1
|
Chen S, Duan J, Zhang N, Qi M, Li J, Wang H, Wang R, Ju R, Duan Y, Qi S. MSA-YOLOv5: Multi-scale attention-based YOLOv5 for automatic detection of acute ischemic stroke from multi-modality MRI images. Comput Biol Med 2023; 165:107471. [PMID: 37716245 DOI: 10.1016/j.compbiomed.2023.107471] [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: 05/12/2023] [Revised: 09/02/2023] [Accepted: 09/04/2023] [Indexed: 09/18/2023]
Abstract
BACKGROUND AND OBJECTIVE Acute ischemic stroke (AIS) is a common neurological disorder characterized by the sudden onset of cerebral ischemia, leading to functional impairments. Swift and precise detection of AIS lesions is crucial for stroke diagnosis and treatment but poses a significant challenge. This study aims to leverage multimodal fusion technology to combine complementary information from various modalities, thereby enhancing the detection performance of AIS target detection models. METHODS In this retrospective study of AIS, we collected data from 316 AIS patients and created a multi-modality magnetic resonance imaging (MRI) dataset. We propose a Multi-Scale Attention-based YOLOv5 (MSA-YOLOv5), targeting challenges such as small lesion size and blurred borders at low resolutions. Specifically, we augment YOLOv5 with a prediction head to detect objects at various scales. Next, we replace the original prediction head with a Multi-Scale Swin Transformer Prediction Head (MS-STPH), which reduces computational complexity to linear levels and enhances the ability to detect small lesions. We incorporate a Second-Order channel attention (SOCA) module to adaptively rescale channel features by employing second-order feature statistics for more discriminative representations. Finally, we further validate the effectiveness of our method using the ISLES 2022 dataset. RESULTS On our in-house AIS dataset, MSA-YOLOv5 achieves a 79.0% mAP0.5, substantially surpassing other single-stage models. Compared to two-stage models, it maintains a comparable performance level while significantly reducing the number of parameters and resolution. On the ISLES 2022 dataset, MSA-YOLOv5 attains an 80.0% mAP0.5, outperforming other network models by a considerable margin. MS-STPH and SOCA modules can significantly increase mAP0.5 by 2.7% and 1.9%, respectively. Visualization interpretability results show that the proposed MSA-YOLOv5 restricts high attention in the small regions of AIS lesions. CONCLUSIONS The proposed MSA-YOLOv5 is capable of automatically and effectively detecting acute ischemic stroke lesions in multimodal images, particularly for small lesions and artifacts. Our enhanced model reduces the number of parameters while improving detection accuracy. This model can potentially assist radiologists in providing more accurate diagnosis, and enable clinicians to develop better treatment plans.
Collapse
Affiliation(s)
- Shannan Chen
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China; Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, China.
| | - Jinfeng Duan
- Department of Cardiovascular Surgery, General Hospital of Northern Theater Command, Shenyang, China; Postgraduate College, China Medical University, Shenyang, China.
| | - Nan Zhang
- Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China.
| | - Miao Qi
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China; Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China.
| | - Jinze Li
- Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China.
| | - Hong Wang
- Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China.
| | - Rongqiang Wang
- Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China.
| | - Ronghui Ju
- Department of Radiology, The People's Hospital of Liaoning Province, Shenyang, China.
| | - Yang Duan
- Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China.
| | - Shouliang Qi
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China; Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, China.
| |
Collapse
|
2
|
Wu G, Chen X, Lin J, Wang Y, Yu J. Identification of invisible ischemic stroke in noncontrast CT based on novel two-stage convolutional neural network model. Med Phys 2021; 48:1262-1275. [PMID: 33378585 DOI: 10.1002/mp.14691] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2020] [Revised: 10/12/2020] [Accepted: 12/22/2020] [Indexed: 11/12/2022] Open
Abstract
PURPOSE Early identification of ischemic stroke lesion regions plays a vital role in its treatments like thrombolytic therapy and patients' recovery. Noncontrast computed tomography (ncCT) is the most widespread imaging modality in emergency departments. Unfortunately, it is extremely hard to distinguish the lesion from healthy tissue during the hyper-acute phase of stroke. In this paper, a two-stage convolutional neural network-based method was proposed to identify the invisible ischemic stroke from ncCT. METHODS In order to combine the global and local information of images effectively, a cascaded structure with two coordinated networks was used to detect the suspicious stroke regions on the whole and optimize the detailed localization. In the first stage, an end-to-end U-net with adaptive threshold was proposed to integrate global position, symmetry and gray texture information to detect the suspicious regions. After reducing the interference from most normal regions, a ResNet-based patch classification network was used to eliminate some false positive samples on suspicious regions by mining deeper image features, contributing to a more precise localization of stroke. Finally, a MAP model was used to optimize the result by combining the classification results of each patch with their spatial constraint information. RESULTS Three independent experiments, that is, training and testing on dataset from one hospital, on the combination of two, and on the two respectively, were performed on a total of 277 cases from two hospitals to validate the proposed model, The proposed method achieved identification accuracy of 91.89%, 87.21%, and 85.71% in the three experiments, and the final localization accuracy in terms of precise localization of stroke were 82.35%, 83.02%, and 81.40%, respectively, which indicated the robustness and clinical values of the method. CONCLUSIONS There are some deep image feature differences between stroke region and normal region on ncCT images. The proposed two-stage convolutional neural network model can well seize these features and use them to effectively identify and locate stroke.
Collapse
Affiliation(s)
- Guoqing Wu
- Department of Electronic Engineering, Fudan University, Shanghai, 200433, China
| | - Xi Chen
- Department of Electronic Engineering, Fudan University, Shanghai, 200433, China
| | - Jixian Lin
- Department of Neurology, Minhang Branch, Zhongshan Hospital, Fudan University, Shanghai, 200433, China
| | - Yuanyuan Wang
- KeyLaboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai, Department of Electronic Engineering, Fudan University, Shanghai, 200433, China
| | - Jinhua Yu
- KeyLaboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai, Department of Electronic Engineering, Fudan University, Shanghai, 200433, China
| |
Collapse
|
3
|
Yeo M, Tahayori B, Kok HK, Maingard J, Kutaiba N, Russell J, Thijs V, Jhamb A, Chandra RV, Brooks M, Barras CD, Asadi H. Review of deep learning algorithms for the automatic detection of intracranial hemorrhages on computed tomography head imaging. J Neurointerv Surg 2021; 13:369-378. [PMID: 33479036 DOI: 10.1136/neurintsurg-2020-017099] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/11/2020] [Revised: 12/05/2020] [Accepted: 12/09/2020] [Indexed: 02/06/2023]
Abstract
Artificial intelligence is a rapidly evolving field, with modern technological advances and the growth of electronic health data opening new possibilities in diagnostic radiology. In recent years, the performance of deep learning (DL) algorithms on various medical image tasks have continually improved. DL algorithms have been proposed as a tool to detect various forms of intracranial hemorrhage on non-contrast computed tomography (NCCT) of the head. In subtle, acute cases, the capacity for DL algorithm image interpretation support might improve the diagnostic yield of CT for detection of this time-critical condition, potentially expediting treatment where appropriate and improving patient outcomes. However, there are multiple challenges to DL algorithm implementation, such as the relative scarcity of labeled datasets, the difficulties in developing algorithms capable of volumetric medical image analysis, and the complex practicalities of deployment into clinical practice. This review examines the literature and the approaches taken in the development of DL algorithms for the detection of intracranial hemorrhage on NCCT head studies. Considerations in crafting such algorithms will be discussed, as well as challenges which must be overcome to ensure effective, dependable implementations as automated tools in a clinical setting.
Collapse
Affiliation(s)
- Melissa Yeo
- Melbourne Medical School, The University of Melbourne Faculty of Medicine Dentistry and Health Sciences, Melbourne, Victoria, Australia
| | - Bahman Tahayori
- Department of Biomedical Engineering, The University of Melbourne, Melbourne, Victoria, Australia.,IBM Research Australia, Melbourne, Victoria, Australia
| | - Hong Kuan Kok
- Department of Radiology, Northern Health, Epping, Victoria, Australia.,School of Medicine, Deakin University Faculty of Health, Burwood, Victoria, Australia
| | - Julian Maingard
- School of Medicine, Deakin University Faculty of Health, Burwood, Victoria, Australia.,Interventional Neuroradiology Unit, Monash Health, Clayton, Victoria, Australia
| | - Numan Kutaiba
- Department of Radiology, Austin Health, Heidelberg, Victoria, Australia
| | - Jeremy Russell
- Department of Neurosurgery, Austin Health, Heidelberg, Victoria, Australia
| | - Vincent Thijs
- Stroke Theme, Florey Institute of Neuroscience and Mental Health, Heidelberg, Victoria, Australia.,Department of Neurology, Austin Health, Heidelberg, Victoria, Australia
| | - Ashu Jhamb
- Department of Radiology, St Vincent's Hospital Melbourne Pty Ltd, Fitzroy, Victoria, Australia
| | - Ronil V Chandra
- Interventional Neuroradiology Unit, Monash Health, Clayton, Victoria, Australia.,Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, Victoria, Australia
| | - Mark Brooks
- Stroke Theme, Florey Institute of Neuroscience and Mental Health, Heidelberg, Victoria, Australia.,Interventional Neuroradiology Service, Austin Health, Heidelberg, Victoria, Australia
| | - Christen D Barras
- School of Medicine, The University of Adelaide, Adelaide, South Australia, Australia.,South Australian Health and Medical Research Institute, Adelaide, South Australia, Australia
| | - Hamed Asadi
- Stroke Theme, Florey Institute of Neuroscience and Mental Health, Heidelberg, Victoria, Australia.,Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, Victoria, Australia
| |
Collapse
|
4
|
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
|