1
|
Jing M, Xi H, Liu Q, Zhu H, Sun Q, Zhang Y, Liu X, Ren W, Deng L, Zhou J. Correlation between left atrial appendage morphology based on fractal dimension quantification and its hemodynamic parameters in patients with atrial fibrillation. Clin Radiol 2024:S0009-9260(24)00334-9. [PMID: 39054176 DOI: 10.1016/j.crad.2024.05.022] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2024] [Revised: 03/24/2024] [Accepted: 05/01/2024] [Indexed: 07/27/2024]
Abstract
AIMS To investigate the relationship between left atrial appendage (LAA) morphology, quantified based on fractal dimension (FD), and LAA hemodynamic parameters in patients with atrial fibrillation (AF), in an effort to reveal the effect of LAA shape on blood flow. MATERIALS AND METHODS 225 patients with AF who underwent cardiac computed tomography angiography (CTA) and transesophageal echocardiography (TEE) were enrolled. LAA morphology was quantified based on FD on cardiac CTA images, and LAA hemodynamic parameters, including injection fraction (EF), filling peak flow velocity (FV), maximum speed of emptying (PEV), and wall motion velocity (WMV), were assessed using TEE. RESULTS We divided the patients with AF into two groups based on a mean LAA FD of 1.32: the low FD group (n=124) and the high FD group (n=101). Compared to the low FD group, there were more patients with LAA circulatory stasis/thrombus (P=0.008) in the high FD group, as well as lower LAA FV (P=0.004), LAA PEV (P=0.007), and LAA WMV (P=0.007). LAA FD was an independent and significant determinant of LAA EF (β = -11.755, P=0.001), LAA FV (β = -17.364, P=0.004), LAA PEV (β = -18.743, P<0.001), and LAA WMV (β = -7.740, P=0.001) in multiple linear regression analysis. CONCLUSIONS LAA FD is an essential determinant of LAA hemodynamic parameters, suggesting that the relatively complex morphology of the LAA may influence its hemodynamics, which can correlate with embolic events.
Collapse
Affiliation(s)
- M Jing
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China; Second Clinical School, Lanzhou University, Lanzhou, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou, China
| | - H Xi
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China; Second Clinical School, Lanzhou University, Lanzhou, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou, China
| | - Q Liu
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China; Second Clinical School, Lanzhou University, Lanzhou, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou, China
| | - H Zhu
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China; Second Clinical School, Lanzhou University, Lanzhou, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou, China
| | - Q Sun
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China; Second Clinical School, Lanzhou University, Lanzhou, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou, China
| | - Y Zhang
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China; Second Clinical School, Lanzhou University, Lanzhou, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou, China
| | - X Liu
- Ultrasound Medical Center, Lanzhou University Second Hospital, Lanzhou, China
| | - W Ren
- GE Healthcare, Computed Tomography Research Center, Beijing, China
| | - L Deng
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China; Second Clinical School, Lanzhou University, Lanzhou, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou, China
| | - J Zhou
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China; Second Clinical School, Lanzhou University, Lanzhou, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou, China.
| |
Collapse
|
3
|
Tenti JM, Hernández Guiance SN, Irurzun IM. Fractal dimension of diffusion-limited aggregation clusters grown on spherical surfaces. Phys Rev E 2021; 103:012138. [PMID: 33601584 DOI: 10.1103/physreve.103.012138] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2020] [Accepted: 01/04/2021] [Indexed: 01/18/2023]
Abstract
In this work we study the fractal properties of diffusion-limited aggregation (DLA) clusters grown on spherical surfaces. Diffusion-limited aggregation clusters, or DLA trees, are highly branched fractal clusters formed by the adhesion of particles. In two-dimensional media, DLA clusters have a fractal dimension D_{f}=1.70 in the continuous limit. In some physical systems, the existence of characteristic lengths leads us to model them as discrete systems. Such characteristic lengths may result also from limitations in measuring instruments, for example, the resolution of biomedical imaging systems. We simulate clusters for different particle sizes and examine the influence of discretization by exploring the systems in terms of the relationship between the particle size r and the radius of the sphere R. We also study the effect of stereographic projection on the fractal properties of DLA clusters. Both discretization and projection alter the fractal dimension of DLA clusters grown on curved surfaces and must be considered in the interpretation of photographic biomedical images.
Collapse
Affiliation(s)
- J M Tenti
- Facultad de Ciencias Exactas, Instituto de Investigaciones Fisicoquímicas Teóricas y Aplicadas, CCT La Plata, Universidad Nacional de La Plata, B1904 La Plata, Buenos Aires, Argentine Republic
| | - S N Hernández Guiance
- Facultad de Ciencias Exactas, Instituto de Investigaciones Fisicoquímicas Teóricas y Aplicadas, CCT La Plata, Universidad Nacional de La Plata, B1904 La Plata, Buenos Aires, Argentine Republic
| | - I M Irurzun
- Facultad de Ciencias Exactas, Instituto de Investigaciones Fisicoquímicas Teóricas y Aplicadas, CCT La Plata, Universidad Nacional de La Plata, B1904 La Plata, Buenos Aires, Argentine Republic
| |
Collapse
|
4
|
Additive value of exposure parameters for breast cancer diagnosis in digital mammography. Eur Radiol 2020; 31:2539-2547. [PMID: 32979051 DOI: 10.1007/s00330-020-07311-9] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2020] [Revised: 08/07/2020] [Accepted: 09/17/2020] [Indexed: 01/02/2023]
Abstract
OBJECTIVES To investigate the effect of different breast lesions on exposure parameters in digital mammography and to determine whether the exposure parameters can additively improve diagnostic efficiency. METHODS Craniocaudal view and mediolateral view full-field digital mammography images from 982 women with unilateral lesions (341 with malignant lesions, 189 with benign lesions, and 452 healthy women) obtained at Nanfang Hospital were reviewed. Differences in exposure parameters (tube voltage and load, breast thickness (BT), and average glandular dose (AGD)) between breasts were calculated. The relationships between parameter differences and lesion size were explored. A logistic regression model was used based on the AGD and BT differences, and the area under the receiver operating characteristic curve (AUC) was used to assess the performance of these parameters in differentiating malignant from benign and healthy subjects. Independently, data from 129 women (82 with malignant and 47 with benign lesions) treated at Sun Yat-sen Memorial Hospital were collected to validate the model. RESULTS Differences in tube voltage and load, BT, and AGD between breasts were significantly greater in the malignant subjects than benign (p < 0.05) and healthy subjects (p < 0.05). The AUCs for the comparisons of malignant vs. healthy subjects, malignant vs. benign subjects, and benign vs. healthy subjects were 0.77 ± 0.02, 0.72 ± 0.02, and 0.57 ± 0.02, respectively. The model combining the exposure parameters with the BI-RADS category resulted in a higher AUC (0.910 ± 0.03) compared with physician diagnosis alone (0.820 ± 0.04) for differentiating between malignant and benign lesions. CONCLUSIONS Exposure parameters additively improved diagnostic accuracy for breast cancer and yielded more reliable results. KEY POINTS • Differences in kVp, mAs, BT, and AGD between breasts were significantly greater in the malignant subjects than benign and healthy subjects. • The model combining exposure parameters with the BI-RADS category resulted in a higher AUC compared with the physician's diagnosis for differentiating between malignant and benign lesions. • Exposure parameters additively improved diagnostic accuracy for breast cancer.
Collapse
|
5
|
Hegdé J. Deep learning can be used to train naïve, nonprofessional observers to detect diagnostic visual patterns of certain cancers in mammograms: a proof-of-principle study. J Med Imaging (Bellingham) 2020; 7:022410. [PMID: 32042860 PMCID: PMC6998757 DOI: 10.1117/1.jmi.7.2.022410] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2019] [Accepted: 12/26/2019] [Indexed: 11/27/2022] Open
Abstract
The scientific, clinical, and pedagogical significance of devising methodologies to train nonprofessional subjects to recognize diagnostic visual patterns in medical images has been broadly recognized. However, systematic approaches to doing so remain poorly established. Using mammography as an exemplar case, we use a series of experiments to demonstrate that deep learning (DL) techniques can, in principle, be used to train naïve subjects to reliably detect certain diagnostic visual patterns of cancer in medical images. In the main experiment, subjects were required to learn to detect statistical visual patterns diagnostic of cancer in mammograms using only the mammograms and feedback provided following the subjects' response. We found not only that the subjects learned to perform the task at statistically significant levels, but also that their eye movements related to image scrutiny changed in a learning-dependent fashion. Two additional, smaller exploratory experiments suggested that allowing subjects to re-examine the mammogram in light of various items of diagnostic information may help further improve DL of the diagnostic patterns. Finally, a fourth small, exploratory experiment suggested that the image information learned was similar across subjects. Together, these results prove the principle that DL methodologies can be used to train nonprofessional subjects to reliably perform those aspects of medical image perception tasks that depend on visual pattern recognition expertise.
Collapse
Affiliation(s)
- Jay Hegdé
- Augusta University, Medical College of Georgia, Departments of Neuroscience and Regenerative Medicine and Ophthalmology, Augusta, Georgia, United States
| |
Collapse
|