<< Back to the abstract archive
Artificial Intelligence Based Classification of Indocyanine Green Lymphography Patterns
Berk B. Ozmen, Sonia K. Pandey, Graham Schwarz
Cleveland Clinic Department of Plastic Surgery
2024-02-01
Presenter: Berk B. Ozmen
Affidavit:
Yes.
Director Name: Graham Schwarz
Author Category: Fellow Plastic Surgery
Presentation Category: Clinical
Abstract Category: General Reconstruction
Introduction
Lymphedema diagnosis relies on effective imaging of the lymphatic system. Indocyanine green (ICG) lymphography has become an essential diagnostic tool, but globally accepted protocols and objective analysis methods are lacking. In this study we aim to investigate artificial intelligence (AI) and convolutional neural networks (CNNs) to categorize ICG lymphography images patterns into linear, reticular, splash, stardust and diffuse.
Methods
A dataset comprising 68 ICG lymphography images was compiled and labeled according to 5 recognized pattern types; linear, reticular, splash, stardust and diffuse. Dataset is partitioned into a training set (80%), validation set (10%) and test set (10%) all randomly. An AI CNN model was designed and trained on this dataset utilizing Python 3 and TensorFlow. Leveraging the power of transfer learning, we employed the MobileNetV2 architecture, pre-trained on the extensive ImageNet dataset. Custom dense layers were appended to this base model to adapt it to our specific classification task. To improve the model's generalization capabilities, data augmentation techniques including rotation, width shift, height shift, shear transformations, zoom, and horizontal flipping were applied to the training data.
Results
Our AI model achieved 97.78% accuracy and 0.0678 loss in categorizing images into five ICG pattern types, demonstrating potential for enhancing ICG interpretation.
Conclusion
Integrating AI computer vision into ICG lymphography could significantly improve diagnostic accuracy and reproducibility. Refining ICG analysis with AI may enable better clinical decision-making and patient outcomes for lymphedema.
