prikaz prve stranice dokumenta Automated Vertebral Bone Quality Determination from T1-Weighted Lumbar Spine MRI Data Using a Hybrid Convolutional Neural Network–Transformer Neural Network
  Preuzmi
PDF 5.49 MB
Znanstveni rad - Izvorni znanstveni rad
Automated Vertebral Bone Quality Determination from T1-Weighted Lumbar Spine MRI Data Using a Hybrid Convolutional Neural Network–Transformer Neural Network
Applied Sciences, 14 (2024), 22; 10343. https://doi.org/10.3390/app142210343
Stojšić, Kristian; Miletić Rigo, Dina; Jurković, Slaven

Citirajte ovaj rad

Stojšić, K., Miletić Rigo, D. i Jurković, S. (2024). Automated Vertebral Bone Quality Determination from T1-Weighted Lumbar Spine MRI Data Using a Hybrid Convolutional Neural Network–Transformer Neural Network. Applied Sciences, 14. (22). doi: 10.3390/app142210343

Stojšić, Kristian, et al. "Automated Vertebral Bone Quality Determination from T1-Weighted Lumbar Spine MRI Data Using a Hybrid Convolutional Neural Network–Transformer Neural Network." Applied Sciences, vol. 14, br. 22, 2024. https://doi.org/10.3390/app142210343

Stojšić, Kristian, Dina Miletić Rigo i Slaven Jurković. "Automated Vertebral Bone Quality Determination from T1-Weighted Lumbar Spine MRI Data Using a Hybrid Convolutional Neural Network–Transformer Neural Network." Applied Sciences 14, br. 22 (2024). https://doi.org/10.3390/app142210343

Stojšić, K., Miletić Rigo, D. i Jurković, S. (2024) 'Automated Vertebral Bone Quality Determination from T1-Weighted Lumbar Spine MRI Data Using a Hybrid Convolutional Neural Network–Transformer Neural Network', Applied Sciences, 14(22). doi: 10.3390/app142210343

Stojšić K, Miletić Rigo D, Jurković S. Automated Vertebral Bone Quality Determination from T1-Weighted Lumbar Spine MRI Data Using a Hybrid Convolutional Neural Network–Transformer Neural Network. Applied Sciences [Internet]. 11.11.2024. [pristupljeno 14.11.2024.];14(22). doi: 10.3390/app142210343

K. Stojšić, D. Miletić Rigo i S. Jurković, "Automated Vertebral Bone Quality Determination from T1-Weighted Lumbar Spine MRI Data Using a Hybrid Convolutional Neural Network–Transformer Neural Network", Applied Sciences, vol. 14, br. 22, Studeni 2024. [Online]. Dostupno na: https://urn.nsk.hr/urn:nbn:hr:184:946958. [Citirano: 14.11.2024.]

Za citiranje koristite ovu mrežnu adresu: https://urn.nsk.hr/urn:nbn:hr:184:946958
Prijavite se u repozitorij kako biste mogli spremiti objekt u svoju listu.
Podaci o radu
Naslov (engleski)Automated Vertebral Bone Quality Determination from T1-Weighted Lumbar Spine MRI Data Using a Hybrid Convolutional Neural Network–Transformer Neural Network
AutorKristian Stojšić
AutorDina Miletić Rigo
AutorSlaven Jurković
Autorova ustanovaSveučilište u Rijeci
Medicinski fakultet
(Katedra za medicinsku fiziku i biofiziku)
Znanstveno / umjetničko
područje, polje i grana		PRIRODNE ZNANOSTI
Fizika
Biofizika i medicinska fizika
Znanstveno / umjetničko
područje, polje i grana		BIOMEDICINA I ZDRAVSTVO
Kliničke medicinske znanosti
Radiologija
Sažetak (engleski)
Vertebral bone quality (VBQ) is a promising new method that can improve screening for osteoporosis. The drawback of the current method is that it requires manual determination of the regions of interest (ROIs) of vertebrae and cerebrospinal fluid (CSF) by a radiologist. In this work, an automatic method for determining the VBQ is proposed, in which the ROIs are obtained using a trained neural network model. A large, publicly available dataset of sagittal lumbar spine MRI images with ground truth segmentations was used to train a BRAU-Net++ hybrid CNN–transformer neural network. The performance of the trained model was evaluated using the dice similarity coefficient (DSC), accuracy, precision, recall and intersection-over-union (IoU) metrics. The trained model performed similarly to state-of-the-art lumbar spine segmentation models, with an average DSC value of 0.914 ± 0.007 for the vertebrae and 0.902 for the spinal canal. Four different methods of VBQ determination with automatic segmentation are presented and compared with one-way ANOVA. These methods use different algorithms for CSF extraction from the segmentation of the spinal canal using T1- and T2-weighted image data and applying erosion to the vertebral ROI to avoid a sharp change in SI at the edge of the vertebral body.
Ključne riječi (engleski)
Jezikengleski
Vrsta publikacijeZnanstveni rad - Izvorni znanstveni rad
Status objaveObjavljen
Vrsta recenzijeRecenziran - međunarodna recenzija
Verzija publikacijeObjavljena verzija rada (izdavačev PDF)
Naslov časopisaApplied Sciences
Brojčani podacivol. 14, br. 22, 10343
e-ISSN2076-3417
DOIhttps://doi.org/10.3390/app142210343
URN:NBNurn:nbn:hr:184:946958
Datum objave publikacije2024-11-11
URL dokumentahttps://www.mdpi.com/2076-3417/14/22/10343
Vrsta resursaTekst
Prava pristupaOtvoreni pristup
Uvjeti korištenjaIkona licence Imenovanje 4.0 međunarodna (CC BY 4.0)
Datum i vrijeme pohrane2024-11-13 11:58:59