Találati lista | Tudóstér

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:
Saját polcon:

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:
Saját polcon:

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:
Saját polcon: