Traditional approach to peer review for non-clinical studies involving a second person review of the slide, data, and interpretation of the slide conducted by a peer has its own downsides that are eliminated by organizations that have long embraced digital pathology.
For anyone who enjoys networking and meeting up with real humans to talk science and technology face-to-face, 2020 and 2021 was a bit of a slog.
Whole-slide imaging (WSI), also known as virtual microscopy, involves the use of scanners to image the entire tissue slide. The resulting high-resolution digital images are available for pathologists to review or share with collaborators around the globe. WSI scanners and technologies for whole-slide image analysis are evolving rapidly. WSI is becoming an integral part of digital pathology, and emerging WSI technologies promise to shape the future of diagnostic pathology.
DeepBio has announced that its deep learning-based prostate cancer pathology diagnosis technology using a Gleason grading system acquired NET (new excellent technology) certification on Tuesday.
The researchers used prostate specimens from patients who underwent surgery more than 10 years ago, so the team knew each patient's outcome and could use that information to train a computer to predict those outcomes. In this study, half of the samples contained a more aggressive cancer.To create 3D samples, the researchers extracted "biopsy cores"—cylindrically shaped plugs of tissue—from surgically removed prostates and then stained the biopsy cores to mimic the typical staining used in the 2D method. Then the team imaged each entire biopsy core using an open-top light-sheet microscope, which uses a sheet of light to optically "slice" through and image a tissue sample without destroying it.The 3D images provided more information than a 2D image—specifically, details about the complex tree-like structure of the glands throughout the tissue. These additional features increased the likelihood that the computer would correctly predict a cancer's aggressiveness.The researchers used new AI methods, including deep-learning image transformation techniques, to help manage and interpret the large datasets this project generated."Over the past decade or so, our lab has focused primarily on building optical imaging devices, including microscopes, for various clinical applications. However, we started to encounter the next big challenge toward clinical adoption: How to manage and interpret the massive datasets that we were acquiring from patient specimens," Liu said. "This paper represents the first study in our lab to develop a novel computational pipeline to analyze our feature-rich datasets. As we continue to refine our imaging technologies and computational analysis methods, and as we perform larger clinical studies, we hope we can help transform the field of pathology to benefit many types of patients."The team published these results in Cancer Research.Source: University of Washington
Paige, the global leader in AI-based diagnostic software in pathology, today announced that the United Kingdom’s National Institute for Health and Care Excellence (NICE) published a Medtech Innovation Briefing (MIB) on Paige Prostate, a clinical-grade artificial intelligence (AI)-based diagnostic software system that aids pathologists in detecting, grading and measuring prostate tumors in biopsies obtained from patients at risk of prostate cancer. This marks the first-ever MIB for a digital pathology product.NICE conducted a systematic literature review and thoroughly evaluated five peer-reviewed clinical utility studies that included a total of 3,444 prostate needle biopsies.
The analysis of biomarkers in tissue sections is a powerful tool to study the molecular and histological features of healthy and pathological tissues, diagnose diseases, and monitor—or even predict—treatment response. Traditionally, the expression status of certain biomarkers, such as growth factor receptors, has been used to distinguish molecular subtypes of diseases and determine the best treatment for [...]
Sierra ICC profiles generated by FFEI colour calibration products can now be imported into Visiopharm to ensure ground-truth colour standardisation of digital samples November 26th 2021 FFEI Ltd, the global developer of award-winning digital pathology imaging solutions, today announced that their patented Sierra colour calibration technology has been integrated into Visiopharm’s viewer, for AI-based image analysis and workflow. Visiopharm is on a mission to transform pathology through AI and [...]
DeepBio said its DeepDx-Prostate Pro, an artificial intelligence (AI)-based pathology diagnosis assistance software, has received a Class 3 in-vitro diagnostic medical device from the Ministry of Food and Drug Safety.According to the company, the approval marks the first AI-based medical device that assists in classifying prostate cancer severity in the world. The company had also received approval for AI-based prostate cancer diagnosis assistance software for the first time in Korea in April last year.The company could receive approval for the device after demonstrating excellent performance in an evaluation study. DeepDx-Prostate Pro showed a 98.7-percent grade group classification agreement and 96.9-percent no grade group classification agreement.As a result of comparing the analysis of this software with the analysis of three pathologists in the same study, DeepDx-Prostate Pro recorded a Kappa statistic of 0.713 and a weighted Kappa statistic of 0.922 indicating high agreement with the pathologist.The device also drastically shortened the time needed for the analysis. While it took 550 minutes for a pathologist to analyze the slides of an entire sample through an existing method, the device greatly reduced the time needed to 364 minutes.“It is very meaningful that DeepBio introduced the world’s first AI technology that aids in pathological tissue diagnosis,” Deep Bio CEO Kim Sun-woo said. “In the diagnosis of prostate cancer, the severity diagnosis according to the Gleason classification method is very important for patient prognosis and treatment, and it is one of the areas requiring AI diagnosis support due to frequent diagnosis discrepancies between pathologists.”Following the launch of an auxiliary medical device for diagnosing the presence or absence of prostate cancer with deep learning technology last year, the company expects that the new approval will enable faster and more accurate diagnosis of prostate cancer, Kim added.DeepDx-Prostate Pro automatically classifies the histological severity of prostate cancer by analyzing whole slide images of prostate needle biopsy tissue stained with Hematoxylin & Eosin with AI.The system provides the analysis results in five grades and a Gleason score based on the Gleason grading system, which is the most used method for classifying the degree of differentiation of prostate cancer tissues.SOURCE: Korea Biomedical Review
Digital image analysis can fail due to poor slide quality or regressive performance when applied to data from sources that are not included in the training data. To overcome these problems, research is being done with human-in-the-loop (HITL) AI systems where the pathologists interact with DIA resulting in an improvement in performance.
