1
|
Wang Z, Yang W, Li Z, Rong Z, Wang X, Han J, Ma L. A 25-Year Retrospective of the Use of AI for Diagnosing Acute Stroke: Systematic Review. J Med Internet Res 2024; 26:e59711. [PMID: 39255472 DOI: 10.2196/59711] [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: 04/20/2024] [Revised: 06/25/2024] [Accepted: 07/15/2024] [Indexed: 09/12/2024] Open
Abstract
BACKGROUND Stroke is a leading cause of death and disability worldwide. Rapid and accurate diagnosis is crucial for minimizing brain damage and optimizing treatment plans. OBJECTIVE This review aims to summarize the methods of artificial intelligence (AI)-assisted stroke diagnosis over the past 25 years, providing an overview of performance metrics and algorithm development trends. It also delves into existing issues and future prospects, intending to offer a comprehensive reference for clinical practice. METHODS A total of 50 representative articles published between 1999 and 2024 on using AI technology for stroke prevention and diagnosis were systematically selected and analyzed in detail. RESULTS AI-assisted stroke diagnosis has made significant advances in stroke lesion segmentation and classification, stroke risk prediction, and stroke prognosis. Before 2012, research mainly focused on segmentation using traditional thresholding and heuristic techniques. From 2012 to 2016, the focus shifted to machine learning (ML)-based approaches. After 2016, the emphasis moved to deep learning (DL), which brought significant improvements in accuracy. In stroke lesion segmentation and classification as well as stroke risk prediction, DL has shown superiority over ML. In stroke prognosis, both DL and ML have shown good performance. CONCLUSIONS Over the past 25 years, AI technology has shown promising performance in stroke diagnosis.
Collapse
Affiliation(s)
| | | | | | - Ze Rong
- Nantong University, Nantong, China
| | | | | | - Lei Ma
- Nantong University, Nantong, China
| |
Collapse
|
2
|
Jeong H, Lim H, Yoon C, Won J, Lee GY, de la Rosa E, Kirschke JS, Kim B, Kim N, Kim C. Robust Ensemble of Two Different Multimodal Approaches to Segment 3D Ischemic Stroke Segmentation Using Brain Tumor Representation Among Multiple Center Datasets. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01099-6. [PMID: 38693333 DOI: 10.1007/s10278-024-01099-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/23/2023] [Revised: 03/18/2024] [Accepted: 03/22/2024] [Indexed: 05/03/2024]
Abstract
Ischemic stroke segmentation at an acute stage is vital in assessing the severity of patients' impairment and guiding therapeutic decision-making for reperfusion. Although many deep learning studies have shown attractive performance in medical segmentation, it is difficult to use these models trained on public data with private hospitals' datasets. Here, we demonstrate an ensemble model that employs two different multimodal approaches for generalization, a more effective way to perform on external datasets. First, after we jointly train a segmentation model on diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) MR modalities, the model is inferred on the DWI images. Second, a channel-wise segmentation model is trained by concatenating the DWI and ADC images as input, and then is inferred using both MR modalities. Before training with ischemic stroke data, we utilized BraTS 2021, a public brain tumor dataset, for transfer learning. An extensive ablation study evaluates which strategy learns better representations for ischemic stroke segmentation. In our study, nnU-Net well-known for robustness is selected as our baseline model. Our proposed method is evaluated on three different datasets: the Asan Medical Center (AMC) I and II, and the 2022 Ischemic Stroke Lesion Segmentation (ISLES). Our experiments are widely validated over a large, multi-center, and multi-scanner dataset with a huge amount of 846 scans. Not only stroke lesion models can benefit from transfer learning using brain tumor data, but combining the MR modalities using different training schemes also highly improves segmentation performance. The method achieved a top-1 ranking in the ongoing ISLES'22 challenge and performed particularly well on lesion-wise metrics of interest to neuroradiologists, achieving a Dice coefficient of 78.69% and a lesion-wise F1 score of 82.46%. Also, the method was relatively robust on the AMC I (Dice, 60.35%; lesion-wise F1, 68.30%) and II (Dice; 74.12%; lesion-wise F1, 67.53%) datasets in different settings. The high segmentation accuracy of our proposed method could improve radiologists' ability to detect ischemic stroke lesions in MRI images. Our model weights and inference code are available on https://github.com/MDOpx/ISLES22-model-inference .
Collapse
Affiliation(s)
- Hyunsu Jeong
- Graduate School of Artificial Intelligence (GSAI), Department of Electrical Engineering, Medical Science and Engineering, and Medical Device Innovation Center, Convergence IT Engineering, Mechanical Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea
| | - Hyunseok Lim
- Graduate School of Artificial Intelligence (GSAI), Department of Electrical Engineering, Medical Science and Engineering, and Medical Device Innovation Center, Convergence IT Engineering, Mechanical Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea
| | - Chiho Yoon
- Graduate School of Artificial Intelligence (GSAI), Department of Electrical Engineering, Medical Science and Engineering, and Medical Device Innovation Center, Convergence IT Engineering, Mechanical Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea
| | - Jongjun Won
- Department of Medical Science, Asan Medical Center, Asan Medical Institute of Convergence Science and Technology, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Grace Yoojin Lee
- Department of Medical Science, Asan Medical Center, Asan Medical Institute of Convergence Science and Technology, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Ezequiel de la Rosa
- icometrix, Leuven, Belgium
- Department of Informatics, Technical University of Munich, Neuroradiology Munich, Germany
| | - Jan S Kirschke
- Department of Informatics, Technical University of Munich, Neuroradiology Munich, Germany
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum Rechtsder Isar, Technical University of Munich, Munich, Germany
| | - Bumjoon Kim
- Department of Biomedical Engineering, Convergence Medicine, Radiology, Neurology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea.
| | - Namkug Kim
- Department of Biomedical Engineering, Convergence Medicine, Radiology, Neurology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea.
| | - Chulhong Kim
- Graduate School of Artificial Intelligence (GSAI), Department of Electrical Engineering, Medical Science and Engineering, and Medical Device Innovation Center, Convergence IT Engineering, Mechanical Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea.
| |
Collapse
|
3
|
Khosravi P, Mohammadi S, Zahiri F, Khodarahmi M, Zahiri J. AI-Enhanced Detection of Clinically Relevant Structural and Functional Anomalies in MRI: Traversing the Landscape of Conventional to Explainable Approaches. J Magn Reson Imaging 2024. [PMID: 38243677 DOI: 10.1002/jmri.29247] [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: 09/01/2023] [Revised: 01/05/2024] [Accepted: 01/08/2024] [Indexed: 01/21/2024] Open
Abstract
Anomaly detection in medical imaging, particularly within the realm of magnetic resonance imaging (MRI), stands as a vital area of research with far-reaching implications across various medical fields. This review meticulously examines the integration of artificial intelligence (AI) in anomaly detection for MR images, spotlighting its transformative impact on medical diagnostics. We delve into the forefront of AI applications in MRI, exploring advanced machine learning (ML) and deep learning (DL) methodologies that are pivotal in enhancing the precision of diagnostic processes. The review provides a detailed analysis of preprocessing, feature extraction, classification, and segmentation techniques, alongside a comprehensive evaluation of commonly used metrics. Further, this paper explores the latest developments in ensemble methods and explainable AI, offering insights into future directions and potential breakthroughs. This review synthesizes current insights, offering a valuable guide for researchers, clinicians, and medical imaging experts. It highlights AI's crucial role in improving the precision and speed of detecting key structural and functional irregularities in MRI. Our exploration of innovative techniques and trends furthers MRI technology development, aiming to refine diagnostics, tailor treatments, and elevate patient care outcomes. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 1.
Collapse
Affiliation(s)
- Pegah Khosravi
- Department of Biological Sciences, New York City College of Technology, CUNY, New York City, New York, USA
- The CUNY Graduate Center, City University of New York, New York City, New York, USA
| | - Saber Mohammadi
- Department of Biological Sciences, New York City College of Technology, CUNY, New York City, New York, USA
- Department of Biophysics, Tarbiat Modares University, Tehran, Iran
| | - Fatemeh Zahiri
- Department of Cell and Molecular Sciences, Kharazmi University, Tehran, Iran
| | | | - Javad Zahiri
- Department of Neuroscience, University of California San Diego, San Diego, California, USA
| |
Collapse
|
4
|
Malik M, Chong B, Fernandez J, Shim V, Kasabov NK, Wang A. Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review. Bioengineering (Basel) 2024; 11:86. [PMID: 38247963 PMCID: PMC10813717 DOI: 10.3390/bioengineering11010086] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2023] [Revised: 01/05/2024] [Accepted: 01/15/2024] [Indexed: 01/23/2024] Open
Abstract
Stroke is a medical condition that affects around 15 million people annually. Patients and their families can face severe financial and emotional challenges as it can cause motor, speech, cognitive, and emotional impairments. Stroke lesion segmentation identifies the stroke lesion visually while providing useful anatomical information. Though different computer-aided software are available for manual segmentation, state-of-the-art deep learning makes the job much easier. This review paper explores the different deep-learning-based lesion segmentation models and the impact of different pre-processing techniques on their performance. It aims to provide a comprehensive overview of the state-of-the-art models and aims to guide future research and contribute to the development of more robust and effective stroke lesion segmentation models.
Collapse
Affiliation(s)
- Mishaim Malik
- Auckland Bioengineering Institute, The University of Auckland, Auckland 1010, New Zealand; (M.M.); (B.C.); (N.K.K.)
| | - Benjamin Chong
- Auckland Bioengineering Institute, The University of Auckland, Auckland 1010, New Zealand; (M.M.); (B.C.); (N.K.K.)
- Faculty of Medical and Health Sciences, The University of Auckland, Auckland 1010, New Zealand
- Centre for Brain Research, The University of Auckland, Auckland 1010, New Zealand
| | - Justin Fernandez
- Auckland Bioengineering Institute, The University of Auckland, Auckland 1010, New Zealand; (M.M.); (B.C.); (N.K.K.)
- Centre for Brain Research, The University of Auckland, Auckland 1010, New Zealand
- Mātai Medical Research Institute, Gisborne 4010, New Zealand
| | - Vickie Shim
- Auckland Bioengineering Institute, The University of Auckland, Auckland 1010, New Zealand; (M.M.); (B.C.); (N.K.K.)
- Mātai Medical Research Institute, Gisborne 4010, New Zealand
| | - Nikola Kirilov Kasabov
- Auckland Bioengineering Institute, The University of Auckland, Auckland 1010, New Zealand; (M.M.); (B.C.); (N.K.K.)
- Knowledge Engineering and Discovery Research Innovation, School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New Zealand
- Institute for Information and Communication Technologies, Bulgarian Academy of Sciences, 1113 Sofia, Bulgaria
- Knowledge Engineering Consulting Ltd., Auckland 1071, New Zealand
| | - Alan Wang
- Auckland Bioengineering Institute, The University of Auckland, Auckland 1010, New Zealand; (M.M.); (B.C.); (N.K.K.)
- Faculty of Medical and Health Sciences, The University of Auckland, Auckland 1010, New Zealand
- Centre for Brain Research, The University of Auckland, Auckland 1010, New Zealand
- Mātai Medical Research Institute, Gisborne 4010, New Zealand
- Medical Imaging Research Centre, The University of Auckland, Auckland 1010, New Zealand
- Centre for Co-Created Ageing Research, The University of Auckland, Auckland 1010, New Zealand
| |
Collapse
|
5
|
Wang Z, Zhu H, Huang B, Wang Z, Lu W, Chen N, Wang Y. M-MSSEU: source-free domain adaptation for multi-modal stroke lesion segmentation using shadowed sets and evidential uncertainty. Health Inf Sci Syst 2023; 11:46. [PMID: 37780536 PMCID: PMC10539264 DOI: 10.1007/s13755-023-00247-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2023] [Accepted: 09/08/2023] [Indexed: 10/03/2023] Open
Abstract
Due to the unavailability of source domain data encountered in unsupervised domain adaptation, there has been an increasing number of studies on source-free domain adaptation (SFDA) in recent years. To better solve the SFDA problem and effectively leverage the multi-modal information in medical images, this paper presents a novel SFDA method for multi-modal stroke lesion segmentation in which evidential deep learning instead of convolutional neural network. Specifically, for multi-modal stroke images, we design a multi-modal opinion fusion module which uses Dempster-Shafer evidence theory for decision fusion of different modalities. Besides, for the SFDA problem, we use the pseudo label learning method, which obtains pseudo labels from the pre-trained source model to perform the adaptation process. To solve the unreliability of pseudo label caused by domain shift, we propose a pseudo label filtering scheme using shadowed sets theory and a pseudo label refining scheme using evidential uncertainty. These two schemes can automatically extract unreliable parts in pseudo labels and jointly improve the quality of pseudo labels with low computational costs. Experiments on two multi-modal stroke lesion datasets demonstrate the superiority of our method over other state-of-the-art SFDA methods.
Collapse
Affiliation(s)
- Zhicheng Wang
- School of Information Science and Engineering, East China University of Science and Technology, No.130 Meilong Road, Shanghai, 200237 China
| | - Hongqing Zhu
- School of Information Science and Engineering, East China University of Science and Technology, No.130 Meilong Road, Shanghai, 200237 China
| | - Bingcang Huang
- Department of Radiology, Gongli Hospital of Shanghai Pudong New Area, Shanghai, 200135 China
| | - Ziying Wang
- School of Information Science and Engineering, East China University of Science and Technology, No.130 Meilong Road, Shanghai, 200237 China
| | - Weiping Lu
- Department of Radiology, Gongli Hospital of Shanghai Pudong New Area, Shanghai, 200135 China
| | - Ning Chen
- School of Information Science and Engineering, East China University of Science and Technology, No.130 Meilong Road, Shanghai, 200237 China
| | - Ying Wang
- Shanghai Health Commission Key Lab of Artificial Intelligence (AI)-Based Management of Inflammation and Chronic Diseases, Sino-French Cooperative Central Lab, Gongli Hospital of Shanghai Pudong New Area, Shanghai, 200135 China
| |
Collapse
|
6
|
Yu W, Huang Z, Zhang J, Shan H. SAN-Net: Learning generalization to unseen sites for stroke lesion segmentation with self-adaptive normalization. Comput Biol Med 2023; 156:106717. [PMID: 36878125 DOI: 10.1016/j.compbiomed.2023.106717] [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: 07/25/2022] [Revised: 01/31/2023] [Accepted: 02/26/2023] [Indexed: 03/06/2023]
Abstract
There are considerable interests in automatic stroke lesion segmentation on magnetic resonance (MR) images in the medical imaging field, as stroke is an important cerebrovascular disease. Although deep learning-based models have been proposed for this task, generalizing these models to unseen sites is difficult due to not only the large inter-site discrepancy among different scanners, imaging protocols, and populations, but also the variations in stroke lesion shape, size, and location. To tackle this issue, we introduce a self-adaptive normalization network, termed SAN-Net, to achieve adaptive generalization on unseen sites for stroke lesion segmentation. Motivated by traditional z-score normalization and dynamic network, we devise a masked adaptive instance normalization (MAIN) to minimize inter-site discrepancies, which standardizes input MR images from different sites into a site-unrelated style by dynamically learning affine parameters from the input; i.e., MAIN can affinely transform the intensity values. Then, we leverage a gradient reversal layer to force the U-net encoder to learn site-invariant representation with a site classifier, which further improves the model generalization in conjunction with MAIN. Finally, inspired by the "pseudosymmetry" of the human brain, we introduce a simple yet effective data augmentation technique, termed symmetry-inspired data augmentation (SIDA), that can be embedded within SAN-Net to double the sample size while halving memory consumption. Experimental results on the benchmark Anatomical Tracings of Lesions After Stroke (ATLAS) v1.2 dataset, which includes MR images from 9 different sites, demonstrate that under the "leave-one-site-out" setting, the proposed SAN-Net outperforms recently published methods in terms of quantitative metrics and qualitative comparisons.
Collapse
Affiliation(s)
- Weiyi Yu
- Institute of Science and Technology for Brain-inspired Intelligence and MOE Frontiers Center for Brain Science, Fudan University, Shanghai, 200433, China
| | - Zhizhong Huang
- Shanghai Key Lab of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai 200433, China
| | - Junping Zhang
- Shanghai Key Lab of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai 200433, China
| | - Hongming Shan
- Institute of Science and Technology for Brain-inspired Intelligence and MOE Frontiers Center for Brain Science, Fudan University, Shanghai, 200433, China; Shanghai Center for Brain Science and Brain-inspired Technology, Shanghai 201210, China.
| |
Collapse
|
7
|
A Deep Learning Approach for Detecting Stroke from Brain CT Images Using OzNet. BIOENGINEERING (BASEL, SWITZERLAND) 2022; 9:bioengineering9120783. [PMID: 36550989 PMCID: PMC9774129 DOI: 10.3390/bioengineering9120783] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/05/2022] [Revised: 12/01/2022] [Accepted: 12/04/2022] [Indexed: 12/14/2022]
Abstract
A brain stroke is a life-threatening medical disorder caused by the inadequate blood supply to the brain. After the stroke, the damaged area of the brain will not operate normally. As a result, early detection is crucial for more effective therapy. Computed tomography (CT) images supply a rapid diagnosis of brain stroke. However, while doctors are analyzing each brain CT image, time is running fast. This circumstance may lead to result in a delay in treatment and making errors. Therefore, we targeted the utilization of an efficient artificial intelligence algorithm in stroke detection. In this paper, we designed hybrid algorithms that include a new convolution neural networks (CNN) architecture called OzNet and various machine learning algorithms for binary classification of real brain stroke CT images. When we classified the dataset with OzNet, we acquired successful performance. However, for this target, we combined it with a minimum Redundancy Maximum Relevance (mRMR) method and Decision Tree (DT), k-Nearest Neighbors (kNN), Linear Discriminant Analysis (LDA), Naïve Bayes (NB), and Support Vector Machines (SVM). In addition, 4096 significant features were obtained from the fully connected layer of OzNet, and we reduced the dimension of features from 4096 to 250 using the mRMR method. Finally, we utilized these machine learning algorithms to classify important features. As a result, OzNet-mRMR-NB was an excellent hybrid algorithm and achieved an accuracy of 98.42% and AUC of 0.99 to detect stroke from brain CT images.
Collapse
|
8
|
Nazari-Farsani S, Yu Y, Duarte Armindo R, Lansberg M, Liebeskind DS, Albers G, Christensen S, Levin CS, Zaharchuk G. Predicting final ischemic stroke lesions from initial diffusion-weighted images using a deep neural network. Neuroimage Clin 2022; 37:103278. [PMID: 36481696 PMCID: PMC9727698 DOI: 10.1016/j.nicl.2022.103278] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2022] [Revised: 11/20/2022] [Accepted: 11/30/2022] [Indexed: 12/03/2022]
Abstract
BACKGROUND For prognosis of stroke, measurement of the diffusion-perfusion mismatch is a common practice for estimating tissue at risk of infarction in the absence of timely reperfusion. However, perfusion-weighted imaging (PWI) adds time and expense to the acute stroke imaging workup. We explored whether a deep convolutional neural network (DCNN) model trained with diffusion-weighted imaging obtained at admission could predict final infarct volume and location in acute stroke patients. METHODS In 445 patients, we trained and validated an attention-gated (AG) DCNN to predict final infarcts as delineated on follow-up studies obtained 3 to 7 days after stroke. The input channels consisted of MR diffusion-weighted imaging (DWI), apparent diffusion coefficients (ADC) maps, and thresholded ADC maps with values less than 620 × 10-6 mm2/s, while the output was a voxel-by-voxel probability map of tissue infarction. We evaluated performance of the model using the area under the receiver-operator characteristic curve (AUC), the Dice similarity coefficient (DSC), absolute lesion volume error, and the concordance correlation coefficient (ρc) of the predicted and true infarct volumes. RESULTS The model obtained a median AUC of 0.91 (IQR: 0.84-0.96). After thresholding at an infarction probability of 0.5, the median sensitivity and specificity were 0.60 (IQR: 0.16-0.84) and 0.97 (IQR: 0.93-0.99), respectively, while the median DSC and absolute volume error were 0.50 (IQR: 0.17-0.66) and 27 ml (IQR: 7-60 ml), respectively. The model's predicted lesion volumes showed high correlation with ground truth volumes (ρc = 0.73, p < 0.01). CONCLUSION An AG-DCNN using diffusion information alone upon admission was able to predict infarct volumes at 3-7 days after stroke onset with comparable accuracy to models that consider both DWI and PWI. This may enable treatment decisions to be made with shorter stroke imaging protocols.
Collapse
Affiliation(s)
| | - Yannan Yu
- Department of Radiology, Stanford University, CA, USA; Internal Medicine Department, University of Massachusetts Memorial Medical Center, University of Massachusetts, Boston, USA
| | - Rui Duarte Armindo
- Department of Radiology, Stanford University, CA, USA; Department of Neuroradiology, Hospital Beatriz Ângelo, Loures, Lisbon, Portugal
| | | | - David S Liebeskind
- Department of Neurology, University of California Los Angeles, Los Angeles, CA, USA
| | | | | | - Craig S Levin
- Department of Radiology, Stanford University, CA, USA
| | | |
Collapse
|
9
|
Le HL, Roh HG, Kim HJ, Kwak JT. A 3D Multi-task Regression and Ordinal Regression Deep Neural Network for Collateral Imaging from Dynamic Susceptibility Contrast-Enhanced MR perfusion in Acute Ischemic Stroke. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 225:107071. [PMID: 35994873 DOI: 10.1016/j.cmpb.2022.107071] [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: 09/01/2021] [Revised: 07/19/2022] [Accepted: 08/09/2022] [Indexed: 06/15/2023]
Abstract
BACKGROUND AND OBJECTIVE Cerebral collaterals have been identified as one of the primary determinants for treatment options in acute ischemic stroke. Several works have been proposed, but these have not been adopted for a routine clinical usage due to their manual and heuristic nature as well as inconsistency and instability of the assessment. Herein, we present an advanced deep learning-based method that can automatically generate a multiphase collateral imaging (collateral map) derived from dynamic susceptibility contrast-enhanced MR perfusion (DSC-MRP) in an accurate and robust manner. METHODS We develop a 3D multi-task regression and ordinal regression deep neural network for generating collateral maps from DSC-MRP, which formulates the prediction of collateral maps as both a regression task and an ordinal regression task. For an ordinal regression task, we introduce a spacing-decreasing discretization (SDD) strategy to represent the intensity of the collateral status on a discrete, ordinal scale. We also devise loss functions to achieve effective and efficient multi-task learning. RESULTS We systematically evaluated the performance of the proposed network using DSC-MRP from 802 patients. On average, the proposed network achieved ≥0.900 squared correlation coefficient (R-Squared), ≥0.916 Tanimoto measure (TM), ≥0.0913 structural similarity index measure (SSIM), and ≤0.564 × 10-1 mean absolute error (MAE), outperforming eight competing models that have been recently developed in medical imaging and computer vision. We also found that the proposed network could provide an improved contrast between the low and high intensity regions in the collateral maps, which is a key to an accurate evaluation of the collateral status. CONCLUSIONS The experimental results demonstrate that the proposed network is able to generate collateral maps with high accuracy, facilitating a timely and prompt assessment of the collateral status in clinlcs. The future study will entail the optimization of the proposed network and its clinical evalution in a prospective manner.
Collapse
Affiliation(s)
- Hoang Long Le
- Department of Computer Science and Engineering, Sejong University, Seoul 05006, Korea
| | - Hong Gee Roh
- Department of Radiology, Konkuk University Medical Center, Konkuk University School of Medicine, Seoul 05030, Korea
| | - Hyun Jeong Kim
- Department of Radiology, Daejeon St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Daejeon 34943, Korea
| | - Jin Tae Kwak
- School of Electrical Engineering, Korea University, Seoul 02841, Korea.
| |
Collapse
|
10
|
Chen S, Qiu C, Yang W, Zhang Z. Combining edge guidance and feature pyramid for medical image segmentation. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2022.103960] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
11
|
DGCU–Net: A new dual gradient-color deep convolutional neural network for efficient skin lesion segmentation. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2022.103829] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
|
12
|
Qin Z, Liu Z, Guo Q, Zhu P. 3D convolutional neural networks with hybrid attention mechanism for early diagnosis of Alzheimer’s disease. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2022.103828] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/02/2022]
|
13
|
A Deep Learning Approach for Sentiment Analysis of COVID-19 Reviews. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12083709] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/27/2023]
Abstract
User-generated multi-media content, such as images, text, videos, and speech, has recently become more popular on social media sites as a means for people to share their ideas and opinions. One of the most popular social media sites for providing public sentiment towards events that occurred during the COVID-19 period is Twitter. This is because Twitter posts are short and constantly being generated. This paper presents a deep learning approach for sentiment analysis of Twitter data related to COVID-19 reviews. The proposed algorithm is based on an LSTM-RNN-based network and enhanced featured weighting by attention layers. This algorithm uses an enhanced feature transformation framework via the attention mechanism. A total of four class labels (sad, joy, fear, and anger) from publicly available Twitter data posted in the Kaggle database were used in this study. Based on the use of attention layers with the existing LSTM-RNN approach, the proposed deep learning approach significantly improved the performance metrics, with an increase of 20% in accuracy and 10% to 12% in precision but only 12–13% in recall as compared with the current approaches. Out of a total of 179,108 COVID-19-related tweets, tweets with positive, neutral, and negative sentiments were found to account for 45%, 30%, and 25%, respectively. This shows that the proposed deep learning approach is efficient and practical and can be easily implemented for sentiment classification of COVID-19 reviews.
Collapse
|
14
|
Classification of cervical cells leveraging simultaneous super-resolution and ordinal regression. Appl Soft Comput 2022. [DOI: 10.1016/j.asoc.2021.108208] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
15
|
Inamdar MA, Raghavendra U, Gudigar A, Chakole Y, Hegde A, Menon GR, Barua P, Palmer EE, Cheong KH, Chan WY, Ciaccio EJ, Acharya UR. A Review on Computer Aided Diagnosis of Acute Brain Stroke. SENSORS (BASEL, SWITZERLAND) 2021; 21:8507. [PMID: 34960599 PMCID: PMC8707263 DOI: 10.3390/s21248507] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/04/2021] [Revised: 12/05/2021] [Accepted: 12/09/2021] [Indexed: 01/01/2023]
Abstract
Amongst the most common causes of death globally, stroke is one of top three affecting over 100 million people worldwide annually. There are two classes of stroke, namely ischemic stroke (due to impairment of blood supply, accounting for ~70% of all strokes) and hemorrhagic stroke (due to bleeding), both of which can result, if untreated, in permanently damaged brain tissue. The discovery that the affected brain tissue (i.e., 'ischemic penumbra') can be salvaged from permanent damage and the bourgeoning growth in computer aided diagnosis has led to major advances in stroke management. Abiding to the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines, we have surveyed a total of 177 research papers published between 2010 and 2021 to highlight the current status and challenges faced by computer aided diagnosis (CAD), machine learning (ML) and deep learning (DL) based techniques for CT and MRI as prime modalities for stroke detection and lesion region segmentation. This work concludes by showcasing the current requirement of this domain, the preferred modality, and prospective research areas.
Collapse
Affiliation(s)
- Mahesh Anil Inamdar
- Department of Mechatronics, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, India;
| | - Udupi Raghavendra
- Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, India; (A.G.); (Y.C.)
| | - Anjan Gudigar
- Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, India; (A.G.); (Y.C.)
| | - Yashas Chakole
- Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, India; (A.G.); (Y.C.)
| | - Ajay Hegde
- Department of Neurosurgery, Kasturba Medical College, Manipal Academy of Higher Education, Manipal 576104, India; (A.H.); (G.R.M.)
| | - Girish R. Menon
- Department of Neurosurgery, Kasturba Medical College, Manipal Academy of Higher Education, Manipal 576104, India; (A.H.); (G.R.M.)
| | - Prabal Barua
- School of Management & Enterprise, University of Southern Queensland, Toowoomba, QLD 4350, Australia;
- Faculty of Engineering and Information Technology, University of Technology, Sydney, NSW 2007, Australia
- Cogninet Brain Team, Cogninet Australia, Sydney, NSW 2010, Australia
| | - Elizabeth Emma Palmer
- School of Women’s and Children’s Health, University of New South Wales, Sydney, NSW 2052, Australia;
| | - Kang Hao Cheong
- Science, Mathematics and Technology Cluster, Singapore University of Technology and Design, Singapore 487372, Singapore;
| | - Wai Yee Chan
- Department of Biomedical Imaging, Research Imaging Centre, University of Malaya, Kuala Lumpur 59100, Malaysia;
| | - Edward J. Ciaccio
- Department of Medicine, Columbia University, New York, NY 10032, USA;
| | - U. Rajendra Acharya
- Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia;
- School of Engineering, Ngee Ann Polytechnic, Singapore 599489, Singapore
- Department of Biomedical Engineering, School of Science and Technology, SUSS University, Singapore 599491, Singapore
- Department of Biomedical Informatics and Medical Engineering, Asia University, Taichung 41354, Taiwan
| |
Collapse
|
16
|
Liu CF, Hsu J, Xu X, Ramachandran S, Wang V, Miller MI, Hillis AE, Faria AV. Deep learning-based detection and segmentation of diffusion abnormalities in acute ischemic stroke. COMMUNICATIONS MEDICINE 2021; 1:61. [PMID: 35602200 PMCID: PMC9053217 DOI: 10.1038/s43856-021-00062-8] [Citation(s) in RCA: 23] [Impact Index Per Article: 7.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/21/2021] [Accepted: 11/23/2021] [Indexed: 01/19/2023] Open
Abstract
Background Accessible tools to efficiently detect and segment diffusion abnormalities in acute strokes are highly anticipated by the clinical and research communities. Methods We developed a tool with deep learning networks trained and tested on a large dataset of 2,348 clinical diffusion weighted MRIs of patients with acute and sub-acute ischemic strokes, and further tested for generalization on 280 MRIs of an external dataset (STIR). Results Our proposed model outperforms generic networks and DeepMedic, particularly in small lesions, with lower false positive rate, balanced precision and sensitivity, and robustness to data perturbs (e.g., artefacts, low resolution, technical heterogeneity). The agreement with human delineation rivals the inter-evaluator agreement; the automated lesion quantification of volume and contrast has virtually total agreement with human quantification. Conclusion Our tool is fast, public, accessible to non-experts, with minimal computational requirements, to detect and segment lesions via a single command line. Therefore, it fulfills the conditions to perform large scale, reliable and reproducible clinical and translational research.
Collapse
Affiliation(s)
- Chin-Fu Liu
- Center for Imaging Science, Johns Hopkins University, Baltimore, MD USA
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD USA
| | - Johnny Hsu
- Department of Radiology, School of Medicine, Johns Hopkins University, Baltimore, MD USA
| | - Xin Xu
- Department of Radiology, School of Medicine, Johns Hopkins University, Baltimore, MD USA
| | - Sandhya Ramachandran
- Center for Imaging Science, Johns Hopkins University, Baltimore, MD USA
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD USA
| | - Victor Wang
- Center for Imaging Science, Johns Hopkins University, Baltimore, MD USA
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD USA
| | - Michael I. Miller
- Center for Imaging Science, Johns Hopkins University, Baltimore, MD USA
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD USA
- Kavli Neuroscience Discovery Institute, Johns Hopkins University, Baltimore, MD USA
| | - Argye E. Hillis
- Department of Neurology, School of Medicine, Johns Hopkins University, Baltimore, MD USA
- Department of Physical Medicine & Rehabilitation, and Department of Cognitive Science, Johns Hopkins University, Baltimore, MD USA
| | - Andreia V. Faria
- Department of Radiology, School of Medicine, Johns Hopkins University, Baltimore, MD USA
| |
Collapse
|
17
|
DGFAU-Net: Global feature attention upsampling network for medical image segmentation. Neural Comput Appl 2021. [DOI: 10.1007/s00521-021-05908-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
18
|
Su YH, Jiang W, Chitrakar D, Huang K, Peng H, Hannaford B. Local Style Preservation in Improved GAN-Driven Synthetic Image Generation for Endoscopic Tool Segmentation. SENSORS (BASEL, SWITZERLAND) 2021; 21:5163. [PMID: 34372398 PMCID: PMC8346972 DOI: 10.3390/s21155163] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/01/2021] [Revised: 07/25/2021] [Accepted: 07/27/2021] [Indexed: 12/19/2022]
Abstract
Accurate semantic image segmentation from medical imaging can enable intelligent vision-based assistance in robot-assisted minimally invasive surgery. The human body and surgical procedures are highly dynamic. While machine-vision presents a promising approach, sufficiently large training image sets for robust performance are either costly or unavailable. This work examines three novel generative adversarial network (GAN) methods of providing usable synthetic tool images using only surgical background images and a few real tool images. The best of these three novel approaches generates realistic tool textures while preserving local background content by incorporating both a style preservation and a content loss component into the proposed multi-level loss function. The approach is quantitatively evaluated, and results suggest that the synthetically generated training tool images enhance UNet tool segmentation performance. More specifically, with a random set of 100 cadaver and live endoscopic images from the University of Washington Sinus Dataset, the UNet trained with synthetically generated images using the presented method resulted in 35.7% and 30.6% improvement over using purely real images in mean Dice coefficient and Intersection over Union scores, respectively. This study is promising towards the use of more widely available and routine screening endoscopy to preoperatively generate synthetic training tool images for intraoperative UNet tool segmentation.
Collapse
Affiliation(s)
- Yun-Hsuan Su
- Department of Computer Science, Mount Holyoke College, 50 College Street, South Hadley, MA 01075, USA;
| | - Wenfan Jiang
- Department of Computer Science, Mount Holyoke College, 50 College Street, South Hadley, MA 01075, USA;
| | - Digesh Chitrakar
- Department of Engineering, Trinity College, 300 Summit St., Hartford, CT 06106, USA; (D.C.); (K.H.)
| | - Kevin Huang
- Department of Engineering, Trinity College, 300 Summit St., Hartford, CT 06106, USA; (D.C.); (K.H.)
| | - Haonan Peng
- Department of Electrical and Computer Engineering, University of Washington, 185 Stevens Way, Paul Allen Center, Seattle, WA 98105, USA; (H.P.); (B.H.)
| | - Blake Hannaford
- Department of Electrical and Computer Engineering, University of Washington, 185 Stevens Way, Paul Allen Center, Seattle, WA 98105, USA; (H.P.); (B.H.)
| |
Collapse
|
19
|
Faust O, En Wei Koh J, Jahmunah V, Sabut S, Ciaccio EJ, Majid A, Ali A, Lip GYH, Acharya UR. Fusion of Higher Order Spectra and Texture Extraction Methods for Automated Stroke Severity Classification with MRI Images. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2021; 18:8059. [PMID: 34360349 PMCID: PMC8345794 DOI: 10.3390/ijerph18158059] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/18/2021] [Revised: 07/05/2021] [Accepted: 07/23/2021] [Indexed: 11/18/2022]
Abstract
This paper presents a scientific foundation for automated stroke severity classification. We have constructed and assessed a system which extracts diagnostically relevant information from Magnetic Resonance Imaging (MRI) images. The design was based on 267 images that show the brain from individual subjects after stroke. They were labeled as either Lacunar Syndrome (LACS), Partial Anterior Circulation Syndrome (PACS), or Total Anterior Circulation Stroke (TACS). The labels indicate different physiological processes which manifest themselves in distinct image texture. The processing system was tasked with extracting texture information that could be used to classify a brain MRI image from a stroke survivor into either LACS, PACS, or TACS. We analyzed 6475 features that were obtained with Gray-Level Run Length Matrix (GLRLM), Higher Order Spectra (HOS), as well as a combination of Discrete Wavelet Transform (DWT) and Gray-Level Co-occurrence Matrix (GLCM) methods. The resulting features were ranked based on the p-value extracted with the Analysis Of Variance (ANOVA) algorithm. The ranked features were used to train and test four types of Support Vector Machine (SVM) classification algorithms according to the rules of 10-fold cross-validation. We found that SVM with Radial Basis Function (RBF) kernel achieves: Accuracy (ACC) = 93.62%, Specificity (SPE) = 95.91%, Sensitivity (SEN) = 92.44%, and Dice-score = 0.95. These results indicate that computer aided stroke severity diagnosis support is possible. Such systems might lead to progress in stroke diagnosis by enabling healthcare professionals to improve diagnosis and management of stroke patients with the same resources.
Collapse
Affiliation(s)
- Oliver Faust
- Department of Engineering and Mathematics, Sheffield Hallam University, Sheffield S1 1WB, UK
| | - Joel En Wei Koh
- School of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore 599489, Singapore; (J.E.W.K.); (V.J.); (U.R.A.)
| | - Vicnesh Jahmunah
- School of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore 599489, Singapore; (J.E.W.K.); (V.J.); (U.R.A.)
| | - Sukant Sabut
- School of Electronics Engineering, Kalinga Institute of Industrial Technology, Bhubaneswar, Odisha 751024, India;
| | - Edward J. Ciaccio
- Department of Medicine-Cardiology, Columbia University, New York, NY 10027, USA;
| | - Arshad Majid
- Sheffield Institute for Translational Neuroscience, University of Sheffield, Sheffield S10 2HQ, UK;
| | - Ali Ali
- Sheffield Teaching Hospitals NIHR Biomedical Research Centre, Sheffield S10 2JF, UK;
| | - Gregory Y. H. Lip
- Liverpool Centre for Cardiovascular Science, University of Liverpool and Liverpool Heart & Chest Hospital, Liverpool L69 7TX, UK;
- Aalborg Thrombosis Research Unit, Department of Clinical Medicine, Aalborg University, 9000 Aalborg, Denmark
| | - U. Rajendra Acharya
- School of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore 599489, Singapore; (J.E.W.K.); (V.J.); (U.R.A.)
- School of Science and Technology, Singapore University of Social Sciences, 463 Clementi Road, Singapore 599494, Singapore
- Department of Bioinformatics and Medical Engineering, Asia University, Taichung 41354, Taiwan
- International Research Organization for Advanced Science and Technology (IROAST), Kumamoto University, Kumamoto 860-8555, Japan
| |
Collapse
|
20
|
Multi-view iterative random walker for automated salvageable tissue delineation in ischemic stroke from multi-sequence MRI. J Neurosci Methods 2021; 360:109260. [PMID: 34146591 DOI: 10.1016/j.jneumeth.2021.109260] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2021] [Revised: 05/19/2021] [Accepted: 06/13/2021] [Indexed: 12/13/2022]
Abstract
BACKGROUND AND OBJECTIVE Non-invasive and robust identification of salvageable tissue (penumbra) is crucial for interventional stroke therapy. Besides identifying stroke injury as a whole, the ability to automatically differentiate core and penumbra tissues, using both diffusion and perfusion magnetic resonance imaging (MRI) sequences is essential for ischemic stroke treatment. METHOD A fully automated and novel one-shot multi-view iterative random walker (MIRW) method with an automated injury seed point detection is developed for lesion delineation. MIRW utilizes the heirarchical decomposition of multi-sequence MRI physical properties of the underlying tissue within the lesion to maximize the inter-class variations of the volumetric histogram to estimate the probable seed points. These estimates are further utilized to conglomerate the lesion estimations iteratively from axial, coronal and sagittal MRI volumes for a computationally efficient segmentation and quantification of salvageable and necrotic tissues from multi-sequence MRI. RESULTS Comprehensive experimental analysis of MIRW is performed on three challenging adult(sub-)acute ischemic stroke datasets using performance measures like precision, sensitivity, specificity and Dice similarity score (DSC), which are computed with respect to the manual ground-truth. COMPARISON WITH EXISTING METHODS MIRW method resulted in a high DSC of 83.5% in a very less computational time of 98.23 s/volume, which is a significant improvement on the ISLES benchmark dataset for penumbra detection, compared to the state-of-the-art techniques. CONCLUSION Quantitative measures demonstrate the promising potential of MIRW for computational analysis of adult stroke and quantifying penumbra in stroke patients which is essential for selecting the good candidates for recanalization.
Collapse
|
21
|
Deep neural networks for improving physical accuracy of 2D and 3D multi-mineral segmentation of rock micro-CT images. Appl Soft Comput 2021. [DOI: 10.1016/j.asoc.2021.107185] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
|
22
|
Arora R, Raman B, Nayyar K, Awasthi R. Automated skin lesion segmentation using attention-based deep convolutional neural network. Biomed Signal Process Control 2021. [DOI: 10.1016/j.bspc.2020.102358] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
|
23
|
Karthik R, Menaka R, Hariharan M, Won D. Ischemic Lesion Segmentation using Ensemble of Multi-Scale Region Aligned CNN. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2021; 200:105831. [PMID: 33223277 DOI: 10.1016/j.cmpb.2020.105831] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/26/2020] [Accepted: 11/03/2020] [Indexed: 06/11/2023]
Abstract
The first and foremost step in the diagnosis of ischemic stroke is the delineation of the lesion from radiological images for effective treatment planning. Manual delineation of the lesion by radiological experts is generally laborious and time-consuming. Sometimes, it is prone to intra-observer and inter-observer variability. State of the art deep architectures based on Fully Convolutional Networks (FCN) and cascaded CNNs have shown good results in automated lesion segmentation. This work proposes a series of enhancements over the learning paradigm in the existing methods, by focusing on learning meticulous feature representations through the CNN layers for accurate ischemic lesion segmentation from multimodal MRI. Multiple levels of losses, integration of features from multiple scales, an ensemble of prediction maps from sub-networks are employed to enable the CNN to correlate between features seen from different receptive fields. To allow for progressive refinement of features from block to block, a custom dropout module has been proposed that suppresses noisy features. Multi-branch residual connections and attention mechanisms were also included in the CNN blocks to enable the integration of information from multiple receptive fields and selectively weigh significant features. Also, to tackle data imbalance both at voxel and sample level, patch-based modeling and separation of concerns into classification & segmentation functional branches are proposed. By incorporating the above mentioned architectural enhancements, the proposed deep architecture was able to achieve better segmentation performance against the existing models. The proposed approach was evaluated on the ISLES 2015 SISS dataset, and it achieved a mean dice coefficient of 0.775. By combining sample classification and lesion segmentation into a fully automated framework, the proposed approach has yielded better results compared to most of the existing works.
Collapse
Affiliation(s)
- R Karthik
- Senior Assistant Professor, Centre for Cyber Physical Systems, Vellore Institute of Technology, Chennai, India.
| | - R Menaka
- Professor, Centre for Cyber Physical Systems, Vellore Institute of Technology, Chennai, India.
| | - M Hariharan
- School of Computing Sciences and Engineering, Vellore Institute of Technology, Chennai, India.
| | - Daehan Won
- Assistant Professor, System Sciences and Industrial Engineering, Binghamton University.
| |
Collapse
|
24
|
Karthik R, Menaka R, Johnson A, Anand S. Neuroimaging and deep learning for brain stroke detection - A review of recent advancements and future prospects. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2020; 197:105728. [PMID: 32882591 DOI: 10.1016/j.cmpb.2020.105728] [Citation(s) in RCA: 29] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/19/2020] [Accepted: 08/23/2020] [Indexed: 05/24/2023]
Abstract
BACKGROUND AND OBJECTIVE In recent years, deep learning algorithms have created a massive impact on addressing research challenges in different domains. The medical field also greatly benefits from the use of improving deep learning models which save time and produce accurate results. This research aims to emphasize the impact of deep learning models in brain stroke detection and lesion segmentation. This is achieved by discussing the state of the art approaches proposed by the recent works in this field. METHODS In this study, the advancements in stroke lesion detection and segmentation were focused. The survey analyses 113 research papers published in different academic research databases. The research articles have been filtered out based on specific criteria to obtain the most prominent insights related to stroke lesion detection and segmentation. RESULTS The features of the stroke lesion vary based on the type of imaging modality. To develop an effective method for stroke lesion detection, the features need to be carefully extracted from the input images. This review takes an attempt to categorize and discuss the different deep architectures employed for stroke lesion detection and segmentation, based on the underlying imaging modality. This further assists in understanding the relevance of the two-deep neural network components in medical image analysis namely Convolutional Neural Network (CNN) and Fully Convolutional Network (FCN). It hints at other possible deep architectures that can be proposed for better results towards stroke lesion detection. Also, the emerging trends and breakthroughs in stroke detection have been detailed in this evaluation. CONCLUSION This work concludes by examining the technical and non-technical challenges faced by researchers and indicate the future implications in stroke detection. It could support the bio-medical researchers to propose better solutions for stroke lesion detection.
Collapse
Affiliation(s)
- R Karthik
- Center for Cyber Physical Systems, Vellore Institute of Technology, Chennai, India.
| | - R Menaka
- Center for Cyber Physical Systems, Vellore Institute of Technology, Chennai, India.
| | - Annie Johnson
- School of Electronics Engineering, Vellore Institute of Technology, Chennai, India
| | - Sundar Anand
- School of Electronics Engineering, Vellore Institute of Technology, Chennai, India
| |
Collapse
|
25
|
Karthik R, Radhakrishnan M, Rajalakshmi R, Raymann J. Delineation of ischemic lesion from brain MRI using attention gated fully convolutional network. Biomed Eng Lett 2020; 11:3-13. [PMID: 33747599 DOI: 10.1007/s13534-020-00178-1] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2020] [Revised: 10/16/2020] [Accepted: 10/24/2020] [Indexed: 11/30/2022] Open
Abstract
Precise delineation of the ischemic lesion from unimodal Magnetic Resonance Imaging (MRI) is a challenging task due to the subtle intensity difference between the lesion and normal tissues. Hence, multispectral MRI modalities are used for characterizing the properties of brain tissues. Traditional lesion detection methods rely on extracting significant hand-engineered features to differentiate normal and abnormal brain tissues. But the identification of those discriminating features is quite complex, as the degree of differentiation varies according to each modality. This can be addressed well by Convolutional Neural Networks (CNN) which supports automatic feature extraction. It is capable of learning the global features from images effectively for image classification. But it loses the context of local information among the pixels that need to be retained for segmentation. Also, it must provide more emphasis on the features of the lesion region for precise reconstruction. The major contribution of this work is the integration of attention mechanism with a Fully Convolutional Network (FCN) to segment ischemic lesion. This attention model is applied to learn and concentrate only on salient features of the lesion region by suppressing the details of other regions. Hence the proposed FCN with attention mechanism was able to segment ischemic lesion of varying size and shape. To study the effectiveness of attention mechanism, various experiments were carried out on ISLES 2015 dataset and a mean dice coefficient of 0.7535 was obtained. Experimental results indicate that there is an improvement of 5% compared to the existing works.
Collapse
Affiliation(s)
- R Karthik
- Centre for Cyber Physical Systems, Vellore Institute of Technology, Chennai, India
| | - Menaka Radhakrishnan
- Centre for Cyber Physical Systems, Vellore Institute of Technology, Chennai, India
| | - R Rajalakshmi
- School of Computing Sciences and Engineering, Vellore Institute of Technology, Chennai, Chennai, India
| | - Joel Raymann
- School of Computing Sciences and Engineering, Vellore Institute of Technology, Chennai, Chennai, India
| |
Collapse
|
26
|
Gerami Seresht N, Lourenzutti R, Fayek AR. A fuzzy clustering algorithm for developing predictive models in construction applications. Appl Soft Comput 2020. [DOI: 10.1016/j.asoc.2020.106679] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
27
|
de Albuquerque VHC, Gupta D, De Falco I, Sannino G, Bouguila N. Special issue on Bio-inspired optimization techniques for Biomedical Data Analysis: Methods and applications. Appl Soft Comput 2020. [DOI: 10.1016/j.asoc.2020.106672] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/30/2022]
|
28
|
Sirsat MS, Fermé E, Câmara J. Machine Learning for Brain Stroke: A Review. J Stroke Cerebrovasc Dis 2020; 29:105162. [DOI: 10.1016/j.jstrokecerebrovasdis.2020.105162] [Citation(s) in RCA: 22] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2020] [Revised: 07/08/2020] [Accepted: 07/11/2020] [Indexed: 12/29/2022] Open
|
29
|
Clèrigues A, Valverde S, Bernal J, Freixenet J, Oliver A, Lladó X. Acute and sub-acute stroke lesion segmentation from multimodal MRI. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2020; 194:105521. [PMID: 32434099 DOI: 10.1016/j.cmpb.2020.105521] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/25/2019] [Revised: 03/30/2020] [Accepted: 04/23/2020] [Indexed: 05/25/2023]
Abstract
BACKGROUND AND OBJECTIVE Acute stroke lesion segmentation tasks are of great clinical interest as they can help doctors make better informed time-critical treatment decisions. Magnetic resonance imaging (MRI) is time demanding but can provide images that are considered the gold standard for diagnosis. Automated stroke lesion segmentation can provide with an estimate of the location and volume of the lesioned tissue, which can help in the clinical practice to better assess and evaluate the risks of each treatment. METHODS We propose a deep learning methodology for acute and sub-acute stroke lesion segmentation using multimodal MR imaging. We pre-process the data to facilitate learning features based on the symmetry of brain hemispheres. The issue of class imbalance is tackled using small patches with a balanced training patch sampling strategy and a dynamically weighted loss function. Moreover, a combination of whole patch predictions, using a U-Net based CNN architecture, and high degree of overlapping patches reduces the need for additional post-processing. RESULTS The proposed method is evaluated using two public datasets from the 2015 Ischemic Stroke Lesion Segmentation challenge (ISLES 2015). These involve the tasks of sub-acute stroke lesion segmentation (SISS) and acute stroke penumbra estimation (SPES) from multiple diffusion, perfusion and anatomical MRI modalities. The performance is compared against state-of-the-art methods with a blind online testing set evaluation on each of the challenges. At the time of submitting this manuscript, our approach is the first method in the online rankings for the SISS (DSC=0.59 ± 0.31) and SPES sub-tasks (DSC=0.84 ± 0.10). When compared with the rest of submitted strategies, we achieve top rank performance with a lower Hausdorff distance. CONCLUSIONS Better segmentation results are obtained by leveraging the anatomy and pathophysiology of acute stroke lesions and using a combined approach to minimize the effects of class imbalance. The same training procedure is used for both tasks, showing the proposed methodology can generalize well enough to deal with different unrelated tasks and imaging modalities without hyper-parameter tuning. In order to promote the reproducibility of our results, a public version of the proposed method has been released to the scientific community.
Collapse
Affiliation(s)
- Albert Clèrigues
- Institute of Computer Vision and Robotics, University of Girona, P-IV, Campus Montilivi, 17003 Girona Spain.
| | - Sergi Valverde
- Institute of Computer Vision and Robotics, University of Girona, P-IV, Campus Montilivi, 17003 Girona Spain
| | - Jose Bernal
- Institute of Computer Vision and Robotics, University of Girona, P-IV, Campus Montilivi, 17003 Girona Spain
| | - Jordi Freixenet
- Institute of Computer Vision and Robotics, University of Girona, P-IV, Campus Montilivi, 17003 Girona Spain
| | - Arnau Oliver
- Institute of Computer Vision and Robotics, University of Girona, P-IV, Campus Montilivi, 17003 Girona Spain
| | - Xavier Lladó
- Institute of Computer Vision and Robotics, University of Girona, P-IV, Campus Montilivi, 17003 Girona Spain
| |
Collapse
|
30
|
Ischemic stroke lesion detection, characterization and classification in CT images with optimal features selection. Biomed Eng Lett 2020; 10:333-344. [PMID: 32864172 DOI: 10.1007/s13534-020-00158-5] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/03/2019] [Revised: 05/05/2020] [Accepted: 05/13/2020] [Indexed: 01/16/2023] Open
Abstract
Ischemic stroke is the dominant disorder for mortality and morbidity. For immediate diagnosis and treatment plan of ischemic stroke, computed tomography (CT) images are used. This paper proposes a histogram bin based novel algorithm to segment the ischemic stroke lesion using CT and optimal feature group selection to classify normal and abnormal regions. Steps followed are pre-processing, segmentation, extracting texture features, feature ranking, feature grouping, classification and optimal feature group (FG) selection. The first order features, gray level run length matrix features, gray level co-occurrence matrix features and Hu's moment features are extracted. Classification is done using logistic regression (LR), support vector machine classifier (SVMC), random forest classifier (RFC) and neural network classifier (NNC). This proposed approach effectively detects ischemic stroke lesion with a classification accuracy of 88.77%, 97.86%, 99.79% and 99.79% obtained by the LR, SVMC, RFC and NNC when FG12 is opted, which is validated by fourfold cross validation.
Collapse
|
31
|
Li P, Zhou J, Li W, Wu H, Hu J, Ding Q, Lü S, Pan J, Zhang C, Li N, Long M. Characterizing liver sinusoidal endothelial cell fenestrae on soft substrates upon AFM imaging and deep learning. Biochim Biophys Acta Gen Subj 2020; 1864:129702. [PMID: 32814074 DOI: 10.1016/j.bbagen.2020.129702] [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: 04/13/2020] [Revised: 07/02/2020] [Accepted: 08/02/2020] [Indexed: 02/06/2023]
Abstract
BACKGROUND Liver sinusoidal endothelial cells (LSECs) display unique fenestrated morphology. Alterations in the size and number of fenestrae play a crucial role in the progression of various liver diseases. While their features have been visualized using atomic force microscopy (AFM), the in situ imaging methods and off-line analyses are further required for fenestra quantification. METHODS Primary mouse LSECs were cultured on a collagen-I-coated culture dish, or a polydimethylsiloxane (PDMS) or polyacrylamide (PA) hydrogel substrate. An AFM contact mode was applied to visualize fenestrae on individual fixed LSECs. Collected images were analyzed using an in-house developed image recognition program based on fully convolutional networks (FCN). RESULTS Key scanning parameters were first optimized for visualizing the fenestrae on LSECs on culture dish, which was also applicable for the LSECs cultured on various hydrogels. The intermediate-magnification morphology images of LSECs were used for developing the FCN-based, fenestra recognition program. This program enabled us to recognize the vast majority of fenestrae from AFM images after twice trainings at a typical accuracy of 81.6% on soft substrate and also quantify the statistics of porosity, number of fenestrae and distribution of fenestra diameter. CONCLUSIONS Combining AFM imaging with FCN training is able to quantify the morphological distributions of LSEC fenestrae on various substrates. SIGNIFICANCE AFM images acquired and analyzed here provided the global information of surface ultramicroscopic structures over an entire cell, which is fundamental in understanding their regulatory mechanisms and pathophysiological relevance in fenestra-like evolution of individual cells on stiffness-varied substrates.
Collapse
Affiliation(s)
- Peiwen Li
- School of Life Science, Beijing Institute of Technology, Beijing 10081, China; Center for Biomechanics and Bioengineering, Key Laboratory of Microgravity (National Microgravity Laboratory), and Beijing Key Laboratory of Engineered Construction and Mechanobiology, Institute of Mechanics, Chinese Academy of Sciences, Beijing 100190, China
| | - Jin Zhou
- Center for Biomechanics and Bioengineering, Key Laboratory of Microgravity (National Microgravity Laboratory), and Beijing Key Laboratory of Engineered Construction and Mechanobiology, Institute of Mechanics, Chinese Academy of Sciences, Beijing 100190, China
| | - Wang Li
- Center for Biomechanics and Bioengineering, Key Laboratory of Microgravity (National Microgravity Laboratory), and Beijing Key Laboratory of Engineered Construction and Mechanobiology, Institute of Mechanics, Chinese Academy of Sciences, Beijing 100190, China; School of Engineering Sciences, University of Chinese Academy of Sciences, Beijing 100049, China
| | - Huan Wu
- Center for Biomechanics and Bioengineering, Key Laboratory of Microgravity (National Microgravity Laboratory), and Beijing Key Laboratory of Engineered Construction and Mechanobiology, Institute of Mechanics, Chinese Academy of Sciences, Beijing 100190, China; Key Laboratory of Biorheological Science and Technology (Chongqing University), Ministry of Education, Chongqing 400044, China
| | - Jinrong Hu
- Center for Biomechanics and Bioengineering, Key Laboratory of Microgravity (National Microgravity Laboratory), and Beijing Key Laboratory of Engineered Construction and Mechanobiology, Institute of Mechanics, Chinese Academy of Sciences, Beijing 100190, China
| | - Qihan Ding
- Center for Biomechanics and Bioengineering, Key Laboratory of Microgravity (National Microgravity Laboratory), and Beijing Key Laboratory of Engineered Construction and Mechanobiology, Institute of Mechanics, Chinese Academy of Sciences, Beijing 100190, China; School of Engineering Sciences, University of Chinese Academy of Sciences, Beijing 100049, China
| | - Shouqin Lü
- Center for Biomechanics and Bioengineering, Key Laboratory of Microgravity (National Microgravity Laboratory), and Beijing Key Laboratory of Engineered Construction and Mechanobiology, Institute of Mechanics, Chinese Academy of Sciences, Beijing 100190, China; School of Engineering Sciences, University of Chinese Academy of Sciences, Beijing 100049, China
| | - Jun Pan
- Key Laboratory of Biorheological Science and Technology (Chongqing University), Ministry of Education, Chongqing 400044, China
| | - Chunyu Zhang
- School of Life Science, Beijing Institute of Technology, Beijing 10081, China.
| | - Ning Li
- Center for Biomechanics and Bioengineering, Key Laboratory of Microgravity (National Microgravity Laboratory), and Beijing Key Laboratory of Engineered Construction and Mechanobiology, Institute of Mechanics, Chinese Academy of Sciences, Beijing 100190, China; School of Engineering Sciences, University of Chinese Academy of Sciences, Beijing 100049, China.
| | - Mian Long
- Center for Biomechanics and Bioengineering, Key Laboratory of Microgravity (National Microgravity Laboratory), and Beijing Key Laboratory of Engineered Construction and Mechanobiology, Institute of Mechanics, Chinese Academy of Sciences, Beijing 100190, China; School of Engineering Sciences, University of Chinese Academy of Sciences, Beijing 100049, China.
| |
Collapse
|
32
|
Lee AR, Woo I, Kang DW, Jung SC, Lee H, Kim N. Fully automated segmentation on brain ischemic and white matter hyperintensities lesions using semantic segmentation networks with squeeze-and-excitation blocks in MRI. INFORMATICS IN MEDICINE UNLOCKED 2020. [DOI: 10.1016/j.imu.2020.100440] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022] Open
|
33
|
Vupputuri A, Ashwal S, Tsao B, Ghosh N. Ischemic stroke segmentation in multi-sequence MRI by symmetry determined superpixel based hierarchical clustering. Comput Biol Med 2019; 116:103536. [PMID: 31783255 DOI: 10.1016/j.compbiomed.2019.103536] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2019] [Revised: 11/07/2019] [Accepted: 11/07/2019] [Indexed: 02/02/2023]
Abstract
Automated estimation of ischemic stroke evolution across different brain anatomical regions has immense potential to revolutionize stroke treatment. Multi-sequence Magnetic Resonance Imaging (MRI) techniques provide information to characterize abnormal tissues based on their anatomy and physical properties. Asymmetry of the right and left hemispheres of the brain is an important cue for abnormality estimation but using it alone is susceptible to occasional error due to self-asymmetry of the brain. A precise estimate of the symmetry axis is therefore essential for accurate asymmetry identification, which holds the key to the proposed method. The proposed symmetry determined superpixel based hierarchical clustering (SSHC) method initially estimates the lesion from inter-hemispheric asymmetry. This asymmetry further determines the thresholding parameter for hierarchically clustering the superpixels leading to an automated and accurate lesion delineation. A multi-sequence MRI based pipeline also combines the estimations from individual sequences. SSHC is evaluated on different sequences of the Loma Linda University (LLU) dataset with 26 patients and the Ischemic Stroke Lesion Segmentation (ISLES'15) dataset with 28 patients. SSHC eliminates the need for manual determination of threshold for combining the superpixel clusters and is more reliable as it derives the information from the quick estimation of asymmetry. SSHC outperforms the state-of-the-art resulting in a high Dice similarity score of 0.704±0.27 and a recall of 0.85±0.01 which are 6% and 35% respectively higher than the challenge winning method. SSHC thus demonstrates a promising potential in the automated detection of (sub-)acute adult ischemic stroke.
Collapse
Affiliation(s)
- Anusha Vupputuri
- Department of Electrical Engineering, Indian Institute of Technology, Kharagpur, 721302, India.
| | - Stephen Ashwal
- Department of Pediatrics, Loma Linda University, Loma Linda, CA, 92354, USA.
| | - Bryan Tsao
- Department of Neurology, Loma Linda University, Loma Linda, CA, 92354, USA.
| | - Nirmalya Ghosh
- Department of Electrical Engineering, Indian Institute of Technology, Kharagpur, 721302, India.
| |
Collapse
|