
News • Deep learning refinement
Colorectal cancer: AI tool improves diagnostic accuracy
Researchers from Finland have developed an artificial intelligence tool for automatic colorectal cancer tissue analysis that outperforms prior methods.
Researchers from Finland have developed an artificial intelligence tool for automatic colorectal cancer tissue analysis that outperforms prior methods.
For the first time, researchers show that AI-based predictions can deliver comparable results to clinical tests on biopsies of patients with colorectal cancer (CRC).
Experts have highlighted how precision pathology using Artificial Intelligence can provide an effective alternative to molecular diagnostics. This, say a team from the Karolinska Institutet (KI) in Stockholm, Sweden, can also offer multiple advantages within a clinical setting and support risk stratification.
An 'encyclopaedia' of protein alterations in soft tissue sarcomas could open the door to a new era of understanding and treatment for this group of rare cancers.
A new study led by researchers from the University of Notre Dame links a high body mass index (BMI) to alterations in the structure and environment of cancerous tumors.
With the introduction of digital pathology, the University of Queensland and Sullivan Nicolaides Pathology aim to provide significantly improved tests in terms of cost, quality and speed.
Researchers have found a possible explanation as to why higher breast density and older age increase the risk of breast cancer. According to the experts, adipocytes play a vital role here.
A research team at UCLA has made an important advancement to address one of the major challenges in cell-free DNA (cfDNA) testing, also known as liquid biopsy.
From current mixed reality assistance, technological advances could soon make fully digital autopsies a reality. This could enhance efficiency and legal certainty, and also benefit training.
Researchers at Harvard Medical School developed a new tool that promises to improve the way pathologists see and evaluate a tumor by providing detailed clues about the cancer.
A study led by the National Institutes of Health’s RECOVER Initiative and supported by NYU Langone Health provides an expanded working definition of long Covid.
Lyme disease, the most common tick-transmitted bacterial infection in the world, is challenging to diagnose. Initial early-stage symptoms may include skin rash, fever, headache, fatigue, swollen lymph nodes, and/or body and joint aches. However, these symptoms are also associated with many other diseases and medical conditions.
It is crucial that labs can rely on their slides for a seamless – and accurate – diagnosis. With many more commercial instruments focusing on flexibility and choice, these qualities are difficult to separate from subjectivity and complexity.
The Netherlands Cancer Institute (NKI) will deploy a diagnostic platform from digital and computational pathology solutions provider Proscia, the company announced.
A new blood test that can track and follow the neurodegeneration in Alzheimer's disease - and exclude other dementias.
Dutch scientists have discovered how specialized immune cells can detect and remove cancers that are ‘invisible’ to the conventional defense mechanisms of the immune system.
Swedish researchers have developed a method that should be able to predict whether a patient with breast cancer will benefit from a particular treatment or not.
New research shows the power of artificial intelligence (AI) applied to endometrial carcinoma microscopy images. This could improve diagnosis and treatment of uterine cancer.
In a recent study, a US research team developed a revolutionary laser-based approach to perform microbiopsies. Their novel method could make biopsies faster, more cost-effective, and less harmful to the patient.
The Tissue-Tek Genie Advanced Staining System is the first and only fully automated, true random access stainer for immunohistochemistry (IHC) and in situ hybridisation (ISH); allowing any IHC or ISH capsule or probe to be loaded at any time on any station.
Imagine, one single standardising solution, enabling uncompromisingly fast results and providing you with the exact same predictable turnaround time.
Scientists have discovered that cervical cancer can be divided into 2 distinct molecular subgroups – one far more aggressive than the other – as part of the largest ‘omics’ study of its kind.
The tall cell variant (TCV) is an aggressive subtype of papillary thyroid carcinoma (PTC). Sebastian Stenman, researcher from the Institute for Molecular Medicine, and the Department of Pathology at the University of Helsinki, Finland, is developing and training a deep learning algorithm using supervised learning to detect and quantify the proportion of tall cells in PTC.
Renal cell carcinoma is among the fifteen most common cancers worldwide. Dr Titus Brinker, from the German Cancer Research Center (DKFZ), looked at whether a convolutional neural network (CNN) can extract relevant image features from a typical H&E-stained slide to predict 5-year overall survival.
Deaths from cancer are currently estimated at 10 million each year worldwide. Conventional cancer staging systems aim to categorize patients into different groups with distinct outcomes. ‘However, even within a specific stage, there is often substantial variation in patient outcomes,’ Markus Plass, academic researcher from the Medical University of Graz, Austria, explained to Healthcare in…