Skip to main content

cancer

Artificial Intelligence Speeds Brain Tumor Diagnosis

Posted on by

Real time diagnostics in the operating room
Caption: Artificial intelligence speeds diagnosis of brain tumors. Top, doctor reviews digitized tumor specimen in operating room; left, the AI program predicts diagnosis; right, surgeons review results in near real-time.
Credit: Joe Hallisy, Michigan Medicine, Ann Arbor

Computers are now being trained to “see” the patterns of disease often hidden in our cells and tissues. Now comes word of yet another remarkable use of computer-generated artificial intelligence (AI): swiftly providing neurosurgeons with valuable, real-time information about what type of brain tumor is present, while the patient is still on the operating table.

This latest advance comes from an NIH-funded clinical trial of 278 patients undergoing brain surgery. The researchers found they could take a small tumor biopsy during surgery, feed it into a trained computer in the operating room, and receive a diagnosis that rivals the accuracy of an expert pathologist.

Traditionally, sending out a biopsy to an expert pathologist and getting back a diagnosis optimally takes about 40 minutes. But the computer can do it in the operating room on average in under 3 minutes. The time saved helps to inform surgeons how to proceed with their delicate surgery and make immediate and potentially life-saving treatment decisions to assist their patients.

As reported in Nature Medicine, researchers led by Daniel Orringer, NYU Langone Health, New York, and Todd Hollon, University of Michigan, Ann Arbor, took advantage of AI and another technological advance called stimulated Raman histology (SRH). The latter is an emerging clinical imaging technique that makes it possible to generate detailed images of a tissue sample without the usual processing steps.

The SRH technique starts off by bouncing laser light rapidly through a tissue sample. This light enables a nearby fiberoptic microscope to capture the cellular and structural details within the sample. Remarkably, it does so by picking up on subtle differences in the way lipids, proteins, and nucleic acids vibrate when exposed to the light.

Then, using a virtual coloring program, the microscope quickly pieces together and colors in the fine structural details, pixel by pixel. The result: a high-resolution, detailed image that you might expect from a pathology lab, minus the staining of cells, mounting of slides, and the other time-consuming processing procedures.

To interpret the SRH images, the researchers turned to computers and machine learning. To teach a computer, it must be fed large datasets of examples in order to learn how to perform a given task. In this case, they used a special class of machine learning called deep neural networks, or deep learning. It’s inspired by the way neural networks in the human brain process information.

In deep learning, computers look for patterns in large collections of data. As they begin to recognize complex relationships, some connections in the network are strengthened while others are weakened. The finished network is typically composed of multiple information-processing layers, which operate on the data to return a result, in this case a brain tumor diagnosis.

The team trained the computer to classify tissues samples into one of 13 categories commonly found in a brain tumor sample. Those categories included the most common brain tumors: malignant glioma, lymphoma, metastatic tumors, and meningioma. The training was based on more than 2.5 million labeled images representing samples from 415 patients.

Next, they put the machine to the test. The researchers split each of 278 brain tissue samples into two specimens. One was sent to a conventional pathology lab for prepping and diagnosis. The other was imaged with SRH, and then the trained machine made a diagnosis.

Overall, the machine’s performance was quite impressive, returning the right answer about 95 percent of the time. That’s compared to an accuracy of 94 percent for conventional pathology.

Interestingly, the machine made a correct diagnosis in all 17 cases that a pathologist got wrong. Likewise, the pathologist got the right answer in all 14 cases in which the machine slipped up.

The findings show that the combination of SRH and AI can be used to make real-time predictions of a patient’s brain tumor diagnosis to inform surgical decision-making. That may be especially important in places where expert neuropathologists are hard to find.

Ultimately, the researchers suggest that AI may yield even more useful information about a tumor’s underlying molecular alterations, adding ever greater precision to the diagnosis. Similar approaches are also likely to work in supplying timely information to surgeons operating on patients with other cancers too, including cancers of the skin and breast. The research team has made a brief video to give you a more detailed look at the new automated tissue-to-diagnosis pipeline.

Reference:

[1] Near real-time intraoperative brain tumor diagnosis using stimulated Raman histology and deep neural networks. Hollon TC, Pandian B, Adapa AR, Urias E, Save AV, Khalsa SSS, Eichberg DG, D’Amico RS, Farooq ZU, Lewis S, Petridis PD, Marie T, Shah AH, Garton HJL, Maher CO, Heth JA, McKean EL, Sullivan SE, Hervey-Jumper SL, Patil PG, Thompson BG, Sagher O, McKhann GM 2nd, Komotar RJ, Ivan ME, Snuderl M, Otten ML, Johnson TD, Sisti MB, Bruce JN, Muraszko KM, Trautman J, Freudiger CW, Canoll P, Lee H, Camelo-Piragua S, Orringer DA. Nat Med. 2020 Jan 6.

Links:

Video: Artificial Intelligence: Collecting Data to Maximize Potential (NIH)

New Imaging Technique Allows Quick, Automated Analysis of Brain Tumor Tissue During Surgery (National Institute of Biomedical Imaging and Bioengineering/NIH)

Daniel Orringer (NYU Langone, Perlmutter Cancer Center, New York City)

Todd Hollon (University of Michigan, Ann Arbor)

NIH Support: National Cancer Institute; National Institute of Biomedical Imaging and Bioengineering


Seeing the Cytoskeleton in a Whole New Light

Posted on by

It’s been 25 years since researchers coaxed a bacterium to synthesize an unusual jellyfish protein that fluoresced bright green when irradiated with blue light. Within months, another group had also fused this small green fluorescent protein (GFP) to larger proteins to make their whereabouts inside the cell come to light—like never before.

To mark the anniversary of this Nobel Prize-winning work and show off the rainbow of color that is now being used to illuminate the inner workings of the cell, the American Society for Cell Biology (ASCB) recently held its Green Fluorescent Protein Image and Video Contest. Over the next few months, my blog will feature some of the most eye-catching entries—starting with this video that will remind those who grew up in the 1980s of those plasma balls that, when touched, light up with a simulated bolt of colorful lightning.

This video, which took third place in the ASCB contest, shows the cytoskeleton of a frequently studied human breast cancer cell line. The cytoskeleton is made from protein structures called microtubules, made visible by fluorescently tagging a protein called doublecortin (orange). Filaments of another protein called actin (purple) are seen here as the fine meshwork in the cell periphery.

The cytoskeleton plays an important role in giving cells shape and structure. But it also allows a cell to move and divide. Indeed, the motion in this video shows that the complex network of cytoskeletal components is constantly being organized and reorganized in ways that researchers are still working hard to understand.

Jeffrey van Haren, Erasmus University Medical Center, Rotterdam, the Netherlands, shot this video using the tools of fluorescence microscopy when he was a postdoctoral researcher in the NIH-funded lab of Torsten Wittman, University of California, San Francisco.

All good movies have unusual plot twists, and that’s truly the case here. Though the researchers are using a breast cancer cell line, their primary interest is in the doublecortin protein, which is normally found in association with microtubules in the developing brain. In fact, in people with mutations in the gene that encodes this protein, neurons fail to migrate properly during development. The resulting condition, called lissencephaly, leads to epilepsy, cognitive disability, and other neurological problems.

Cancer cells don’t usually express doublecortin. But, in some of their initial studies, the Wittman team thought it would be much easier to visualize and study doublecortin in the cancer cells. And so, the researchers tagged doublecortin with an orange fluorescent protein, engineered its expression in the breast cancer cells, and van Haren started taking pictures.

This movie and others helped lead to the intriguing discovery that doublecortin binds to microtubules in some places and not others [1]. It appears to do so based on the ability to recognize and bind to certain microtubule geometries. The researchers have since moved on to studies in cultured neurons.

This video is certainly a good example of the illuminating power of fluorescent proteins: enabling us to see cells and their cytoskeletons as incredibly dynamic, constantly moving entities. And, if you’d like to see much more where this came from, consider visiting van Haren’s Twitter gallery of microtubule videos here:

Reference:

[1] Doublecortin is excluded from growing microtubule ends and recognizes the GDP-microtubule lattice. Ettinger A, van Haren J, Ribeiro SA, Wittmann T. Curr Biol. 2016 Jun 20;26(12):1549-1555.

Links:

Lissencephaly Information Page (National Institute of Neurological Disorders and Stroke/NIH)

Wittman Lab (University of California, San Francisco)

Green Fluorescent Protein Image and Video Contest (American Society for Cell Biology, Bethesda, MD)

NIH Support: National Institute of General Medical Sciences


Giving Thanks for Biomedical Research

Posted on by

This Thanksgiving, Americans have an abundance of reasons to be grateful—loving family and good food often come to mind. Here’s one more to add to the list: exciting progress in biomedical research. To check out some of that progress, I encourage you to watch this short video, produced by NIH’s National Institute of Biomedical Imaging and Engineering (NIBIB), that showcases a few cool gadgets and devices now under development.

Among the technological innovations is a wearable ultrasound patch for monitoring blood pressure [1]. The patch was developed by a research team led by Sheng Xu and Chonghe Wang, University of California San Diego, La Jolla. When this small patch is worn on the neck, it measures blood pressure in the central arteries and veins by emitting continuous ultrasound waves.

Other great technologies featured in the video include:

Laser-Powered Glucose Meter. Peter So and Jeon Woong Kang, researchers at Massachusetts Institute of Technology (MIT), Cambridge, and their collaborators at MIT and University of Missouri, Columbia have developed a laser-powered device that measures glucose through the skin [2]. They report that this device potentially could provide accurate, continuous glucose monitoring for people with diabetes without the painful finger pricks.

15-Second Breast Scanner. Lihong Wang, a researcher at California Institute of Technology, Pasadena, and colleagues have combined laser light and sound waves to create a rapid, noninvasive, painless breast scan. It can be performed while a woman rests comfortably on a table without the radiation or compression of a standard mammogram [3].

White Blood Cell Counter. Carlos Castro-Gonzalez, then a postdoc at Massachusetts Institute of Technology, Cambridge, and colleagues developed a portable, non-invasive home monitor to count white blood cells as they pass through capillaries inside a finger [4]. The test, which takes about 1 minute, can be carried out at home, and will help those undergoing chemotherapy to determine whether their white cell count has dropped too low for the next dose, avoiding risk for treatment-compromising infections.

Neural-Enabled Prosthetic Hand (NEPH). Ranu Jung, a researcher at Florida International University, Miami, and colleagues have developed a prosthetic hand that restores a sense of touch, grip, and finger control for amputees [5]. NEPH is a fully implantable, wirelessly controlled system that directly stimulates nerves. More than two years ago, the FDA approved a first-in-human trial of the NEPH system.

If you want to check out more taxpayer-supported innovations, take a look at NIBIB’s two previous videos from 2013 and 2018 As always, let me offer thanks to you from the NIH family—and from all Americans who care about the future of their health—for your continued support. Happy Thanksgiving!

References:

[1] Monitoring of the central blood pressure waveform via a conformal ultrasonic device. Wang C, Li X, Hu H, Zhang, L, Huang Z, Lin M, Zhang Z, Yun Z, Huang B, Gong H, Bhaskaran S, Gu Y, Makihata M, Guo Y, Lei Y, Chen Y, Wang C, Li Y, Zhang T, Chen Z, Pisano AP, Zhang L, Zhou Q, Xu S. Nature Biomedical Engineering. September 2018, 687-695.

[2] Evaluation of accuracy dependence of Raman spectroscopic models on the ratio of calibration and validation points for non-invasive glucose sensing. Singh SP, Mukherjee S, Galindo LH, So PTC, Dasari RR, Khan UZ, Kannan R, Upendran A, Kang JW. Anal Bioanal Chem. 2018 Oct;410(25):6469-6475.

[3] Single-breath-hold photoacoustic computed tomography of the breast. Lin L, Hu P, Shi J, Appleton CM, Maslov K, Li L, Zhang R, Wang LV. Nat Commun. 2018 Jun 15;9(1):2352.

[4] Non-invasive detection of severe neutropenia in chemotherapy patients by optical imaging of nailfold microcirculation. Bourquard A, Pablo-Trinidad A, Butterworth I, Sánchez-Ferro Á, Cerrato C, Humala K, Fabra Urdiola M, Del Rio C, Valles B, Tucker-Schwartz JM, Lee ES, Vakoc BJ9, Padera TP, Ledesma-Carbayo MJ, Chen YB, Hochberg EP, Gray ML, Castro-González C. Sci Rep. 2018 Mar 28;8(1):5301.

[5] Enhancing Sensorimotor Integration Using a Neural Enabled Prosthetic Hand System

Links:

Sheng Xu Lab (University of California San Diego, La Jolla)

So Lab (Massachusetts Institute of Technology, Cambridge)

Lihong Wang (California Institute of Technology, Pasadena)

Video: Lihong Wang: Better Cancer Screenings

Carlos Castro-Gonzalez (Madrid-MIT M + Visión Consortium, Cambridge, MA)

Video: Carlos Castro-Gonzalez (YouTube)

Ranu Jung (Florida International University, Miami)

Video: New Prosthetic System Restores Sense of Touch (Florida International)

NIH Support: National Institute of Biomedical Imaging and Bioengineering; National Institute of Neurological Diseases and Stroke; National Heart, Lung, and Blood Institute; National Cancer Institute; Common Fund


Study Suggests Repurposed Drugs Might Treat Aggressive Lung Cancer

Posted on by

Small cell lung cancer cells
Caption: Small cell lung cancer cells (red) spreading via blood vessels (white) from the lung to the liver of a genetically-engineered mouse model.
Credit: Leanne Li, Koch Institute at MIT

Despite continued progress in treatment and prevention, lung cancer remains our nation’s leading cause of cancer death. In fact, more Americans die of lung cancer each year than of breast, colon, and prostate cancers combined [1,2]. While cigarette smoking is a major cause, lung cancer also occurs in non-smokers. I’m pleased to report discovery of what we hope will be a much-needed drug target for a highly aggressive, difficult-to-treat form of the disease, called small cell lung cancer (SCLC).

Using gene-editing technology to conduct a systematic, large-scale search for druggable vulnerabilities in certain types of cancer cells grown in lab dishes, NIH-funded researchers recently identified a metabolic pathway that appears to play a key role in SCLC. What makes this news even more encouraging is drugs that block this pathway already exist. That includes one in clinical testing for other types of cancer, and another that’s FDA-approved and has been safely used for more than 20 years to treat people with rheumatoid arthritis.

The new work comes from the lab of Tyler Jacks, Massachusetts Institute of Technology (MIT), Cambridge. The Jacks lab, which is dedicated to understanding the genetic events that lead to cancer, develops mouse models engineered to carry the same genetic mutations that turn up in human cancers.

In work described in Science Translational Medicine, the team, co-led by Leanne Li and Sheng Rong Ng, applied CRISPR gene-editing tools to cells grown from some of their mouse models. Aiming high in terms of scale, researchers used CRISPR to knock out systematically, one by one, each of about 5,000 genes in cells from the SCLC mouse model, as well in cells from mouse models of other types of lung and pancreatic cancers. They looked to see what gene knockouts would slow down or kill the cancer cells, because that would be a good indication that the protein products of these genes, or the pathways they mediated, would be potential drug targets.

Out of those thousands of genes, one rose to the top of the list. It encodes an enzyme called DHODH (dihydroorotate dehydrogenase). This enzyme plays an important role in synthesizing pyrimidine, which is a major building block in DNA and RNA. Cytosine and thymine, the C and T in the four-letter DNA code, are pyrimidines; so is uracil, the U in RNA that takes the place of T in DNA. Because cancer cells are constantly dividing, there is a continual need to synthesize new DNA and RNA molecules to support the production of new daughter cells. And that means, unlike healthy cells, cancer cells require a steady supply of pyrimidine.

It turns out that the SCLC cells have an unexpected weakness relative to other cancer cells: they don’t produce as much pyrimidine. As a result, the researchers found blocking DHODH left the cells short on pyrimidine, leading to reduced growth and survival of the cancer.

This was especially good news because DHODH-blocking drugs, including one called brequinar, have already been tested in clinical trials for other cancers. In fact, brequinar is now being explored as a potential treatment for acute myeloid leukemia.

Might brequinar also hold promise for treating SCLC? To explore further, the researchers looked again to their genetic mouse model of SCLC. Their studies showed that mice treated with brequinar lived about 40 days longer than control animals. That’s a significant survival benefit in this system.

Brequinar treatment appeared to work even better when combined with other approved cancer drugs in mice that had SCLC cells transplanted into them. Further study in mice carrying SCLC tumors derived from four human patients added to this evidence. Two of the four human tumors shrunk in mice treated with brequinar.

Of course, mice are not people. But the findings suggest that brequinar or another DHODH blocker might hold promise as a new way to treat SCLC. While more study is needed to understand even better how brequinar works and explore potentially promising drug combinations, the fact that this drug is already in human testing for another indication suggests that a clinical trial to explore its use for SCLC might happen more quickly.

More broadly, the new findings show the promise of gene-editing technology as a research tool for uncovering elusive cancer targets. Such hard-fought discoveries will help to advance precise approaches to the treatment of even the most aggressive cancer types. And that should come as encouraging news to all those who are hoping to find new answers for hard-to-treat cancers.

References:

[1] Cancer Stat Facts: Lung and Bronchus Cancer (National Cancer Institute/NIH)

[2] Key Statistics for Lung Cancer (American Cancer Society)

[3] Identification of DHODH as a therapeutic target in small cell lung cancer. Li L, Ng SR, Colón CI, Drapkin BJ, Hsu PP, Li Z, Nabel CS, Lewis CA, Romero R, Mercer KL, Bhutkar A, Phat S, Myers DT, Muzumdar MD, Westcott PMK, Beytagh MC, Farago AF, Vander Heiden MG, Dyson NJ, Jacks T. Sci Transl Med. 2019 Nov 6;11(517).

Links:

Small Cell Lung Cancer Treatment (NCI/NIH)

Video: Introduction to Genome Editing Using CRISPR Cas9 (NIH)

Tyler Jacks (Massachusetts Institute of Technology, Cambridge)

NIH Support: National Cancer Institute


Caught on Video: Cancer Cells in Act of Cannibalism

Posted on by

Tumors rely on a variety of tricks to grow, spread, and resist our best attempts to destroy them. Now comes word of yet another of cancer’s surprising stunts: when chemotherapy treatment hits hard, some cancer cells survive by cannibalizing other cancer cells.

Researchers recently caught this ghoulish behavior on video. In what, during this Halloween season, might look a little bit like The Blob, you can see a down-for-the-count breast cancer cell (green), treated earlier with the chemotherapy drug doxorubicin, gobbling up a neighboring cancer cell (red). The surviving cell delivers its meal to internal compartments called lysosomes, which digest it in a last-ditch effort to get some nourishment and keep going despite what should have been a lethal dose of a cancer drug.

Crystal Tonnessen-Murray, a postdoctoral researcher in the lab of James Jackson, Tulane University School of Medicine, New Orleans, captured these dramatic interactions using time-lapse and confocal microscopy. When Tonnessen-Murray saw the action, she almost couldn’t believe her eyes. Tumor cells eating tumor cells wasn’t something that she’d learned about in school.

As the NIH-funded team described in the Journal of Cell Biology, these chemotherapy-treated breast cancer cells were not only cannibalizing their neighbors, they were doing it with remarkable frequency [1]. But why?

A possible explanation is that some cancer cells resist chemotherapy by going dormant and not dividing. The new study suggests that while in this dormant state, cannibalism is one way that tumor cells can keep going.

The study also found that these acts of cancer cell cannibalism depend on genetic programs closely resembling those of immune cells called macrophages. These scavenging cells perform their important protective roles by gobbling up invading bacteria, viruses, and other infectious microbes. Drug-resistant breast cancer cells have apparently co-opted similar programs in response to chemotherapy but, in this case, to eat their own neighbors.

Tonnessen-Murray’s team confirmed that cannibalizing cancer cells have a survival advantage. The findings suggest that treatments designed to block the cells’ cannibalistic tendencies might hold promise as a new way to treat otherwise hard-to-treat cancers. That’s a possibility the researchers are now exploring, although they report that stopping the cells from this dramatic survival act remains difficult.

Reference:

[1] Chemotherapy-induced senescent cancer cells engulf other cells to enhance their survival. Tonnessen-Murray CA, Frey WD, Rao SG, Shahbandi A, Ungerleider NA, Olayiwola JO, Murray LB, Vinson BT, Chrisey DB, Lord CJ, Jackson JG. J Cell Biol. 2019 Sep 17.

Links:

Breast Cancer (National Cancer Institute/NIH)

James Jackson (Tulane University School of Medicine, New Orleans)

NIH Support: National Institute of General Medical Sciences


Next Page