As outlined in the recent blog article by Dr. Ralf Huss, CMO of Definiens, we believe in big data and machine learning to significantly influence decision making in medicine. Already in digital histopathology, machine learning is a key component, for example, for the detection of regions of interest (e.g., tumor metastasis regions, stroma regions) or for the detection, segmentation and classification of objects of interest (e.g., nuclei, cells, mitosis, glomeruli and glands). The use of machine learning in digital pathology is motivated by the complexity and variety of the problems, and it has been enabled only recently by the availability of large amounts of raw data (e.g., the public TCGA database from the NIH) and of efficient algorithms or increased computing power. However, while big data is getting even bigger by the minute, we cannot accept algorithms without a medical plausibility check and robust clinical validation.Read More
Machine Learning in Digital Pathology: A Journey from Handcrafted Feature Descriptors to Deep Learning Approaches
Highly-paid doctors will not be obsolete and radiologists or anatomical pathologists will not be obsolete in the age of AI in medical practice. In a recent New England Journal of Medicine Paper (http://www.nejm.org/doi/full/10.1056/NEJMp1606181) Drs. Obermeyer and Emanuel (1) rightly suggest that big data will transform daily medical practice and computer-based algorithms will guide clinical decision making.Read More
Path to personalised medicine
Pathology is one of the main driving forces behind personalised or precision medicine. In fact it has always striven towards the accurate diagnosis and prognosis of a patient’s disease through the observation of tissue architecture under the microscope. Through the application of international staging guidelines, such as the Tissue, Node, Metastasis (TNM) system in the majority of cancers, pathologists are very good at predicting prognosis at the population scale but not so good at predicting a prognosis for the individual patient. For example, if a patient presents with stage II colorectal cancer (CRC) they are predicted to have 20-30% chance of succumbing to their disease. However, it is currently difficult to accurately identify if an individual patient will be within that 20-30% group.Read More
When you hear the term “Big Data”, most people think of the huge volumes of structured or unstructured data from different sources. For diagnostics, extracting meaningful information from big data offers the great potential of detecting novel biomarkers to provide targeted patient treatment.
Tissue Phenomics™ is a big data approach to clinical oncology that enables all of the data in tissue images to be fully quantified in context. This automated quantification takes all standard pathological tissue biomarkers used to make diagnoses plus new complex tissue signatures – which often are difficult to assess with the human eye – and makes them available for bioinformatic analysis.
The core of Tissue Phenomics™ is the Definiens' Cognition Network Technology® (CNT) which has been used by many researchers on a small data scale.Read More