Clinical imaging · 2026
Real-world use of PACS-integrated automated spine numbering in MRI.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
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.
Son Young, Joo Bio, Park Mina, Ahn Sung Jun, Kim Sungjun, Lee Hong-Seon
Аннотация
PURPOSE: Traditional methods of vertebral identification have predominantly relied on relative approaches, depending on discernible landmarks. Artificial Intelligence (AI) has emerged as a transformative force in radiology, aiming to augment the workflow of radiologists and the benefit of patients. This study aims to investigate the real-world application of picture archiving and communication system (PACS)-integrated automated spine numbering for the daily interpretation of spinal magnetic resonance imaging (MRI) scans.
METHODS: This retrospective study, at a tertiary hospital, analyzed 235 spine MRI cases from November 2023 to January 2024. The study focused on the effect of AI-assisted spine labeling system. We measured reading times from PACS log records, leading to the exclusion of 32 cases due to time outliers. Thus, 109 (53.7%) implemented AI, while 94 (46.3%) did not. Subgroup analysis evaluated differences based on the type of radiologist (specialist vs. resident), whether the examination was an initial or follow-up, and the anatomic region (lumbar vs. non-lumbar).
RESULTS: Integrating an AI-assisted spine labeling algorithm into the PACS significantly reduced reading times for residents (p < 0.05) but not for specialists. AI-implemented cases demonstrated high accuracy, with only 2.8% discordance. Despite AI implementation, overall reading times did not differ significantly (p = 0.0858).
CONCLUSION: AI has the potential to enhance efficiency, particularly benefiting trainees, by providing a consistent reference for the spinal anatomy. Future studies should explore the effect of AI on clinical outcomes and patient care.
METHODS: This retrospective study, at a tertiary hospital, analyzed 235 spine MRI cases from November 2023 to January 2024. The study focused on the effect of AI-assisted spine labeling system. We measured reading times from PACS log records, leading to the exclusion of 32 cases due to time outliers. Thus, 109 (53.7%) implemented AI, while 94 (46.3%) did not. Subgroup analysis evaluated differences based on the type of radiologist (specialist vs. resident), whether the examination was an initial or follow-up, and the anatomic region (lumbar vs. non-lumbar).
RESULTS: Integrating an AI-assisted spine labeling algorithm into the PACS significantly reduced reading times for residents (p < 0.05) but not for specialists. AI-implemented cases demonstrated high accuracy, with only 2.8% discordance. Despite AI implementation, overall reading times did not differ significantly (p = 0.0858).
CONCLUSION: AI has the potential to enhance efficiency, particularly benefiting trainees, by providing a consistent reference for the spinal anatomy. Future studies should explore the effect of AI on clinical outcomes and patient care.