Artificial Intelligence-Based Indocyanine Green Lymphography Pattern Classification for Management of Lymphatic Disease.

Background: 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 aimed to investigate artificial intelligence (AI), specifically convolutional neural networks, to categorize ICG lymphography images patterns into linear, reticular, splash, stardust, and diffuse. Methods: A dataset composed of 68 ICG lymphography images was compiled and labeled according to five recognized pattern types: linear, reticular, splash, stardust, and diffuse. A convolutional neural network model, using MobileNetV2 and TensorFlow, was developed and coded in Python for pattern classification. Results: The AI model achieved 97.78% accuracy and 0.0678 loss in categorizing images into five ICG lymphography patterns, demonstrating high potential for enhancing ICG lymphography interpretation. The high level of accuracy with a low loss achieved by our model demonstrates its effectiveness in pattern recognition with a high degree of precision. Conclusions: This study demonstrates that AI models can accurately classify ICG lymphography patterns. AI can assist in standardizing and automating the interpretation of ICG lymphographic imaging.

Lumbar intervertebral disc degeneration, end-plates and paraspinal muscle changes in children and adolescents with low-back pain.

The prevalence of low-back pain (LBP) in adolescents ranges from 7 to 72%. We aimed to define the radiologic characteristics of the lumbar spine in children and adolescents with LBP with/without leg pain. Two hundred and fourteen children and adolescents, who were born between 2001 and 2009 and had lumbar spine MRI for LBP with/without leg pain, were evaluated in terms of intervertebral disc degeneration (IVDD), end-plates and paraspinal muscle changes on lumbar spine MRIs. Severe IVDD was detected at all lumbar levels except for L2-L3. Modic changes were present in 4.2% of the patients. Modic changes were more common in patients with severe IVDD than in those with mild-to-moderate IVDD. Severe IVDD was significantly associated with Modic changes at the corresponding L1-L2 and L3-L4 disc levels. Girls had significantly more fatty infiltration in the paraspinal muscles when compared to boys. The risk of having severe IVDD concomitant with Modic changes was high [odds ratio (OR), 8.6]. The OR was 20.7 for predicting the presence of severe IVDD at any level if Modic changes presented particularly at the L3-L4 level. The ORs of Modic changes presented at any lumbar level at the background of fat-infiltrated multifidus at L3-L4 and L4-L5 levels were 8.3 and 9.1, respectively. Fatty infiltration in the paraspinal muscles and IVDD were closely associated with Modic changes in children and adolescents with LBP. Lumbar IVDD in children and adolescents could be the result of a mechanical pathology.