostate samples containing cancer and discern between cancer positive and cancer negative samples.
Canine Olfactory Combined with Artificial Intelligence Analysis Approach
The part of a canine brain that controls smell is 40 million times greater than that of humans. Some dog breeds have 300 to 350 million sensory receptors, compared to about five million in humans. With their keen sense of smell, dogs are proving to be vital resources in the detection of some diseases.
The pilot study examined how dogs could be trained to detect prostate cancer in human urine samples.
To perform the study, the researchers trained two dogs to sniff urine samples from men with high-grade prostate cancer and from men without the cancer. The two dogs used in the study were a four-year-old female Labrador Retriever named Florin, and a seven-year-old female wirehaired Hungarian Vizsla named Midas. The dogs were trained to respond to cancer-related chemicals, known as volatile organic compounds, or VOCs, the researchers added to the urine samples, and to not respond to the samples without the VOCs.
Both dogs performed well in their cancer detection roles, and both successfully identified five of seven urine samples from men with prostate cancer, correlating to a 71.4% accuracy rate. In addition, Florin correctly identified 16 of 21 non-aggressive or no cancer samples for an accuracy rate of 76.2% and Midas did the same with a 66.7% accuracy rate.
“We wondered if having the dogs detect the chemicals, combined with analysis by GC-MS, bacterial profiling, and an artificial intelligence (AI) neural network trained to emulate the canine cancer detection ability, could significantly improve the diagnosis of high-grade prostate cancer,” said Alan Partin, MD, PhD, Professor of Urology, Pathology and Oncology, Johns Hopkins University School of Medicine and one of the authors of the study, told Futurity.
The researchers determined that canine olfaction was able to distinguish between positive and negative prostate cancer in the samples, and the VOC and microbiota profiling analyses showed a qualitative difference between the two groups. The multisystem approach demonstrated a more sensitive and specific way of detecting the presence of prostate cancer than any of the methods used by themselves.
In their paper, the researchers concluded that “this study demonstrated feasibility and identified the challenges of a multiparametric approach as a first step towards creating a more effective, non-invasive early urine diagnostic method for the highly aggressive histology of prostate cancer.”
Can Man’s Best Friend be Trained to Detect Cancer and Save Lives?
Prostate cancer is the second leading cause of cancer deaths among men in the developed world. And, according to data from the National Cancer Institute, standard clinical laboratory blood tests, such as the prostate-specific antigen (PSA) test for early detection, sometimes miss the presence of cancer.
Establishing an accurate, non-invasive method of sensing the disease could help detect the disease sooner when it is more treatable and save lives.
The American Cancer Society estimates that there will be about 248,530 new cases of prostate cancer diagnosed in 2021 and that there will be approximately 34,130 deaths resulting from the disease during the same year.
Of course, more testing will be needed before Man’s best friend can be put to work detecting cancer in medical environments. But if canines can be trained to detect the disease early, and in a non-invasive way, more timely diagnosis and treatment could result in higher survival rates.
Meanwhile, as researchers identify the elements dogs use to detect cancer and other diseases, this knowledge can result in the creation of new biomarkers than can be used in clinical laboratory tests.
Although there are healthcare providers who see the potential in microbiome testing, many clinical laboratories are not yet ready to embrace microbiome-based testing
In an unlikely string of events, no less than Nordstrom, the national department store chain, announced in September that it would offer microbiome-based test claimed to “check gut health.” Apparently, its customers were interested in this clinical laboratory test, as the Nordstrom website currently indicates that the “Health Intelligence Test Kit by Viome” is already sold out!
What does it say about consumer interest in clinical laboratory self-testing that Nordstrom has decided to offer at-home microbiome tests to its store customers? Can it be assumed that Nordstrom conducted enough marketing surveys of its customers to determine: a) that they were interested in microbiome testing; and b) they would buy enough microbiome tests that Nordstrom would benefit financially from either the mark-up on the tests or from the derived goodwill for meeting customer expectations?
Whatever the motivation, the retail giant recently announced it had partnered with Viome Life Sciences to sell Viome’s microbiome testing kits to its customers online, and in 2022, at some Nordstrom retail locations. These tests are centered around helping consumers understand the relationship between their microbiome and nutrition.
Pathologists and clinical laboratories will want to track Nordstrom’s success or failure in selling microbiome-based assays to its consumers. Microbiomics is in its infancy and remains a very unsettled area of diagnostics. Similarly, Viome, a self-described precision health and wellness company that conducts mRNA analysis at scale, will need to demonstrate that its strategy of developing precision medicine diagnostics and therapeutics based on the human microbiome has clinical relevance.
Helping Consumers with ‘Precision Nutrition’
In a September news release, Viome founder and CEO Naveen Jain, a serial entrepreneur, said, “Both Viome and Nordstrom believe that true health and beauty start from within. There is no such thing as a universal healthy food or healthy supplement. What is right for one person can be wrong for someone else, especially when it comes to nutrition which is key to human longevity and vitality. Precision nutrition is the future!”
“Precision medicine seeks to improve the personalized treatment of diseases, and precision nutrition is specific to dietary intake. Both develop interventions to prevent or treat chronic diseases based on a person’s unique characteristics like DNA, race, gender, health history, and lifestyle habits. Both aim to provide safer and more effective ways to prevent and treat disease by providing more accurate and targeted strategies.
“Precision nutrition assumes that each person may have a different response to specific foods and nutrients, so that the best diet for one individual may look very different than the best diet for another.
“Precision nutrition also considers the microbiome, trillions of bacteria in our bodies that play a key role in various daily internal operations. What types and how much bacteria we have are unique to each individual. Our diets can determine which types of bacteria live in our digestive tracts, and according to precision nutrition the reverse is also true: the types of bacteria we house might determine how we break down certain foods and what types of foods are most beneficial for our bodies.”
Medical Laboratory Testing, not Guessing
Viome Life Sciences is a microbiome and RNA analysis company based in Bellevue, Wash. The test kit that Nordstrom is selling is called the Health Intelligence Test. It is an at-home mRNA test that can provide users with some insights regarding their health. Consumers use the kit to collect blood and fecal samples, then return those samples to Viome for testing.
In a press release announcing its collaboration with Nordstrom, Viome said, “In a world overwhelmed by information relating to diet and supplement advice, Viome believes in testing, not guessing and empowering its users with actionable insights. To date, Viome has helped over 250,000 individuals improve their health through precision nutrition powered by microbial and human gene expression insights.”
Nordstrom began offering Viome’s Health Intelligence Test kit for $199 on its website starting in September. As of this writing and noted above, the kits are sold out. Nordstrom plans to stock the kit in select stores starting in 2022.
Individuals who purchase the test submit blood and stool samples to Viome’s lab which performs an analysis of gene activity patterns in the user’s cells and microbiome. Viome provides the results to consumers within two to three weeks.
“This partnership is a giant step towards making our technology more accessible, so people can understand what’s right for their unique body,” Jain said in the news release. “We are inspired each day by the incredible changes our customers are seeing in their health including improvements in digestion, weight, stress, ability to focus, and more.”
According to the news release, Viome conducted blind studies earlier this year that revealed significant successes based on their precision nutritional approach to wellness. Study participants, Viome claims, improved their outcomes to four diseases through nutrition:
Is Microbiome Diagnostics Testing Ready for Clinical Use?
Microbiomics is a relatively new field of diagnostics research. Much more research and testing will be needed to prove its clinical value and efficacy in healthcare diagnostics. Nevertheless, companies are offering microbiomics testing to consumers and that has some healthcare providers concerned.
In the GeekWire article, David Suskind, MD, a gastroenterologist at Seattle Children’s Hospital and Professor of Pediatrics at the University of Washington, described Viome’s study methodology as “questionable,” adding, “I think this is a very interesting and exciting space and I do think there are definite potential implications, down the road. [However] we are not there in terms of looking at microbiome and making broad recommendation for individuals, as of yet.”
Will at-home clinical laboratory testing kits that analyze an individual’s microbiome someday provide data that help people lead healthier lives and ward off diseases? That’s Jain’s prediction.
In an article published in Well+Good, Jain said, “COVID-19 has, of course, been such a dark time, but one positive that did come from it is that more people are taking control of their own health. I really believe that the future of healthcare will be delivered not at the hospital, but at home.”
If this collaboration between Nordstrom and Viome proves successful, similar partnerships between at-home diagnostics developers and established retail chains may become even more common. And that should be on the radars of pathologists and clinical laboratories.
Proteins in human saliva make up its proteome and may be the key to new, precision medicine diagnostics that would give clinical pathologists new capabilities to identify disease
Clinical pathologists may soon have an array of new precision medicine diagnostic tools based on peoples’ saliva. There are an increasing number of “–omes” that can be the source of useful diagnostic biomarkers for developing clinical laboratory tests. The latest is the world’s first saliva protein biome wiki.
Called the Human Salivary Proteome Wiki (HSP Wiki), the “public data platform,” which was created by researchers at the University of Buffalo, is the “first of its kind,” according to Labroots, and “contains data on the many thousands of proteins present in saliva.”
The HSP Wiki brings together data from independent studies on proteins present in human saliva. One of the researchers’ goals is to speed up the development of saliva-based diagnostics and personalized medicine tools.
In “The Human Salivary Proteome Wiki: A Community-Driven Research Platform,” published in the Journal of Dental Research, the researchers wrote, “Saliva has become an attractive body fluid for on-site, remote, and real-time monitoring of oral and systemic health. At the same time, the scientific community needs a saliva-centered information platform that keeps pace with the rapid accumulation of new data and knowledge by annotating, refining, and updating the salivary proteome catalog.
“We developed the Human Salivary Proteome (HSP) Wiki as a public data platform for researching and retrieving custom-curated data and knowledge on the saliva proteome. … The HSP Wiki will pave the way for harnessing the full potential of the salivary proteome for diagnosis, risk prediction, therapy of oral and systemic diseases, and preparedness for emerging infectious diseases,” they concluded.
Where Does Saliva Come From?
Saliva is a complex biological fluid that has long been linked to oral health and the health of the upper gastrointestinal tract. Only recently, though, have scientists begun to understand from where in the body saliva proteins originate.
The authors wrote: “Salivary proteins are essential for maintaining health in the oral cavity and proximal digestive tract, and they serve as potential diagnostic markers for monitoring human health and disease. However, their precise organ origins remain unclear.
“Through transcriptomic analysis of major adult and fetal salivary glands and integration with the saliva proteome, the blood plasma proteome, and transcriptomes of 28+ organs, we link human saliva proteins to their source, identify salivary-gland-specific genes, and uncover fetal- and adult-specific gene repertoires,” they added.
“Our results pave the way for future investigations into glandular biology and pathology, as well as saliva’s use as a diagnostic fluid,” the researchers concluded.
Saliva plays a crucial role in digestion by breaking down starches. It also provides a protective barrier in the mouth. When salivary glands malfunction, patients can face serious health consequences. Although clinicians and scientists have long understood the importance of saliva to good health, the question now is whether it contains markers of specific diseases.
“The Human Salivary Proteome Wiki contains proteomic, genomic, transcriptomic data, as well as data on the glycome, sugar molecules present on salivary glycoproteins. New data goes through an interdisciplinary team of curators, which ensures that all input data is accurate and scientifically sound,” noted Labroots.
Omics and Their Role in Clinical Laboratory Diagnostics
Proteomics is just one of several hotly-researched -omics that hold the potential to develop into important personalized medicine and diagnostics tools for pathologists. Genomics is a related area of research being studied for its potential to benefit precision medicine diagnostics.
However, unlike genomes, which do not change, proteomes change constantly. That is one of the main reasons studying the human salivary proteome could lead to valuable diagnostics tools.
Combining the study of the -omes with tools like mass spectrometry, a new era of pathology may be evolving. “With the rapid decrease in the costs of omics technologies over the past few years, whole-proteome profiling from tissue slides has become more accessible to diagnostic labs as a means of characterization of global protein expression patterns to evaluate the pathophysiology of diseases,” noted Pathology News.
Saliva and the Age of Precision Medicine
The study of the -omes may be an important element in the evolution of precision medicine, because of its ability to provide information about what is happening in patients’ bodies at the point of care.
Thus, a full understanding of the proteome of saliva and what causes it to change in response to different health conditions and diseases could open the door to an entirely new branch of diagnostics and laboratory medicine. It is easy and non-invasive to gather and, given that saliva contains so much information, it offers an avenue of study that may improve patients’ lives.
It also would bring us closer to the age of precision medicine where clinical laboratory scientists and pathologists can contribute even more value to referring physicians and their patients.