Comparing image normalization techniques in an end-to-end model for automated modic changes classification from MRI images

Cina, Andrea; Haschtmann, Daniel; Damopoulos, Dimitrios; Gerber, Nicolas; Loibl, Markus; Fekete, Tamas; Kleinstück, Frank; Galbusera, Fabio (2024). Comparing image normalization techniques in an end-to-end model for automated modic changes classification from MRI images. Brain and Spine, 4 Elsevier 10.1016/j.bas.2023.102738

Preview

Text Cina_et_al._-_2024_-_Comparing_image_normalization_techniques_in_an_end-to-end_model_for_automated_modic_changes_classifi.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (1MB) | Preview

Introduction
Modic Changes (MCs) are MRI alterations in spine vertebrae's signal intensity. This study introduces an end-to-end model to automatically detect and classify MCs in lumbar MRIs. The model's two-step process involves locating intervertebral regions and then categorizing MC types (MC0, MC1, MC2) using paired T1-and T2-weighted images. This approach offers a promising solution for efficient and standardized MC assessment.

Research question
The aim is to investigate how different MRI normalization techniques affect MCs classification and how the model can be used in a clinical setting.

Material and methods
A combination of Faster R–CNN and a 3D Convolutional Neural Network (CNN) is employed. The model first identifies intervertebral regions and then classifies MC types (MC0, MC1, MC2) using paired T1-and T2-weighted lumbar MRIs. Two datasets are used for model development and evaluation.

Results
The detection model achieves high accuracy in identifying intervertebral areas, with Intersection over Union (IoU) values above 0.7, indicating strong localization alignment. Confidence scores above 0.9 demonstrate the model's accurate levels identification. In the classification task, standardization proves the best performances for MC type assessment, achieving mean sensitivities of 0.83 for MC0, 0.85 for MC1, and 0.78 for MC2, along with balanced accuracy of 0.80 and F1 score of 0.88.

Discussion and conclusion
The study's end-to-end model shows promise in automating MC assessment, contributing to standardized diagnostics and treatment planning. Limitations include dataset size, class imbalance, and lack of external validation. Future research should focus on external validation, refining model generalization, and improving clinical applicability.

Interest & Impact

Downloads

10 since deposited on 18 Jun 2024
10 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item