Optimization of FFR prediction algorithm for gray zone by hemodynamic features with synthetic model and biometric data

Lee, Hyeong Jun; Kim, Young Woo; Kim, Jun Hong; Lee, Yong-Joon; Moon, Jin-Seok; Jeong, Peter; Jeong, Jaeyong; Kim, Jung-Sun; Lee, Joon Sang

doi:10.1016/j.cmpb.2022.106827

“…Thus, reference distal pressure measurements taken at the terminal ends of the fluid domain should be avoided. Refining automatic segmentation methods and integrating numerical and data‐driven approaches can mitigate input uncertainties 58 . Meanwhile, according to these results, one could wonder if it is worth including distal segments in the 3D fluid domain if the patient has a lesion located at a proximal level.…”

Section: Resultsmentioning

confidence: 99%

“…Refining automatic segmentation methods and integrating numerical and data-driven approaches can mitigate input uncertainties. 58 Meanwhile, according to these results, one could wonder if it is worth including distal segments in the 3D fluid domain if the patient has a lesion located at a proximal level. However, it is well known that if the truncation level is set at a higher position, the general flow split of the coronary tree could change, leading to potential errors in the computation of the pressure drop along the stenotic segment.…”

Section: Extension To the Patient Populationmentioning

confidence: 99%

Impact of minimal lumen segmentation uncertainty on patient‐specific coronary simulations: A look at FFR_CT

Fernández‐Martínez,

González‐Fernández,

Nogales‐Asensio

et al. 2024

Numer Methods Biomed Eng

0

View full text Add to dashboard Cite

We examined the effect of minimal lumen segmentation uncertainty on Fractional Flow Reserve obtained from Coronary Computed Tomography Angiography . A total of 14 patient‐specific coronary models with different stenosis locations and degrees of severity were enrolled in this study. The optimal segmented coronary lumens were disturbed using intra and inter‐operator variations on the segmentation threshold. was evaluated in each case by 3D‐OD CFD simulations. The findings suggest that the sensitivity of to this type of uncertainty increases distally and with the stenosis severity. Cases with moderate or severe distal coronary lesions should undergo either exact and thorough segmentation operations or invasive FFR measurements, particularly if the is close to the cutoff (0.80). Therefore, we conclude that it is crucial to consider the lesion's location and degree of severity when evaluating results.

show abstract

“…This study demonstrated that various imaging tools have been used, including CCTA [ 24 – 40 ], OCT [ 41 – 43 ], XCA [ 44 ], and IVUS [ 45 ]. Several studies used a combination of CCTA with OCT [ 46 ], IVUS [ 47 ], and XCA [ 48 ], and a study combined IVUS and XCA [ 49 ] to estimate the FFR.…”

Section: Resultsmentioning

confidence: 99%

“…AI methods used include methods based on DL [ 25 , 27 – 29 , 34 , 40 , 41 , 48 ] and ML [ 26 , 42 , 30 , 32 , 33 , 37 , 39 , 44 , 46 , 49 ]. Some studies have used a combination of DL and ML techniques [ 24 , 32 , 37 , 38 , 45 , 47 ].…”

Section: Resultsmentioning

confidence: 99%

Artificial intelligence in estimating fractional flow reserve: a systematic literature review of techniques

Farhad,

Reza,

Azamossadat

et al. 2023

BMC Cardiovasc Disord

View full text Add to dashboard Cite

Background Fractional Flow Reserve (FFR) is the gold standard for the functional evaluation of coronary arteries, which is effective in selecting patients for revascularization, avoiding unnecessary procedures, and reducing treatment costs. However, its use is limited due to invasiveness, high cost, and complexity. Therefore, the non-invasive estimation of FFR using artificial intelligence (AI) methods is crucial. Objective This study aimed to identify the AI techniques used for FFR estimation and to explore the features of the studies that applied AI techniques in FFR estimation. Methods The present systematic review was conducted by searching five databases, PubMed, Scopus, Web of Science, IEEE, and Science Direct, based on the search strategy of each database. Results Five hundred seventy-three articles were extracted, and by applying the inclusion and exclusion criteria, twenty-five were finally selected for review. The findings revealed that AI methods, including Machine Learning (ML) and Deep Learning (DL), have been used to estimate the FFR. Conclusion This study shows that AI methods can be used non-invasively to estimate FFR, which can help physicians diagnose and treat coronary artery occlusion and provide significant clinical performance for patients.

show abstract

“…This study demonstrated that various imaging tools have been used, including CCTV [24][25][26][27][28][29][30][31][32][33][34][35][36][37][38][39][40], OCT [41][42][43], XCA [44], and IVUS [45]. Several studies used a combination of CCTV with OCT [46], IVUS [47], and XCA [48], and a study combined IVUS and XCA [49] to estimate the FFR.…”

Section: Critical Review and Quality Assessmentmentioning

confidence: 99%

Artificial Intelligence in Estimating Fractional Flow Reserve: A Systematic Literature Review

Arefinia

¹

,

Rabiei

²

,

Hosseini

³

et al. 2023

Preprint

0

View full text Add to dashboard Cite

Background Fractional Flow Reserve (FFR) is the gold standard for the functional evaluation of coronary arteries, which is effective in selecting patients for revascularization, avoiding unnecessary procedures, and reducing treatment costs. However, its use is limited due to invasiveness, high cost, and complexity. Therefore, the non-invasive estimation of FFR using artificial intelligence (AI) methods is crucial. Objective This study aimed to identify the AI techniques used for FFR estimation and to explore the features of the studies that applied AI techniques in FFR estimation. Methods The present systematic review was conducted by searching five databases, PubMed, Scopus, Web of Science, IEEE, and Science Direct, based on the search strategy of each database. Results Five hundred seventy-three articles were extracted, and by applying the inclusion and exclusion criteria, twenty-five were finally selected for review. The findings revealed that AI methods, including Machine Learning (ML) and Deep Learning (DL), have been used to estimate the FFR. Conclusion This study shows that AI methods can be used non-invasively to estimate FFR, which can help physicians diagnose and treat coronary artery occlusion and provide significant clinical performance for patients.

show abstract

Optimization of FFR prediction algorithm for gray zone by hemodynamic features with synthetic model and biometric data

Cited by 12 publications

References 33 publications

Impact of minimal lumen segmentation uncertainty on patient‐specific coronary simulations: A look at FFR_CT

Impact of minimal lumen segmentation uncertainty on patient‐specific coronary simulations: A look at FFR_CT

Artificial intelligence in estimating fractional flow reserve: a systematic literature review of techniques

Artificial Intelligence in Estimating Fractional Flow Reserve: A Systematic Literature Review

Contact Info

Product

Resources

About

Optimization of FFR prediction algorithm for gray zone by hemodynamic features with synthetic model and biometric data

Cited by 12 publications

References 33 publications

Impact of minimal lumen segmentation uncertainty on patient‐specific coronary simulations: A look at FFRCT

Impact of minimal lumen segmentation uncertainty on patient‐specific coronary simulations: A look at FFRCT

Artificial intelligence in estimating fractional flow reserve: a systematic literature review of techniques

Artificial Intelligence in Estimating Fractional Flow Reserve: A Systematic Literature Review

Contact Info

Product

Resources

About

Impact of minimal lumen segmentation uncertainty on patient‐specific coronary simulations: A look at FFR_CT

Impact of minimal lumen segmentation uncertainty on patient‐specific coronary simulations: A look at FFR_CT