1
|
Zhou HM, Zhou ZL, He YH, Liu TA, Wan L, Wang YH. Forensic bone age assessment of hand and wrist joint MRI images in Chinese han male adolescents based on deep convolutional neural networks. Int J Legal Med 2024:10.1007/s00414-024-03282-4. [PMID: 39060444 DOI: 10.1007/s00414-024-03282-4] [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: 01/24/2024] [Accepted: 06/23/2024] [Indexed: 07/28/2024]
Abstract
In Chinese criminal law, the ages of 12, 14, 16, and 18 years old play a significant role in the determination of criminal responsibility. In this study, we developed an epiphyseal grading system based on magnetic resonance image (MRI) of the hand and wrist for the Chinese Han population and explored the feasibility of employing deep learning techniques for bone age assessment based on MRI of the hand and wrist. This study selected 282 Chinese Han Chinese males aged 6.0-21.0 years old. In the course of our study, we proposed a novel deep learning model for extracting and enhancing MRI hand and wrist bone features to enhance the prediction of target MRI hand and wrist bone age and achieve precise classification of the target MRI and regression of bone age. The evaluation metric for the classification model including precision, specificity, sensitivity, and accuracy, while the evaluation metrics chosen for the regression model are MAE. The epiphyseal grading was used as a supervised method, which effectively solved the problem of unbalanced sample distribution, and the two experts showed strong consistency in the epiphyseal plate grading process. In the classification results, the accuracy in distinguishing between adults and minors was 91.1%, and the lowest accuracy in the three minor classifications (12, 14, and 16 years of age) was 94.6%, 91.1% and 96.4%, respectively. The MAE of the regression results was 1.24 years. In conclusion, the deep learning model proposed enabled the age assessment of hand and wrist bones based on MRI.
Collapse
Affiliation(s)
- Hui-Ming Zhou
- Academy of Forensic Science, Shanghai Key Laboratory of Forensic Medicine (21DZ2270800), Shanghai Forensic Service Platform, Key Laboratory of Forensic Science, Ministry of Justice, 1347 GuangFu West Road, Shanghai, 200063, China
- School of Forensic Medicine, Shanxi Medical University, Jinzhong, Shanxi, 030604, China
| | - Zhi-Lu Zhou
- Department of forensic medicine, Guizhou Medical University, Guiyang, 550009, China
| | - Yu-Heng He
- Shanghai Shuzhiwei Information Technology Co., LTD, 333 WenHai Road, Shanghai, 200444, China
| | - Tai-Ang Liu
- Shanghai Shuzhiwei Information Technology Co., LTD, 333 WenHai Road, Shanghai, 200444, China
| | - Lei Wan
- Academy of Forensic Science, Shanghai Key Laboratory of Forensic Medicine (21DZ2270800), Shanghai Forensic Service Platform, Key Laboratory of Forensic Science, Ministry of Justice, 1347 GuangFu West Road, Shanghai, 200063, China.
- Department of radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai, 201508, China.
| | - Ya-Hui Wang
- Academy of Forensic Science, Shanghai Key Laboratory of Forensic Medicine (21DZ2270800), Shanghai Forensic Service Platform, Key Laboratory of Forensic Science, Ministry of Justice, 1347 GuangFu West Road, Shanghai, 200063, China.
| |
Collapse
|
2
|
Jiao YS, Tuerhong Y, Chen CX, Dai XH, Lu T, Peng Z, Deng ZH, Fan F. Bone age assessment based on different MRI modalities of the proximal humerus epiphysis: the comparisons of T 1WI, T 2WI, and PDWI. Int J Legal Med 2024; 138:1509-1521. [PMID: 38332350 DOI: 10.1007/s00414-024-03182-7] [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: 08/08/2023] [Accepted: 02/01/2024] [Indexed: 02/10/2024]
Abstract
Bone age assessment (BAA) is crucial in various fields, including legal proceedings, athletic competitions, and clinical medicine. However, the use of X-ray methods for age estimation without medical indication is subject to ethical debate, especially in forensic and athletic fields. The application of magnetic resonance imaging (MRI) with non-ionizing radiation can overcome this limitation in BAA. This study aimed to compare the application value of several MRI modalities of proximal humeral in BAA. A total of 468 patients with shoulder MRIs were retrospectively collected from a Chinese Han population aged 12-30 years (259 males and 209 females) for training and testing, including T1 weighted MRI (T1WI), T2 weighted MRI (T2WI), and Proton density weighted MRI (PDWI). Optimal regression models were established for age estimation, yielding mean absolute error (MAE) values below 2.0 years. The MAE values of T1WI were the lowest, with 1.700 years in males and 1.798 years in females. The area under the curve (AUC) and accuracy values of different MRI modalities of 16-year and 18-year thresholds were all around 0.9. For the 18-year threshold, T1WI outperformed T2WI and PDWI. In conclusion, the three MRI modalities of the proximal humerus can serve as reliable indicators for age assessment, while the T1WI performed better in age assessment and classification.
Collapse
Affiliation(s)
- Yu-Su Jiao
- West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People's Republic of China
| | - Yilitabier Tuerhong
- West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People's Republic of China
| | - Cheng-Xu Chen
- West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People's Republic of China
| | - Xin-Hua Dai
- Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, 610041, People's Republic of China
| | - Ting Lu
- West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People's Republic of China
| | - Zhao Peng
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, People's Republic of China
| | - Zhen-Hua Deng
- West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People's Republic of China.
| | - Fei Fan
- West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People's Republic of China.
| |
Collapse
|
3
|
Fan F, Liu H, Dai X, Liu G, Liu J, Deng X, Peng Z, Wang C, Zhang K, Chen H, Yin C, Zhan M, Deng Z. Automated bone age assessment from knee joint by integrating deep learning and MRI-based radiomics. Int J Legal Med 2024; 138:927-938. [PMID: 38129687 DOI: 10.1007/s00414-023-03148-1] [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: 07/30/2023] [Accepted: 12/09/2023] [Indexed: 12/23/2023]
Abstract
Bone age assessment (BAA) is a crucial task in clinical, forensic, and athletic fields. Since traditional age estimation methods are suffered from potential radiation damage, this study aimed to develop and evaluate a deep learning radiomics method based on multiparametric knee MRI for noninvasive and automatic BAA. This retrospective study enrolled 598 patients (age range,10.00-29.99 years) who underwent MR examinations of the knee joint (T1/T2*/PD-weighted imaging). Three-dimensional convolutional neural networks (3D CNNs) were trained to extract and fuse multimodal and multiscale MRI radiomic features for age estimation and compared to traditional machine learning models based on hand-crafted features. The age estimation error was greater in individuals aged 25-30 years; thus, this method may not be suitable for individuals over 25 years old. In the test set aged 10-25 years (n = 95), the 3D CNN (a fusion of T1WI, T2*WI, and PDWI) demonstrated the lowest mean absolute error of 1.32 ± 1.01 years, which is higher than that of other MRI modalities and the hand-crafted models. In the classification for 12-, 14-, 16-, and 18- year thresholds, accuracies and the areas under the ROC curves were all over 0.91 and 0.96, which is similar to the manual methods. Visualization of important features showed that 3D CNN estimated age by focusing on the epiphyseal plates. The deep learning radiomics method enables non-invasive and automated BAA from multimodal knee MR images. The use of 3D CNN and MRI-based radiomics has the potential to assist radiologists or medicolegists in age estimation.
Collapse
Affiliation(s)
- Fei Fan
- West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People's Republic of China
| | - Han Liu
- College of Computer Science, Sichuan University, Chengdu, 610064, People's Republic of China
| | - Xinhua Dai
- Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, 610041, People's Republic of China
| | - Guangfeng Liu
- West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People's Republic of China
| | - Junhong Liu
- West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People's Republic of China
| | - Xiaodong Deng
- West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People's Republic of China
| | - Zhao Peng
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, People's Republic of China
| | - Chang Wang
- Department of Radiology, Anhui Provincial Children's Hospital, Hefei, 230054, People's Republic of China
| | - Kui Zhang
- West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People's Republic of China
| | - Hu Chen
- College of Computer Science, Sichuan University, Chengdu, 610064, People's Republic of China
| | - Chuangao Yin
- Department of Radiology, Anhui Provincial Children's Hospital, Hefei, 230054, People's Republic of China.
| | - Mengjun Zhan
- West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People's Republic of China.
| | - Zhenhua Deng
- West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People's Republic of China.
| |
Collapse
|
4
|
Fang C, Zhou P, Li R, Guo J, Qiu H, Zhang J, Li M, Yu C, Meng D, Xu X, Liu X, Guan D, Yan J. Development of a novel forensic age estimation strategy for aged blood samples by combining piRNA and miRNA markers. Int J Legal Med 2023; 137:1327-1335. [PMID: 37264192 DOI: 10.1007/s00414-023-03028-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/25/2022] [Accepted: 05/22/2023] [Indexed: 06/03/2023]
Abstract
In forensic investigations, age estimation is vital for determining whether a suspect is under or over the legally defined adult age. With breakthroughs in RNA sequencing technology, small noncoding RNAs have provided new ways to solve problems related to the age estimation of trace or aged samples, owing to their small molecular weight and better stability. In our previous study, we had applied miRNAs for the age estimation of bloodstains; however, further improvement of the existing model is needed. PIWI-interacting RNAs (PiRNAs), which are 24-32 nt noncoding small RNA molecules involved in the PIWI-piRNA pathway, play an important role in the aging process. In this study, we explored the possibility of simultaneously analyzing piRNAs and miRNAs for better age estimation purpose. Through massively parallel sequencing, five age-related piRNAs were identified in blood samples that had been stored for eight years. Further real-time PCR analysis revealed that two piRNAs (piR-000753 and piR-020548) showed relatively higher efficiency in age estimation. Additionally, two age-related miRNAs (miR-324-3p and miR-330-5p) were used to build the estimation model. Among all algorithms tested, gradient boosting showed the lowest mean absolute error (MAE) and root mean square error (RMSE) values (3.171 and 4.403 years, respectively) for the validation dataset (n = 110). The errors of the model were less than 5 years and 10 years for 81.82% and 96.36% of the samples, respectively. The results suggest that the combined use of piRNA and miRNA markers may increase the accuracy of age estimation, and our new model has great potential for application in forensic casework.
Collapse
Affiliation(s)
- Chen Fang
- Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, 250021, People's Republic of China.
- Department of Pathology and Forensic Medicine, School of Clinical and Basic Medical Sciences, Shandong First Medical University& Shandong Academy of Medical Sciences, Jinan, 250117, People's Republic of China.
| | - Peng Zhou
- Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, 250021, People's Republic of China
- Department of Pathology and Forensic Medicine, School of Clinical and Basic Medical Sciences, Shandong First Medical University& Shandong Academy of Medical Sciences, Jinan, 250117, People's Republic of China
| | - Ran Li
- Department of Pathology and Forensic Medicine, School of Clinical and Basic Medical Sciences, Shandong First Medical University& Shandong Academy of Medical Sciences, Jinan, 250117, People's Republic of China
| | - Jinghan Guo
- Department of Pathology and Forensic Medicine, School of Clinical and Basic Medical Sciences, Shandong First Medical University& Shandong Academy of Medical Sciences, Jinan, 250117, People's Republic of China
| | - Huixian Qiu
- Department of Pathology and Forensic Medicine, School of Clinical and Basic Medical Sciences, Shandong First Medical University& Shandong Academy of Medical Sciences, Jinan, 250117, People's Republic of China
| | - Jingjuan Zhang
- Department of Pathology and Forensic Medicine, School of Clinical and Basic Medical Sciences, Shandong First Medical University& Shandong Academy of Medical Sciences, Jinan, 250117, People's Republic of China
| | - Min Li
- Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, 250021, People's Republic of China
- Department of Pathology and Forensic Medicine, School of Clinical and Basic Medical Sciences, Shandong First Medical University& Shandong Academy of Medical Sciences, Jinan, 250117, People's Republic of China
| | - Chunjiang Yu
- Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, 250021, People's Republic of China
- Department of Pathology and Forensic Medicine, School of Clinical and Basic Medical Sciences, Shandong First Medical University& Shandong Academy of Medical Sciences, Jinan, 250117, People's Republic of China
| | - Deping Meng
- Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, 250021, People's Republic of China
- Department of Pathology and Forensic Medicine, School of Clinical and Basic Medical Sciences, Shandong First Medical University& Shandong Academy of Medical Sciences, Jinan, 250117, People's Republic of China
| | - Xiaoqun Xu
- Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, 250021, People's Republic of China
- Department of Pathology and Forensic Medicine, School of Clinical and Basic Medical Sciences, Shandong First Medical University& Shandong Academy of Medical Sciences, Jinan, 250117, People's Republic of China
| | - Xu Liu
- Institute of Analysis and Testing, Beijing Academy of Science and Technology (Beijing Center for Physical and Chemical Analysis), Beijing, 100094, People's Republic of China
| | - Di Guan
- Institute of Analysis and Testing, Beijing Academy of Science and Technology (Beijing Center for Physical and Chemical Analysis), Beijing, 100094, People's Republic of China
| | - Jiangwei Yan
- Shanxi Medical University, 030001, Taiyuan, People's Republic of China.
- Department of Pathology and Forensic Medicine, School of Clinical and Basic Medical Sciences, Shandong First Medical University& Shandong Academy of Medical Sciences, Jinan, 250117, People's Republic of China.
| |
Collapse
|
5
|
Chitavishvili N, Papageorgiou I, Malich A, Hahnemann ML, Mall G, Mentzel HJ, Wittschieber D. The distal femoral epiphysis in forensic age diagnostics: studies on the evaluation of the ossification process by means of T1- and PD/T2-weighted magnetic resonance imaging. Int J Legal Med 2023; 137:427-435. [PMID: 36565316 PMCID: PMC9902329 DOI: 10.1007/s00414-022-02927-6] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2022] [Accepted: 11/30/2022] [Indexed: 01/16/2023]
Abstract
The age of majority, which corresponds to the age of 18 years in most European countries, plays a crucial role for a large number of legal decisions. Accordingly, an increasing number of requests by authorities to forensic age estimation experts comprise the question of whether the age of 18 years has been reached by an individual. In recent years, novel study data suggested that magnetic resonance imaging (MRI) of the knee might likewise allow for the determination of majority beyond reasonable doubt. However, the data basis, especially concerning the distal femoral epiphysis (DFE), is still poor. For this reason, 392 routine MRI cases of the knee (204 males and 188 females of a Western Caucasian population, aged between 12 and 25 years) were retrospectively analyzed. T1-weighted and water-selective fat-saturated PD/T2-weighted sequences, generated at 1.5 and 3.0 T clinical MR scanners, were available. Ossification stages of the DFE were determined by means of the classification system by Vieth et al. (Eur Radiol 2018; 28:3255-3262). Both the intra-observer agreement and inter-observer agreement were found to be "very good" (κ = 0.899 and κ = 0.830). The present study confirmed that MRI of the DFE is suitable to determine majority in both sexes when stage 6 is present as the study revealed minimum ages above the age of 18 years for this stage (20.40 years in males and 20.60 years in females). Accordingly, the data represent a strong support for the so far existing database. Hence, the investigation of the knee using routine MRI appears to become a realistic alternative for forensic age estimation practice in the near future.
Collapse
Affiliation(s)
- Natia Chitavishvili
- Section of Pediatric Radiology, Department of Radiology, Jena University Hospital, Friedrich Schiller University Jena, Jena, Germany ,Department of Radiology, Jena University Hospital, Jena, Germany
| | - Ismini Papageorgiou
- Department of Radiology, Jena University Hospital, Jena, Germany ,Institute of Radiology, Südharz Klinikum Nordhausen, Nordhausen, Germany
| | - Ansgar Malich
- Institute of Radiology, Südharz Klinikum Nordhausen, Nordhausen, Germany
| | - Maria L. Hahnemann
- Institute of Legal Medicine, Jena University Hospital, Friedrich Schiller University Jena, Am Klinikum 1, 07747 Jena, Germany
| | - Gita Mall
- Institute of Legal Medicine, Jena University Hospital, Friedrich Schiller University Jena, Am Klinikum 1, 07747 Jena, Germany
| | - Hans-Joachim Mentzel
- Section of Pediatric Radiology, Department of Radiology, Jena University Hospital, Friedrich Schiller University Jena, Jena, Germany
| | - Daniel Wittschieber
- Institute of Legal Medicine, Jena University Hospital, Friedrich Schiller University Jena, Am Klinikum 1, 07747, Jena, Germany.
| |
Collapse
|