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 Tool Detects Tiny Protein Clumps in Microscopy Images in Real-Time
- New Tool Enables Better Classification of Inherited Disease-Causing Variants
- Groundbreaking CRISPR Screen Technology Rapidly Determines Disease Mechanism from Tissues
- New AI Tool Classifies Brain Tumors More Quickly and Accurately
- AI Integrated With Optical Imaging Technology Enables Rapid Intraoperative Diagnosis
- HPV Self-Collection Solution Improves Access to Cervical Cancer Testing
- Hyperspectral Dark-Field Microscopy Enables Rapid and Accurate Identification of Cancerous Tissues
- AI Advancements Enable Leap into 3D Pathology
- New Blood Test Device Modeled on Leeches to Help Diagnose Malaria
- Robotic Blood Drawing Device to Revolutionize Sample Collection for Diagnostic Testing
- Use of DICOM Images for Pathology Diagnostics Marks Significant Step towards Standardization
- First of Its Kind Universal Tool to Revolutionize Sample Collection for Diagnostic Tests
- AI-Powered Digital Imaging System to Revolutionize Cancer Diagnosis
- New Mycobacterium Tuberculosis Panel to Support Real-Time Surveillance and Combat Antimicrobial Resistance
- New Method Offers Sustainable Approach to Universal Metabolic Cancer Diagnosis
- Spatial Tissue Analysis Identifies Patterns Associated With Ovarian Cancer Relapse