A deep learning model to predict RNA-Seq expression of tumours from whole slide images was among the industry innovations outlined at the 7th Digital Pathology and AI Congress for Europe. Created by French-American start-up Owkin, the detail of how the compny’s HE2RNA model provides virtual spatialization of gene expression was detailed to online delegates by senior translational scientist…
Researchers at Massachusetts General Hospital (MGH) in Boston have developed a novel blood test using an enhanced form of liquid biopsy capable of detecting the most common types of genetic mutations that occur in glioma brain tumors. The test is easy to use, inexpensive, produces results rapidly, and can be performed in most clinical laboratories. The researchers believe that the blood test has…
Hologic, Inc. has completed the acquisition of Somatex Medical Technologies GmbH, a leader in biopsy site markers and localization technologies, for approximately $64 million. The company was previously owned by E-Med Solutions GmbH, Berlin, a group of investors led by German private equity company Westlake Partners.
Colon cancer stem cells have one weak spot: the enzyme Mll1. An MDC team led by Walter Birchmeier has now shown in Nature Communications that blocking this protein prevents the development of new tumors in the body. Since colonoscopies were introduced in Germany for early cancer detection, the number of diagnoses of advanced cancer every year has decreased, as precancerous lesions can now be…
A software tool to predict the most effective therapy for non-small cell lung cancer (NSCLC) developed by applying deep learning artificial intelligence (AI) to positron emission tomography/computed tomography (PET/CT) images has been developed by researchers at H. Lee Moffitt Cancer Center and Research Institute in Tampa, Florida. The tool is designed to provide a noninvasive, accurate method to…
Tumours with the same biology have different prognoses based on their method of detection, and this information should be taken into account when deciding which treatments might be needed, a Dutch researcher explained at the 12th European Breast Cancer Conference.
In order to analyze tumors, they have to be cut into thin slices. Now, a new technology has been developed that makes pieces of the tumor visible in 3D without cutting them.
Research led by Barts Cancer Institute (BCI), Queen Mary University of London, has revealed novel insights into the mechanisms employed by melanoma cells to form tumours at secondary sites around the body. The findings from the study may help to identify new targets to inhibit melanoma spread and guide treatment decisions in the clinic.
Researchers have found a surprising effect of the stem cell-regulating growth factor R-spondin in intestinal cancer.
Spatial analytics offers greater clarity in the assessment of tumours beyond routine microscopic analysis. High-capacity digital image analysis enables new methods of spatial statistics to extract features not immediately distinguishable by visual inspection. These subvisual features reflect complex properties, such as intratumour heterogeneity and have the additional benefit that they can target…
Neuroradiologist Dr Sofie Van Cauter described the challenges to brain tumour image segmentation during the European Society of Medical Imaging Informatics (EuSoMII) annual meeting in Valencia. She also outlined how, when clinically validated, AI could help tackle such problems. The WHO classification of brain tumours has come a long way since first introduced in 1979. The 2016 classification was…
To answer medical questions that can be applied to a wide patient population, machine learning models rely on large, diverse datasets from a variety of institutions. However, health systems and hospitals are often resistant to sharing patient data, due to legal, privacy, and cultural challenges. An emerging technique called federated learning is a solution to this dilemma, according to a study…
Scientists from the German Cancer Research Center (DKFZ) and the Universities of Cambridge and Edinburgh have been studying the evolution of tumors following chemical damage. They discovered that the DNA lesions caused by the chemical are not eliminated immediately, but are passed on unrepaired over several rounds of cell division. This "lesion segregation" can drive unexpectedly…
A new machine learning approach classifies a common type of brain tumour into low or high grades with almost 98% accuracy, researchers report in the journal IEEE Access. Scientists in India and Japan, including from Kyoto University’s Institute for Integrated Cell-Material Sciences (iCeMS), developed the method to help clinicians choose the most effective treatment strategy for individual…
Early detection of tumors is extremely important in treating cancer. A new technique developed by researchers at the University of California, Davis, offers a significant advance in using magnetic resonance imaging (MRI) to pick out even very small tumors from normal tissue. The work is published in the journal Nature Nanotechnology. Chemical probes that produce a signal on MRI can be used to…
Our immune system not only protects us against infection, but also against cancer. This powerful protection is based in particular on the activation of special cells of the immune system, CD8+ T cells. These cells recognize infected or cancer cells and kill them specifically. “The ability of the immune system and especially CD8+ T cells to eliminate cancer cells in tissues such as the lung, gut…
A receptor in the cell layer that lines the blood vessels from the inside stimulates both the formation of new blood vessels in tumors and metastasis.
The causes of 40 percent of all cases of certain medulloblastoma – dangerous brain tumors affecting children – are hereditary. These are the findings of a recent genetic analysis carried out by scientists from the Hopp Children's Cancer Center (KiTZ), the European Molecular Biology Laboratory (EMBL) and numerous colleagues around the world, which have just been published in the scientific…
Novel advanced imaging biomarkers are being developed in a series of studies at several UK centres that may lead to the earlier assessment of treatment response to glioblastoma (GBM) and a better survival rate.
Glioblastomas are complex, fast-growing malignant brain tumors that are made up of various types of cells. Even with aggressive treatment — which often includes surgery, radiation, and chemotherapy — glioblastomas are difficult to treat, leading to an average survival of 11-15 months. In research published in Science Advances, Xavier Intes, a professor of biomedical engineering at Rensselaer,…
The human immune system can recognize and eliminate not only germs but also cancer cells. This is why treatments with weakened germs can help the immune system in its fight against cancer. Researchers at the Max Planck Institute for Infection Biology in Berlin have genetically modified the tuberculosis vaccine BCG in a way that it stimulates the immune system more specifically. Consequently, the…
A simple blood test coupled with artificial intelligence (AI) analysis could help spot the signs of a brain tumour sooner in patients. Brain tumour diagnosis is difficult: patients often see their family doctor (GP) several times before referral for a scan. However, research presented at the 2019 National Cancer Research Institute (NCRI) Cancer Conference in Glasgow last November suggests the…
Scientists have created one of the most detailed maps of breast cancer ever achieved, revealing how genetic changes shape the physical tumour landscape. An international team of scientists, brought together by a £20 million Grand Challenge award from Cancer Research UK, has developed intricate maps of breast tumour samples, with a resolution smaller than a single cell. These maps show how the…
How can the treatment of soft tissue sarcomas, these particularly resistant and aggressive forms of cancer, be improved and better personalized? An international team led by Wolf Hervé Fridman with researchers from Inserm, Sorbonne Université and Université de Paris at the Cordeliers Research Center, in collaboration with the French League against cancer and Institut Bergonié, has shown that…
Researchers at Osaka University have developed a computer method that uses magnetic resonance imaging (MRI) and machine learning to rapidly forecast genetic mutations in glioma tumors, which occur in the brain or spine. The work may help glioma patients to receive more suitable treatment faster, giving better outcomes. The research was recently published in Scientific Reports. Cancer treatment…