CCL

Összesen 5 találat.
#/oldal:
Részletezés:
Rendezés:

1.

001-es BibID:BIBFORM132031
Első szerző:Barna Sándor (kutató orvos)
Cím:Artificial Intelligence Based CT-free Attenuation Correction in Adolescent and Young Adult Mandibular Condylar Hyperplasia Patients / Barna Sándor, Szoliková Melinda, Csikos Csaba, Török Judit, Husztik Borbála, Varga József, Kovács Ákos, Garai Ildikó
Dátum:2024
ISSN:1619-7070 1619-7089
Megjegyzések:Aim/Introduction: Mandibular condylar hyperplasia is a condition in which one of the mandibular condyles is growing faster than the one on the other side resulting in facial asymmetry. It might be accompanied by chewing dysfunction or dental malocclusion. The cornerstone of diagnosis is 99mTc-MDP bone scan and SPECT/CT. Quantitative analysis of the uptake values can further improve diagnostic accuracy, however, standardized uptake values (SUV) can only be generated with CT-based attenuation correction (AC) which gives unnecessary radiation exposure to patients. AI-based AC could help us eliminate unnecessary radiation while providing sufficient data for quantification. Our aim was to compare the SUV values of patients with condylar hyperplasia using CT-based attenuation correction (CT-AC) and an AI-based synthetic CT attenuation correction (SynCT-AC). Materials and Methods: SUVmax and SUVmean values of 13 patients (12 female, 1 male + mean age 24) were measured using both CT-based and AI-based attenuation correction. 600MBq 99mTc-MDP iv. administered and 120view, 128matrix size SPECT and Low-Dose CT were done. The reconstruction method was OSEM-3D-RR with attenuation and scatter correcton based on original CT and SynCT. Reference SUV values (clivus, calvaria, vertebra) were also measured. SUV values were measured using 2 cm diameter volume of interests (VOIs). Correlation between CT-AC and Sy-CT-AC was measured in all reference areas and in the mandibles as well. Significance of the differences between CT-AC and Sy-CT-AC based uptake values were analyzed using paired t-test (in case of Gaussian distribution) and Wilcoxon signed rank test. To visualized the difference in the parameters of Sy-CT-AC and CT-based AC, Bland-Altman plots and box-and-whiskers plots were created. Results: The CT-AC and SyCT-AC based uptake values correlated well (r2 is above 0.93) in all cases. Mandibular and vertebral SUVs turned out to be biased since both SUVmax and SUVmean values were higher with AI-based AC. SUVmax values of the mandibles and vertebrae had a proportional error with AI, meaning the difference in SUVs from CT-based AC is greater at higher SUV values. The relative mandibular uptakes were not biased. Ratios of SUVmax values resulted in less deviation from the CT-based values. Conclusion: AI-based attenuation correction can be a promising tool in patient evaluation for mandibular condylar hyperplasia, since it provides appropriate quantitative analysis while avoiding unnecessary CT dose We detected high correlation between CT-based and AI-based SUV values. Further studies need to be conducted to elucidate the difference at higher SUV values.
Tárgyszavak:Orvostudományok Klinikai orvostudományok idézhető absztrakt
folyóiratcikk
Megjelenés:European Journal Of Nuclear Medicine And Molecular Imaging. - 51 : Suppl. 1 (2024), p. S778-S779. -
További szerzők:Szolikova, Melinda Csikos Csaba (1997-) (orvos) Török Judit (1973-) (egyetemi tanársegéd, fogszakorvos) Husztik Borbála Varga József (1955-) (fizikus) Kovács Ákos Garai Ildikó (1966-) (radiológus)
Internet cím:Szerző által megadott URL
DOI
Intézményi repozitóriumban (DEA) tárolt változat
Borító:

2.

001-es BibID:BIBFORM132028
035-os BibID:(WoS)001332779400001
Első szerző:Csikos Csaba (orvos)
Cím:Validation of an AI-Based Noise Reduction Filter on Bone Scan Images / Csikos Csaba, Barna Sándor, Kovács Ákos, Budai Ádám, Szoliková Melinda, Nagy Iván, Husztik Borbála, Kiszler Gábor, Garai Ildikó
Dátum:2024
ISSN:1619-7070 1619-7089
Megjegyzések:Aim/Introduction: Artificial intelligence (AI) is a promising tool in helping physician workflow and raise the effectiveness of their reads. Our work focuses on the validation of an AI based tool developed by Kovacs et al., 2022. In our validation, we aimed to evaluate the performance of an AI-based noise reduction filter. Materials and Methods: The AI bone scan filter (BS-AI) was validated retrospectively on 99mTc-MDP whole body images. The examinations were performed according to the institutional routine protocol. Validation was done using 47 planar bone scans of different patients which form a representative group of the training set. 3 nuclear medicine experts scored AI-filtered and original images for image quality and contrast. The performance of the BS-AI filter was tested on artificially degraded noisy images - 75-50-25% of total counts - which were generated by binominal sampling. For quantitative analysis, we used an automatic lesion detector (BS-annotator). The total number of lesions detected by the BS-annotator in the BS-AI filtered low-count images were compared to the original filtered images. The total number of pixels in the filtered low-count images relative to the number of pixels in the original filtered images were compared with one-way ANOVA. Results: Based on visual assessment, observers agreed that image contrast and quality were better in the BS-AI filtered images, increasing their diagnostic confidence. In addition, no new or disappearing lesions were detected in the filtered total- count and in the images degraded to counts of 75% and 50%. However, new and disappearing lesions were detected in images degraded to a count of 25%. The similarities of lesions detected by BS-annotator compared to filtered total-count images were 89%, 83%, 75% for images degraded to counts of 75%, 50% and 25%. There was no significant difference in the number of annotated pixels between filtered images with different counts. Conclusion: Our results showed that this BS-AI noise reduction filter is able to improve image quality and contrast not only on images with conventional protocol but also on low-count images. The use of this filter may provide an opportunity to reduce acquisition time or decrease the injected dose. References: Kovacs A, Bukki T, Legradi G, et al. Robustness analysis of denoising neural networks for Bone Scintigraphy. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment. 2022;1039:167003.
Tárgyszavak:Orvostudományok Klinikai orvostudományok idézhető absztrakt
folyóiratcikk
Megjelenés:European Journal of Nuclear Medicine and Molecular Imaging. - 51 : Suppl. 1 (2024), p. S787. -
További szerzők:Barna Sándor (1982-) (kutató orvos) Kovács Ákos Budai Ádám Szolikova, Melinda Nagy Iván Gábor Husztik Borbála Kiszler Gábor Garai Ildikó (1966-) (radiológus)
Pályázati támogatás:EKÖP-24-3-II
Egyéb
Internet cím:Szerző által megadott URL
DOI
Intézményi repozitóriumban (DEA) tárolt változat
Borító:

3.

001-es BibID:BIBFORM126339
035-os BibID:(scopus)85211822029 (wos)001377328800001
Első szerző:Csikos Csaba (orvos)
Cím:AI-Based Noise-Reduction Filter for Whole-Body Planar Bone Scintigraphy Reliably Improves Low-Count Images / Csikos Csaba, Barna Sándor, Kovács Ákos, Czina Péter, Budai Ádám, Szoliková Melinda, Nagy Iván Gábor, Husztik Borbála, Kiszler Gábor, Garai Ildikó
Dátum:2024
ISSN:2075-4418
Megjegyzések:Background/Objectives: Artificial intelligence (AI) is a promising tool for the enhancement of physician workflow and serves to further improve the efficiency of their diagnostic evaluations. This study aimed to assess the performance of an AI-based bone scan noise-reduction filter on noisy, low-count images in a routine clinical environment. Methods: The performance of the AI bone-scan filter (BS-AI filter) in question was retrospectively evaluated on 47 different patients' 99mTc-MDP bone scintigraphy image pairs (anterior- and posterior-view images), which were obtained in such a manner as to represent the diverse characteristics of the general patient population. The BS-AI filter was tested on artificially degraded noisy images?75, 50, and 25% of total counts?which were generated by binominal sampling. The AI-filtered and unfiltered images were concurrently appraised for image quality and contrast by three nuclear medicine physicians. It was also determined whether there was any difference between the lesions seen on the unfiltered and filtered images. For quantitative analysis, an automatic lesion detector (BS-AI annotator) was utilized as a segmentation algorithm. The total number of lesions and their locations as detected by the BS-AI annotator in the BS-AI-filtered low-count images was compared to the total-count filtered images. The total number of pixels labeled as lesions in the filtered low-count images in relation to the number of pixels in the total-count filtered images was also compared to ensure the filtering process did not change lesion sizes significantly. The comparison of pixel numbers was performed using the reduced-count filtered images that contained only those lesions that were detected in the total-count images. Results: Based on visual assessment, observers agreed that image contrast and quality were better in the BS-AI-filtered images, increasing their diagnostic confidence. Similarities in lesion numbers and sites detected by the BS-AI annotator compared to filtered total-count images were 89%, 83%, and 75% for images degraded to counts of 75%, 50%, and 25%, respectively. No significant difference was found in the number of annotated pixels between filtered images with different counts (p > 0.05). Conclusions: Our findings indicate that the BS-AI noise-reduction filter enhances image quality and contrast without loss of vital information. The implementation of this filter in routine diagnostic procedures reliably improves diagnostic confidence in low-count images and elicits a reduction in the administered dose or acquisition time by a minimum of 50% relative to the original dose or acquisition time.
Tárgyszavak:Orvostudományok Klinikai orvostudományok idegen nyelvű folyóiratközlemény külföldi lapban
folyóiratcikk
bone scan
nuclear medicine
imaging
noise reduction filter
artificial intelligence
Megjelenés:Diagnostics. - 14 : 23 (2024), p. 1-11. -
További szerzők:Barna Sándor (1982-) (kutató orvos) Kovács Ákos Czina Péter Budai Ádám Szolikova, Melinda Nagy Iván Gábor Husztik Borbála Kiszler Gábor Garai Ildikó (1966-) (radiológus)
Internet cím:Szerző által megadott URL
DOI
Intézményi repozitóriumban (DEA) tárolt változat
Borító:

4.

001-es BibID:BIBFORM118927
Első szerző:Kovács Ákos
Cím:A mesterséges és emberi intelligencia értéke a csontszcintigráfia példáján keresztül / Kovács Ákos, Légrádi Gábor, Wirth András, Nagy Ferenc, Forgács Attila, Barna Sándor Kristóf, Garai Ildikó, Bükki Tamás
Dátum:2020
ISSN:0025-0244
Megjegyzések:Bemutatjuk a mesterséges intelligencián (MI) alapuló módszerek egy lehetséges klinikai alkalmazását, mely képes a jelentős zajjal terhelt csontszcintigráfiás felvételek hatékony zajszűrésére. A speciális MI-alkalmazás az előzetes vizsgálatok alapján lehetővé teszi, hogy számottevően csökkenthessük a vizsgálati időt vagy a betegnek beadott aktivitást, így csökkentheti a beteget, asszisztenst, orvost ért sugárterhelést. Bemutatjuk az MI-szűrő alkalmazása működésének sajátosságait, tanítási folyamatát, melyet fontos érteni ahhoz, hogy a leletező orvos biztonsággal, ?másodlagos megbízható véleményként" figyelembe vehesse az MI-feldolgozott képet, és ezáltal pontosabb diagnózist fogalmazhasson meg a segítségével. Kitérünk az algoritmus robusztusságvizsgálatára, valamint a komplex klinikai ellenőrzés sajátosságaira és kihívásaira is.
Tárgyszavak:Orvostudományok Klinikai orvostudományok magyar nyelvű folyóiratközlemény hazai lapban
folyóiratcikk
mesterséges intelligencia
csontszcintigráfia
klinikai validáció
zajcsökkentés
jel-zaj viszony javítása
Megjelenés:Magyar Onkologia. - 64 (2020), p. 153-158. -
További szerzők:Legrádi Gábor Wirth András Nagy Ferenc (1984-) (fizikus) Forgács Attila (1985-) (fizikus) Barna Sándor (1982-) (kutató orvos) Garai Ildikó (1966-) (radiológus) Bükki Tamás
Internet cím:Szerző által megadott URL
Intézményi repozitóriumban (DEA) tárolt változat
Borító:

5.

001-es BibID:BIBFORM102569
035-os BibID:(Wos)000822408700002 (Scopus)85133810929
Első szerző:Kovács Ákos
Cím:Robustness analysis of denoising neural networks for bone scintigraphy / Kovacs Akos, Bukki Tamas, Legradi Gabor, Meszaros Nora J., Kovacs Gyula Z., Prajczer Peter, Tamaga Istvan, Seress Zoltan, Kiszler Gabor, Forgacs Attila, Barna Sandor, Garai Ildiko, Horvath Andras
Dátum:2022
ISSN:0168-9002
Tárgyszavak:Orvostudományok Klinikai orvostudományok idegen nyelvű folyóiratközlemény külföldi lapban
folyóiratcikk
Megjelenés:Nuclear Instruments & Methods In Physics Research Section A-Accelerators Spectrometers Detectors And Associated Equipment. - 1039 (2022), p. 1-11. -
További szerzők:Bükki Tamás Legrádi Gábor Mészáros Nóra J. Kovács Gyula Z. Prajczer Péter Tamaga István Seress Zoltán Kiszler Gábor Forgács Attila (1985-) (fizikus) Barna Sándor (1982-) (kutató orvos) Garai Ildikó (1966-) (radiológus) Horváth András (1976-) (vegyész)
Internet cím:Szerző által megadott URL
DOI
Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Rekordok letöltése1 
Corvina könyvtári katalógus v10.11.18-SNAPSHOT © 2024 Monguz kft. Minden jog fenntartva.