Zielsetzung To apply quantitative imaging analysis for noninvasive classification of the most
frequent subtypes of Non-Hodgkin Lymphoma (NHL) as a basis for a clinical imaging
genomic model to support therapeutic monitoring and clinical decision making.
Material und Methoden In this single-center study, 201 treatment-naïve patients with biopsy-proven NHL
(50 diffuse large B-cell lymphoma [DLBCL], 51 mantle cell lymphoma [MCL], 49 follicular
lymphoma [FL], and 51 chronic lymphocytic leukemia [CLL]) and 39 treatment-naïve non-small
cell lung cancer patients with positron emission tomography (PET)/computed tomography
(CT)-confirmed healthy axillary lymph nodes (LNs) were retrospectively analyzed. Three-dimensional
(3D) segmentation and radiomic analysis of pathologically enlarged nodes (n=1,628)
were performed on contrast-enhanced CT scans, including healthy LNs as references.
Feature selection was performed using a random forest (RF) classifier. Multiclass
Classifier was performed using a Light Gradient Boosting Machine (LGBM) classifier
for lymphoma subtype classification.
Ergebnisse Performance to classify lymphoma from non-lymphoma and lymphoma subtypes was as follows:
malignant lymphoma vs. non-lymphoma: area under the curve (AUC)=0.998; MCL vs. other
NHL: AUC=0.996; DLBCL vs. other NHL: AUC=0.983; CLL vs. other NHL: AUC=0.964; FL vs.
other NHL: AUC=0.914.
Schlussfolgerungen Our study demonstrates the potential of a radiomics-based machine learning framework
for distinguishing lymphoma from non-lymphoma and classifying the most common NHL
subtypes. Coupled with the ability to non-invasively assess multiple LNs at different
sites in the body for therapy monitoring and the potential to identify early progression
to a more aggressive disease course, our findings may help to expand the applicability
of radiomics in precision oncology.
