Developed by VHIO, a novel AI-based and non-invasive diagnostic tool enables accurate brain tumor diagnosis, outperforming current classification methods

2024-03-11

(Press-News.org)

Developed by VHIO, a novel AI-based and non-invasive diagnostic tool enables accurate brain tumor diagnosis, outperforming current classification methods

Developed by VHIO’s Radiomics Group in close collaboration with researchers of the Neuroradiology Unit at the Bellvitge University Hospital (HUB), DISCERN is a deep learning tool that leverages information of magnetic resonance imaging and facilitates brain tumor classification to aid clinical decision making. Currently, a definitive diagnosis often requires neurosurgical interventions that compromise the quality of life of patients. Trained to differentiate between the three most common brain malignancies, DISCERN has demonstrated 78% accuracy in the classification of these tumors. Results of this VHIO-led study have now been published in the journal Cell Reports Medicine.

Jointly developed by investigators of the Vall d’Hebron Institute of Oncology’s (VHIO) Radiomics Group and the Bellvitge University Hospital’s Neuroradiology Unit, the Diagnosis in Susceptibility Contrast Enhancing Regions for Neuroncology (DISCERN) is an open access, deep learning tool based on the training of patterns using artificial intelligence models from information of standard magnetic resonance imaging (MRI). Published in the journal Cell Reports Medicine*, results of a VHIO-led study demonstrate the feasibility and accuracy of DISCERN as an enabler of accurate brain tumor diagnosis from perfusion MRI, outperforming conventional methods.

Differential diagnosis of brain tumors

Glioblastoma multiforme, brain metastasis from solid tumors, and primary central nervous system lymphoma account for up to 70% of all malignant brain cancers. Given that each of these malignancies require a distinct therapeutic approach, differential diagnosis between these different malignancies represents an unmet clinical need.

“The non-invasive differential diagnosis of brain tumors is currently based on the assessment of magnetic resonance imaging before and after contrast administration. However, a definitive diagnosis often requires neurosurgical interventions that compromise the quality of life of patients,” said Raquel Perez-Lopez, Head of VHIO’s Radiomics Group and corresponding author of this present study.

“This work is the result of more than five years’ research focused on the identification of innovative magnetic resonance perfusion imaging biomarkers to enable the differential diagnosis of brain tumors. This present study integrates insights generated by other previous research projects on artificial intelligence, resulting in the development of software that automates presurgical diagnostic classification with very good precision, while facilitating its clinical applicability with a user-friendly interface for clinicians," added Albert Pons-Escoda, a Clinical Neuroradiologist and Investigator of the Neuroradiology Unit at the Bellvitge University Hospital, and co-author of this study.

This novel deep learning tool leverages the full spatial and temporal information of conventional MRI to identify behavioral patterns on imaging specific to each tumor.

“Deep learning teaches the machine the characteristics of each tumor detected by magnetic resonance imaging of already diagnosed patients. For example, if we show the machine thousands of images of dogs and cats, it will learn the distinct and defining characteristics of both species, and when it sees a new image, it can differentiate between the two,” added Alonso García-Ruiz, a Ph.D. Student of VHIO’s Radiomics Group and first author of this study.

In this case, the learning units are voxels which represent the minimum measurement of volume to study MRI scans and are equivalent to pixels, but three-dimensional display elements. The investigators trained DISCERN to learn the characteristics of these three most common brain malignancies on 50,000 voxels from 40 diagnosed patients.

“Validating this deep learning tool in more than 500 additional cases, results of this present study demonstrate 78% accuracy in the classification of these tumors, surpassing conventional methods,” observed Perez-Lopez

“DISCERN is a computerized diagnostic support tool that facilitates the classification of brain tumors to help guide medical decision making by multidisciplinary teams regarding the need for and type of surgery required to confirm diagnosis,” said Carles Majós, Clinical Neuroradiologist and Investigator of the Neuroradiology at the Bellvitge University Hospital, and a co-author of this study.

To enhance study reproducibility and accelerate its adoption in clinical studies, the proposed method developed by VHIO’s Radiomics Group, in close collaboration with investigators of HUB’s Neuroradiology Unit, has been implemented on the user-friendly, open access DISCERN application. For demonstrative purposes, the DISCERN app can be accessed at http://84.88.64.102:5000/discern-app for research purposes.

This study was carried out in collaboration with colleagues at the Neuroradiology Unit of the Bellvitge Biomedical Research Institute – IDIBELL and Clínic Hospital (Barcelona, Spain), and HT Medica (Andalucia, Spain), and Radiation Medicine and Applied Sciences and Bioengineering Departments of the University of California (San Diego, USA).

This work has been carried out thanks to the support received from the CRIS Cancer Foundation, FERO Foundation, and “la Caixa” Foundation, which fund research of VHIO’s Radiomics Group through various initiatives.

###

Reference:

*Alonso Garcia-Ruiz, Albert Pons-Escoda, Francesco Grussu, Pablo Naval-Baudin, Camilo Monreal-Aguero, Gretchen Hermann, Roshan Karunamuni, Marta Ligero, Antonio Lopez-Rueda, Laura Oleaga, Manuel Álvaro Berbís, Alberto Cabrera-Zubizarreta, Teodoro Martin-Noguerol, Antonio Luna, Tyler M. Seibert, Carlos Majos, Raquel Perez-Lopez. An accessible deep learning tool for voxel-wise classification of brain malignancies from perfusion MRI. Cell Reports Medicine (2024), http://dx.doi.org/10.2139/ssrn.4559395

About VHIO

The Vall d’Hebron Institute of Oncology (VHIO), established in 2006 and located within the Vall d’Hebron Campus, is a reference comprehensive cancer center for personalized medicine in oncology. Through our purely translational and multidisciplinary research model, we aim to improve the prevention, early diagnosis and treatment of cancer by transforming the latest scientific discoveries made in the laboratory into early phase clinical trials for the development of more effective therapies to improve the quality of life and survival of cancer patients.

VHIO forms part of the CERCA – Research Centres of Catalonia system and is accredited as a Severo Ochoa Center of Excellence.

Research at VHIO would not be possible without the support received from our patrons - Generalitat de Catalunya, Fundació Privada CELLEX, "La Caixa" Foundation, Fundación FERO, and the Fundación BBVA, the public funding it receives as well as the generous support from institutional supporters, private institutions, companies, associations, societies, and individual donors. Only with such continued support will VHIO continue to advance personalized and targeted therapies against cancer.

END

[Attachments] See images for this press release:

ELSE PRESS RELEASES FROM THIS DATE:

Natural history specimens have never been so accessible

2024-03-11

With the help of 16 grants from the National Science Foundation, researchers have painstakingly taken computed topography (CT) scans of more than 13,000 individual specimens to create 3D images of more than half of all the world's animal groups, including mammals, fishes, amphibians and reptiles. The research team, made of members from The University of Texas at Arlington and 25 other institutions, are now a quarter of the way through inputting nearly 30,000 media files to the open-source repository MorphoSource. This will allow researchers ...

NRL research physicists explore fiber optic computing using distributed feedback

2024-03-11

WASHINGTON – U.S. Naval Research Laboratory (NRL) researchers deliver novel contribution in fiber optics computing, Fiber Optic Computing Using Distributed Feedback paper recently published in Communications Physics journal, brings the Navy one step closer to faster, more efficient computing technologies. Optical computing uses the properties of light, such as its speed and ability to carry large amounts of data, to process information more efficiently than traditional electronic computers. In collaboration with Sandia National Laboratories and the University of Central Florida, NRL is aiming ...

Canals used to drain peatlands are underappreciated hotspots for carbon emissions

2024-03-11

A new study led by UC San Diego Scripps Institution of Oceanography postdoctoral scholar Jennifer Bowen finds that canals used to drain soggy peatlands in Southeast Asia are likely hotspots for greenhouse gas emissions. The results, published March 8 in Nature Geoscience and supported by the Scripps Institutional Postdoctoral Program and Stanford University’s Precourt Institute for Energy, identify a previously unaccounted for source of emissions from these threatened, carbon-rich landscapes. Findings from the study suggest that the degradation of tropical peatlands in Southeast Asia has released even more planet-warming ...

Nutritional value of meat should be considered when comparing carbon footprints

2024-03-11

The nutritional value of meat must be considered when comparing carbon footprints – that is the key message from a recent study undertaken by Hybu Cig Cymru – Meat Promotion Wales (HCC), Bangor University, Queen’s University, and the Agri-Food and Biosciences Institute (AFBI). The scientific paper, published in the journal Frontiers in Sustainable Food Systems using data from the Welsh Lamb Meat Quality project, focuses on different lamb production systems, specifically the ‘finishing’ period – at the end of which lambs have reached the required weight, meat and fat cover for ...

Microscopy plus deep learning to advance prostate cancer diagnosis

2024-03-11

Prostate cancer stands as a prevalent threat to men's health, ranking second in cancer-related deaths in the United States. Each year, approximately 250,000 men in the U.S. receive a prostate cancer diagnosis. While most cases have low morbidity and mortality rates, a subset of cases demands aggressive treatment. Urologists assess the need for such treatment primarily through the Gleason score, which evaluates prostate gland appearance on histology slides. However, there's considerable variability in interpretation, leading to both undertreatment and overtreatment. The current method, based on histology ...

Cancer researchers awarded $3.2 million grant to find better ways to treat advanced melanoma

2024-03-11

A team of investigators from the UCLA Health Jonsson Comprehensive Cancer and the University of Arkansas for Medical Sciences (UAMS) Winthrop P. Rockefeller Cancer Institute was awarded a $3.2 million grant from the National Institutes of Health to identify new ways to prevent and overcome treatment resistance to targeted therapy in patients with all sub-types of cutaneous melanoma, an aggressive form of skin cancer. Virtually all cutaneous melanomas display genetic alterations that ...

The liver immune system eats up ‘bad cholesterol’

2024-03-11

A new study from Karolinska Institutet in Sweden reveals that immune cells in the liver react to high cholesterol levels and eat up excess cholesterol that can otherwise cause damage to arteries. The findings, published in Nature Cardiovascular Research, suggest that the response to the onset of atherosclerosis begins in the liver. Cholesterol is a type of fat that is essential for many functions in the body, such as making hormones and cell membranes. However, too much cholesterol in the blood can be harmful, as it can stick to the walls of the arteries ...

New study finds female entrepreneurs do better with guidance from female mentors

2024-03-11

INFORMS Journal Marketing Science Study Key Takeaways: Female entrepreneurs increase their chances of success and improved performance with female mentors. One of the key benefits to female entrepreneurs is a mentoring style characterized as “positive engagement.” BALTIMORE, MD, March 11, 2024 – In business and in life, the power of mentorship has long been understood, but how important is it that your mentor look like you? This question was at the center of a new study, which specifically found that mentor gender has a powerful impact on ...

Using wrist-worn activity trackers to help patients reduce long COVID symptoms

2024-03-11

LA JOLLA, CA—Scientists at the Scripps Research Digital Trials Center have partnered with the health technology company CareEvolution to launch a remote study that will investigate whether wrist-worn devices, such as activity trackers and smartwatches, can help people with long COVID manage and reduce the severity of their symptoms. “New treatments and interventions are urgently needed,” says the study principal investigator Julia Moore Vogel, PhD. “We’re excited to launch the Long COVID Wearable Study and ...

AI-generated food images look tastier than real ones

2024-03-11

With the Global Nutrition and Hydration Week 2024 starting today, researchers have announced an intriguing discovery – consumers generally prefer AI-generated images of food over real food images, especially when they are unaware of their true nature. The new findings have been published in Food Quality and Preference. According to the researchers, the results suggest that AI-generated food visuals excel at enhancing the appeal of depicted foods by leveraging key features such as symmetry, shape, glossiness, and overall lighting and colour. All of these are known to contribute significantly ...

LAST 30 PRESS RELEASES:

Lower dose of mpox vaccine is safe and generates six-week antibody response equivalent to standard regimen

Personalised “cocktails” of antibiotics, probiotics and prebiotics hold great promise in treating a common form of irritable bowel syndrome, pilot study finds

Mobile device location data is already used by private companies, so why not for studying human-wildlife interactions, scientists ask

[Press-News.org] Developed by VHIO, a novel AI-based and non-invasive diagnostic tool enables accurate brain tumor diagnosis, outperforming current classification methods