1
|
Zhou Y, Jia G, Ren Y, Ren Y, Xiao Z, Wang Y. Advancing ASD identification with neuroimaging: a novel GARL methodology integrating Deep Q-Learning and generative adversarial networks. BMC Med Imaging 2024; 24:186. [PMID: 39054419 PMCID: PMC11270770 DOI: 10.1186/s12880-024-01360-y] [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: 12/26/2023] [Accepted: 07/08/2024] [Indexed: 07/27/2024] Open
Abstract
Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that affects an individual's behavior, speech, and social interaction. Early and accurate diagnosis of ASD is pivotal for successful intervention. The limited availability of large datasets for neuroimaging investigations, however, poses a significant challenge to the timely and precise identification of ASD. To address this problem, we propose a breakthrough approach, GARL, for ASD diagnosis using neuroimaging data. GARL innovatively integrates the power of GANs and Deep Q-Learning to augment limited datasets and enhance diagnostic precision. We utilized the Autistic Brain Imaging Data Exchange (ABIDE) I and II datasets and employed a GAN to expand these datasets, creating a more robust and diversified dataset for analysis. This approach not only captures the underlying sample distribution within ABIDE I and II but also employs deep reinforcement learning for continuous self-improvement, significantly enhancing the capability of the model to generalize and adapt. Our experimental results confirmed that GAN-based data augmentation effectively improved the performance of all prediction models on both datasets, with the combination of InfoGAN and DQN's GARL yielding the most notable improvement.
Collapse
Affiliation(s)
- Yujing Zhou
- Center for Sleep and Circadian Medicine, The Affiliated Brain Hospital, Guangzhou Medical University, Guangzhou, 510370, Guangdong, China
- Key Laboratory of Neurogenetics and Channelopathies of Guangdong Province and the Ministry of Education of China, Guangzhou Medical University, Guangzhou, 510260, Guangdong, China
| | - Guangbo Jia
- Shenzhen Mental Health Center & Shenzhen Kangning Hospital, Shenzhen, China
| | - Yingtong Ren
- Biomedical Engineering, Northeastern University, Shenyang, China
| | - Yingxin Ren
- Automation, Northeastern University, Shenyang, China
| | - Zhifeng Xiao
- China Nanhu Academy of Electronics And Information Technology, Jiaxing, China.
| | - Yinmei Wang
- Psychiatric Department of The Second Affiliated Hospital, School of Medicine, The Chinese University of Hong Kong, Shenzhen and Longgang District People's Hospital of Shenzhen, Shenzhen, 518172, China.
| |
Collapse
|
2
|
Sun P, Yang J, Tian X, Yuan G. Image fusion-based low-dose CBCT enhancement method for visualizing miniscrew insertion in the infrazygomatic crest. BMC Med Imaging 2024; 24:114. [PMID: 38760689 PMCID: PMC11100247 DOI: 10.1186/s12880-024-01289-2] [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: 03/04/2024] [Accepted: 05/03/2024] [Indexed: 05/19/2024] Open
Abstract
Digital dental technology covers oral cone-beam computed tomography (CBCT) image processing and low-dose CBCT dental applications. A low-dose CBCT image enhancement method based on image fusion is proposed to address the need for subzygomatic small screw insertion. Specifically, firstly, a sharpening correction module is proposed, where the CBCT image is sharpened to compensate for the loss of details in the underexposed/over-exposed region. Secondly, a visibility restoration module based on type II fuzzy sets is designed, and a contrast enhancement module using curve transformation is designed. In addition to this, we propose a perceptual fusion module that fuses visibility and contrast of oral CBCT images. As a result, the problems of overexposure/underexposure, low visibility, and low contrast that occur in oral CBCT images can be effectively addressed with consistent interpretability. The proposed algorithm was analyzed in comparison experiments with a variety of algorithms, as well as ablation experiments. After analysis, compared with advanced enhancement algorithms, this algorithm achieved excellent results in low-dose CBCT enhancement and effective observation of subzygomatic small screw implantation. Compared with the best performing method, the evaluation metric is 0.07-2 higher on both datasets. The project can be found at: https://github.com/sunpeipei2024/low-dose-CBCT .
Collapse
Affiliation(s)
- Peipei Sun
- State Key Laboratory of Oral & Maxillofacial Reconstruction and Regeneration, Key Laboratory of Oral Biomedicine Ministry of Education, Hubei Key Laboratory of Stomatology, School & Hospital of Stomatology, Wuhan University, Wuhan, China
- Department of Pediatric Dentistry, School and Hospital of Stomatology, Wuhan University, Wuhan, China
| | - Jinghui Yang
- State Key Laboratory of Oral & Maxillofacial Reconstruction and Regeneration, Key Laboratory of Oral Biomedicine Ministry of Education, Hubei Key Laboratory of Stomatology, School & Hospital of Stomatology, Wuhan University, Wuhan, China
- Department of Pediatric Dentistry, School and Hospital of Stomatology, Wuhan University, Wuhan, China
| | - Xue Tian
- State Key Laboratory of Oral & Maxillofacial Reconstruction and Regeneration, Key Laboratory of Oral Biomedicine Ministry of Education, Hubei Key Laboratory of Stomatology, School & Hospital of Stomatology, Wuhan University, Wuhan, China
- Department of Pediatric Dentistry, School and Hospital of Stomatology, Wuhan University, Wuhan, China
| | - Guohua Yuan
- State Key Laboratory of Oral & Maxillofacial Reconstruction and Regeneration, Key Laboratory of Oral Biomedicine Ministry of Education, Hubei Key Laboratory of Stomatology, School & Hospital of Stomatology, Wuhan University, Wuhan, China.
- Department of Pediatric Dentistry, School and Hospital of Stomatology, Wuhan University, Wuhan, China.
- Frontier Science Center for Immunology and Metabolism, Wuhan University, Wuhan, China.
| |
Collapse
|
3
|
Zhang K, Liang W, Cao P, Liu X, Yang J, Zaiane O. Label correlation guided discriminative label feature learning for multi-label chest image classification. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 245:108032. [PMID: 38244339 DOI: 10.1016/j.cmpb.2024.108032] [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: 11/12/2023] [Revised: 01/02/2024] [Accepted: 01/12/2024] [Indexed: 01/22/2024]
Abstract
BACKGROUND AND OBJECTIVE Multi-label Chest X-ray (CXR) images often contain rich label relationship information, which is beneficial to improve classification performance. However, because of the intricate relationships among labels, most existing works fail to effectively learn and make full use of the label correlations, resulting in limited classification performance. In this study, we propose a multi-label learning framework that learns and leverages the label correlations to improve multi-label CXR image classification. METHODS In this paper, we capture the global label correlations through the self-attention mechanism. Meanwhile, to better utilize label correlations for guiding feature learning, we decompose the image-level features into label-level features. Furthermore, we enhance label-level feature learning in an end-to-end manner by a consistency constraint between global and local label correlations, and a label correlation guided multi-label supervised contrastive loss. RESULTS To demonstrate the superior performance of our proposed approach, we conduct three times 5-fold cross-validation experiments on the CheXpert dataset. Our approach obtains an average F1 score of 44.6% and an AUC of 76.5%, achieving a 7.7% and 1.3% improvement compared to the state-of-the-art results. CONCLUSION More accurate label correlations and full utilization of the learned label correlations help learn more discriminative label-level features. Experimental results demonstrate that our approach achieves exceptionally competitive performance compared to the state-of-the-art algorithms.
Collapse
Affiliation(s)
- Kai Zhang
- Computer Science and Engineering, Northeastern University, Shenyang, China
| | - Wei Liang
- Computer Science and Engineering, Northeastern University, Shenyang, China
| | - Peng Cao
- Computer Science and Engineering, Northeastern University, Shenyang, China; Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education, Northeastern University, Shenyang, China; National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Shenyang, China.
| | - Xiaoli Liu
- DAMO Academy, Alibaba Group, Hangzhou, China
| | - Jinzhu Yang
- Computer Science and Engineering, Northeastern University, Shenyang, China; Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education, Northeastern University, Shenyang, China; National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Shenyang, China
| | - Osmar Zaiane
- Alberta Machine Intelligence Institute, University of Alberta, Edmonton, Alberta, Canada
| |
Collapse
|
4
|
Mun C, Ha H, Lee O, Cheon M. Enhancing AI-CDSS with U-AnoGAN: Tackling data imbalance. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 244:107954. [PMID: 38041995 DOI: 10.1016/j.cmpb.2023.107954] [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: 09/25/2023] [Revised: 11/12/2023] [Accepted: 11/25/2023] [Indexed: 12/04/2023]
Abstract
BACKGROUND AND OBJECTIVE Clinical Decision Support Systems (CDSS) have substantially evolved, aiding healthcare professionals in informed patient care decision-making. The integration of AI, encompassing machine learning and natural language processing, has notably enhanced the capabilities of CDSS. However, a significant challenge remains in addressing data imbalance and the black box nature of AI algorithms, particularly for rare diseases or underrepresented demographic groups. This study aims to propose a model, U-AnoGAN, designed to overcome these hurdles and augment the diagnostic accuracy of AI-integrated CDSS. METHODS The U-AnoGAN was trained using masks derived from normal data, focusing on the Covid-19 and pneumonia datasets. Anomaly scores were calculated to assess the model's performance compared to existing AnoGAN-related algorithms. The study also evaluated the model's interpretability through the visualization of abnormal regions. RESULTS The results indicated that U-AnoGAN surpassed its counterparts in performance and interpretability. It effectively addressed the data imbalance problem by necessitating only normal data and showcased enhanced diagnostic accuracy. Precision, sensitivity, and specificity values reflected U-AnoGAN's superior capability in accurate disease prediction, diagnosis, treatment recommendations, and adverse event detection. CONCLUSIONS U-AnoGAN significantly bolsters the predictive power of AI-integrated CDSS, enabling more precise and timely diagnoses while providing better visualization to potentially overcome the black box problem. This model presents tremendous potential in elevating patient care with advanced AI tools and fostering more accurate and effective decision-making in healthcare environments. As the healthcare sector grapples with escalating data complexity and volume, the importance of models like U-AnoGAN in enhancing CDSS cannot be overstated.
Collapse
Affiliation(s)
- Changbae Mun
- Korea Institute of Science and Technology (KIST), 5, Hwarang-ro 14-gil Seongbuk-gu Seoul, 02792, Republic of Korea
| | - Hyodong Ha
- Hanyang Women's University, 200, Salgoji-gil, Seongdong-gu, Seoul 04763, Republic of Korea
| | - Ook Lee
- Hanyang University, 222, Wangsimni-ro, Seongdong-gu, Seoul 04763, Republic of Korea
| | - Minjong Cheon
- Hanyang Cyber University, 220, Wangsimni-ro, Seongdong-gu, Seoul 04763, Republic of Korea.
| |
Collapse
|
5
|
Gerbasi A, Dagliati A, Albi G, Chiesa M, Andreini D, Baggiano A, Mushtaq S, Pontone G, Bellazzi R, Colombo G. CAD-RADS scoring of coronary CT angiography with Multi-Axis Vision Transformer: A clinically-inspired deep learning pipeline. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 244:107989. [PMID: 38141455 DOI: 10.1016/j.cmpb.2023.107989] [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: 08/26/2023] [Revised: 11/10/2023] [Accepted: 12/17/2023] [Indexed: 12/25/2023]
Abstract
BACKGROUND AND OBJECTIVE The standard non-invasive imaging technique used to assess the severity and extent of Coronary Artery Disease (CAD) is Coronary Computed Tomography Angiography (CCTA). However, manual grading of each patient's CCTA according to the CAD-Reporting and Data System (CAD-RADS) scoring is time-consuming and operator-dependent, especially in borderline cases. This work proposes a fully automated, and visually explainable, deep learning pipeline to be used as a decision support system for the CAD screening procedure. The pipeline performs two classification tasks: firstly, identifying patients who require further clinical investigations and secondly, classifying patients into subgroups based on the degree of stenosis, according to commonly used CAD-RADS thresholds. METHODS The pipeline pre-processes multiplanar projections of the coronary arteries, extracted from the original CCTAs, and classifies them using a fine-tuned Multi-Axis Vision Transformer architecture. With the aim of emulating the current clinical practice, the model is trained to assign a per-patient score by stacking the bi-dimensional longitudinal cross-sections of the three main coronary arteries along channel dimension. Furthermore, it generates visually interpretable maps to assess the reliability of the predictions. RESULTS When run on a database of 1873 three-channel images of 253 patients collected at the Monzino Cardiology Center in Milan, the pipeline obtained an AUC of 0.87 and 0.93 for the two classification tasks, respectively. CONCLUSION According to our knowledge, this is the first model trained to assign CAD-RADS scores learning solely from patient scores and not requiring finer imaging annotation steps that are not part of the clinical routine.
Collapse
Affiliation(s)
- Alessia Gerbasi
- Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Via Ferrata 5, Pavia, Italy.
| | - Arianna Dagliati
- Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Via Ferrata 5, Pavia, Italy
| | - Giuseppe Albi
- Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Via Ferrata 5, Pavia, Italy
| | | | - Daniele Andreini
- Centro Cardiologico Monzino IRCCS, Milan, Italy; Department of Biomedical and Clinical Sciences, University of Milan, Milan, Italy
| | - Andrea Baggiano
- Centro Cardiologico Monzino IRCCS, Milan, Italy; Department of Clinical Sciences and Community Health, University of Milan, Milan, Italy
| | | | - Gianluca Pontone
- Centro Cardiologico Monzino IRCCS, Milan, Italy; Department of Biomedical, Surgical and Dental Sciences, University of Milan, Milan, Italy
| | - Riccardo Bellazzi
- Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Via Ferrata 5, Pavia, Italy; IRCCS Istituti Clinici Scientifici Maugeri, Pavia, Pavia, Italy
| | | |
Collapse
|
6
|
Zhang W, Zhao W, Li J, Zhuang P, Sun H, Xu Y, Li C. CVANet: Cascaded visual attention network for single image super-resolution. Neural Netw 2024; 170:622-634. [PMID: 38056409 DOI: 10.1016/j.neunet.2023.11.049] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Revised: 09/27/2023] [Accepted: 11/22/2023] [Indexed: 12/08/2023]
Abstract
Deep convolutional neural networks (DCNNs) have exhibited excellent feature extraction and detail reconstruction capabilities for single image super-resolution (SISR). Nevertheless, most previous DCNN-based methods do not fully utilize the complementary strengths between feature maps, channels, and pixels. Therefore, it hinders the ability of DCNNs to represent abundant features. To tackle the aforementioned issues, we present a Cascaded Visual Attention Network for SISR called CVANet, which simulates the visual attention mechanism of the human eyes to focus on the reconstruction process of details. Specifically, we first designed a trainable feature attention module (FAM) for feature-level attention learning. Afterward, we introduce a channel attention module (CAM) to reinforce feature maps under channel-level attention learning. Meanwhile, we propose a pixel attention module (PAM) that adaptively selects representative features from the previous layers, which are utilized to generate a high-resolution image. Satisfactory, our CVANet can effectively improve the resolution of images by exploring the feature representation capabilities of different modules and the visual perception properties of the human eyes. Extensive experiments with different methods on four benchmarks demonstrate that our CVANet outperforms the state-of-the-art (SOTA) methods in subjective visual perception, PSNR, and SSIM.The code will be made available https://github.com/WilyZhao8/CVANet.
Collapse
Affiliation(s)
- Weidong Zhang
- School of Information Engineering, Henan Institute of Science and Technology, Xinxiang, 453003, China
| | - Wenyi Zhao
- School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, 100876, China.
| | - Jia Li
- School of Information Engineering, Henan Institute of Science and Technology, Xinxiang, 453003, China
| | - Peixian Zhuang
- School of Automation and Electrical Engineering, University of Science and Technology Beijing, 100084, China
| | - Haihan Sun
- School of Engineering, University of Tasmania, Tasmania, 7005, Australia
| | - Yibo Xu
- School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, 100876, China
| | - Chongyi Li
- School of Computer Science, Nankai University, Tianjing, 300073, China
| |
Collapse
|
7
|
Zhang J, Wang Q, Wang X, Qiao L, Liu M. Preserving specificity in federated graph learning for fMRI-based neurological disorder identification. Neural Netw 2024; 169:584-596. [PMID: 37956575 DOI: 10.1016/j.neunet.2023.11.004] [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: 08/14/2023] [Revised: 10/22/2023] [Accepted: 11/03/2023] [Indexed: 11/15/2023]
Abstract
Resting-state functional magnetic resonance imaging (rs-fMRI) offers a non-invasive approach to examining abnormal brain connectivity associated with brain disorders. Graph neural network (GNN) gains popularity in fMRI representation learning and brain disorder analysis with powerful graph representation capabilities. Training a general GNN often necessitates a large-scale dataset from multiple imaging centers/sites, but centralizing multi-site data generally faces inherent challenges related to data privacy, security, and storage burden. Federated Learning (FL) enables collaborative model training without centralized multi-site fMRI data. Unfortunately, previous FL approaches for fMRI analysis often ignore site-specificity, including demographic factors such as age, gender, and education level. To this end, we propose a specificity-aware federated graph learning (SFGL) framework for rs-fMRI analysis and automated brain disorder identification, with a server and multiple clients/sites for federated model aggregation and prediction. At each client, our model consists of a shared and a personalized branch, where parameters of the shared branch are sent to the server while those of the personalized branch remain local. This can facilitate knowledge sharing among sites and also helps preserve site specificity. In the shared branch, we employ a spatio-temporal attention graph isomorphism network to learn dynamic fMRI representations. In the personalized branch, we integrate vectorized demographic information (i.e., age, gender, and education years) and functional connectivity networks to preserve site-specific characteristics. Representations generated by the two branches are then fused for classification. Experimental results on two fMRI datasets with a total of 1218 subjects suggest that SFGL outperforms several state-of-the-art approaches.
Collapse
Affiliation(s)
- Junhao Zhang
- School of Mathematics Science, Liaocheng University, Liaocheng, Shandong, 252000, China
| | - Qianqian Wang
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA
| | - Xiaochuan Wang
- School of Mathematics Science, Liaocheng University, Liaocheng, Shandong, 252000, China
| | - Lishan Qiao
- School of Mathematics Science, Liaocheng University, Liaocheng, Shandong, 252000, China; School of Computer Science and Technology, Shandong Jianzhu University, Jinan, Shandong, 250101, China.
| | - Mingxia Liu
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA.
| |
Collapse
|