1
|
Xie H, Xu W, Wang YX, Wu X. Deep learning network with differentiable dynamic programming for retina OCT surface segmentation. BIOMEDICAL OPTICS EXPRESS 2023; 14:3190-3202. [PMID: 37497505 PMCID: PMC10368040 DOI: 10.1364/boe.492670] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/10/2023] [Revised: 05/19/2023] [Accepted: 05/23/2023] [Indexed: 07/28/2023]
Abstract
Multiple-surface segmentation in optical coherence tomography (OCT) images is a challenging problem, further complicated by the frequent presence of weak image boundaries. Recently, many deep learning-based methods have been developed for this task and yield remarkable performance. Unfortunately, due to the scarcity of training data in medical imaging, it is challenging for deep learning networks to learn the global structure of the target surfaces, including surface smoothness. To bridge this gap, this study proposes to seamlessly unify a U-Net for feature learning with a constrained differentiable dynamic programming module to achieve end-to-end learning for retina OCT surface segmentation to explicitly enforce surface smoothness. It effectively utilizes the feedback from the downstream model optimization module to guide feature learning, yielding better enforcement of global structures of the target surfaces. Experiments on Duke AMD (age-related macular degeneration) and JHU MS (multiple sclerosis) OCT data sets for retinal layer segmentation demonstrated that the proposed method was able to achieve subvoxel accuracy on both datasets, with the mean absolute surface distance (MASD) errors of 1.88 ± 1.96μm and 2.75 ± 0.94μm, respectively, over all the segmented surfaces.
Collapse
Affiliation(s)
- Hui Xie
- Department of Electrical and Computer Engineering, The University of Iowa, Iowa City, IA, USA
| | - Weiyu Xu
- Department of Electrical and Computer Engineering, The University of Iowa, Iowa City, IA, USA
| | - Ya Xing Wang
- Beijing Institute of Ophthalmology, Beijing Tongren Hospital, Capital University of Medical Science, Beijing Ophthalmology and Visual Sciences Key Laboratory, Beijing, China
| | - Xiaodong Wu
- Department of Electrical and Computer Engineering, The University of Iowa, Iowa City, IA, USA
| |
Collapse
|
2
|
Boehm C, Schlaeger S, Meineke J, Weiss K, Makowski MR, Karampinos DC. On the water-fat in-phase assumption for quantitative susceptibility mapping. Magn Reson Med 2023; 89:1068-1082. [PMID: 36321543 DOI: 10.1002/mrm.29516] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2022] [Revised: 10/06/2022] [Accepted: 10/15/2022] [Indexed: 11/07/2022]
Abstract
PURPOSE To (a) define multi-peak fat model-based effective in-phase echo times for quantitative susceptibility mapping (QSM) in water-fat regions, (b) analyze the relationship between fat fraction, field map quantification bias and susceptibility bias, and (c) evaluate the susceptibility mapping performance of the proposed effective in-phase echoes in comparison to single-peak in-phase echoes and water-fat separation for regions where both water and fat are present. METHODS Effective multipeak in-phase echo times for a bone marrow and a liver fat spectral model were derived from a single voxel simulation. A Monte Carlo simulation was performed to assess the field map estimation error as a function of fat fraction for the different in-phase echoes. Additionally, a phantom scan and in vivo scans in the liver, spine, and breast were performed and evaluated with respect to quantification accuracy. RESULTS The use of single-peak in-phase echoes can introduce a worst-case susceptibility bias of 0.43 $$ 0.43 $$ ppm. The use of effective multipeak in-phase echoes shows a similar quantitative performance in the numerical simulation, the phantom and in all in vivo anatomies when compared to water-fat separation-based QSM. CONCLUSION QSM based on the proposed effective multipeak in-phase echoes can alleviate the quantification bias present in QSM based on single-peak in-phase echoes. When compared to water-fat separation-based QSM the proposed effective in-phase echo times achieve a similar quantitative performance while drastically reducing the computational expense for field map estimation.
Collapse
Affiliation(s)
- Christof Boehm
- Department of Diagnostic and Interventional Radiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Sarah Schlaeger
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | | | | | - Marcus R Makowski
- Department of Diagnostic and Interventional Radiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Dimitrios C Karampinos
- Department of Diagnostic and Interventional Radiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| |
Collapse
|
3
|
Xie H, Pan Z, Zhou L, Zaman FA, Chen DZ, Jonas JB, Xu W, Wang YX, Wu X. Globally optimal OCT surface segmentation using a constrained IPM optimization. OPTICS EXPRESS 2022; 30:2453-2471. [PMID: 35209385 DOI: 10.1364/oe.444369] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/27/2021] [Accepted: 01/01/2022] [Indexed: 06/14/2023]
Abstract
Segmentation of multiple surfaces in optical coherence tomography (OCT) images is a challenging problem, further complicated by the frequent presence of weak boundaries, varying layer thicknesses, and mutual influence between adjacent surfaces. The traditional graph-based optimal surface segmentation method has proven its effectiveness with its ability to capture various surface priors in a uniform graph model. However, its efficacy heavily relies on handcrafted features that are used to define the surface cost for the "goodness" of a surface. Recently, deep learning (DL) is emerging as a powerful tool for medical image segmentation thanks to its superior feature learning capability. Unfortunately, due to the scarcity of training data in medical imaging, it is nontrivial for DL networks to implicitly learn the global structure of the target surfaces, including surface interactions. This study proposes to parameterize the surface cost functions in the graph model and leverage DL to learn those parameters. The multiple optimal surfaces are then simultaneously detected by minimizing the total surface cost while explicitly enforcing the mutual surface interaction constraints. The optimization problem is solved by the primal-dual interior-point method (IPM), which can be implemented by a layer of neural networks, enabling efficient end-to-end training of the whole network. Experiments on spectral-domain optical coherence tomography (SD-OCT) retinal layer segmentation demonstrated promising segmentation results with sub-pixel accuracy.
Collapse
|
4
|
Colombo E, Fick T, Esposito G, Germans M, Regli L, van Doormaal T. Segmentation techniques of brain arteriovenous malformations for 3D visualization: a systematic review. LA RADIOLOGIA MEDICA 2022; 127:1333-1341. [PMID: 36255659 PMCID: PMC9747834 DOI: 10.1007/s11547-022-01567-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/26/2022] [Accepted: 09/30/2022] [Indexed: 12/15/2022]
Abstract
BACKGROUND Visualization, analysis and characterization of the angioarchitecture of a brain arteriovenous malformation (bAVM) present crucial steps for understanding and management of these complex lesions. Three-dimensional (3D) segmentation and 3D visualization of bAVMs play hereby a significant role. We performed a systematic review regarding currently available 3D segmentation and visualization techniques for bAVMs. METHODS PubMed, Embase and Google Scholar were searched to identify studies reporting 3D segmentation techniques applied to bAVM characterization. Category of input scan, segmentation (automatic, semiautomatic, manual), time needed for segmentation and 3D visualization techniques were noted. RESULTS Thirty-three studies were included. Thirteen (39%) used MRI as baseline imaging modality, 9 used DSA (27%), and 7 used CT (21%). Segmentation through automatic algorithms was used in 20 (61%), semiautomatic segmentation in 6 (18%), and manual segmentation in 7 (21%) studies. Median automatic segmentation time was 10 min (IQR 33), semiautomatic 25 min (IQR 73). Manual segmentation time was reported in only one study, with the mean of 5-10 min. Thirty-two (97%) studies used screens to visualize the 3D segmentations outcomes and 1 (3%) study utilized a heads-up display (HUD). Integration with mixed reality was used in 4 studies (12%). CONCLUSIONS A golden standard for 3D visualization of bAVMs does not exist. This review describes a tendency over time to base segmentation on algorithms trained with machine learning. Unsupervised fuzzy-based algorithms thereby stand out as potential preferred strategy. Continued efforts will be necessary to improve algorithms, integrate complete hemodynamic assessment and find innovative tools for tridimensional visualization.
Collapse
Affiliation(s)
- Elisa Colombo
- Department of Neurosurgery, Clinical Neuroscience Center and University of Zürich, University Hospital Zurich, Frauenklinikstrasse 10, 8091, Zürich, ZH, Switzerland.
| | - Tim Fick
- Prinses Màxima Center, Department of Neurosurgery, Utrecht, CS, The Netherlands
| | - Giuseppe Esposito
- Department of Neurosurgery and Clinical Neuroscience Centerentrum, University Hospital of Zurich, Zürich, ZH, Switzerland
| | - Menno Germans
- Department of Neurosurgery and Clinical Neuroscience Centerentrum, University Hospital of Zurich, Zürich, ZH, Switzerland
| | - Luca Regli
- Department of Neurosurgery and Clinical Neuroscience Centerentrum, University Hospital of Zurich, Zürich, ZH, Switzerland
| | - Tristan van Doormaal
- Department of Neurosurgery and Clinical Neuroscience Centerentrum, University Hospital of Zurich, Zürich, ZH, Switzerland
| |
Collapse
|
5
|
Zaman F, Ponnapureddy R, Wang YG, Chang A, Cadaret LM, Abdelhamid A, Roy SD, Makan M, Zhou R, Jayanna MB, Gnall E, Dai X, Singh A, Zheng J, Boppana VS, Wang F, Singh P, Wu X, Liu K. Spatio-temporal hybrid neural networks reduce erroneous human "judgement calls" in the diagnosis of Takotsubo syndrome. EClinicalMedicine 2021; 40:101115. [PMID: 34522872 PMCID: PMC8426197 DOI: 10.1016/j.eclinm.2021.101115] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/23/2021] [Revised: 08/08/2021] [Accepted: 08/16/2021] [Indexed: 11/11/2022] Open
Abstract
BACKGROUND We investigate whether deep learning (DL) neural networks can reduce erroneous human "judgment calls" on bedside echocardiograms and help distinguish Takotsubo syndrome (TTS) from anterior wall ST segment elevation myocardial infarction (STEMI). METHODS We developed a single-channel (DCNN[2D SCI]), a multi-channel (DCNN[2D MCI]), and a 3-dimensional (DCNN[2D+t]) deep convolution neural network, and a recurrent neural network (RNN) based on 17,280 still-frame images and 540 videos from 2-dimensional echocardiograms in 10 years (1 January 2008 to 1 January 2018) retrospective cohort in University of Iowa (UI) and eight other medical centers. Echocardiograms from 450 UI patients were randomly divided into training and testing sets for internal training, testing, and model construction. Echocardiograms of 90 patients from the other medical centers were used for external validation to evaluate the model generalizability. A total of 49 board-certified human readers performed human-side classification on the same echocardiography dataset to compare the diagnostic performance and help data visualization. FINDINGS The DCNN (2D SCI), DCNN (2D MCI), DCNN(2D+t), and RNN models established based on UI dataset for TTS versus STEMI prediction showed mean diagnostic accuracy 73%, 75%, 80%, and 75% respectively, and mean diagnostic accuracy of 74%, 74%, 77%, and 73%, respectively, on the external validation. DCNN(2D+t) (area under the curve [AUC] 0·787 vs. 0·699, P = 0·015) and RNN models (AUC 0·774 vs. 0·699, P = 0·033) outperformed human readers in differentiating TTS and STEMI by reducing human erroneous judgement calls on TTS. INTERPRETATION Spatio-temporal hybrid DL neural networks reduce erroneous human "judgement calls" in distinguishing TTS from anterior wall STEMI based on bedside echocardiographic videos. FUNDING University of Iowa Obermann Center for Advanced Studies Interdisciplinary Research Grant, and Institute for Clinical and Translational Science Grant. National Institutes of Health Award (1R01EB025018-01).
Collapse
Affiliation(s)
- Fahim Zaman
- Department of Electrical and Electronic Engineering, University of Iowa, Iowa city, IA, United States
| | - Rakesh Ponnapureddy
- Division of Cardiology, Department of Medicine, University of Iowa, Iowa City, IA, United States
| | - Yi Grace Wang
- Department of Mathematics, California State University Dominguez Hills, Carson, CA, United States
| | - Amanda Chang
- Division of Cardiology, Department of Medicine, University of Iowa, Iowa City, IA, United States
| | - Linda M Cadaret
- Division of Cardiology, Department of Medicine, University of Iowa, Iowa City, IA, United States
| | - Ahmed Abdelhamid
- Division of Cardiology, Department of Medicine, University of Iowa, Iowa City, IA, United States
| | - Shubha D Roy
- Division of Cardiology, Department of Medicine, University of Iowa, Iowa City, IA, United States
| | - Majesh Makan
- Division of Cardiology, Department of Medicine, Washington University in St. Louis, St. Louis, MO, United States
| | - Ruihai Zhou
- Division of Cardiology, Department of Medicine, University of North Carolina, Chapel Hill, United States
| | - Manju B Jayanna
- Division of Cardiology, Department of Medicine, Lankenau Medical Center, Wynnewood, PA, United States
| | - Eric Gnall
- Division of Cardiology, Department of Medicine, Lankenau Medical Center, Wynnewood, PA, United States
| | - Xuming Dai
- Department of Cardiology, New York Presbyterian Queens/Weill Cornell Medical College, New York City, NY, United States
| | - Avneet Singh
- Division of Cardiology, Department of Medicine, State University of New York, Syracuse, NY, United States
| | - Jingsheng Zheng
- Department of Cardiology, AtlaniCare Regional Medical Center, Pomona, NJ, United States
| | - Venkata S Boppana
- Division of Cardiology, Department of Medicine, University of Kansas-Wichita, Wichita, KS, United States
| | - Feng Wang
- Department of Cardiology, Providence Regional Medical Center, Washington State University, Everett, WA, United States
| | - Pahul Singh
- Department of Cardiology, Northwest Health Medical Center, Bentonville, AR, United States
| | - Xiaodong Wu
- Department of Electrical and Electronic Engineering, University of Iowa, Iowa city, IA, United States
- Corresponding authors.
| | - Kan Liu
- Division of Cardiology, Department of Medicine, University of Iowa, Iowa City, IA, United States
- Corresponding authors.
| |
Collapse
|
6
|
Weidlich D, Honecker J, Boehm C, Ruschke S, Junker D, Van AT, Makowski MR, Holzapfel C, Claussnitzer M, Hauner H, Karampinos DC. Lipid droplet-size mapping in human adipose tissue using a clinical 3T system. Magn Reson Med 2021; 86:1256-1270. [PMID: 33797107 DOI: 10.1002/mrm.28755] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2020] [Revised: 02/08/2021] [Accepted: 02/08/2021] [Indexed: 11/07/2022]
Abstract
PURPOSE To develop a methodology for probing lipid droplet sizes with a clinical system based on a diffusion-weighted stimulated echo-prepared turbo spin-echo sequence and to validate the methodology in water-fat emulsions and show its applicability in ex vivo adipose-tissue samples. METHODS A diffusion-weighted stimulated echo-prepared preparation was combined with a single-shot turbo spin-echo readout for measurements at different b-values and diffusion times. The droplet size was estimated with an analytical expression, and three fitting approaches were compared: magnitude-based spatial averaging with voxel-wise residual minimization, complex-based spatial averaging with voxel-wise residual minimization, and complex-based spatial averaging with neighborhood-regularized residual minimization. Simulations were performed to characterize the fitting residual landscape and the approaches' noise performance. The applicability was assessed in oil-in-water emulsions in comparison with laser deflection and in ten human white adipose tissue samples in comparison with histology. RESULTS The fitting residual landscape showed a minimum valley with increasing extent as the droplet size increased. In phantoms, a very good agreement of the mean droplet size was observed between the diffusion-weighted MRI-based and the laser deflection measurements, showing the best performance with complex-based spatial averaging with neighborhood-regularized residual minimization processing (R2 /P: 0.971/0.014). In the human adipose-tissue samples, complex-based spatial averaging with neighborhood-regularized residual minimization processing showed a significant correlation (R2 /P: 0.531/0.017) compared with histology. CONCLUSION The proposed acquisition and parameter-estimation methodology was able to probe restricted diffusion effects in lipid droplets. The methodology was validated using phantoms, and its feasibility in measuring an apparent lipid droplet size was demonstrated ex vivo in white adipose tissue.
Collapse
Affiliation(s)
- Dominik Weidlich
- Department of Diagnostic and Interventional Radiology, School of Medicine, Technical University of Munich, Munich, Germany
| | - Julius Honecker
- Else Kröner Fresenius Center for Nutritional Medicine, School of Life Sciences, Technical University of Munich, Munich, Germany
| | - Christof Boehm
- Department of Diagnostic and Interventional Radiology, School of Medicine, Technical University of Munich, Munich, Germany
| | - Stefan Ruschke
- Department of Diagnostic and Interventional Radiology, School of Medicine, Technical University of Munich, Munich, Germany
| | - Daniela Junker
- Department of Diagnostic and Interventional Radiology, School of Medicine, Technical University of Munich, Munich, Germany
| | - Anh T Van
- Department of Diagnostic and Interventional Radiology, School of Medicine, Technical University of Munich, Munich, Germany
| | - Marcus R Makowski
- Department of Diagnostic and Interventional Radiology, School of Medicine, Technical University of Munich, Munich, Germany
| | - Christina Holzapfel
- Institute for Nutritional Medicine, School of Medicine, Technical University of Munich, Munich, Germany
| | - Melina Claussnitzer
- Broad Institute of MIT and Harvard, Cambridge, Massachusetts, USA.,Division of Gerontology, Department of Medicine, Beth Israel Deaconess Medical Center, Boston, Massachusetts, USA.,Harvard Medical School, Harvard University, Boston, Massachusetts, USA
| | - Hans Hauner
- Else Kröner Fresenius Center for Nutritional Medicine, School of Life Sciences, Technical University of Munich, Munich, Germany.,Institute for Nutritional Medicine, School of Medicine, Technical University of Munich, Munich, Germany
| | - Dimitrios C Karampinos
- Department of Diagnostic and Interventional Radiology, School of Medicine, Technical University of Munich, Munich, Germany
| |
Collapse
|
7
|
Boehm C, Diefenbach MN, Makowski MR, Karampinos DC. Improved body quantitative susceptibility mapping by using a variable-layer single-min-cut graph-cut for field-mapping. Magn Reson Med 2020; 85:1697-1712. [PMID: 33151604 DOI: 10.1002/mrm.28515] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2020] [Revised: 08/20/2020] [Accepted: 08/21/2020] [Indexed: 12/18/2022]
Abstract
PURPOSE To develop a robust algorithm for field-mapping in the presence of water-fat components, large B 0 field inhomogeneities and MR signal voids and to apply the developed method in body applications of quantitative susceptibility mapping (QSM). METHODS A framework solving the cost-function of the water-fat separation problem in a single-min-cut graph-cut based on the variable-layer graph construction concept was developed. The developed framework was applied to a numerical phantom enclosing an MR signal void, an air bubble experimental phantom, 14 large field of view (FOV) head/neck region in vivo scans and to 6 lumbar spine in vivo scans. Field-mapping and subsequent QSM results using the proposed algorithm were compared to results using an iterative graph-cut algorithm and a formerly proposed single-min-cut graph-cut. RESULTS The proposed method was shown to yield accurate field-map and susceptibility values in all simulation and in vivo datasets when compared to reference values (simulation) or literature values (in vivo). The proposed method showed improved field-map and susceptibility results compared to iterative graph-cut field-mapping especially in regions with low SNR, strong field-map variations and high R 2 ∗ values. CONCLUSIONS A single-min-cut graph-cut field-mapping method with a variable-layer construction was developed for field-mapping in body water-fat regions, improving quantitative susceptibility mapping particularly in areas close to MR signal voids.
Collapse
Affiliation(s)
- Christof Boehm
- Department of Diagnostic and Interventional Radiology, Technical University of Munich, Munich, Germany
| | - Maximilian N Diefenbach
- Department of Diagnostic and Interventional Radiology, Technical University of Munich, Munich, Germany.,Division of Infectious Diseases and Tropical Medicine, University Hospital, LMU Munich, Munich, Germany
| | - Marcus R Makowski
- Department of Diagnostic and Interventional Radiology, Technical University of Munich, Munich, Germany
| | - Dimitrios C Karampinos
- Department of Diagnostic and Interventional Radiology, Technical University of Munich, Munich, Germany
| |
Collapse
|