1
|
Zhang X, Pan Y, Wu T, Zhao W, Zhang H, Ding J, Ji Q, Jia X, Li X, Lee Z, Zhang J, Bai L. Brain age prediction using interpretable multi-feature-based convolutional neural network in mild traumatic brain injury. Neuroimage 2024; 297:120751. [PMID: 39048043 DOI: 10.1016/j.neuroimage.2024.120751] [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: 07/15/2024] [Accepted: 07/22/2024] [Indexed: 07/27/2024] Open
Abstract
BACKGROUND Convolutional neural network (CNN) can capture the structural features changes of brain aging based on MRI, thus predict brain age in healthy individuals accurately. However, most studies use single feature to predict brain age in healthy individuals, ignoring adding information from multiple sources and the changes in brain aging patterns after mild traumatic brain injury (mTBI) were still unclear. METHODS Here, we leveraged the structural data from a large, heterogeneous dataset (N = 1464) to implement an interpretable 3D combined CNN model for brain-age prediction. In addition, we also built an atlas-based occlusion analysis scheme with a fine-grained human Brainnetome Atlas to reveal the age-sstratified contributed brain regions for brain-age prediction in healthy controls (HCs) and mTBI patients. The correlations between brain predicted age gaps (brain-PAG) following mTBI and individual's cognitive impairment, as well as the level of plasma neurofilament light were also examined. RESULTS Our model utilized multiple 3D features derived from T1w data as inputs, and reduced the mean absolute error (MAE) of age prediction to 3.08 years and improved Pearson's r to 0.97 on 154 HCs. The strong generalizability of our model was also validated across different centers. Regions contributing the most significantly to brain age prediction were the caudate and thalamus for HCs and patients with mTBI, and the contributive regions were mostly located in the subcortical areas throughout the adult lifespan. The left hemisphere was confirmed to contribute more in brain age prediction throughout the adult lifespan. Our research showed that brain-PAG in mTBI patients was significantly higher than that in HCs in both acute and chronic phases. The increased brain-PAG in mTBI patients was also highly correlated with cognitive impairment and a higher level of plasma neurofilament light, a marker of neurodegeneration. The higher brain-PAG and its correlation with severe cognitive impairment showed a longitudinal and persistent nature in patients with follow-up examinations. CONCLUSION We proposed an interpretable deep learning framework on a relatively large dataset to accurately predict brain age in both healthy individuals and mTBI patients. The interpretable analysis revealed that the caudate and thalamus became the most contributive role across the adult lifespan in both HCs and patients with mTBI. The left hemisphere contributed significantly to brain age prediction may enlighten us to be concerned about the lateralization of brain abnormality in neurological diseases in the future. The proposed interpretable deep learning framework might also provide hope for testing the performance of related drugs and treatments in the future.
Collapse
Affiliation(s)
- Xiang Zhang
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Yizhen Pan
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Tingting Wu
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Wenpu Zhao
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Haonan Zhang
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Jierui Ding
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Qiuyu Ji
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Xiaoyan Jia
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Xuan Li
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Zhiqi Lee
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China
| | - Jie Zhang
- Department of Radiation Medicine, School of Preventive Medicine, Air Force Medical University, Xi'an 710032, China.
| | - Lijun Bai
- The Key Laboratory of Biomedical Information Engineering, Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China.
| |
Collapse
|
2
|
Wu Y, Gao H, Zhang C, Ma X, Zhu X, Wu S, Lin L. Machine Learning and Deep Learning Approaches in Lifespan Brain Age Prediction: A Comprehensive Review. Tomography 2024; 10:1238-1262. [PMID: 39195728 PMCID: PMC11359833 DOI: 10.3390/tomography10080093] [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: 07/18/2024] [Revised: 08/09/2024] [Accepted: 08/09/2024] [Indexed: 08/29/2024] Open
Abstract
The concept of 'brain age', derived from neuroimaging data, serves as a crucial biomarker reflecting cognitive vitality and neurodegenerative trajectories. In the past decade, machine learning (ML) and deep learning (DL) integration has transformed the field, providing advanced models for brain age estimation. However, achieving precise brain age prediction across all ages remains a significant analytical challenge. This comprehensive review scrutinizes advancements in ML- and DL-based brain age prediction, analyzing 52 peer-reviewed studies from 2020 to 2024. It assesses various model architectures, highlighting their effectiveness and nuances in lifespan brain age studies. By comparing ML and DL, strengths in forecasting and methodological limitations are revealed. Finally, key findings from the reviewed articles are summarized and a number of major issues related to ML/DL-based lifespan brain age prediction are discussed. Through this study, we aim at the synthesis of the current state of brain age prediction, emphasizing both advancements and persistent challenges, guiding future research, technological advancements, and improving early intervention strategies for neurodegenerative diseases.
Collapse
Affiliation(s)
| | | | | | | | | | | | - Lan Lin
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing 100124, China; (Y.W.); (H.G.); (C.Z.); (X.M.); (X.Z.); (S.W.)
| |
Collapse
|
3
|
Nguyen H, Clément M, Mansencal B, Coupé P. Brain structure ages-A new biomarker for multi-disease classification. Hum Brain Mapp 2024; 45:e26558. [PMID: 38224546 PMCID: PMC10785199 DOI: 10.1002/hbm.26558] [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: 05/11/2023] [Revised: 11/20/2023] [Accepted: 11/25/2023] [Indexed: 01/17/2024] Open
Abstract
Age is an important variable to describe the expected brain's anatomy status across the normal aging trajectory. The deviation from that normative aging trajectory may provide some insights into neurological diseases. In neuroimaging, predicted brain age is widely used to analyze different diseases. However, using only the brain age gap information (i.e., the difference between the chronological age and the estimated age) can be not enough informative for disease classification problems. In this paper, we propose to extend the notion of global brain age by estimating brain structure ages using structural magnetic resonance imaging. To this end, an ensemble of deep learning models is first used to estimate a 3D aging map (i.e., voxel-wise age estimation). Then, a 3D segmentation mask is used to obtain the final brain structure ages. This biomarker can be used in several situations. First, it enables to accurately estimate the brain age for the purpose of anomaly detection at the population level. In this situation, our approach outperforms several state-of-the-art methods. Second, brain structure ages can be used to compute the deviation from the normal aging process of each brain structure. This feature can be used in a multi-disease classification task for an accurate differential diagnosis at the subject level. Finally, the brain structure age deviations of individuals can be visualized, providing some insights about brain abnormality and helping clinicians in real medical contexts.
Collapse
Affiliation(s)
- Huy‐Dung Nguyen
- Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800TalenceFrance
| | - Michaël Clément
- Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800TalenceFrance
| | - Boris Mansencal
- Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800TalenceFrance
| | - Pierrick Coupé
- Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800TalenceFrance
| |
Collapse
|
4
|
Peng S, Xu R, Wei K, Liu N, Lv Y, Lin Y. Association between kidney function and biological age: a China Health and Retirement Longitudinal Study. Front Public Health 2023; 11:1259074. [PMID: 38164447 PMCID: PMC10757928 DOI: 10.3389/fpubh.2023.1259074] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2023] [Accepted: 12/04/2023] [Indexed: 01/03/2024] Open
Abstract
Introduction The chronological age (CA) cannot precisely reflect the health status. Our study aimed to establish a model of kidney biological age to evaluate kidney function more elaborately. Methods The modeling group was used to establish the model, consisting of 1,303 respondents of the China Health and Retirement Longitudinal Study (CHARLS). The biological age of the kidney (BA) was constructed by principal component analysis (PCA) and Klemera and Doubal's method (KDM) with the 1,303 health respondents. Results PCA was chosen as the best method for our research step by step. The test group was used to apply the model. (a) BA of the kidney can distinguish respondents with from without kidney disease. (b) BA of the kidney was significantly different in various levels of kidney function. The BA of the eGFR <60 group and 60 ≤ eGFR <90 group were older than GFR ≥90 group. (c) The group with younger BA of kidney at baseline had a lower risk of kidney function decreased. (d) The risk of decreased kidney function caused by increasing BA every additional year is higher than CA. Discussion The BA of the kidney is a parameter negatively correlated with decreased kidney function and fills the blank of evaluation among people in the middle of heathy and kidney diseases.
Collapse
Affiliation(s)
- Shanshan Peng
- Department of Laboratory Medicine, Huashan Hospital, Fudan University, Shanghai, China
- Health Management Centre, Huashan Hospital, Fudan University, Shanghai, China
| | - Rui Xu
- Department of Rheumatology, Huashan Hospital, Fudan University, Shanghai, China
| | - Kai Wei
- Department of Laboratory Medicine, Huashan Hospital, Fudan University, Shanghai, China
| | - Na Liu
- Department of Laboratory Medicine, Huashan Hospital, Fudan University, Shanghai, China
| | - Yuan Lv
- Department of Laboratory Medicine, Huashan Hospital, Fudan University, Shanghai, China
| | - Yong Lin
- Department of Laboratory Medicine, Huashan Hospital, Fudan University, Shanghai, China
| |
Collapse
|
5
|
Kerber B, Hepp T, Küstner T, Gatidis S. Deep learning-based age estimation from clinical Computed Tomography image data of the thorax and abdomen in the adult population. PLoS One 2023; 18:e0292993. [PMID: 37934735 PMCID: PMC10629654 DOI: 10.1371/journal.pone.0292993] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Accepted: 10/03/2023] [Indexed: 11/09/2023] Open
Abstract
Aging is an important risk factor for disease, leading to morphological change that can be assessed on Computed Tomography (CT) scans. We propose a deep learning model for automated age estimation based on CT- scans of the thorax and abdomen generated in a clinical routine setting. These predictions could serve as imaging biomarkers to estimate a "biological" age, that better reflects a patient's true physical condition. A pre-trained ResNet-18 model was modified to predict chronological age as well as to quantify its aleatoric uncertainty. The model was trained using 1653 non-pathological CT-scans of the thorax and abdomen of subjects aged between 20 and 85 years in a 5-fold cross-validation scheme. Generalization performance as well as robustness and reliability was assessed on a publicly available test dataset consisting of thorax-abdomen CT-scans of 421 subjects. Score-CAM saliency maps were generated for interpretation of model outputs. We achieved a mean absolute error of 5.76 ± 5.17 years with a mean uncertainty of 5.01 ± 1.44 years after 5-fold cross-validation. A mean absolute error of 6.50 ± 5.17 years with a mean uncertainty of 6.39 ± 1.46 years was obtained on the test dataset. CT-based age estimation accuracy was largely uniform across all age groups and between male and female subjects. The generated saliency maps highlighted especially the lumbar spine and abdominal aorta. This study demonstrates, that accurate and generalizable deep learning-based automated age estimation is feasible using clinical CT image data. The trained model proved to be robust and reliable. Methods of uncertainty estimation and saliency analysis improved the interpretability.
Collapse
Affiliation(s)
- Bjarne Kerber
- Department of Diagnostic and Interventional Radiology, University Hospital Tuebingen, Tuebingen, Germany
| | - Tobias Hepp
- Max Planck Institute for Intelligent Systems, Tuebingen, Germany
| | - Thomas Küstner
- Department of Diagnostic and Interventional Radiology, University Hospital Tuebingen, Tuebingen, Germany
| | - Sergios Gatidis
- Department of Diagnostic and Interventional Radiology, University Hospital Tuebingen, Tuebingen, Germany
- Max Planck Institute for Intelligent Systems, Tuebingen, Germany
| |
Collapse
|
6
|
Ruprecht NA, Singhal S, Schaefer K, Gill JS, Bansal B, Sens D, Singhal SK. Establishing a genomic radiation-age association for space exploration supplements lung disease differentiation. Front Public Health 2023; 11:1161124. [PMID: 37250098 PMCID: PMC10213902 DOI: 10.3389/fpubh.2023.1161124] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2023] [Accepted: 04/07/2023] [Indexed: 05/31/2023] Open
Abstract
Purpose One possible way to quantify each individual's response or damage from ionizing radiation is to estimate their accelerated biological age following exposure. Since there is currently no definitive way to know if biological age estimations are accurate, we aim to establish a rad-age association using genomics as its foundation. Methods Two datasets were combined and used to empirically find the age cutoff between young and old patients. With age as both a categorical and continuous variable, two other datasets that included radiation exposure are used to test the interaction between radiation and age. The gene lists are oriented in preranked lists for both pathway and diseases analysis. Finally, these genes are used to evaluate another dataset on the clinical relevance in differentiating lung disease given ethnicity and sex using both pairwise t-tests and linear models. Results Using 12 well-known genes associated with aging, a threshold of 29-years-old was found to be the difference between young and old patients. The two interaction tests yielded 234 unique genes such that pathway analysis flagged IL-1 signaling and PRPP biosynthesis as significant with high cell proliferation diseases and carcinomas being a common trend. LAPTM4B was the only gene with significant interaction among lung disease, ethnicity, and sex, with fold change greater than two. Conclusion The results corroborate an initial association between radiation and age, given inflammation and metabolic pathways and multiple genes emphasizing mitochondrial function, oxidation, and histone modification. Being able to tie rad-age genes to lung disease supplements future work for risk assessment following radiation exposure.
Collapse
Affiliation(s)
- Nathan A. Ruprecht
- Department of Biomedical Engineering, University of North Dakota, Grand Forks, ND, United States
| | - Sonalika Singhal
- Department of Pathology, University of North Dakota, Grand Forks, ND, United States
| | - Kalli Schaefer
- Department of Biomedical Engineering, University of North Dakota, Grand Forks, ND, United States
| | - Jappreet S. Gill
- Department of Biomedical Engineering, University of North Dakota, Grand Forks, ND, United States
| | - Benu Bansal
- Department of Biomedical Engineering, University of North Dakota, Grand Forks, ND, United States
| | - Donald Sens
- Department of Pathology, University of North Dakota, Grand Forks, ND, United States
| | - Sandeep K. Singhal
- Department of Biomedical Engineering, University of North Dakota, Grand Forks, ND, United States
- Department of Pathology, University of North Dakota, Grand Forks, ND, United States
| |
Collapse
|
7
|
Kondou H, Morohashi R, Ichioka H, Bandou R, Matsunari R, Kawamoto M, Idota N, Ting D, Kimura S, Ikegaya H. Deep Neural Networks-Based Age Estimation of Cadavers Using CT Imaging of Vertebrae. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2023; 20:4806. [PMID: 36981720 PMCID: PMC10049236 DOI: 10.3390/ijerph20064806] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/16/2023] [Revised: 03/06/2023] [Accepted: 03/07/2023] [Indexed: 06/18/2023]
Abstract
Although age estimation upon death is important in the identification of unknown cadavers for forensic scientists, to the best of our knowledge, no study has examined the utility of deep neural network (DNN) models for age estimation among cadavers. We performed a postmortem computed tomography (CT) examination of 1000 and 500 male and female cadavers, respectively. These CT slices were converted into 3-dimensional images, and only the thoracolumbar region was extracted. Eighty percent of them were categorized as training datasets and the others as test datasets for both sexes. We fine-tuned the ResNet152 models using the training datasets. We conducted 4-fold cross-validation, and the mean absolute error (MAE) of the test datasets was calculated using the ensemble learning of four ResNet152 models. Consequently, the MAE of the male and female models was 7.25 and 7.16, respectively. Our study shows that DNN models can be useful tools in the field of forensic medicine.
Collapse
|
8
|
Wu F, Ma H, Guan Y, Tian L. Manifold-based unsupervised metric Learning, with applications in individualized predictions based on functional connectivity. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104081] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/15/2022]
|
9
|
Li Y, Zhang X, Nie J, Zhang G, Fang R, Xu X, Wu Z, Hu D, Wang L, Zhang H, Lin W, Li G. Brain Connectivity Based Graph Convolutional Networks and Its Application to Infant Age Prediction. IEEE TRANSACTIONS ON MEDICAL IMAGING 2022; 41:2764-2776. [PMID: 35500083 PMCID: PMC10041448 DOI: 10.1109/tmi.2022.3171778] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Infancy is a critical period for the human brain development, and brain age is one of the indices for the brain development status associated with neuroimaging data. The difference between the predicted age based on neuroimaging and the chronological age can provide an important early indicator of deviation from the normal developmental trajectory. In this study, we utilize the Graph Convolutional Network (GCN) to predict the infant brain age based on resting-state fMRI data. The brain connectivity obtained from rs-fMRI can be represented as a graph with brain regions as nodes and functional connections as edges. However, since the brain connectivity is a fully connected graph with features on edges, current GCN cannot be directly used for it is a node-based method for sparse graphs. Hence, we propose an edge-based Graph Path Convolution (GPC) method, which aggregates the information from different paths and can be naturally applied on dense graphs. We refer the whole model as Brain Connectivity Graph Convolutional Networks (BC-GCN). Further, two upgraded network structures are proposed by including the residual and attention modules, referred as BC-GCN-Res and BC-GCN-SE to emphasize the information of the original data and enhance influential channels. Moreover, we design a two-stage coarse-to-fine framework, which determines the age group first and then predicts the age using group-specific BC-GCN-SE models. To avoid accumulated errors from the first stage, a cross-group training strategy is adopted for the second stage regression models. We conduct experiments on infant fMRI scans from 6 to 811 days of age. The coarse-to-fine framework shows significant improvements when being applied to several models (reducing error over 10 days). Comparing with state-of-the-art methods, our proposed model BC-GCN-SE with coarse-to-fine framework reduces the mean absolute error of the prediction from >70 days to 49.9 days. The code is now available at https://github.com/SCUT-Xinlab/BC-GCN.
Collapse
|
10
|
He S, Feng Y, Grant PE, Ou Y. Deep Relation Learning for Regression and Its Application to Brain Age Estimation. IEEE TRANSACTIONS ON MEDICAL IMAGING 2022; 41:2304-2317. [PMID: 35320092 PMCID: PMC9782832 DOI: 10.1109/tmi.2022.3161739] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Most deep learning models for temporal regression directly output the estimation based on single input images, ignoring the relationships between different images. In this paper, we propose deep relation learning for regression, aiming to learn different relations between a pair of input images. Four non-linear relations are considered: "cumulative relation," "relative relation," "maximal relation" and "minimal relation." These four relations are learned simultaneously from one deep neural network which has two parts: feature extraction and relation regression. We use an efficient convolutional neural network to extract deep features from the pair of input images and apply a Transformer for relation learning. The proposed method is evaluated on a merged dataset with 6,049 subjects with ages of 0-97 years using 5-fold cross-validation for the task of brain age estimation. The experimental results have shown that the proposed method achieved a mean absolute error (MAE) of 2.38 years, which is lower than the MAEs of 8 other state-of-the-art algorithms with statistical significance (p<0.05) in paired T-test (two-side).
Collapse
|
11
|
He S, Grant PE, Ou Y. Global-Local Transformer for Brain Age Estimation. IEEE TRANSACTIONS ON MEDICAL IMAGING 2022; 41:213-224. [PMID: 34460370 PMCID: PMC9746186 DOI: 10.1109/tmi.2021.3108910] [Citation(s) in RCA: 36] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/13/2023]
Abstract
Deep learning can provide rapid brain age estimation based on brain magnetic resonance imaging (MRI). However, most studies use one neural network to extract the global information from the whole input image, ignoring the local fine-grained details. In this paper, we propose a global-local transformer, which consists of a global-pathway to extract the global-context information from the whole input image and a local-pathway to extract the local fine-grained details from local patches. The fine-grained information from the local patches are fused with the global-context information by the attention mechanism, inspired by the transformer, to estimate the brain age. We evaluate the proposed method on 8 public datasets with 8,379 healthy brain MRIs with the age range of 0-97 years. 6 datasets are used for cross-validation and 2 datasets are used for evaluating the generality. Comparing with other state-of-the-art methods, the proposed global-local transformer reduces the mean absolute error of the estimated ages to 2.70 years and increases the correlation coefficient of the estimated age and the chronological age to 0.9853. In addition, our proposed method provides regional information of which local patches are most informative for brain age estimation. Our source code is available on: https://github.com/shengfly/global-local-transformer.
Collapse
|
12
|
Thurzo A, Kosnáčová HS, Kurilová V, Kosmeľ S, Beňuš R, Moravanský N, Kováč P, Kuracinová KM, Palkovič M, Varga I. Use of Advanced Artificial Intelligence in Forensic Medicine, Forensic Anthropology and Clinical Anatomy. Healthcare (Basel) 2021; 9:1545. [PMID: 34828590 PMCID: PMC8619074 DOI: 10.3390/healthcare9111545] [Citation(s) in RCA: 26] [Impact Index Per Article: 8.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2021] [Revised: 11/10/2021] [Accepted: 11/10/2021] [Indexed: 12/11/2022] Open
Abstract
Three-dimensional convolutional neural networks (3D CNN) of artificial intelligence (AI) are potent in image processing and recognition using deep learning to perform generative and descriptive tasks. Compared to its predecessor, the advantage of CNN is that it automatically detects the important features without any human supervision. 3D CNN is used to extract features in three dimensions where input is a 3D volume or a sequence of 2D pictures, e.g., slices in a cone-beam computer tomography scan (CBCT). The main aim was to bridge interdisciplinary cooperation between forensic medical experts and deep learning engineers, emphasizing activating clinical forensic experts in the field with possibly basic knowledge of advanced artificial intelligence techniques with interest in its implementation in their efforts to advance forensic research further. This paper introduces a novel workflow of 3D CNN analysis of full-head CBCT scans. Authors explore the current and design customized 3D CNN application methods for particular forensic research in five perspectives: (1) sex determination, (2) biological age estimation, (3) 3D cephalometric landmark annotation, (4) growth vectors prediction, (5) facial soft-tissue estimation from the skull and vice versa. In conclusion, 3D CNN application can be a watershed moment in forensic medicine, leading to unprecedented improvement of forensic analysis workflows based on 3D neural networks.
Collapse
Affiliation(s)
- Andrej Thurzo
- Department of Stomatology and Maxillofacial Surgery, Faculty of Medicine, Comenius University in Bratislava, 81250 Bratislava, Slovakia
- Department of Simulation and Virtual Medical Education, Faculty of Medicine, Comenius University, Sasinkova 4, 81272 Bratislava, Slovakia;
- forensic.sk Institute of Forensic Medical Analyses Ltd., Boženy Němcovej 8, 81104 Bratislava, Slovakia; (R.B.); (N.M.); (P.K.)
| | - Helena Svobodová Kosnáčová
- Department of Simulation and Virtual Medical Education, Faculty of Medicine, Comenius University, Sasinkova 4, 81272 Bratislava, Slovakia;
- Department of Genetics, Cancer Research Institute, Biomedical Research Center, Slovak Academy Sciences, Dúbravská Cesta 9, 84505 Bratislava, Slovakia
| | - Veronika Kurilová
- Faculty of Electrical Engineering and Information Technology, Slovak University of Technology, Ilkovičova 3, 81219 Bratislava, Slovakia;
| | - Silvester Kosmeľ
- Deep Learning Engineering Department at Cognexa, Faculty of Informatics and Information Technologies, Slovak University of Technology, Ilkovičova 2, 84216 Bratislava, Slovakia;
| | - Radoslav Beňuš
- forensic.sk Institute of Forensic Medical Analyses Ltd., Boženy Němcovej 8, 81104 Bratislava, Slovakia; (R.B.); (N.M.); (P.K.)
- Department of Anthropology, Faculty of Natural Sciences, Comenius University in Bratislava, Mlynská dolina Ilkovičova 6, 84215 Bratislava, Slovakia
| | - Norbert Moravanský
- forensic.sk Institute of Forensic Medical Analyses Ltd., Boženy Němcovej 8, 81104 Bratislava, Slovakia; (R.B.); (N.M.); (P.K.)
- Institute of Forensic Medicine, Faculty of Medicine, Comenius University in Bratislava, Sasinkova 4, 81108 Bratislava, Slovakia
| | - Peter Kováč
- forensic.sk Institute of Forensic Medical Analyses Ltd., Boženy Němcovej 8, 81104 Bratislava, Slovakia; (R.B.); (N.M.); (P.K.)
- Department of Criminal Law and Criminology, Faculty of Law Trnava University, Kollárova 10, 91701 Trnava, Slovakia
| | - Kristína Mikuš Kuracinová
- Institute of Pathological Anatomy, Faculty of Medicine, Comenius University in Bratislava, Sasinkova 4, 81108 Bratislava, Slovakia; (K.M.K.); (M.P.)
| | - Michal Palkovič
- Institute of Pathological Anatomy, Faculty of Medicine, Comenius University in Bratislava, Sasinkova 4, 81108 Bratislava, Slovakia; (K.M.K.); (M.P.)
- Forensic Medicine and Pathological Anatomy Department, Health Care Surveillance Authority (HCSA), Sasinkova 4, 81108 Bratislava, Slovakia
| | - Ivan Varga
- Institute of Histology and Embryology, Faculty of Medicine, Comenius University in Bratislava, 81372 Bratislava, Slovakia;
| |
Collapse
|
13
|
Sudarshan VP, Upadhyay U, Egan GF, Chen Z, Awate SP. Towards lower-dose PET using physics-based uncertainty-aware multimodal learning with robustness to out-of-distribution data. Med Image Anal 2021; 73:102187. [PMID: 34348196 DOI: 10.1016/j.media.2021.102187] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2020] [Revised: 07/12/2021] [Accepted: 07/16/2021] [Indexed: 10/20/2022]
Abstract
Radiation exposure in positron emission tomography (PET) imaging limits its usage in the studies of radiation-sensitive populations, e.g., pregnant women, children, and adults that require longitudinal imaging. Reducing the PET radiotracer dose or acquisition time reduces photon counts, which can deteriorate image quality. Recent deep-neural-network (DNN) based methods for image-to-image translation enable the mapping of low-quality PET images (acquired using substantially reduced dose), coupled with the associated magnetic resonance imaging (MRI) images, to high-quality PET images. However, such DNN methods focus on applications involving test data that match the statistical characteristics of the training data very closely and give little attention to evaluating the performance of these DNNs on new out-of-distribution (OOD) acquisitions. We propose a novel DNN formulation that models the (i) underlying sinogram-based physics of the PET imaging system and (ii) the uncertainty in the DNN output through the per-voxel heteroscedasticity of the residuals between the predicted and the high-quality reference images. Our sinogram-based uncertainty-aware DNN framework, namely, suDNN, estimates a standard-dose PET image using multimodal input in the form of (i) a low-dose/low-count PET image and (ii) the corresponding multi-contrast MRI images, leading to improved robustness of suDNN to OOD acquisitions. Results on in vivo simultaneous PET-MRI, and various forms of OOD data in PET-MRI, show the benefits of suDNN over the current state of the art, quantitatively and qualitatively.
Collapse
Affiliation(s)
- Viswanath P Sudarshan
- Computer Science and Engineering (CSE) Department, Indian Institute of Technology (IIT) Bombay, Mumbai, India; IITB-Monash Research Academy, Indian Institute of Technology (IIT) Bombay, Mumbai, India
| | - Uddeshya Upadhyay
- Computer Science and Engineering (CSE) Department, Indian Institute of Technology (IIT) Bombay, Mumbai, India
| | - Gary F Egan
- Monash Biomedical Imaging (MBI), Monash University, Melbourne, Australia
| | - Zhaolin Chen
- Monash Biomedical Imaging (MBI), Monash University, Melbourne, Australia
| | - Suyash P Awate
- Computer Science and Engineering (CSE) Department, Indian Institute of Technology (IIT) Bombay, Mumbai, India.
| |
Collapse
|