Fine-Scale Histologic Features Estimated at Low Magnification
By LabMedica International staff writers Posted on 03 Jul 2018 |
Image: The Aperio Scanscope XT whole-slide scanner (Photo courtesy of Leica Microsystems).
Whole-slide imaging has ushered in a new era of technology that has fostered the use of computational image analysis for diagnostic support and has begun to transfer the act of analyzing a slide to computer monitors.
Due to the overwhelming amount of detail available in whole-slide images, analytic procedures, whether computational or visual, often operate at magnifications lower than the magnification at which the image was acquired and as a result, a corresponding reduction in image resolution occurs.
A team of scientists led by those at Drexel University College of Medicine (Philadelphia, PA, USA) examined the correspondence between the color and spatial properties of whole-slide images to elucidate the impact of resolution reduction on the histologic attributes of the slide. They simulated image resolution reduction and modeled its effect on classification of the underlying histologic structure. By harnessing measured histologic features and the intrinsic spatial relationships between histologic structures, they developed a predictive model to estimate the histologic composition of tissue in a manner that exceeds the resolution of the image.
The scientists acquired high-resolution (0.25 µm/pixel) digital images of H&E-stained slides from 88 excised breast specimens at ×40 magnification using the Aperio Scanscope XT whole-slide scanner. For each whole-slide image, they selected two regions of interest (ROIs) for analysis, each 800 µm × 800 µm in size, with an effort made to capture epithelium and stroma. To estimate histologic composition from low-magnification images, they developed a model that uses the color of a pixel to surmise its content. By exploiting the spatial relationships between histologic elements, and measuring their individual color properties, they derived axes in hue-saturation-value (HSV) space that can be used to predict the histologic composition of a pixel.
The team analyzed 79 images acquired at ×40 magnification using whole-slide imaging. Images were stored in a proprietary format that enabled direct access to the image at lower resolutions, thereby reducing bandwidth and facilitating rapid loading for viewing and analysis. The investigators reported that reduction in resolution resulted in a significant loss of the ability to accurately characterize histologic components at magnifications less than ×10, but by utilizing pixel color, this ability was improved at all magnifications.
The authors concluded that multiscale analysis of histologic images requires an adequate understanding of the limitations imposed by image resolution and their findings suggest that some of these limitations may be overcome with computational modeling. The study was published on June 18, 2018, in the journal Archives Of Pathology & Laboratory Medicine.
Related Links:
Drexel University College of Medicine
Due to the overwhelming amount of detail available in whole-slide images, analytic procedures, whether computational or visual, often operate at magnifications lower than the magnification at which the image was acquired and as a result, a corresponding reduction in image resolution occurs.
A team of scientists led by those at Drexel University College of Medicine (Philadelphia, PA, USA) examined the correspondence between the color and spatial properties of whole-slide images to elucidate the impact of resolution reduction on the histologic attributes of the slide. They simulated image resolution reduction and modeled its effect on classification of the underlying histologic structure. By harnessing measured histologic features and the intrinsic spatial relationships between histologic structures, they developed a predictive model to estimate the histologic composition of tissue in a manner that exceeds the resolution of the image.
The scientists acquired high-resolution (0.25 µm/pixel) digital images of H&E-stained slides from 88 excised breast specimens at ×40 magnification using the Aperio Scanscope XT whole-slide scanner. For each whole-slide image, they selected two regions of interest (ROIs) for analysis, each 800 µm × 800 µm in size, with an effort made to capture epithelium and stroma. To estimate histologic composition from low-magnification images, they developed a model that uses the color of a pixel to surmise its content. By exploiting the spatial relationships between histologic elements, and measuring their individual color properties, they derived axes in hue-saturation-value (HSV) space that can be used to predict the histologic composition of a pixel.
The team analyzed 79 images acquired at ×40 magnification using whole-slide imaging. Images were stored in a proprietary format that enabled direct access to the image at lower resolutions, thereby reducing bandwidth and facilitating rapid loading for viewing and analysis. The investigators reported that reduction in resolution resulted in a significant loss of the ability to accurately characterize histologic components at magnifications less than ×10, but by utilizing pixel color, this ability was improved at all magnifications.
The authors concluded that multiscale analysis of histologic images requires an adequate understanding of the limitations imposed by image resolution and their findings suggest that some of these limitations may be overcome with computational modeling. The study was published on June 18, 2018, in the journal Archives Of Pathology & Laboratory Medicine.
Related Links:
Drexel University College of Medicine
Latest Pathology News
- 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
- Unique Hand-Warming Technology Supports High-Quality Fingertip Blood Sample Collection
- Image-Based AI Shows Promise for Parasite Detection in Digitized Stool Samples
- Deep Learning Powered AI Algorithms Improve Skin Cancer Diagnostic Accuracy
- Microfluidic Device for Cancer Detection Precisely Separates Tumor Entities
- Virtual Skin Biopsy Determines Presence of Cancerous Cells
- AI Detects Viable Tumor Cells for Accurate Bone Cancer Prognoses Post Chemotherapy
- First Ever Technique Identifies Single Cancer Cells in Blood for Targeted Treatments
- Innovative Blood Collection Device Overcomes Common Obstacles Related to Phlebotomy
- Intra-Operative POC Device Distinguishes Between Benign and Malignant Ovarian Cysts within 15 Minutes
- Simple Skin Biopsy Test Detects Parkinson’s and Related Neurodegenerative Diseases
- Bioinformatics Tool to Identify Chromosomal Alterations in Tumor Cells Can Improve Cancer Diagnosis
- Coin-Sized Device Rapidly Isolates Blood Plasma for Quicker and More Precise Clinical Diagnoses