Differentiation of low-grade non-Hodgkin's lymphomas using paraffin sections by image processing
1Institute of Virology and Immunology, Laboratory for Image Processing, University of Würzburg, Germany. susanne@megabase.aecom.yu.edu
Insights
Digital image analysis of paraffin sections can reliably differentiate benign lymphoid tissues from non-Hodgkin's lymphomas (NHLs). This method shows potential for identifying NHL subtypes, advancing diagnostic capabilities.
Area of Science:
- Digital pathology
- Hematopathology
- Computational imaging
Background:
- Previous studies demonstrated digital image analysis of touch imprints for non-Hodgkin's lymphoma (NHL) differentiation.
- Touch imprints are not routinely available in diagnostics, necessitating alternative methods.
Purpose of the Study:
- To evaluate the feasibility of digital image analysis of paraffin-embedded sections for NHL classification.
- To differentiate between reactive lymphoid tissues (RLTs) and various NHL subtypes using histological images.
Main Methods:
- Paraffin-embedded sections from 53 NHL cases and 9 RLTs were analyzed.
- A color-video-based microscope system and digital image processing were employed.
- The Revised European American Lymphoma (REAL) classification was used for NHL subtyping.
Main Results:
- The analysis achieved reliable differentiation between benign RLTs (78% correctly identified) and neoplastic NHLs (94% correctly identified).
- Average correct identification across six subgroups was 66%, with specific accuracies for RLTs (78%), chronic lymphocytic lymphomas (50%), MALT-type lymphomas (50%), mantle cell lymphomas (72%), and follicle center cell lymphoma (67%).
Conclusions:
- High-resolution image analysis of paraffin sections enables reliable differentiation of reactive versus neoplastic lymphoproliferative lesions.
- The study demonstrates the potential for defining nuclear structures to identify NHL subtypes, although not yet suitable for daily practice.
Abstract:
In a previous study, we were able to demonstrate that the differentiation of low-grade non-Hodgkin's lymphomas (NHLs) using digital image analysis of touch imprints obtained from native tumor tissue is feasible. The availability of touch imprints in routine diagnostics, however, is restricted. Therefore, we extended our studies toward paraffin sections being used as routine material for histological diagnoses. To identify five types of NHL classified according to the Revised European American Lymphoma classification, paraffin sections (n=53) of NHL and 9 reactive lymphoid tissues (RLTs) were scanned with a color-video-based microscope system and analyzed by digital image processing. A reliable division between benign and neoplastic lymphoproliferations was achieved. We were able to identify 78% of RLTs as benign and 94% of NHLs as neoplastic. The average probability of correct identification into the six subgroups was 66%. In detail, 78% of RLTs, 50% of chronic lymphocytic lymphomas and MALT-type lymphomas, 72% of mantle cell lymphomas, and 67% of follicle center cell lymphoma were classified correctly. Although the method of subclassifying or identifying NHLs on the basis of a computer-mediated assay is still not usable in daily practice, we show that a reliable differentiation between reactive and neoplastic lymphoproliferative lesions can be achieved by analysis of paraffin sections with high-resolution image analysis and that it is possible to define nuclear structures by identifying subtypes of NHL.
