Background: Atrial fibrillation (AF) is the most common heart rhythm disorder. In\norder for late Gd enhancement cardiovascular magnetic resonance (LGE CMR) to\nameliorate the AF management, the ready availability of the accurate enhancement\nsegmentation is required. However, the computer-aided segmentation of enhancement\nin LGE CMR of AF is still an open question. Additionally, the number of centres\nthat have reported successful application of LGE CMR to guide clinical AF strategies\nremains low, while the debate on LGE CMR�s diagnostic ability for AF still holds. The\naim of this study is to propose a method that reliably distinguishes enhanced (abnormal)\nfrom non-enhanced (healthy) tissue within the left atrial wall of (pre-ablation and\n3 months post-ablation) LGE CMR data-sets from long-standing persistent AF patients\nstudied at our centre.\nMethods: Enhancement segmentation was achieved by employing thresholds benchmarked\nagainst the statistics of the whole left atrial blood-pool (LABP). The test-set\ncross-validation mechanism was applied to determine the input feature representation\nand algorithm that best predict enhancement threshold levels.\nResults: Global normalized intensity threshold levels TPRE = 1 1/4 and TPOST = 1\n5/8 were found to segment enhancement in data-sets acquired pre-ablation and at\n3 months post-ablation, respectively. The segmentation results were corroborated\nby using visual inspection of LGE CMR brightness levels and one endocardial bipolar\nvoltage map. The measured extent of pre-ablation fibrosis fell within the normal range\nfor the specific arrhythmia phenotype. 3D volume renderings of segmented post ablation\nenhancement emulated the expected ablation lesion patterns. By comparing\nour technique with other related approaches that proposed different threshold levels\n(although they also relied on reference regions from within the LABP) for segmenting\nenhancement in LGE CMR data-sets of AF patients, we illustrated that the cut-off levels\nemployed by other centres may not be usable for clinical studies performed in our\ncentre.\nConclusions: The proposed technique has great potential for successful employment\nin the AF management within our centre. It provides a highly desirable validation of\nthe LGE CMR technique for AF studies. Inter-centre differences in the CMR acquisition\nprotocol and image analysis strategy inevitably impede the selection of a universally\noptimal algorithm for segmentation of enhancement in AF studies.
Loading....