New AI Algorithm for Use on Eight Types of Cancer Trained on Seven Scanner Models
|
By LabMedica International staff writers Posted on 04 Oct 2023 |
|
A new artificial intelligence (AI) algorithm for use on one of the broadest trained environments is now available for commercial or research work.
Gestalt Diagnostics (Spokane, WA, USA) has released the Mitotic Counting algorithm which has been trained on more than 100,000 individual mitosis and across seven scanner models. The algorithm performs impressively with an F1-Score of 0.74, matching the performance of top-of-the-line methods in the field. The algorithm is currently available in the Gestalt AI Studio for use on a variety of cancers including cutaneous mast cell tumors, breast cancer, lymphoma, lung cancer, melanoma, neuroendocrine, colon cancer, and bladder carcinoma. The algorithm has been trained on several scanner models, including those from Hamamatsu, Leica, 3D Histech, and Aperio.
Key to the broad applicability of deep learning algorithms is their ability to adapt to new scanners and different types of tissue; a broad dataset is crucial to achieve this goal. Gestalt Diagnostics' dataset encompasses seven types of tissues spanning eight tumors and is digitized with seven different scanner models. Additionally, Gestalt Diagnostics also offers PathFlow, a smart and customizable workflow solution that offers genuine interoperability for optimal efficiency. This solution supports both digital and glass slides and allows for tailored rules that can be can be configured to meet specific needs and requirements.
"What does this mean for our customers? Confidence,” said Lisa-Jean Clifford, Gestalt COO & Chief Strategy Officer. “Gestalt is focused on providing solutions that provide a foundation of confidence in use as this industry continues to evolve, innovate, and incorporate products that are meant to enhance a pathologist's or scientist's daily life."
"We are extremely proud of the comprehensive approach we take to AI development as an organization,” added Brian Napora, Gestalt VP, AI Solutions. “Our position is to not only look at development and training with a small subset of images or on one or two scanners, that would not prove as effective or accurate as we feel our customers and the industry require. Therefore, we train on tens of thousands images, tumors cells, or in this case, mitosis and multiple scanner models across several scanner vendors to ensure the most accurate, clinically usable options for our customers."
Related Links:
Gestalt Diagnostics
Latest Pathology News
- AI Matches Pathologists in Predicting Breast Cancer Prognosis from Immune Cells
- AI-Pathologist Framework Improves Accuracy and Reliability in Cancer Diagnosis
- New Review Highlights Intelligent Agents as Next Step for Digital Pathology
- Simple Immunohistochemical Size Ratio Improves Classification of Primary Aldosteronism
- AI Links Organ-Specific Aging Patterns in Histology to Blood-Based Signals
- 30-Minute 3D Histology Tool Supports Intraoperative Glioma Margin Assessment
- AI Uses H&E Slides to Predict Key Biomarkers Across 32 Cancers
- AI Tool Identifies Slide Artifacts to Speed Digital Pathology Diagnosis
- FDA-Cleared Digital Pathology Platform Expands Interoperability for Primary Diagnosis
- AI Pathology Tool Predicts Relapse Risk in Stage II Colorectal Cancer
- AI Pathology Tool Stratifies Rectal Cancer to Guide Chemoradiotherapy
- PD-L1 Assay Guides Pembrolizumab Eligibility in Ovarian, Fallopian Tube, and Peritoneal Cancers
- AI Digital Pathology Platform Standardizes IHC Scoring in Breast Cancer
- AI Bone Marrow Mapping Provides New Tool to Track Blood Cancer Severity
- Digital Pathology Tool Predicts Breast Cancer Outcomes and Therapy Response
- AI Tissue Imaging Helps Guide Targeted Therapy for Lung Cancer
Channels
Clinical Chemistry
view channel
Multiprotein Plasma Panel Identifies Remission in Vasculitis
Vasculitis causes immune-mediated inflammation of blood vessel walls and can lead to kidney and lung damage. Clinicians rely on immunosuppressive drugs, but treatment carries significant side effects and... Read more
Rapid Urine Biomarker Panel Supports Better Kidney Transplant Decisions
Kidney transplantation remains constrained by organ scarcity and uncertainty about the quality of deceased-donor kidneys. In the United States, more than 92,000 people are awaiting a kidney transplant,... Read more
Molecular Diagnostics
view channel
New Blood RNA Markers Help Advance Precision Medicine for Respiratory Patients
Risk stratification in hospitalized respiratory disease, particularly among older adults with COVID-19, remains challenging despite rich clinical datasets. Blood-based non-coding RNA biomarkers are promising,... Read more
Single Genetic Analysis Identifies Causes of Premature Ovarian Insufficiency
Premature ovarian insufficiency (POI) affects up to 3.5% of women and represents a major cause of infertility. In most cases, the underlying etiology remains unknown, making patient counseling and clinical... Read more
Hematology
view channel
New Genetic Findings Reveal Cause of Bone Marrow Failure Syndrome
Inherited bone marrow failure syndromes (IBMFS) impair the bone marrow’s ability to produce sufficient healthy blood cells and are associated with an increased risk of early-onset myelodysplastic syndromes (MDS).... Read more
Ultra-Portable Device Enables Finger-Prick Blood Testing at Home
Patients who need frequent blood tests often face repeated clinic visits that burden services and disrupt care. In the UK, millions of tests are performed each year to diagnose disease, guide therapy,... Read more
Immunology
view channel
Gut “Memory” May Explain Why IBD Flares Return
Inflammatory bowel diseases (IBD), including Crohn’s disease and ulcerative colitis, are characterized by recurring flare-ups that damage the intestinal mucosa and remain difficult to predict.... Read more
AI-Based Antibody Profiling Predicts Strength of COVID-19 Vaccine Response
Vaccine-induced protection can vary widely between individuals, creating uncertainty for clinicians, particularly in patients with immunosuppressive conditions. Demographic and health factors explain only... Read more
Microbiology
view channel
New Diagnostic Workflow Identifies Bloodstream Pathogens and Antibiotic Response in Hours
Sepsis is a life-threatening complication of infection that affects more than 1.5 million patients annually in the United States and contributes to roughly one in three in-hospital deaths.... Read more
Genetic Marker Identifies Emerging Resistance to Frontline Malaria Drugs
Artemisinin-based combination therapy remains central to controlling Plasmodium falciparum malaria, but emerging drug resistance is complicating treatment and surveillance. In Uganda and across sub-Saharan... Read more
Technology
view channel
Autonomous Robotic System Receives FDA Authorization for Blood Collection
Venipuncture is central to many diagnostic pathways, but routine blood collection can be affected by staffing constraints and procedural variability that influence consistency and patient experience.... Read more
Interoperable Data Platform Standardizes Multi-Cancer Blood Test Results
Proteotype Diagnostics has introduced Alchemi, a proprietary data and clinical workflow platform being developed for Enlighten, the company’s investigational blood-based multi-cancer test.... Read more
Industry
view channel
Tumor-Informed MRD Assay Gains Medicare Coverage for Immunotherapy Monitoring
NeoGenomics’ RaDaR ST molecular residual disease (MRD) assay has received expanded coverage from the Centers for Medicare & Medicaid Services’ Molecular Diagnostic Services Program (MolDX) for monitoring... Read more
