1
|
Zhang H, Cai Z. ConvNextUNet: A small-region attentioned model for cardiac MRI segmentation. Comput Biol Med 2024; 177:108592. [PMID: 38781642 DOI: 10.1016/j.compbiomed.2024.108592] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2023] [Revised: 04/08/2024] [Accepted: 05/09/2024] [Indexed: 05/25/2024]
Abstract
Cardiac MRI segmentation is a significant research area in medical image processing, holding immense clinical and scientific importance in assisting the diagnosis and treatment of heart diseases. Currently, existing cardiac MRI segmentation algorithms are often constrained by specific datasets and conditions, leading to a notable decrease in segmentation performance when applied to diverse datasets. These limitations affect the algorithm's overall performance and generalization capabilities. Inspired by ConvNext, we introduce a two-dimensional cardiac MRI segmentation U-shaped network called ConvNextUNet. It is the first application of a combination of ConvNext and the U-shaped architecture in the field of cardiac MRI segmentation. Firstly, we incorporate up-sampling modules into the original ConvNext architecture and combine it with the U-shaped framework to achieve accurate reconstruction. Secondly, we integrate Input Stem into ConvNext, and introduce attention mechanisms along the bridging path. By merging features extracted from both the encoder and decoder, a probability distribution is obtained through linear and nonlinear transformations, serving as attention weights, thereby enhancing the signal of the same region of interest. The resulting attention weights are applied to the decoder features, highlighting the region of interest. This allows the model to simultaneously consider local context and global details during the learning phase, fully leveraging the advantages of both global and local perception for a more comprehensive understanding of cardiac anatomical structures. Consequently, the model demonstrates a clear advantage and robust generalization capability, especially in small-region segmentation. Experimental results on the ACDC, LVQuan19, and RVSC datasets confirm that the ConvNextUNet model outperforms the current state-of-the-art models, particularly in small-region segmentation tasks. Furthermore, we conducted cross-dataset training and testing experiments, which revealed that the pre-trained model can accurately segment diverse cardiac datasets, showcasing its powerful generalization capabilities. The source code of this project is available at https://github.com/Zemin-Cai/ConvNextUNet.
Collapse
Affiliation(s)
- Huiyi Zhang
- The Department of Electronic Engineering, Shantou University, Shantou, Guangdong 515063, PR China; Key Laboratory of Digital Signal and Image Processing of Guangdong Province, Shantou, Guangdong 515063, PR China
| | - Zemin Cai
- The Department of Electronic Engineering, Shantou University, Shantou, Guangdong 515063, PR China; Key Laboratory of Digital Signal and Image Processing of Guangdong Province, Shantou, Guangdong 515063, PR China.
| |
Collapse
|
2
|
Deng Y, Qiu M, Li Y, Wang C, Zhong J, Xiao Z, Wang C, Chen R. A generalized model of cardiac surface motion for evaluating left anterior descending coronary artery dose in left breast cancer radiotherapy. Med Phys 2024. [PMID: 38922708 DOI: 10.1002/mp.17261] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2024] [Revised: 05/22/2024] [Accepted: 05/22/2024] [Indexed: 06/28/2024] Open
Abstract
BACKGROUND Retrospective studies indicate that radiation damage to left anterior descending coronary artery (LAD) may be critical for late-stage radiation-induced cardiac morbidity. Developing a method that accurately depicts LAD motion and perform dose assessment is crucial. PURPOSE To construct a generalized cardiac surface motion model for LAD dose assessment in left breast cancer radiotherapy. METHODS Cine MRI of 25 cases were divided into training and testing sets for model construction, and five external cases were gathered for generalization validation. Motion prediction from average intensity projection images (AIP) surface point cloud to that of each phase was realized by mapping the relationship between datum points and corresponding points with statistical shape modeling (SSM). Root mean square error (RMSE) for predicted corresponding points and Euclidean distance (ED) for predicted surface point cloud were used to assess model's accuracy. LAD dose assessment for 10 left breast cancer radiotherapy cases was perform by model application. RESULTS The RMSE in testing cases and external cases were 0.209 ± 0.020 mm to 0.841 ± 0.074 mm and 0.895 ± 0.093 mm to 1.912 ± 0.138 mm, respectively; while the ED were 1.399 ± 0.029 mm to 1.658 ± 0.100 mm, 1.571 ± 0.080 mm to 1.779 ± 0.104 mm, respectively, proving the generalized model's high accuracy. The volume of LAD characterizing motion range (WPLAD) (2.392 ± 0.639 cm3) was approximately twice that of LAD from superimposed images (SPLAD) (0.927 ± 0.326 cm3) with p < 0.05, and the former's Dmax (3582.06 ± 575.92 cGy) was significantly larger than latter's (3222.71 ± 665.37 cGy) (p < 0.05). While WPLAD's Dmean (1408.06 ± 413.06 cGy) was slightly smaller than that of SPLAD (1504.15 ± 448.03 cGy), the difference did not reach statistical significance (p > 0.05). WPLAD's V20 (23.42% ± 16.62%) was less than SPLAD's (29.18% ± 21.07%) with p < 0.05, but their comparison in V30 and V40 did not yield statistically significant results. It implies the conventional LAD dose assessment ignores motion impact and may not be justified. CONCLUSIONS The generalized cardiac surface motion model informs LAD dose accurate assessment in left breast cancer radiotherapy.
Collapse
Affiliation(s)
- Yongjin Deng
- The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong Province, PR China
| | - Minmin Qiu
- The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong Province, PR China
| | - Yangchan Li
- The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong Province, PR China
| | - Chaoyang Wang
- The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong Province, PR China
| | - Jiajian Zhong
- The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong Province, PR China
| | - Zhenhua Xiao
- The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong Province, PR China
| | - Chengtao Wang
- The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong Province, PR China
| | - Ruiwan Chen
- The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong Province, PR China
| |
Collapse
|
3
|
Villegas-Martinez M, de Villedon de Naide V, Muthurangu V, Bustin A. The beating heart: artificial intelligence for cardiovascular application in the clinic. MAGMA (NEW YORK, N.Y.) 2024:10.1007/s10334-024-01180-9. [PMID: 38907767 DOI: 10.1007/s10334-024-01180-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/26/2023] [Revised: 04/25/2024] [Accepted: 06/13/2024] [Indexed: 06/24/2024]
Abstract
Artificial intelligence (AI) integration in cardiac magnetic resonance imaging presents new and exciting avenues for advancing patient care, automating post-processing tasks, and enhancing diagnostic precision and outcomes. The use of AI significantly streamlines the examination workflow through the reduction of acquisition and postprocessing durations, coupled with the automation of scan planning and acquisition parameters selection. This has led to a notable improvement in examination workflow efficiency, a reduction in operator variability, and an enhancement in overall image quality. Importantly, AI unlocks new possibilities to achieve spatial resolutions that were previously unattainable in patients. Furthermore, the potential for low-dose and contrast-agent-free imaging represents a stride toward safer and more patient-friendly diagnostic procedures. Beyond these benefits, AI facilitates precise risk stratification and prognosis evaluation by adeptly analysing extensive datasets. This comprehensive review article explores recent applications of AI in the realm of cardiac magnetic resonance imaging, offering insights into its transformative potential in the field.
Collapse
Affiliation(s)
- Manuel Villegas-Martinez
- IHU LIRYC, Electrophysiology and Heart Modeling Institute, Hôpital Xavier Arnozan, Université de Bordeaux-INSERM U1045, Avenue du Haut Lévêque, 33604, Pessac, France
- Department of Cardiovascular Imaging, Hôpital Cardiologique du Haut-Lévêque, CHU de Bordeaux, Avenue de Magellan, 33604, Pessac, France
| | - Victor de Villedon de Naide
- IHU LIRYC, Electrophysiology and Heart Modeling Institute, Hôpital Xavier Arnozan, Université de Bordeaux-INSERM U1045, Avenue du Haut Lévêque, 33604, Pessac, France
- Department of Cardiovascular Imaging, Hôpital Cardiologique du Haut-Lévêque, CHU de Bordeaux, Avenue de Magellan, 33604, Pessac, France
| | - Vivek Muthurangu
- Center for Cardiovascular Imaging, UCL Institute of Cardiovascular Science, University College London, London, WC1N 1EH, UK
| | - Aurélien Bustin
- IHU LIRYC, Electrophysiology and Heart Modeling Institute, Hôpital Xavier Arnozan, Université de Bordeaux-INSERM U1045, Avenue du Haut Lévêque, 33604, Pessac, France.
- Department of Cardiovascular Imaging, Hôpital Cardiologique du Haut-Lévêque, CHU de Bordeaux, Avenue de Magellan, 33604, Pessac, France.
- Department of Diagnostic and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
| |
Collapse
|
4
|
Qin Y, Qin X, Zhang J, Guo X. Artificial intelligence: The future for multimodality imaging of right ventricle. Int J Cardiol 2024; 404:131970. [PMID: 38490268 DOI: 10.1016/j.ijcard.2024.131970] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/26/2023] [Revised: 03/05/2024] [Accepted: 03/12/2024] [Indexed: 03/17/2024]
Abstract
The crucial pathophysiological and prognostic roles of the right ventricle in various diseases have been well-established. Nonetheless, conventional cardiovascular imaging modalities are frequently associated with intrinsic limitations when evaluating right ventricular (RV) morphology and function. The integration of artificial intelligence (AI) in multimodality imaging presents a promising avenue to circumvent these obstacles, paving the way for future fully automated imaging paradigms. This review aimed to address the current challenges faced by clinicians and researchers in integrating RV imaging and AI technology, to provide a comprehensive overview of the current applications of AI in RV imaging, and to offer insights into future directions, opportunities, and potential challenges in this rapidly advancing field.
Collapse
Affiliation(s)
- Yuhan Qin
- Department of Cardiology, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China
| | - Xiaohan Qin
- Department of Cardiology, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China
| | - Jing Zhang
- Department of Cardiology, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China
| | - Xiaoxiao Guo
- Department of Cardiology, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China.
| |
Collapse
|
5
|
Onnis C, van Assen M, Muscogiuri E, Muscogiuri G, Gershon G, Saba L, De Cecco CN. The Role of Artificial Intelligence in Cardiac Imaging. Radiol Clin North Am 2024; 62:473-488. [PMID: 38553181 DOI: 10.1016/j.rcl.2024.01.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/02/2024]
Abstract
Artificial intelligence (AI) is having a significant impact in medical imaging, advancing almost every aspect of the field, from image acquisition and postprocessing to automated image analysis with outreach toward supporting decision making. Noninvasive cardiac imaging is one of the main and most exciting fields for AI development. The aim of this review is to describe the main applications of AI in cardiac imaging, including CT and MR imaging, and provide an overview of recent advancements and available clinical applications that can improve clinical workflow, disease detection, and prognostication in cardiac disease.
Collapse
Affiliation(s)
- Carlotta Onnis
- Translational Laboratory for Cardiothoracic Imaging and Artificial Intelligence, Department of Radiology and Imaging Sciences, Emory University, 100 Woodruff Circle, Atlanta, GA 30322, USA; Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari-Polo di Monserrato, SS 554 km 4,500 Monserrato, Cagliari 09042, Italy. https://twitter.com/CarlottaOnnis
| | - Marly van Assen
- Translational Laboratory for Cardiothoracic Imaging and Artificial Intelligence, Department of Radiology and Imaging Sciences, Emory University, 100 Woodruff Circle, Atlanta, GA 30322, USA. https://twitter.com/marly_van_assen
| | - Emanuele Muscogiuri
- Translational Laboratory for Cardiothoracic Imaging and Artificial Intelligence, Department of Radiology and Imaging Sciences, Emory University, 100 Woodruff Circle, Atlanta, GA 30322, USA; Division of Thoracic Imaging, Department of Radiology, University Hospitals Leuven, Herestraat 49, Leuven 3000, Belgium
| | - Giuseppe Muscogiuri
- Department of Diagnostic and Interventional Radiology, Papa Giovanni XXIII Hospital, Piazza OMS, 1, Bergamo BG 24127, Italy. https://twitter.com/GiuseppeMuscog
| | - Gabrielle Gershon
- Translational Laboratory for Cardiothoracic Imaging and Artificial Intelligence, Department of Radiology and Imaging Sciences, Emory University, 100 Woodruff Circle, Atlanta, GA 30322, USA. https://twitter.com/gabbygershon
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari-Polo di Monserrato, SS 554 km 4,500 Monserrato, Cagliari 09042, Italy. https://twitter.com/lucasabaITA
| | - Carlo N De Cecco
- Translational Laboratory for Cardiothoracic Imaging and Artificial Intelligence, Department of Radiology and Imaging Sciences, Emory University, 100 Woodruff Circle, Atlanta, GA 30322, USA; Division of Cardiothoracic Imaging, Department of Radiology and Imaging Sciences, Emory University, Emory University Hospital, 1365 Clifton Road Northeast, Suite AT503, Atlanta, GA 30322, USA.
| |
Collapse
|
6
|
Dang HNN, Luong TV, Ho BA. Evaluation of the relationship between left atrial stiffness, left ventricular stiffness, and left atrioventricular coupling index in type 2 diabetes patients: a speckle tracking echocardiography study. Front Cardiovasc Med 2024; 11:1372181. [PMID: 38737712 PMCID: PMC11084270 DOI: 10.3389/fcvm.2024.1372181] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2024] [Accepted: 04/09/2024] [Indexed: 05/14/2024] Open
Abstract
Background Cardiovascular complications are a leading cause of mortality and disability in individuals with diabetes mellitus (DM). Moreover, DM can directly impact the structure and function of cardiac muscle. We conducted a study to evaluate cardiac stiffness in DM patients in both the left atrium (LA) and left ventricle (LV), as well as to assess the impact of DM on the synchronization of the LA and LV, particularly within the Vietnamese population, utilizing speckle tracking echocardiography (STE). Methods We studied 111 research subjects divided into two groups comprising 52 patients with DM and 59 healthy individuals. All the subjects provided relevant clinical information, and echocardiography was performed to assess the indices of LA stiffness, LV stiffness, and left atrioventricular coupling index (LACI). Results Our study indicated that DM patients exhibited greater LA and LV stiffness than control patients. The LACI (%) in the DM group was also greater than that in the control group (17.12% ± 6.72% vs. 12.28% ± 3.96%, respectively; p < 0.001). The LACI was positively correlated with the LA and LV stiffness indices. Decreased levels of LV GLS, adjusted for age, sex, blood pressure, and BMI, have emerged as identified risk factors for DM. Conclusions LA stiffness, LV stiffness, and the LACI are greater in DM patients than in normal individuals.
Collapse
Affiliation(s)
| | - Thang Viet Luong
- Department of Internal Medicine, Hue University of Medicine and Pharmacy, Hue, Vietnam
| | - Binh Anh Ho
- Cardiovascular Center, Hue Central Hospital, Hue, Vietnam
| |
Collapse
|
7
|
Shoieb DA, Fathalla KM, Youssef SM, Younes A. CAT-Seg: cascaded medical assistive tool integrating residual attention mechanisms and Squeeze-Net for 3D MRI biventricular segmentation. Phys Eng Sci Med 2024; 47:153-168. [PMID: 37999903 DOI: 10.1007/s13246-023-01352-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2023] [Accepted: 10/31/2023] [Indexed: 11/25/2023]
Abstract
Cardiac image segmentation is a critical step in the early detection of cardiovascular disease. The segmentation of the biventricular is a prerequisite for evaluating cardiac function in cardiac magnetic resonance imaging (CMRI). In this paper, a cascaded model CAT-Seg is proposed for segmentation of 3D-CMRI volumes. CAT-Seg addresses the problem of biventricular confusion with other regions and localized the region of interest (ROI) to reduce the scope of processing. A modified DeepLabv3+ variant integrating SqueezeNet (SqueezeDeepLabv3+) is proposed as a part of CAT-Seg. SqueezeDeepLabv3+ handles the different shapes of the biventricular through the different cardiac phases, as the biventricular only accounts for small portion of the volume slices. Also, CAT-Seg presents a segmentation approach that integrates attention mechanisms into 3D Residual UNet architecture (3D-ResUNet) called 3D-ARU to improve the segmentation results of the three major structures (left ventricle (LV), Myocardium (Myo), and right ventricle (RV)). The integration of the spatial attention mechanism into ResUNet handles the fuzzy edges of the three structures. The proposed model achieves promising results in training and testing with the Automatic Cardiac Diagnosis Challenge (ACDC 2017) dataset and the external validation using MyoPs. CAT-Seg demonstrates competitive performance with state-of-the-art models. On ACDC 2017, CAT-Seg is able to segment LV, Myo, and RV with an average minimum dice symmetry coefficient (DSC) performance gap of 1.165%, 4.36%, and 3.115% respectively. The average maximum improvement in terms of DSC in segmenting LV, Myo and RV is 4.395%, 6.84% and 7.315% respectively. On MyoPs external validation, CAT-Seg outperformed the state-of-the-art in segmenting LV, Myo, and RV with an average minimum performance gap of 6.13%, 5.44%, and 2.912% respectively.
Collapse
Affiliation(s)
- Doaa A Shoieb
- Computer Engineering Department, Arab Academy for Science, Technology and Maritime Transport (AASTMT), Alexandria, 1029, Egypt.
| | - Karma M Fathalla
- Computer Engineering Department, Arab Academy for Science, Technology and Maritime Transport (AASTMT), Alexandria, 1029, Egypt
| | - Sherin M Youssef
- Computer Engineering Department, Arab Academy for Science, Technology and Maritime Transport (AASTMT), Alexandria, 1029, Egypt
| | - Ahmed Younes
- Department of Mathematics and Computer Science, Faculty of Science, Alexandria University, Alexandria, Egypt
| |
Collapse
|
8
|
Paciorek AM, von Schacky CE, Foreman SC, Gassert FG, Gassert FT, Kirschke JS, Laugwitz KL, Geith T, Hadamitzky M, Nadjiri J. Automated assessment of cardiac pathologies on cardiac MRI using T1-mapping and late gadolinium phase sensitive inversion recovery sequences with deep learning. BMC Med Imaging 2024; 24:43. [PMID: 38350900 PMCID: PMC10865672 DOI: 10.1186/s12880-024-01217-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2023] [Accepted: 01/30/2024] [Indexed: 02/15/2024] Open
Abstract
BACKGROUND A deep learning (DL) model that automatically detects cardiac pathologies on cardiac MRI may help streamline the diagnostic workflow. To develop a DL model to detect cardiac pathologies on cardiac MRI T1-mapping and late gadolinium phase sensitive inversion recovery (PSIR) sequences were used. METHODS Subjects in this study were either diagnosed with cardiac pathology (n = 137) including acute and chronic myocardial infarction, myocarditis, dilated cardiomyopathy, and hypertrophic cardiomyopathy or classified as normal (n = 63). Cardiac MR imaging included T1-mapping and PSIR sequences. Subjects were split 65/15/20% for training, validation, and hold-out testing. The DL models were based on an ImageNet pretrained DenseNet-161 and implemented using PyTorch and fastai. Data augmentation with random rotation and mixup was applied. Categorical cross entropy was used as the loss function with a cyclic learning rate (1e-3). DL models for both sequences were developed separately using similar training parameters. The final model was chosen based on its performance on the validation set. Gradient-weighted class activation maps (Grad-CAMs) visualized the decision-making process of the DL model. RESULTS The DL model achieved a sensitivity, specificity, and accuracy of 100%, 38%, and 88% on PSIR images and 78%, 54%, and 70% on T1-mapping images. Grad-CAMs demonstrated that the DL model focused its attention on myocardium and cardiac pathology when evaluating MR images. CONCLUSIONS The developed DL models were able to reliably detect cardiac pathologies on cardiac MR images. The diagnostic performance of T1 mapping alone is particularly of note since it does not require a contrast agent and can be acquired quickly.
Collapse
Affiliation(s)
- Aleksandra M Paciorek
- Interventional Radiology, School of Medicine & Klinikum rechts der Isar, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany.
| | - Claudio E von Schacky
- Department of Diagnostic and Interventional Radiology, School of Medicine & Klinikum rechts der Isar, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany
| | - Sarah C Foreman
- Department of Diagnostic and Interventional Radiology, School of Medicine & Klinikum rechts der Isar, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany
| | - Felix G Gassert
- Department of Diagnostic and Interventional Radiology, School of Medicine & Klinikum rechts der Isar, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany
| | - Florian T Gassert
- Department of Diagnostic and Interventional Radiology, School of Medicine & Klinikum rechts der Isar, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany
| | - Jan S Kirschke
- TUM-Neuroimaging Center, School of Medicine & Klinikum rechts der Isar, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany
| | - Karl-Ludwig Laugwitz
- Department of Medicine I, School of Medicine & Klinikum rechts der Isar, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany
| | - Tobias Geith
- Interventional Radiology, School of Medicine & Klinikum rechts der Isar, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany
| | - Martin Hadamitzky
- Department of Radiology, German Heart Center Munich, Technical University of Munich, Lazarettstraße 36, 80636, Munich, Germany
| | - Jonathan Nadjiri
- Interventional Radiology, School of Medicine & Klinikum rechts der Isar, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany
| |
Collapse
|
9
|
Qi X, He Y, Qi Y, Kong Y, Yang G, Li S. STANet: Spatio-Temporal Adaptive Network and Clinical Prior Embedding Learning for 3D+T CMR Segmentation. IEEE J Biomed Health Inform 2024; 28:881-892. [PMID: 38048234 DOI: 10.1109/jbhi.2023.3337521] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/06/2023]
Abstract
The segmentation of cardiac structure in magnetic resonance images (CMR) is paramount in diagnosing and managing cardiovascular illnesses, given its 3D+Time (3D+T) sequence. The existing deep learning methods are constrained in their ability to 3D+T CMR segmentation, due to: (1) Limited motion perception. The complexity of heart beating renders the motion perception in 3D+T CMR, including the long-range and cross-slice motions. The existing methods' local perception and slice-fixed perception directly limit the performance of 3D+T CMR perception. (2) Lack of labels. Due to the expensive labeling cost of the 3D+T CMR sequence, the labels of 3D+T CMR only contain the end-diastolic and end-systolic frames. The incomplete labeling scheme causes inefficient supervision. Hence, we propose a novel spatio-temporal adaptation network with clinical prior embedding learning (STANet) to ensure efficient spatio-temporal perception and optimization on 3D+T CMR segmentation. (1) A spatio-temporal adaptive convolution (STAC) treats the 3D+T CMR sequence as a whole for perception. The long-distance motion correlation is embedded into the structural perception by learnable weight regularization to balance long-range motion perception. The structural similarity is measured by cross-attention to adaptively correlate the cross-slice motion. (2) A clinical prior embedding learning strategy (CPE) is proposed to optimize the partially labeled 3D+T CMR segmentation dynamically by embedding clinical priors into optimization. STANet achieves outstanding performance with Dice of 0.917 and 0.94 on two public datasets (ACDC and STACOM), which indicates STANet has the potential to be incorporated into computer-aided diagnosis tools for clinical application.
Collapse
|
10
|
Zhong H, Li A, Chen Y, Huang Q, Chen X, Kang J, You Y. Comparative analysis of automatic segmentation of esophageal cancer using 3D Res-UNet on conventional and 40-keV virtual mono-energetic CT Images: a retrospective study. PeerJ 2023; 11:e15707. [PMID: 37483982 PMCID: PMC10358343 DOI: 10.7717/peerj.15707] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2023] [Accepted: 06/15/2023] [Indexed: 07/25/2023] Open
Abstract
Objectives To assess the performance of 3D Res-UNet for fully automated segmentation of esophageal cancer (EC) and compare the segmentation accuracy between conventional images (CI) and 40-keV virtual mono-energetic images (VMI40 kev). Methods Patients underwent spectral CT scanning and diagnosed of EC by operation or gastroscope biopsy in our hospital from 2019 to 2020 were analyzed retrospectively. All artery spectral base images were transferred to the dedicated workstation to generate VMI40 kev and CI. The segmentation model of EC was constructed by 3D Res-UNet neural network in VMI40 kev and CI, respectively. After optimization training, the Dice similarity coefficient (DSC), overlap (IOU), average symmetrical surface distance (ASSD) and 95% Hausdorff distance (HD_95) of EC at pixel level were tested and calculated in the test set. The paired rank sum test was used to compare the results of VMI40 kev and CI. Results A total of 160 patients were included in the analysis and randomly divided into the training dataset (104 patients), validation dataset (26 patients) and test dataset (30 patients). VMI40 kevas input data in the training dataset resulted in higher model performance in the test dataset in comparison with using CI as input data (DSC:0.875 vs 0.859, IOU: 0.777 vs 0.755, ASSD:0.911 vs 0.981, HD_95: 4.41 vs 6.23, all p-value <0.05). Conclusion Fully automated segmentation of EC with 3D Res-UNet has high accuracy and clinically feasibility for both CI and VMI40 kev. Compared with CI, VMI40 kev indicated slightly higher accuracy in this test dataset.
Collapse
Affiliation(s)
- Hua Zhong
- Department of Radiology, Zhong Shan Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Anqi Li
- Department of Radiology, Zhong Shan Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Yingdong Chen
- Department of Radiology, Zhong Shan Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Qianwen Huang
- Department of Radiology, Zhong Shan Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Xingbiao Chen
- Clinical Science, Philips Healthcare, Shanghai, China
| | - Jianghe Kang
- Department of Radiology, Zhong Shan Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Youkuang You
- Department of Radiology, Xiamen Xianyue Hospital, Xiamen, Fujian, China
| |
Collapse
|
11
|
Jafari M, Shoeibi A, Khodatars M, Ghassemi N, Moridian P, Alizadehsani R, Khosravi A, Ling SH, Delfan N, Zhang YD, Wang SH, Gorriz JM, Alinejad-Rokny H, Acharya UR. Automated diagnosis of cardiovascular diseases from cardiac magnetic resonance imaging using deep learning models: A review. Comput Biol Med 2023; 160:106998. [PMID: 37182422 DOI: 10.1016/j.compbiomed.2023.106998] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2022] [Revised: 03/01/2023] [Accepted: 04/28/2023] [Indexed: 05/16/2023]
Abstract
In recent years, cardiovascular diseases (CVDs) have become one of the leading causes of mortality globally. At early stages, CVDs appear with minor symptoms and progressively get worse. The majority of people experience symptoms such as exhaustion, shortness of breath, ankle swelling, fluid retention, and other symptoms when starting CVD. Coronary artery disease (CAD), arrhythmia, cardiomyopathy, congenital heart defect (CHD), mitral regurgitation, and angina are the most common CVDs. Clinical methods such as blood tests, electrocardiography (ECG) signals, and medical imaging are the most effective methods used for the detection of CVDs. Among the diagnostic methods, cardiac magnetic resonance imaging (CMRI) is increasingly used to diagnose, monitor the disease, plan treatment and predict CVDs. Coupled with all the advantages of CMR data, CVDs diagnosis is challenging for physicians as each scan has many slices of data, and the contrast of it might be low. To address these issues, deep learning (DL) techniques have been employed in the diagnosis of CVDs using CMR data, and much research is currently being conducted in this field. This review provides an overview of the studies performed in CVDs detection using CMR images and DL techniques. The introduction section examined CVDs types, diagnostic methods, and the most important medical imaging techniques. The following presents research to detect CVDs using CMR images and the most significant DL methods. Another section discussed the challenges in diagnosing CVDs from CMRI data. Next, the discussion section discusses the results of this review, and future work in CVDs diagnosis from CMR images and DL techniques are outlined. Finally, the most important findings of this study are presented in the conclusion section.
Collapse
Affiliation(s)
- Mahboobeh Jafari
- Internship in BioMedical Machine Learning Lab, The Graduate School of Biomedical Engineering, UNSW Sydney, Sydney, NSW, 2052, Australia
| | - Afshin Shoeibi
- Internship in BioMedical Machine Learning Lab, The Graduate School of Biomedical Engineering, UNSW Sydney, Sydney, NSW, 2052, Australia; Data Science and Computational Intelligence Institute, University of Granada, Spain.
| | - Marjane Khodatars
- Data Science and Computational Intelligence Institute, University of Granada, Spain
| | - Navid Ghassemi
- Internship in BioMedical Machine Learning Lab, The Graduate School of Biomedical Engineering, UNSW Sydney, Sydney, NSW, 2052, Australia
| | - Parisa Moridian
- Data Science and Computational Intelligence Institute, University of Granada, Spain
| | - Roohallah Alizadehsani
- Institute for Intelligent Systems Research and Innovation, Deakin University, Geelong, Australia
| | - Abbas Khosravi
- Institute for Intelligent Systems Research and Innovation, Deakin University, Geelong, Australia
| | - Sai Ho Ling
- Faculty of Engineering and IT, University of Technology Sydney (UTS), Australia
| | - Niloufar Delfan
- Faculty of Computer Engineering, Dept. of Artificial Intelligence Engineering, K. N. Toosi University of Technology, Tehran, Iran
| | - Yu-Dong Zhang
- School of Computing and Mathematical Sciences, University of Leicester, Leicester, UK
| | - Shui-Hua Wang
- School of Computing and Mathematical Sciences, University of Leicester, Leicester, UK
| | - Juan M Gorriz
- Data Science and Computational Intelligence Institute, University of Granada, Spain; Department of Psychiatry, University of Cambridge, UK
| | - Hamid Alinejad-Rokny
- BioMedical Machine Learning Lab, The Graduate School of Biomedical Engineering, UNSW Sydney, Sydney, NSW, 2052, Australia; UNSW Data Science Hub, The University of New South Wales, Sydney, NSW, 2052, Australia; Health Data Analytics Program, Centre for Applied Artificial Intelligence, Macquarie University, Sydney, 2109, Australia
| | - U Rajendra Acharya
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, Australia; Dept. of Biomedical Informatics and Medical Engineering, Asia University, Taichung, Taiwan
| |
Collapse
|
12
|
Liu X, Xing F, Gaggin HK, Kuo CCJ, El Fakhri G, Woo J. SUCCESSIVE SUBSPACE LEARNING FOR CARDIAC DISEASE CLASSIFICATION WITH TWO-PHASE DEFORMATION FIELDS FROM CINE MRI. PROCEEDINGS. IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING 2023; 2023:10.1109/isbi53787.2023.10230746. [PMID: 38031559 PMCID: PMC10686280 DOI: 10.1109/isbi53787.2023.10230746] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/01/2023]
Abstract
Cardiac cine magnetic resonance imaging (MRI) has been used to characterize cardiovascular diseases (CVD), often providing a noninvasive phenotyping tool. While recently flourished deep learning based approaches using cine MRI yield accurate characterization results, the performance is often degraded by small training samples. In addition, many deep learning models are deemed a "black box," for which models remain largely elusive in how models yield a prediction and how reliable they are. To alleviate this, this work proposes a lightweight successive subspace learning (SSL) framework for CVD classification, based on an interpretable feedforward design, in conjunction with a cardiac atlas. Specifically, our hierarchical SSL model is based on (i) neighborhood voxel expansion, (ii) unsupervised subspace approximation, (iii) supervised regression, and (iv) multi-level feature integration. In addition, using two-phase 3D deformation fields, including end-diastolic and end-systolic phases, derived between the atlas and individual subjects as input offers objective means of assessing CVD, even with small training samples. We evaluate our framework on the ACDC2017 database, comprising one healthy group and four disease groups. Compared with 3D CNN-based approaches, our framework achieves superior classification performance with 140× fewer parameters, which supports its potential value in clinical use.
Collapse
Affiliation(s)
- Xiaofeng Liu
- Dept. of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Fangxu Xing
- Dept. of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Hanna K Gaggin
- Dept. of Medicine, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - C-C Jay Kuo
- Dept. of ECE, University of Southern California, Los Angeles, CA, USA
| | - Georges El Fakhri
- Dept. of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Jonghye Woo
- Dept. of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| |
Collapse
|
13
|
Rabbani A, Gao H, Lazarus A, Dalton D, Ge Y, Mangion K, Berry C, Husmeier D. Image-based estimation of the left ventricular cavity volume using deep learning and Gaussian process with cardio-mechanical applications. Comput Med Imaging Graph 2023; 106:102203. [PMID: 36848766 DOI: 10.1016/j.compmedimag.2023.102203] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2022] [Revised: 11/26/2022] [Accepted: 02/17/2023] [Indexed: 02/27/2023]
Abstract
In this investigation, an image-based method has been developed to estimate the volume of the left ventricular cavity using cardiac magnetic resonance (CMR) imaging data. Deep learning and Gaussian processes have been applied to bring the estimations closer to the cavity volumes manually extracted. CMR data from 339 patients and healthy volunteers have been used to train a stepwise regression model that can estimate the volume of the left ventricular cavity at the beginning and end of diastole. We have decreased the root mean square error (RMSE) of cavity volume estimation approximately from 13 to 8 ml compared to the common practice in the literature. Considering the RMSE of manual measurements is approximately 4 ml on the same dataset, 8 ml of error is notable for a fully automated estimation method, which needs no supervision or user-hours once it has been trained. Additionally, to demonstrate a clinically relevant application of automatically estimated volumes, we inferred the passive material properties of the myocardium given the volume estimates using a well-validated cardiac model. These material properties can be further used for patient treatment planning and diagnosis.
Collapse
Affiliation(s)
- Arash Rabbani
- School of Mathematics & Statistics, University of Glasgow, Glasgow G12 8QQ, United Kingdom; School of Computing, University of Leeds, Leeds LS2 9JT, United Kingdom.
| | - Hao Gao
- School of Mathematics & Statistics, University of Glasgow, Glasgow G12 8QQ, United Kingdom
| | - Alan Lazarus
- School of Mathematics & Statistics, University of Glasgow, Glasgow G12 8QQ, United Kingdom
| | - David Dalton
- School of Mathematics & Statistics, University of Glasgow, Glasgow G12 8QQ, United Kingdom
| | - Yuzhang Ge
- School of Mathematics & Statistics, University of Glasgow, Glasgow G12 8QQ, United Kingdom
| | - Kenneth Mangion
- School of Cardiovascular & Metabolic Health, University of Glasgow, Glasgow G12 8QQ, United Kingdom
| | - Colin Berry
- School of Cardiovascular & Metabolic Health, University of Glasgow, Glasgow G12 8QQ, United Kingdom
| | - Dirk Husmeier
- School of Mathematics & Statistics, University of Glasgow, Glasgow G12 8QQ, United Kingdom
| |
Collapse
|
14
|
Al Khalil Y, Amirrajab S, Lorenz C, Weese J, Pluim J, Breeuwer M. On the usability of synthetic data for improving the robustness of deep learning-based segmentation of cardiac magnetic resonance images. Med Image Anal 2023; 84:102688. [PMID: 36493702 DOI: 10.1016/j.media.2022.102688] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2021] [Revised: 09/14/2022] [Accepted: 11/07/2022] [Indexed: 11/18/2022]
Abstract
Deep learning-based segmentation methods provide an effective and automated way for assessing the structure and function of the heart in cardiac magnetic resonance (CMR) images. However, despite their state-of-the-art performance on images acquired from the same source (same scanner or scanner vendor) as images used during training, their performance degrades significantly on images coming from different domains. A straightforward approach to tackle this issue consists of acquiring large quantities of multi-site and multi-vendor data, which is practically infeasible. Generative adversarial networks (GANs) for image synthesis present a promising solution for tackling data limitations in medical imaging and addressing the generalization capability of segmentation models. In this work, we explore the usability of synthesized short-axis CMR images generated using a segmentation-informed conditional GAN, to improve the robustness of heart cavity segmentation models in a variety of different settings. The GAN is trained on paired real images and corresponding segmentation maps belonging to both the heart and the surrounding tissue, reinforcing the synthesis of semantically-consistent and realistic images. First, we evaluate the segmentation performance of a model trained solely with synthetic data and show that it only slightly underperforms compared to the baseline trained with real data. By further combining real with synthetic data during training, we observe a substantial improvement in segmentation performance (up to 4% and 40% in terms of Dice score and Hausdorff distance) across multiple data-sets collected from various sites and scanner. This is additionally demonstrated across state-of-the-art 2D and 3D segmentation networks, whereby the obtained results demonstrate the potential of the proposed method in tackling the presence of the domain shift in medical data. Finally, we thoroughly analyze the quality of synthetic data and its ability to replace real MR images during training, as well as provide an insight into important aspects of utilizing synthetic images for segmentation.
Collapse
Affiliation(s)
- Yasmina Al Khalil
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.
| | - Sina Amirrajab
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.
| | | | - Jürgen Weese
- Philips Research Laboratories, Hamburg, Germany.
| | - Josien Pluim
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.
| | - Marcel Breeuwer
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands; Philips Healthcare, MR R&D - Clinical Science, Best, The Netherlands.
| |
Collapse
|
15
|
Scuiller Y, Hemon P, Le Rochais M, Pers JO, Jamin C, Foulquier N. YOUPI: Your powerful and intelligent tool for segmenting cells from imaging mass cytometry data. Front Immunol 2023; 14:1072118. [PMID: 36936977 PMCID: PMC10019895 DOI: 10.3389/fimmu.2023.1072118] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2022] [Accepted: 02/13/2023] [Indexed: 03/06/2023] Open
Abstract
The recent emergence of imaging mass cytometry technology has led to the generation of an increasing amount of high-dimensional data and, with it, the need for suitable performant bioinformatics tools dedicated to specific multiparametric studies. The first and most important step in treating the acquired images is the ability to perform highly efficient cell segmentation for subsequent analyses. In this context, we developed YOUPI (Your Powerful and Intelligent tool) software. It combines advanced segmentation techniques based on deep learning algorithms with a friendly graphical user interface for non-bioinformatics users. In this article, we present the segmentation algorithm developed for YOUPI. We have set a benchmark with mathematics-based segmentation approaches to estimate its robustness in segmenting different tissue biopsies.
Collapse
Affiliation(s)
| | | | | | | | - Christophe Jamin
- LBAI, UMR 1227, Univ Brest, Inserm, Brest, France
- CHU de Brest, Brest, France
- *Correspondence: Christophe Jamin,
| | | |
Collapse
|
16
|
Barrios JP, Tison GH. Advancing cardiovascular medicine with machine learning: Progress, potential, and perspective. Cell Rep Med 2022; 3:100869. [PMID: 36543095 PMCID: PMC9798021 DOI: 10.1016/j.xcrm.2022.100869] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2022] [Revised: 10/26/2022] [Accepted: 11/21/2022] [Indexed: 12/24/2022]
Abstract
Recent advances in machine learning (ML) have made it possible to analyze high-dimensional and complex data-such as free text, images, waveforms, videos, and sound-in an automated manner by successfully learning complex associations within these data. Cardiovascular medicine is particularly well poised to take advantage of these ML advances, due to the widespread digitization of medical data and the large number of diagnostic tests used to evaluate cardiovascular disease. Various ML approaches have successfully been applied to cardiovascular tests and diseases to automate interpretation, accurately perform measurements, and, in some cases, predict novel diagnoses from less invasive tests, effectively expanding the utility of more widely accessible diagnostic tests. Here, we present examples of some impactful advances in cardiovascular medicine using ML across a variety of modalities, with a focus on deep learning applications.
Collapse
Affiliation(s)
- Joshua P. Barrios
- Department of Medicine, Division of Cardiology, University of California, San Francisco, 555 Mission Bay Blvd South Box 3120, San Francisco, CA 94158, USA
| | - Geoffrey H. Tison
- Department of Medicine, Division of Cardiology, University of California, San Francisco, 555 Mission Bay Blvd South Box 3120, San Francisco, CA 94158, USA,Bakar Computational Health Sciences Institute, University of California, San Francisco, 555 Mission Bay Blvd South Box 3120, San Francisco, CA 94158, USA,Corresponding author
| |
Collapse
|
17
|
Mostafa FA, Elrefaei LA, Fouda MM, Hossam A. A Survey on AI Techniques for Thoracic Diseases Diagnosis Using Medical Images. Diagnostics (Basel) 2022; 12:diagnostics12123034. [PMID: 36553041 PMCID: PMC9777249 DOI: 10.3390/diagnostics12123034] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2022] [Revised: 11/20/2022] [Accepted: 11/22/2022] [Indexed: 12/12/2022] Open
Abstract
Thoracic diseases refer to disorders that affect the lungs, heart, and other parts of the rib cage, such as pneumonia, novel coronavirus disease (COVID-19), tuberculosis, cardiomegaly, and fracture. Millions of people die every year from thoracic diseases. Therefore, early detection of these diseases is essential and can save many lives. Earlier, only highly experienced radiologists examined thoracic diseases, but recent developments in image processing and deep learning techniques are opening the door for the automated detection of these diseases. In this paper, we present a comprehensive review including: types of thoracic diseases; examination types of thoracic images; image pre-processing; models of deep learning applied to the detection of thoracic diseases (e.g., pneumonia, COVID-19, edema, fibrosis, tuberculosis, chronic obstructive pulmonary disease (COPD), and lung cancer); transfer learning background knowledge; ensemble learning; and future initiatives for improving the efficacy of deep learning models in applications that detect thoracic diseases. Through this survey paper, researchers may be able to gain an overall and systematic knowledge of deep learning applications in medical thoracic images. The review investigates a performance comparison of various models and a comparison of various datasets.
Collapse
Affiliation(s)
- Fatma A. Mostafa
- Department of Electrical Engineering, Faculty of Engineering at Shoubra, Benha University, Cairo 11672, Egypt
| | - Lamiaa A. Elrefaei
- Department of Electrical Engineering, Faculty of Engineering at Shoubra, Benha University, Cairo 11672, Egypt
| | - Mostafa M. Fouda
- Department of Electrical and Computer Engineering, College of Science and Engineering, Idaho State University, Pocatello, ID 83209, USA
- Correspondence:
| | - Aya Hossam
- Department of Electrical Engineering, Faculty of Engineering at Shoubra, Benha University, Cairo 11672, Egypt
| |
Collapse
|
18
|
Kawakubo M, Moriyama D, Yamasaki Y, Abe K, Hosokawa K, Moriyama T, Triadyaksa P, Wibowo A, Nagao M, Arai H, Nishimura H, Kadokami T. Right ventricular strain and volume analyses through deep learning-based fully automatic segmentation based on radial long-axis reconstruction of short-axis cine magnetic resonance images. MAGMA (NEW YORK, N.Y.) 2022; 35:911-921. [PMID: 35585430 DOI: 10.1007/s10334-022-01017-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/01/2022] [Revised: 03/26/2022] [Accepted: 04/25/2022] [Indexed: 06/15/2023]
Abstract
OBJECTIVE We propose a deep learning-based fully automatic right ventricle (RV) segmentation technique that targets radially reconstructed long-axis (RLA) images of the center of the RV region in routine short axis (SA) cardiovascular magnetic resonance (CMR) images. Accordingly, the purpose of this study is to compare the accuracy of deep learning-based fully automatic segmentation of RLA images with the accuracy of conventional deep learning-based segmentation in SA orientation in terms of the measurements of RV strain parameters. MATERIALS AND METHODS We compared the accuracies of the above-mentioned methods in RV segmentations and in measuring RV strain parameters by Dice similarity coefficients (DSCs) and correlation coefficients. RESULTS DSC of RV segmentation of the RLA method exhibited a higher value than those of the conventional SA methods (0.84 vs. 0.61). Correlation coefficient with respect to manual RV strain measurements in the fully automatic RLA were superior to those in SA measurements (0.5-0.7 vs. 0.1-0.2). DISCUSSION Our proposed RLA realizes accurate fully automatic extraction of the entire RV region from an available CMR cine image without any additional imaging. Our findings overcome the complexity of image analysis in CMR without the limitations of the RV visualization in echocardiography.
Collapse
Affiliation(s)
- Masateru Kawakubo
- Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, 3-1-1 Maidashi, Higashi-ku, Fukuoka-shi, Fukuoka, 812-8582, Japan.
| | - Daichi Moriyama
- Department of Health Sciences, School of Medical Sciences, Kyushu University, Fukuoka, Japan
- Department of Radiological Technology, Hiroshima City Hiroshima Citizens Hospital, Hiroshima, Japan
| | - Yuzo Yamasaki
- Department of Clinical Radiology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan
| | - Kohtaro Abe
- Department of Cardiovascular Medicine, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan
| | - Kazuya Hosokawa
- Department of Cardiovascular Medicine, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan
| | - Tetsuhiro Moriyama
- Institute of Mathematics for Industry, Kyushu University, Fukuoka, Japan
| | - Pandji Triadyaksa
- Department of Physics, Faculty of Science and Mathematics, Universitas Diponegoro, Semarang, Indonesia
| | - Adi Wibowo
- Department of Computer Science, Faculty of Science and Mathematics, Universitas Diponegoro, Semarang, Indonesia
| | - Michinobu Nagao
- Department of Diagnostic Imaging and Nuclear Medicine, Tokyo Women's Medical University, Tokyo, Japan
| | - Hideo Arai
- Fukuokaken Saiseikai, Futsukaichi Hospital, Fukuoka, Japan
| | | | | |
Collapse
|
19
|
Multiresolution Mutual Assistance Network for Cardiac Magnetic Resonance Images Segmentation. JOURNAL OF HEALTHCARE ENGINEERING 2022; 2022:5311825. [PMID: 36353681 PMCID: PMC9640236 DOI: 10.1155/2022/5311825] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/23/2022] [Accepted: 10/21/2022] [Indexed: 01/24/2023]
Abstract
The automatic segmentation of cardiac magnetic resonance (MR) images is the basis for the diagnosis of cardiac-related diseases. However, the segmentation of cardiac MR images is a challenging task due to the inhomogeneity of MR images intensity distribution and the unclear boundaries between adjacent tissues. In this paper, we propose a novel multiresolution mutual assistance network (MMA-Net) for cardiac MR images segmentation. It is mainly composed of multibranch input module, multiresolution mutual assistance module, and multilabel deep supervision. First, the multibranch input module helps the network to extract local and global features more pertinently. Then, the multiresolution mutual assistance module implements multiresolution feature interaction and progressively improves semantic features to more completely express the information of the tissue. Finally, the multilabel deep supervision is proposed to generate the final segmentation map. We compare with state-of-the-art medical image segmentation methods on the medical image computing and computer-assisted intervention (MICCAI) automated cardiac diagnosis challenge datasets and the MICCAI atrial segmentation challenge datasets. The mean dice scores of our method in the left atrium, right ventricle, myocardium, and left ventricle are 0.919, 0.920, 0.881, and 0.960, respectively. The analysis of evaluation indicators and segmentation results shows that our method achieves the best performance in cardiac magnetic resonance images segmentation.
Collapse
|
20
|
Cardiac Disease Classification Using Two-Dimensional Thickness and Few-Shot Learning Based on Magnetic Resonance Imaging Image Segmentation. J Imaging 2022; 8:jimaging8070194. [PMID: 35877637 PMCID: PMC9318676 DOI: 10.3390/jimaging8070194] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2022] [Revised: 07/02/2022] [Accepted: 07/06/2022] [Indexed: 12/10/2022] Open
Abstract
Cardiac cine magnetic resonance imaging (MRI) is a widely used technique for the noninvasive assessment of cardiac functions. Deep neural networks have achieved considerable progress in overcoming various challenges in cine MRI analysis. However, deep learning models cannot be used for classification because limited cine MRI data are available. To overcome this problem, features from cine image settings are derived by handcrafting and addition of other clinical features to the classical machine learning approach for ensuring the model fits the MRI device settings and image parameters required in the analysis. In this study, a novel method was proposed for classifying heart disease (cardiomyopathy patient groups) using only segmented output maps. In the encoder–decoder network, the fully convolutional EfficientNetB5-UNet was modified to perform the semantic segmentation of the MRI image slice. A two-dimensional thickness algorithm was used to combine the segmentation outputs for the 2D representation of images of the end-diastole (ED) and end-systole (ES) cardiac volumes. The thickness images were subsequently used for classification by using a few-shot model with an adaptive subspace classifier. Model performance was verified by applying the model to the 2017 MICCAI Medical Image Computing and Computer-Assisted Intervention dataset. High segmentation performance was achieved as follows: the average Dice coefficients of segmentation were 96.24% (ED) and 89.92% (ES) for the left ventricle (LV); the values for the right ventricle (RV) were 92.90% (ED) and 86.92% (ES). The values for myocardium were 88.90% (ED) and 90.48% (ES). An accuracy score of 92% was achieved in the classification of various cardiomyopathy groups without clinical features. A novel rapid analysis approach was proposed for heart disease diagnosis, especially for cardiomyopathy conditions using cine MRI based on segmented output maps.
Collapse
|
21
|
Ahsan MM, Siddique Z. Machine learning-based heart disease diagnosis: A systematic literature review. Artif Intell Med 2022; 128:102289. [DOI: 10.1016/j.artmed.2022.102289] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2021] [Accepted: 03/22/2022] [Indexed: 01/01/2023]
|
22
|
Song Y, Ren S, Lu Y, Fu X, Wong KKL. Deep learning-based automatic segmentation of images in cardiac radiography: A promising challenge. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 220:106821. [PMID: 35487181 DOI: 10.1016/j.cmpb.2022.106821] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/23/2020] [Revised: 04/08/2022] [Accepted: 04/17/2022] [Indexed: 06/14/2023]
Abstract
BACKGROUND Due to the advancement of medical imaging and computer technology, machine intelligence to analyze clinical image data increases the probability of disease prevention and successful treatment. When diagnosing and detecting heart disease, medical imaging can provide high-resolution scans of every organ or tissue in the heart. The diagnostic results obtained by the imaging method are less susceptible to human interference. They can process numerous patient information, assist doctors in early detection of heart disease, intervene and treat patients, and improve the understanding of heart disease symptoms and clinical diagnosis of great significance. In a computer-aided diagnosis system, accurate segmentation of cardiac scan images is the basis and premise of subsequent thoracic function analysis and 3D image reconstruction. EXISTING TECHNIQUES This paper systematically reviews automatic methods and some difficulties for cardiac segmentation in radiographic images. Combined with recent advanced deep learning techniques, the feasibility of using deep learning network models for image segmentation is discussed, and the commonly used deep learning frameworks are compared. DEVELOPED INSIGHTS There are many standard methods for medical image segmentation, such as traditional methods based on regions and edges and methods based on deep learning. Because of characteristics of non-uniform grayscale, individual differences, artifacts and noise of medical images, the above image segmentation methods have certain limitations. It is tough to obtain the needed results sensitivity and accuracy when performing heart segmentation. The deep learning model proposed has achieved good results in image segmentation. Accurate segmentation improves the accuracy of disease diagnosis and reduces subsequent irrelevant computations. SUMMARY There are two requirements for accurate segmentation of radiological images. One is to use image segmentation to improve the development of computer-aided diagnosis. The other is to achieve complete segmentation of the heart. When there are lesions or deformities in the heart, there will be some abnormalities in the radiographic images, and the segmentation algorithm needs to segment the heart altogether. The quantity of processing inside a certain range will no longer be a restriction for real-time detection with the advancement of deep learning and the enhancement of hardware device performance.
Collapse
Affiliation(s)
- Yucheng Song
- School of Computer Science and Engineering, Central South University, Changsha, China
| | - Shengbing Ren
- School of Computer Science and Engineering, Central South University, Changsha, China
| | - Yu Lu
- College of Big Data and Internet, Shenzhen Technology University, Shenzhen, China.
| | - Xianghua Fu
- College of Big Data and Internet, Shenzhen Technology University, Shenzhen, China
| | - Kelvin K L Wong
- School of Computer Science and Engineering, Central South University, Changsha, China.
| |
Collapse
|
23
|
Argentiero A, Muscogiuri G, Rabbat MG, Martini C, Soldato N, Basile P, Baggiano A, Mushtaq S, Fusini L, Mancini ME, Gaibazzi N, Santobuono VE, Sironi S, Pontone G, Guaricci AI. The Applications of Artificial Intelligence in Cardiovascular Magnetic Resonance-A Comprehensive Review. J Clin Med 2022; 11:jcm11102866. [PMID: 35628992 PMCID: PMC9147423 DOI: 10.3390/jcm11102866] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2022] [Revised: 05/13/2022] [Accepted: 05/16/2022] [Indexed: 12/11/2022] Open
Abstract
Cardiovascular disease remains an integral field on which new research in both the biomedical and technological fields is based, as it remains the leading cause of mortality and morbidity worldwide. However, despite the progress of cardiac imaging techniques, the heart remains a challenging organ to study. Artificial intelligence (AI) has emerged as one of the major innovations in the field of diagnostic imaging, with a dramatic impact on cardiovascular magnetic resonance imaging (CMR). AI will be increasingly present in the medical world, with strong potential for greater diagnostic efficiency and accuracy. Regarding the use of AI in image acquisition and reconstruction, the main role was to reduce the time of image acquisition and analysis, one of the biggest challenges concerning magnetic resonance; moreover, it has been seen to play a role in the automatic correction of artifacts. The use of these techniques in image segmentation has allowed automatic and accurate quantification of the volumes and masses of the left and right ventricles, with occasional need for manual correction. Furthermore, AI can be a useful tool to directly help the clinician in the diagnosis and derivation of prognostic information of cardiovascular diseases. This review addresses the applications and future prospects of AI in CMR imaging, from image acquisition and reconstruction to image segmentation, tissue characterization, diagnostic evaluation, and prognostication.
Collapse
Affiliation(s)
- Adriana Argentiero
- University Cardiology Unit, Cardio-Thoracic Department, Policlinic University Hospital, 70121 Bari, Italy; (A.A.); (N.S.); (P.B.); (V.E.S.)
| | - Giuseppe Muscogiuri
- School of Medicine and Surgery, University of Milano-Bicocca, 20126 Milan, Italy; (G.M.); (S.S.)
- Department of Radiology, IRCCS Istituto Auxologico Italiano, San Luca Hospital, 20149 Milan, Italy
| | - Mark G. Rabbat
- Division of Cardiology, Loyola University of Chicago, Chicago, IL 60660, USA;
| | - Chiara Martini
- Radiologic Sciences, Department of Medicine and Surgery, University of Parma, 43126 Parma, Italy;
| | - Nicolò Soldato
- University Cardiology Unit, Cardio-Thoracic Department, Policlinic University Hospital, 70121 Bari, Italy; (A.A.); (N.S.); (P.B.); (V.E.S.)
| | - Paolo Basile
- University Cardiology Unit, Cardio-Thoracic Department, Policlinic University Hospital, 70121 Bari, Italy; (A.A.); (N.S.); (P.B.); (V.E.S.)
| | - Andrea Baggiano
- Perioperative and Cardiovascular Imaging Department, Centro Cardiologico Monzino IRCCS, 20138 Milan, Italy; (A.B.); (S.M.); (L.F.); (M.E.M.); (G.P.)
| | - Saima Mushtaq
- Perioperative and Cardiovascular Imaging Department, Centro Cardiologico Monzino IRCCS, 20138 Milan, Italy; (A.B.); (S.M.); (L.F.); (M.E.M.); (G.P.)
| | - Laura Fusini
- Perioperative and Cardiovascular Imaging Department, Centro Cardiologico Monzino IRCCS, 20138 Milan, Italy; (A.B.); (S.M.); (L.F.); (M.E.M.); (G.P.)
| | - Maria Elisabetta Mancini
- Perioperative and Cardiovascular Imaging Department, Centro Cardiologico Monzino IRCCS, 20138 Milan, Italy; (A.B.); (S.M.); (L.F.); (M.E.M.); (G.P.)
| | - Nicola Gaibazzi
- Department of Cardiology, Azienda Ospedaliero-Universitaria, 43126 Parma, Italy;
| | - Vincenzo Ezio Santobuono
- University Cardiology Unit, Cardio-Thoracic Department, Policlinic University Hospital, 70121 Bari, Italy; (A.A.); (N.S.); (P.B.); (V.E.S.)
| | - Sandro Sironi
- School of Medicine and Surgery, University of Milano-Bicocca, 20126 Milan, Italy; (G.M.); (S.S.)
- Department of Radiology, ASST Papa Giovanni XXIII Hospital, 24127 Bergamo, Italy
| | - Gianluca Pontone
- Perioperative and Cardiovascular Imaging Department, Centro Cardiologico Monzino IRCCS, 20138 Milan, Italy; (A.B.); (S.M.); (L.F.); (M.E.M.); (G.P.)
| | - Andrea Igoren Guaricci
- University Cardiology Unit, Cardio-Thoracic Department, Policlinic University Hospital, 70121 Bari, Italy; (A.A.); (N.S.); (P.B.); (V.E.S.)
- Department of Emergency and Organ Transplantation, University of Bari, 70121 Bari, Italy
- Correspondence:
| |
Collapse
|
24
|
Efficacy of Morphine Combined with Mechanical Ventilation in the Treatment of Heart Failure with Cardiac Magnetic Resonance Imaging under Artificial Intelligence Algorithms. CONTRAST MEDIA & MOLECULAR IMAGING 2022; 2022:1732915. [PMID: 35280707 PMCID: PMC8896927 DOI: 10.1155/2022/1732915] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/03/2021] [Revised: 01/17/2022] [Accepted: 01/20/2022] [Indexed: 11/17/2022]
Abstract
This study was aimed at exploring the efficacy of morphine combined with mechanical ventilation in the treatment of heart failure with artificial intelligence algorithms. The cardiac magnetic resonance imaging (MRI) under the watershed segmentation algorithm was proposed, and the local grayscale clustering watershed (LGCW) model was designed in this study. A total of 136 patients with acute left heart failure were taken as the research objects and randomly divided into the control group (conventional treatment) and the experimental group (morphine combined with mechanical ventilation), with 68 cases in each group. The left ventricular end-diastolic diameter (LVEDD), left ventricular end-systolic diameter (LVESD), left ventricular ejection fraction (LVEF), N-terminal pro-brain natriuretic peptide (NT-proBNP), arterial partial pressure of oxygen (PaO2), and arterial partial pressure of carbon dioxide (PaCO2) were observed. The results showed that the mean absolute deviation (MAD) and maximum mean absolute deviation (max-MAD) of the LGCW model were lower than those of the fuzzy k-nearest neighbor (FKNN) algorithm and local gray-scale clustering model (LGSCm). The Dice metric was also significantly higher than that of other algorithms with statistically significant differences (P < 0.05). After treatment, LVEDD, LVESD, and NT-proBNP of patients in the experimental group were significantly lower than those in the control group, and LVEF in the experimental group was higher than that in the control group (P < 0.05). PaO2 of patients in the experimental group was also significantly higher than that in the control group (P < 0.05). It suggested that the LGCW model had a better segmentation effect, and morphine combined with mechanical ventilation gave a better clinical efficacy in the treatment of acute left heart failure, improving the patients' cardiac function and arterial blood gas effectively.
Collapse
|
25
|
Wang S, Celebi ME, Zhang YD, Yu X, Lu S, Yao X, Zhou Q, Miguel MG, Tian Y, Gorriz JM, Tyukin I. Advances in Data Preprocessing for Biomedical Data Fusion: An Overview of the Methods, Challenges, and Prospects. INFORMATION FUSION 2021; 76:376-421. [DOI: 10.1016/j.inffus.2021.07.001] [Citation(s) in RCA: 43] [Impact Index Per Article: 14.3] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/30/2023]
|
26
|
Liu X, Xing F, Gaggin HK, Wang W, Kuo CCJ, El Fakhri G, Woo J. Segmentation of Cardiac Structures via Successive Subspace Learning with Saab Transform from Cine MRI. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021; 2021:3535-3538. [PMID: 34892002 DOI: 10.1109/embc46164.2021.9629770] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
Assessment of cardiovascular disease (CVD) with cine magnetic resonance imaging (MRI) has been used to non-invasively evaluate detailed cardiac structure and function. Accurate segmentation of cardiac structures from cine MRI is a crucial step for early diagnosis and prognosis of CVD, and has been greatly improved with convolutional neural networks (CNN). There, however, are a number of limitations identified in CNN models, such as limited interpretability and high complexity, thus limiting their use in clinical practice. In this work, to address the limitations, we propose a lightweight and interpretable machine learning model, successive subspace learning with the subspace approximation with adjusted bias (Saab) transform, for accurate and efficient segmentation from cine MRI. Specifically, our segmentation framework is comprised of the following steps: (1) sequential expansion of near-to-far neighborhood at different resolutions; (2) channel-wise subspace approximation using the Saab transform for unsupervised dimension reduction; (3) class-wise entropy guided feature selection for supervised dimension reduction; (4) concatenation of features and pixel-wise classification with gradient boost; and (5) conditional random field for post-processing. Experimental results on the ACDC 2017 segmentation database, showed that our framework performed better than state-of-the-art U-Net models with 200× fewer parameters in delineating the left ventricle, right ventricle, and myocardium, thus showing its potential to be used in clinical practice.Clinical relevance- Delineation of the left ventricular cavity, myocardium, and right ventricle from cardiac MR images is a common clinical task to establish diagnosis and prognosis of CVD.
Collapse
|