Histopathology-driven artificial intelligence predicts TMB-H colorectal cancer
Neural networks and histology based prediction of tumor mutational burden-high colorectal cancer for the effective therapeutic use of immune check point inhibitors
2021-06-14
(Press-News.org) Niigata, Japan - Biomarkers are important determinants of appropriate and effective therapeutic approaches for various diseases including cancer. There is ample evidence pointing toward the significance of immune check point inhibitors (ICI) against cancer, and they showed promising clinical benefits to a specific group of patients with colorectal cancer (CRC). Several reports demonstrated the efficacy of biomarkers such as programmed death-1 protein ligand (PD-L1), density of tumor-infiltrating lymphocytes (TILs), and tumor mutational burden (TMB), to determine the patient responsiveness for the efficient use of ICIs as therapeutics against cancer.
A high level of TMB (TMB-H), which reflects elevated total number of non-synonymous somatic mutations per coding area of a tumor genome and normally derived from gene panel testing, is recognized as a promising biomarker for the ICI therapies of various solid cancers. However, in clinical practice, it is not feasible to perform gene panel testing for all cancer patients.
Dr. Yoshifumi Shimada and coworkers from the Division of Digestive and General Surgery, Graduate School of Medical and Dental Sciences, Niigata University, regarded TMB-H from a specific CRC patient subgroup, as a more robust marker for predicting the efficacy of ICIs, and developed a convolutional neural network (CNN) - based algorithm to predict TMB-H CRC directly from the histopathological characteristics, in particular, the TIL, obtained from the hematoxylin and eosin (H&E) stained slides. A representative microscopic image of the H&E stained tumor mutational burden-high colorectal cancer tumor is shown in the accompanying figure, demonstrating the presence of tumor-infiltrating lymphocytes in significantly elevated level compared to normal surrounding tissue. Digital information from such this neoplastic and also non-neoplastic images obtained from JP-CRC-cohort is transformed and normalized for building a predictive Convoluted Neural Network model employing Inception V3 learning model, by Dr. Shimada group. The CNN-based model developed by Dr. Shimada and coworkers has the potential to not only reduce the burden of proper diagnosis on pathologists but also provide the necessary information on the patients' responsiveness to the ICI based therapeutics, without the use of expensive, time consuming and not easily available gene panel testing. This study by Dr. Shimada and coworkers is published in a recent issue of Journal of Gastroenterology (2021; vol. 56: pp. 547-559; https://doi.org/10.1007/s00535-021-01789-w).
In addition, the studies of Dr. Shimada group also provided means to predict TMB-H CRC only by using the TIL information from the H&E slides from the patients' tumor tissues. However, considering that the patients in the studied cohort were not treated with any ICIs, no conclusions could be drawn regarding their ICI responsiveness following the TMB-H diagnosis and it was suggested that future clinical trials need to be conducted to address whether TIL alone can be useful as a predictive biomarker for the efficacy of ICIs. Dr. Shimada says about the present study: "We have developed artificial intelligence to predict genetic alterations in colorectal cancer by deep learning using hematoxylin and eosin slides. This artificial intelligence is important in solving the cost problems associated with genetic analysis and facilitating personalized medicine in colorectal cancer."
Overall, the studies by Dr. Shimada and associates provide a cost and time effective and reliable method to inform the clinicians if the CRC patient they are managing can benefit from Immune Checkpoint Inhibitor (including inhibitors of the PD-1 protein and its ligand, PD-L1) therapy, without implicating the use of gene panel.
INFORMATION:
[Attachments] See images for this press release:
ELSE PRESS RELEASES FROM THIS DATE:
2021-06-14
Quantum technologies are based on quantum properties of light, electrons, and atoms. In recent decades, scientists have learned to master these phenomena and exploit them in applications. Thus, the construction of a quantum computer for commercial applications is also coming within reach. One of the emerging technologies that is currently being advanced very successfully is ion trap quantum computers. Here, charged particles are trapped with electromagnetic fields in a vacuum chamber and prepared in such a way that they can serve as carriers for information and be used for computing, which includes cooling them to the lowest temperatures permitted by quantum mechanics. However, the quantum mechanical ...
2021-06-14
Various platforms which offer food home delivery services through courier services, such as riders or other types of distributors, have proliferated very quickly in recent years, especially in big cities. Due to this boom in last-mile delivery or logistics, UOC experts have studied the operation of the main food home delivery platforms, such as Just Eat, Glovo and Deliveroo, which work in the city of Barcelona, to analyse the profitability of these business models and estimate the number of orders needed to achieve this profitability.
"It's very difficult for these business models to be profitable by themselves", said Eduard J. Álvarez Palau, a researcher from the SUMA research group of the UOC's Faculty of Economics and Business, the main author of this work ...
2021-06-14
Near-field light is invisible light at the subwavelength scale. Harnessed for a variety of practical applications, such as wireless power transfer, near-field light has an increasingly significant role in the development of miniature on-chip photonic devices. Controlling the direction of near-field light propagation has been an ongoing challenge that is of fundamental interest in photonics physics and can significantly advance a variety of applications.
So far, propagation of near-field light in a single direction is achieved by specific interactions between ...
2021-06-14
The human gut microbiome is a complex community of trillions of microbes that are constantly interacting with each other and our bodies. It supports our wellbeing, immune system and mental health - but how is it sustained?
Researchers in the UK and Germany, alongside other international collaborators, have investigated the evolution of bacteria in the human gut microbiome - asking how these microbes persist throughout their lifetimes - taking into account internal and external influencing factors.
The results of the study will help inform tailored probiotics, live bacteria found in particular foods or supplements, as well as dietary ...
2021-06-14
The structure of a biomolecule can reveal much about its functioning and interaction with the surrounding environment. The double-helical structure of DNA and its implications for the processes of transmission of genetic information form an obvious example. In a new study by SISSA - Scuola Internazionale Superiore di Studi Avanzati, published in Nucleic Acids Research, experimental data were combined with computer simulations of molecular dynamics to examine the conformation of an RNA fragment involved in protein synthesis and its dependence on the salts present in the solution. The research has led to a new method for high-resolution definition of the structures of biomolecules in their physiological environments. ...
2021-06-14
BOSTON - Bronchiolitis--the most common lung infection in young children, and which is most often caused by respiratory syncytial virus, or RSV--is the leading cause of hospitalizations in U.S. infants, and about 30% of those with severe bronchiolitis later develop asthma. A team led by investigators at Massachusetts General Hospital (MGH) has uncovered four distinct molecular subtypes of RSV bronchiolitis and has linked a certain subtype to a higher asthma risk. The findings are published in Nature Communications.
"While bronchiolitis has been considered a single ...
2021-06-14
These are the findings of an Imperial-led study using data from thousands of children in England over a number of years, which looked at the health impact of consuming ultra-processed foods (UPFs) - food and drink heavily processed during their making, such as frozen pizzas, fizzy drinks, mass-produced packaged bread and some ready meals.
Researchers found that not only do UPFs make up a considerably high proportion of children's diets (more than 40% of intake in grams and more than 60% of calories on average), but that the higher the proportion of UPFs they consume, ...
2021-06-14
Coronavirus disruption to weddings has highlighted the complexity and antiquity of marriage law and reinforced the need for reform, a new study shows.
During the pandemic the ease and speed with which couples were able to marry has depended on their chosen route into marriage - religious or civil - experts have found.
Rules to prevent the spread of the pandemic attempted to strike a balance between getting married as a legal event and a wedding as a social event, and this has failed to please anyone, according to the research.
As lockdown loomed, couples marrying in the Anglican church were able to apply for a common or special licence rather than waiting to ...
2021-06-14
LOUISVILLE, Ky. - A clinical trial conducted at the University of Louisville has shown for the first time that heart failure treatments using cells derived from the patient's own bone marrow and heart resulted in improved quality of life and reduced major adverse cardiac events for patients after one year.
"This is a very important advance in the field of cell therapy and in the management of heart failure. It suggests that a treatment, given only once, can produce long-term beneficial effects on the quality of life and prognosis of these patients," said Roberto Bolli, M.D., ...
2021-06-14
HOUSTON - (June 11, 2021) - Scientific studies describing the most basic processes often have the greatest impact in the long run. A new work by Rice University engineers could be one such, and it's a gas, gas, gas for nanomaterials.
Rice materials theorist Boris Yakobson, graduate student Jincheng Lei and alumnus Yu Xie of Rice's Brown School of Engineering have unveiled how a popular 2D material, molybdenum disulfide (MoS2), flashes into existence during chemical vapor deposition (CVD).
Knowing how the process works will give scientists and engineers a way to optimize the bulk manufacture ...
LAST 30 PRESS RELEASES:
[Press-News.org] Histopathology-driven artificial intelligence predicts TMB-H colorectal cancer
Neural networks and histology based prediction of tumor mutational burden-high colorectal cancer for the effective therapeutic use of immune check point inhibitors
