Tissue Phenomics Blog

5B_Her2-classified.jpg

Posts by Topic

see all

Topics:  clinical trials, tissue phenomics, image analysis, machine learning

Benefits of Automated Slide Reading as a Way to Decrease Human Error in Clinical Trials and thus in Patient Care

Sep 14, 2017 8:28:20 AM

Human error is natural. It is a result on how the human brain works and its biological limitations. Though human error is inevitable and also normal in highly specialized experts such as pathologists, it should not end in failure and affecting the quality of diagnosis and the selection of the adequate treatment. However, mistakes also help us and any system to learn. The error rate for complex logic errors (which applies to reading and interpreting tissue slides) is about 5% overall. Despite extensive training and education, it does not seem to drop below this natural threshold.

Read More

Topics:  Immunotherapy, clinical trials, image analysis, predictive test, tumor microenvironment, oncology

Evaluation of the Tumor Microenvironment Using Image Analysis for Clinical Trials

May 8, 2017 7:30:00 AM

Advances in immunotherapy have dramatically changed the landscape for cancer researchers. With significant improvements in overall survival and recurrent free survival in some of the deadliest cancers, lives have been extended by years for some patients while other patients have not experienced benefit from immunotherapy treatment. For some cancer indications, such as non-small cell lung cancer, the FDA approved companion diagnostic test for PD-L1 by immunohistochemistry has predictive value on patient response. However, the test is not a perfect indicator of response as some PD-L1 negative patients will respond to therapy and, conversely, some PD-L1 positive patients will not. At the same time, the number of clinical trials examining immunotherapy and combination therapies with immunotherapy as a backbone has exceeded 1000 in 2017. The possibility of combination therapy brings many questions to light for the researcher and ultimately the physician on which therapy to choose, for how long, in what order and what potential combination. With these questions, comes the increasing need for predictive tests that can lead the physician to the right therapy at the right time.

Read More

Topics:  machine learning, image analysis, digital pathology, deep learning, big data

Machine Learning in Digital Pathology: A Journey from Handcrafted Feature Descriptors to Deep Learning Approaches

Apr 3, 2017 5:00:00 AM

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

Topics:  image analysis, real world evidence, tissue phenomics, Immunotherapy, immuno-oncology

Three reasons image analysis should be incorporated into your immunotherapy real-world evidence development strategy

Jan 9, 2017 5:00:00 AM

Clinical trials are extremely important to assess the safety and effectiveness of a new therapy or of a currently-available therapy in a new indication. However, there are a few drawbacks to clinical trials, such as:

Read More

Topics:  image analysis, drug development, clinical trials, cancer treatment, immuno-oncology, Immunotherapy, predictive biomarkers

How Image Analysis Can Improve the Results of Drug Development and Clinical Trials

Dec 12, 2016 4:00:00 AM

In recent years there have been several potentially life-saving medications approved for cancer treatment, including targeted molecular entities and biologics such as Opdivo (nivolumab) and Keytruda (pembrolizumab). Oncology drugs remain a pharmaceutical priority and investments into cancer account for 30% of all pre-clinical and phase 1 clinical development expenditures. There is an impressive list of close to 800 drugs and vaccines currently in the industry-wide development pipeline, many with promising results in early-stage clinical trials. However by historical measures only 10% or fewer of these drugs will ever make it through FDA approval and become part of routine patient care.

Read More