Frontiers in neuroscience · 2026
Automated PACS-integrated pipeline for TractSeg-based segmentation of the arcuate fasciculus in patients with hearing loss.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Kierońska-Siwak Sara, Zwierko Beata, Mackiewicz-Nartowicz Hanna, Kozakiewicz-Rutkowska Agata, Sinkiewicz Anna, Jaroch Alina, Bracha Marietta, Meder Grzegorz, Grzanka Dariusz
Аннотация
OBJECTIVE: While tractography is used to determine the anatomical course of white matter tracts, it can often be imprecise and time-consuming, which can be a problem when comparing large groups of patients. The aim of this study is to compare the automated process of arcuate fasciculus determination using the TractSeg algorithm with manual AF determination in DSI studio software.
METHODS: The process of importing the structured MPRAGE sequence and raw diffusion-weighted images from the PACS system, performing the TractSeg algorithm, superimposing the bilateral AFs obtained on the MPRAGE image and exporting this composite image to the PACS system was automated. This procedure was used to segment the arcuate fasciculus in 25 patients with hearing loss.
RESULTS: The automated algorithm was able to delineate the arcuate fasciculus bilaterally in all 25 patients, while the manual reference method and automated tractography based on DSI Studio software failed in three and one patient, respectively. TractSeg showed a mean distance of 2.0 ± 0.7 mm from manual segmentation, compared with 2.8 ± 1.0 mm for DSI Studio Auto-Tracking. In addition, TractSeg appeared to involve larger portions of the medial AF fibres than the other methods.
CONCLUSION: The TractSeg algorithm has shown high efficacy in segmenting the arcuate fasciculus in patients with hearing loss. The algorithm is fast to run and has great potential to optimise and improve neural pathway delineation.
METHODS: The process of importing the structured MPRAGE sequence and raw diffusion-weighted images from the PACS system, performing the TractSeg algorithm, superimposing the bilateral AFs obtained on the MPRAGE image and exporting this composite image to the PACS system was automated. This procedure was used to segment the arcuate fasciculus in 25 patients with hearing loss.
RESULTS: The automated algorithm was able to delineate the arcuate fasciculus bilaterally in all 25 patients, while the manual reference method and automated tractography based on DSI Studio software failed in three and one patient, respectively. TractSeg showed a mean distance of 2.0 ± 0.7 mm from manual segmentation, compared with 2.8 ± 1.0 mm for DSI Studio Auto-Tracking. In addition, TractSeg appeared to involve larger portions of the medial AF fibres than the other methods.
CONCLUSION: The TractSeg algorithm has shown high efficacy in segmenting the arcuate fasciculus in patients with hearing loss. The algorithm is fast to run and has great potential to optimise and improve neural pathway delineation.