Journal of Forensic Medicine ›› 2024, Vol. 40 ›› Issue (5): 419-429.DOI: 10.12116/j.issn.1004-5619.2024.440801
• Original Articles • Next Articles
Hao-jie QIN1(
), Yuan-yuan LIU1,2, En-hao FU1,2, Ya-wen LIU2,3, Zhi-ling TIAN2, He-wen DONG2, Tai-ang LIU4, Dong-hua ZOU2, Yi-bin CHENG2(
), Ning-guo LIU2(
)
Received:2024-08-01
Online:2025-02-11
Published:2024-10-25
Contact:
Yi-bin CHENG, Ning-guo LIU
CLC Number:
Hao-jie QIN, Yuan-yuan LIU, En-hao FU, Ya-wen LIU, Zhi-ling TIAN, He-wen DONG, Tai-ang LIU, Dong-hua ZOU, Yi-bin CHENG, Ning-guo LIU. Intelligent Recognition and Segmentation of Blunt Craniocerebral Injury CT Images Based on DeepLabV3+ Model[J]. Journal of Forensic Medicine, 2024, 40(5): 419-429.
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.fyxzz.cn/EN/10.12116/j.issn.1004-5619.2024.440801
| 损伤类型 | Dice值 |
|---|---|
| 头皮血肿 | 0.766 4 |
| 颅骨骨折 | 0.812 3 |
| 硬脑膜外血肿 | 0.938 7 |
| 硬脑膜下血肿 | 0.782 7 |
| 脑挫伤 | 0.858 1 |
| 模型背景 | 0.995 7 |
Tab. 1 The Dice values of DeepLabV3+ model for segmentation of 5 types of craniocerebral injuries
| 损伤类型 | Dice值 |
|---|---|
| 头皮血肿 | 0.766 4 |
| 颅骨骨折 | 0.812 3 |
| 硬脑膜外血肿 | 0.938 7 |
| 硬脑膜下血肿 | 0.782 7 |
| 脑挫伤 | 0.858 1 |
| 模型背景 | 0.995 7 |
| 损伤类型 | 损伤颅脑 | 正常颅脑 | ||||
|---|---|---|---|---|---|---|
| 处 | 真阳 | 假阴 | 数量 | 真阴 | 假阳 | |
| 头皮血肿 | 109 | 100(91.74) | 9(8.26) | 24 | 18(75.00) | 6(25.00) |
| 颅骨骨折 | 77 | 66(85.71) | 11(14.29) | 21 | 17(80.95) | 4(19.05) |
| 硬脑膜外血肿 | 39 | 36(92.31) | 3(7.69) | 24 | 17(70.83) | 7(29.17) |
| 硬脑膜下血肿 | 49 | 46(93.88) | 3(6.12) | 21 | 17(80.95) | 4(19.05) |
| 脑挫伤 | 31 | 29(93.55) | 2(6.45) | 23 | 16(69.57) | 7(30.43) |
Tab. 2 The injury segmentation data of living craniocerebral CT images [n(%)]
| 损伤类型 | 损伤颅脑 | 正常颅脑 | ||||
|---|---|---|---|---|---|---|
| 处 | 真阳 | 假阴 | 数量 | 真阴 | 假阳 | |
| 头皮血肿 | 109 | 100(91.74) | 9(8.26) | 24 | 18(75.00) | 6(25.00) |
| 颅骨骨折 | 77 | 66(85.71) | 11(14.29) | 21 | 17(80.95) | 4(19.05) |
| 硬脑膜外血肿 | 39 | 36(92.31) | 3(7.69) | 24 | 17(70.83) | 7(29.17) |
| 硬脑膜下血肿 | 49 | 46(93.88) | 3(6.12) | 21 | 17(80.95) | 4(19.05) |
| 脑挫伤 | 31 | 29(93.55) | 2(6.45) | 23 | 16(69.57) | 7(30.43) |
| 损伤类型 | 准确率 | 精确率 | 召回率 | F1值 |
|---|---|---|---|---|
| 头皮血肿 | 88.72 | 94.34 | 91.74 | 93.02 |
| 颅骨骨折 | 84.69 | 94.29 | 85.71 | 89.80 |
| 硬脑膜外血肿 | 84.13 | 83.72 | 92.31 | 87.80 |
| 硬脑膜下血肿 | 90.00 | 92.00 | 93.88 | 92.93 |
| 脑挫伤 | 83.33 | 80.56 | 93.55 | 86.57 |
Tab. 3 Evaluation indicators for predicting 5 types of living craniocerebral injuries by the model
| 损伤类型 | 准确率 | 精确率 | 召回率 | F1值 |
|---|---|---|---|---|
| 头皮血肿 | 88.72 | 94.34 | 91.74 | 93.02 |
| 颅骨骨折 | 84.69 | 94.29 | 85.71 | 89.80 |
| 硬脑膜外血肿 | 84.13 | 83.72 | 92.31 | 87.80 |
| 硬脑膜下血肿 | 90.00 | 92.00 | 93.88 | 92.93 |
| 脑挫伤 | 83.33 | 80.56 | 93.55 | 86.57 |
| 损伤类型 | 损伤颅脑 | 正常颅脑 | ||||
|---|---|---|---|---|---|---|
| 处 | 真阳 | 假阴 | 数量 | 真阴 | 假阳 | |
| 头皮血肿 | 139 | 120(86.33) | 19(13.67) | 39 | 12(30.77) | 27(69.23) |
| 颅骨骨折 | 35 | 22(62.86) | 13(37.14) | 48 | 7(14.58) | 41(85.42) |
| 硬脑膜外血肿 | 13 | 13(100.00) | 0(0.00) | 36 | 18(50.00) | 8(22.22) |
| 硬脑膜下血肿 | 36 | 18(50.00) | 18(50.00) | 20 | 18(90.00) | 2(10.00) |
| 脑挫伤 | 34 | 33(97.06) | 1(2.94) | 85 | 17(20.00) | 68(80.00) |
Tab. 4 The injury segmentation data of cadaveric craniocerebral CT images
| 损伤类型 | 损伤颅脑 | 正常颅脑 | ||||
|---|---|---|---|---|---|---|
| 处 | 真阳 | 假阴 | 数量 | 真阴 | 假阳 | |
| 头皮血肿 | 139 | 120(86.33) | 19(13.67) | 39 | 12(30.77) | 27(69.23) |
| 颅骨骨折 | 35 | 22(62.86) | 13(37.14) | 48 | 7(14.58) | 41(85.42) |
| 硬脑膜外血肿 | 13 | 13(100.00) | 0(0.00) | 36 | 18(50.00) | 8(22.22) |
| 硬脑膜下血肿 | 36 | 18(50.00) | 18(50.00) | 20 | 18(90.00) | 2(10.00) |
| 脑挫伤 | 34 | 33(97.06) | 1(2.94) | 85 | 17(20.00) | 68(80.00) |
| 损伤类型 | 准确率 | 精确率 | 召回率 | F1值 |
|---|---|---|---|---|
| 头皮血肿 | 74.16 | 81.63 | 86.33 | 83.92 |
| 颅骨骨折 | 34.94 | 34.92 | 62.86 | 44.90 |
| 硬脑膜外血肿 | 63.27 | 61.90 | 100.00 | 76.47 |
| 硬脑膜下血肿 | 64.29 | 90.00 | 50.00 | 64.29 |
| 脑挫伤 | 42.02 | 32.67 | 97.06 | 48.89 |
Tab. 5 Evaluation indicators for predicting 5 types ofcadaveric craniocerebral injuries by the model
| 损伤类型 | 准确率 | 精确率 | 召回率 | F1值 |
|---|---|---|---|---|
| 头皮血肿 | 74.16 | 81.63 | 86.33 | 83.92 |
| 颅骨骨折 | 34.94 | 34.92 | 62.86 | 44.90 |
| 硬脑膜外血肿 | 63.27 | 61.90 | 100.00 | 76.47 |
| 硬脑膜下血肿 | 64.29 | 90.00 | 50.00 | 64.29 |
| 脑挫伤 | 42.02 | 32.67 | 97.06 | 48.89 |
| 1 | 安永明,张志威,刘剑霞. 骑跨横窦硬膜外血肿致伤方式审查1例[J].中国法医学杂志,2024,39(1):126-127. doi:10.13618/j.issn.1001-5728.2024.01.025 . |
| AN Y M, ZHANG Z W, LIU J X. Review of injury manners of epidural hematoma riding across transverse sinus: A case report[J]. Zhongguo Fayixue Zazhi,2024,39(1):126-127. | |
| 2 | 宋健文,徐彦昊,吕伟平,等. 他伤并自伤致颅脑损伤法医学鉴定1例[J].刑事技术,2023,48(5):543-546.doi:10.16467/j.1008-3650.2023.5013 . |
| SONG J W, XU Y H, LÜ W P, et al. Forensic clinical evaluation of complex craniocerebral injury caused by intentional injuries and self-inflicted injury: A case report[J]. Xingshi Jishu,2023,48(5):543-546. | |
| 3 | KRANIOTI E F, NATHENA D, SPANAKIS K, et al. Unenhanced PMCT in the diagnosis of fatal traumatic brain injury in a charred body[J]. J Forensic Leg Med,2021,77:102093. doi:10.1016/j.jflm.2020.102093 . |
| 4 | KLEVNO V A, CHUMAKOVA Y V, KORO-TENKO O A, et al. Virtopsy for studying the sudden death of an adolescent[J]. Russ J Forensic Med,2020,6(1):41-45. doi:10.19048/2411-8729-2020-6-1-41-45 . |
| 5 | 孙雪阳,杨琦帆,朱运良,等. 基于CT图像推断钝力性颅脑损伤成伤机制的logistic回归分析[J].法医学杂志,2022,38(2):217-222. doi:10.12116/j.issn.1004-5619.2021.410809 . |
| SUN X Y, YANG Q F, ZHU Y L, et al. Logistic regression analysis of the mechanism of blunt brain injury inference based on CT images[J]. Fayixue Zazhi,2022,38(2):217-222. | |
| 6 | 杨琦帆,孙雪阳,王彦斌,等. 基于深度学习的颅脑损伤机制自动化鉴别[J].法医学杂志,2022,38(2):223-230. doi:10.12116/j.issn.1004-5619.2021.410923 . |
| YANG Q F, SUN X Y, WANG Y B, et al. Automatic identification of brain injury mechanism based on deep learning[J]. Fayixue Zazhi,2022,38(2):223-230. | |
| 7 | TAGHANAKI S A, ABHISHEK K, COHEN J P, et al. Deep semantic segmentation of natural and medical images: A review[J]. Artif Intell Rev,2021,54(1):137-178. doi:10.1007/s10462-020-09854-1 . |
| 8 | LI Y, HUANG Z, DONG X, et al. Forensic age estimation for pelvic X-ray images using deep learning[J]. Eur Radiol,2019,29(5):2322-2329. doi:10.1007/s00330-018-5791-6 . |
| 9 | CAO Y, MA Y, VIEIRA D N, et al. A potential method for sex estimation of human skeletons using deep learning and three-dimensional surface scanning[J]. Int J Legal Med,2021,135(6):2409-2421. doi:10.1007/s00414-021-02675-z . |
| 10 | 武斌,李洋,夏志远,等. 虚拟解剖用于尸体颅脑损伤致伤物推断1例[J].中国法医学杂志,2022,37(1):21-23. doi:10.13618/j.issn.1001-5728.2022.01.005 . |
| WU B, LI Y, XIA Z Y, et al. Estimation of the injury instruments of cadaveric craniocerebral injuries using virtual autopsy: A case report[J]. Zhongguo Fayixue Zazhi,2022,37(1):21-23. | |
| 11 | EBERT L C, HEIMER J, SCHWEITZER W, et al. Automatic detection of hemorrhagic pericardial effusion on PMCT using deep learning — A feasibility study[J]. Forensic Sci Med Pathol,2017,13(4):426-431. doi:10.1007/s12024-017-9906-1 . |
| 12 | 尹艺晓,马金刚,张文凯,等. 从U-Net到Transformer:混合模型在医学图像分割中的应用进展[J].激光与光电子学进展,2025,62(2):0200001. doi:10.3788/LOP240875 . |
| YIN Y X, MA J G, ZHANG W K, et al. From U-Net to Transformer: Progress in the application of hybrid models in medical image segmentation[J]. Jiguang Yu Guangdianzixue Jinzhan,2025,62(2):0200001. | |
| 13 | HERNANDEZ PETZSCHE M R, DE LA ROSA E, HANNING U, et al. ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset[J]. Sci Data,2022,9(1):762. doi:10.1038/s41597-022-01875-5 . |
| 14 | WANG Y, WANG C, WU H, et al. An improved Deeplabv3+ semantic segmentation algorithm with multiple loss constraints[J]. PLoS One,2022,17(1):e0261582. doi:10.1371/journal.pone.0261582 . |
| 15 | KHODADADI SHOUSHTARI F, SINA S, DEH-KORDI A N V. Automatic segmentation of glioblastoma multiform brain tumor in MRI images: Using Deeplabv3+ with pre-trained Resnet18 weights[J]. Phys Med,2022,100:51-63. doi:10.1016/j.ejmp.2022.06.007 . |
| 16 | 董贺文,孙溢,钱辉,等. 死后尸体CT影像学特征变化研究进展[J].法医学杂志,2019,35(6):716-720. doi:10.12116/j.issn.1004-5619.2019.06.013 . |
| DONG H W, SUN Y, QIAN H, et al. Research progress on postmortem changes of computed tomography imaging characteristics on corpses[J]. Fayixue Zazhi,2019,35(6):716-720. | |
| 17 | 刘晓菲,晋文举,夏志远,等. 尸体与活体颅脑CT影像的比较[J].中国法医学杂志,2020,35(4):350-354.doi:10.13618/j.issn.1001-5728.2020.04.002 . |
| LIU X F, JIN W J, XIA Z Y, et al. Comparison of craniocerebral computed tomography (CT) of the deceased and the living body[J]. Zhongguo Fayixue Zazhi,2020,35(4):350-354. | |
| 18 | WANG Y, ZHOU Q, LIU J, et al. LEDNet: A lightweight encoder-decoder network for real-time semantic segmentation[C]// 2019 IEEE International Conference on Image Processing (ICIP). China: Taiwan,2019:1860-1864. |
| 19 | NACEUR M B, AKIL M, SAOULI R, et al. Deep convolutional neural networks for brain tumor segmentation: Boosting performance using deep transfer learning: Preliminary results[C]// Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 5th International Workshop, BrainLes 2019, Shenzhen,2019:303-315. |
| 20 | ZHENG H D, SUN Y L, KONG D W, et al. Deep learning-based high-accuracy quantitation for lumbar intervertebral disc degeneration from MRI[J]. Nat Commun,2022,13(1):841. doi:10.1038/s41467-022-28387-5 . |
| 21 | WACHINGER C, REUTER M, KLEIN T. DeepNAT: Deep convolutional neural network for segmenting neuroanatomy[J]. NeuroImage,2018,170:434-445. doi:10.1016/j.neuroimage.2017.02.035 . |
| 22 | MCCOY D B, DUPONT S M, GROS C, et al. Convolutional neural network-based automated segmentation of the spinal cord and contusion injury: Deep learning biomarker correlates of motor impairment in acute spinal cord injury[J]. AJNR Am J Neuroradiol,2019,40(4):737-744. doi:10.3174/ajnr.A6020 . |
| 23 | 李雪梅,曹琼,曹慧敏,等. 基于最大熵阈值分割法的颅脑CT图像血肿自动诊断系统研究[J].中国医学装备,2022,19(8):1-5. doi:10.3969/J.ISSN.1672-8270.2022.08.001 . |
| LI X M, CAO Q, CAO H M, et al. Study on the automatic diagnostic system for hematoma in CT image of brain based on threshold segmentation method of maximum entropy[J]. Zhongguo Yixue Zhuangbei,2022,19(8):1-5. | |
| 24 | CHILAMKURTHY S, GHOSH R, TANAMALA S, et al. Deep learning algorithms for detection of critical findings in head CT scans: A retrospective study[J]. Lancet,2018,392(10162):2388-2396. doi:10.1016/S0140-6736(18)31645-3 . |
| 25 | JANOT K, OLIVEIRA T R, FROMONT-HANKARD G, et al. Quantitative estimation of thrombus-erythro- cytes using MRI. A phantom study with clot analogs and analysis by statistic regression models[J]. J Neurointerv Surg,2020,12(2):181-185. doi:10.1136/neurintsurg-2019-014950 . |
| 26 | WANG X, HU Z, SHI S, et al. A deep learning method for optimizing semantic segmentation accuracy of remote sensing images based on improved UNet[J]. Sci Rep,2023,13(1):7600. doi:10.1038/s41598-023-34379-2 . |
| 27 | PEASE M, AREFAN D, BARBER J, et al. Outcome prediction in patients with severe traumatic brain injury using deep learning from head CT scans[J]. Radiology,2022,304(2):385-394. doi:10.1148/radiol.212181 . |
| 28 | DE FEO R, HÄMÄLÄINEN E, MANNINEN E, et al. Convolutional neural networks enable robust automatic segmentation of the rat hippocampus in MRI after traumatic brain injury[J]. Front Neurol,2022,13:820267. doi:10.3389/fneur.2022.820267 . |
| 29 | HUANG J S, HUANG S Y, LIAO H Z, et al. Point-of-care ultrasound diagnosis of skull fracture in Chinese children 0-6 years old with scalp hematoma from minor head trauma: A preliminary prospective observational study[J]. Heliyon,2023,9(4):e15255. doi:10.1016/j.heliyon.2023.e15255 . |
| 30 | 叶俊花,徐萌艳,方柳絮. 新生儿头皮血肿发生影响因素分析[J].中国实用护理杂志,2022,38(12):902-905. doi:10.3760/cma.j.cn211501-20210322-00860 . |
| YE J H, XU M Y, FANG L X. Analysis of influen-cing factors for the occurrence of neonatal scalp hematoma[J]. Zhongguo Shiyong Huli Zazhi,2022,38(12):902-905. | |
| 31 | WU D R, XU Y F, LU B L. Transfer learning for EEG-based brain-computer interfaces: A review of progress made since 2016[J]. IEEE Trans Cogn Dev Syst,2022,14(1):4-19. doi:10.1109/tcds.2020.3007453 . |
| 32 | 黄腾飞,刘巧梨,易海玲,等. 假性蛛网膜下腔出血征的CT定量分析和鉴别诊断[J].放射学实践,2021,36(12):1488-1492. doi:10.13609/j.cnki.1000-0313.2021.12.006 . |
| HUANG T F, LIU Q L, YI H L, et al. CT value quantitative analysis for diagnosis and differen-tiation of pseudo-subarachnoid hemorrhage[J]. Fangshexue Shijian,2021,36(12):1488-1492. | |
| 33 | KLEVNO V A, CHUMAKOVA Y V, KOROTENKO O A, et al. Virtopsy for studying the sudden death of an adolescent[J]. Russ J Forensic Med,2020,6(1):41-45. doi:10.19048/2411-8729-2020-6-1-41-45 . |
| 34 | MESSAOUDI H, BELAID A, SALEM D BEN, et al. Cross-dimensional transfer learning in medical image segmentation with deep learning[J]. Med Image Anal,2023,88:102868. doi:10.1016/j.media.2023.102868 . |
| 35 | MA J, HE Y, LI F, et al. Segment anything in medical images[J]. Nat Commun,2024,15(1):654. doi:10.1038/s41467-024-44824-z . |
| 36 | CHENG D, LAM E Y. Transfer learning U-Net deep learning for lung ultrasound segmentation[J]. arXiv,2021. doi:10.48550/arXiv.2110.02196 . |
| 37 | 张珊,马勋泰. 头颅CT诊断不明确的3例蛛网膜下腔出血临床分析[J].第三军医大学学报,2014,36(16):1757,1760. doi:10.16016/j.1000-5404.2014.16.026 . |
| ZHANG S, MA X T. Clinical analysis of subarachnoid hemorrhage with unclear diagnosis by craniocerebral CT: Three case reports[J].Di-san Junyi Daxue Xuebao,2014,36(16):1757,1760. | |
| 38 | 张建鹏,王浩馨,陈爱梅. 138例蛛网膜下腔出血CT分析[J].临床荟萃,2012,27(16):1425-1426. |
| ZHANG J P, WANG H X, CHEN A M. CT analysis of 138 cases of subarachnoid haemorrhage[J]. Linchuang Huicui,2012,27(16):1425-1426. |
| [1] | Guohua SHU. Practice and Prospect of Forensic Medicine Technology Transfer Under Policy Empowerment [J]. Journal of Forensic Medicine, 2026, 42(3): 191-195. |
| [2] | Xiaodan HE. Current Status Analysis and Pathway Exploration of the Technology Transfer in Forensic Medicine [J]. Journal of Forensic Medicine, 2026, 42(3): 196-206. |
| [3] | Qunyan LIU, Jinming YANG, Xiaoyu GUO. Strategies for Constructing a Technology Transfer System in Forensic Medicine Based on National Policies and Disciplinary Characteristics [J]. Journal of Forensic Medicine, 2026, 42(3): 207-214. |
| [4] | Jichao XU, Xiaohui CHEN, Qin SU, Dang’en GU, Tianchun LIN, Jianmiao ZHANG, Liang HAN, Ming CAI, Jian ZHAO, Quyi XU. Rapid Detection of Planktonic Microorganism DNA in Drowning: Technology Transfer and Application Implications [J]. Journal of Forensic Medicine, 2026, 42(3): 215-219. |
| [5] | Yunfeng ZHANG, Xinwei LIU, Linpei DONG, Xiaojun WU, Peng ZHAO, Jing RAN. Application of Portable Mass Spectrometry System in On-site Rapid Detection [J]. Journal of Forensic Medicine, 2026, 42(3): 224-231. |
| [6] | Lei TANG, Weihong XIE, Chengfei ZHUO, Chen XU, Huanhuan YAO, Xiaofei LI, Jianwei ZHANG, Yang LI, Jianbo YING. Development of a Fully Automated Blood Alcohol Analyzer and Its Application in Forensic Science [J]. Journal of Forensic Medicine, 2026, 42(3): 232-239. |
| [7] | Yawen XIAO, Yaoran YANG, Chongjun YANG, Yan SUN, Yue CHEN, Naihan HAN, Yuan MENG, Wenjun WANG, Qingshui REN, Jing ZHU, Tongshu ZHANG, Bing WANG, Liyan ZHANG. Application of Automatic Magnetic Solid-Phase Extraction Instrument in Toxic Substances and Illegal Drugs [J]. Journal of Forensic Medicine, 2026, 42(3): 240-246. |
| [8] | Mingjin YANG, Meiyun HE, Weian DU, Pengfei MEI, Xuelian CHENG, Xin LIU, Yuesen SHI, Hao JIN, Yiling HU, Meixin HE, Ling CHEN, Chao LIU. Enzyme Digestion LC-MS/MS Detection of Etomidate, Ketamine, Methamphe‑ tamine and Codeine in Hair [J]. Journal of Forensic Medicine, 2026, 42(3): 261-268. |
| [9] | Zheng QIAO, Hui YAN, Hang CHEN. Illegal Drug: Metonitazene [J]. Journal of Forensic Medicine, 2026, 42(3): 269-272. |
| [10] | Xiaotian YU. Common Problems and Recommendations for Manuscripts Submitted to Fayixue Zazhi [J]. Journal of Forensic Medicine, 2026, 42(3): 273-280. |
| [11] | Jianghong XIONG, Lifeng XU, Chaopeng YANG, Chengren ZHU, Dongbing PENG. Homicide Induced by Barium Chloride Poisoning: A Case Report [J]. Journal of Forensic Medicine, 2026, 42(3): 292-294. |
| [12] | Ruidi SHEN, Zhenhua QIAN. Research Progress on Mescaline and Its Analogues [J]. Journal of Forensic Medicine, 2026, 42(2): 151-158. |
| [13] | Yue LIU, Weiwei LIANG, Huanhui ZHU, Tianfu HE, Yuanyuan TIAN, Cong PENG, Songcai WANG. Detection of Chlormezanone in Blood Using HPLC-MS/MS Method [J]. Journal of Forensic Medicine, 2026, 42(2): 130-134. |
| [14] | Qingxia LIU, Di WEN, Shujin LI, Chunling MA, Bin CONG. Construction and Practice of the “Leading Goose Navigation and Four-Dimensional Synergy” Model for Cultivating Top Innovative Talents in Forensic Medicine [J]. Journal of Forensic Medicine, 2026, 42(2): 159-163. |
| [15] | Haojie QIN, Enhao FU, Yongchao YANG, Yawen LIU, Mingzhu JIA, Zhiling TIAN, Zhe ZHENG, Siyun GUO, Ningguo LIU. Construction of a Multimodal Forensic Pathology Database and Implementation of Model-Augmented Retrieval [J]. Journal of Forensic Medicine, 2026, 42(2): 102-111. |
| Viewed | ||||||
|
Full text |
|
|||||
|
Abstract |
|
|||||