Clinical radiology · 2026
Fractal analysis and magnetic resonance imaging (MRI) semantic features to identify intracranial solitary fibrous tumours and atypical meningiomas.
СтатьяПоддержка исследования: вне правительства СШАНазвание 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.
Zhao Z, Bai R, Zhang J, Yuan S, Zhang H, Yin H, Pan Y, Li Q
Аннотация
AIM: Atypical meningioma (ATM) and solitary fibrous tumour (SFT) are two prevalent meningeal tumours that pose significant challenges in preoperative differentiation. This study aims to distinguish between them using fractal analysis and magnetic resonance imaging (MRI) semantic features.
MATERIALS AND METHODS: This retrospective study included a total of 81 patients, comprising 30 SFTs and 51 ATMs, diagnosed between January 2019 and December 2023. At the maximal tumour cross-section, fractal dimension (FD) and lacunarity were computed for the tumour region using the open-source software ImageJ (version 1.53k; National Institutes of Health). A visual nomogram was subsequently developed to differentiate SFT from ATM by integrating clinical data, preoperative MRI semantic features, and fractal analysis parameters through logistic regression model.
RESULTS: Compared with ATM, the SFT group exhibited a significantly lower prevalence of dural tail sign (P<.001) but a higher necrosis rate (P<.001), along with markedly elevated lacunarity. The area under the curve (AUC) for differentiating the two groups was 0.825 for dural tail sign, 0.741 for necrosis, and 0.770 for lacunarity. The diagnostic nomogram incorporating these features demonstrated further improved performance, achieving an AUC of 0.968, with corresponding accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 0.914, 0.863, 1.000, 1.000, and 0.811, respectively.
CONCLUSION: Preoperative MRI semantic features combined with fractal analysis enable noninvasive differentiation between SFT and ATM, providing a valuable theoretical foundation for optimising clinical treatment strategies and surgical decision-making.
MATERIALS AND METHODS: This retrospective study included a total of 81 patients, comprising 30 SFTs and 51 ATMs, diagnosed between January 2019 and December 2023. At the maximal tumour cross-section, fractal dimension (FD) and lacunarity were computed for the tumour region using the open-source software ImageJ (version 1.53k; National Institutes of Health). A visual nomogram was subsequently developed to differentiate SFT from ATM by integrating clinical data, preoperative MRI semantic features, and fractal analysis parameters through logistic regression model.
RESULTS: Compared with ATM, the SFT group exhibited a significantly lower prevalence of dural tail sign (P<.001) but a higher necrosis rate (P<.001), along with markedly elevated lacunarity. The area under the curve (AUC) for differentiating the two groups was 0.825 for dural tail sign, 0.741 for necrosis, and 0.770 for lacunarity. The diagnostic nomogram incorporating these features demonstrated further improved performance, achieving an AUC of 0.968, with corresponding accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 0.914, 0.863, 1.000, 1.000, and 0.811, respectively.
CONCLUSION: Preoperative MRI semantic features combined with fractal analysis enable noninvasive differentiation between SFT and ATM, providing a valuable theoretical foundation for optimising clinical treatment strategies and surgical decision-making.