Frontiers and Perspectives of Artificial Intelligence in Forensic Research on CT Imaging Diagnosis of Rib Fractures

doi:10.12116/j.issn.1004-5619.2024.240705

Abstract

Abstract:

Rib fractures are relatively common in thoracic trauma, and the number of fractured ribs as well as the presence of malunion are closely associated with criminal sentencing and civil compensation, thereby holding significant forensic significance. At present, the diagnosis of rib fractures in forensic practice primarily relies on computed tomography （CT） examinations. However, achieving accurate results often demands substantial time and effort from experienced forensic experts, with limitations in diagnostic efficiency and consistency. In recent years, the rapid advancement of artificial intelligence （AI） has led to the emergence of multiple AI-assisted imaging diagnostic models with practical applicability, effectively improving the efficiency and accuracy of rib fracture identification. This review systematically summarizes the latest application progress of AI in CT diagnosis of rib fractures, with a particular focus on recent advances in automatic detection, classification, localization, multitask integration, and fracture age estimation. By synthesizing existing literature and methodologies, this work aims to reveal the potential of AI in improving diagnostic efficiency and accuracy, and to provide a reference for the future development of intelligent diagnostic models with greater forensic utility.

Key words: forensic medicine, artificial intelligence （AI）, rib fractures, CT imaging, review

CLC Number:

Ya-ning SUN, Dan-yang LI, Qing XIA, Yan GAO, Zong-shi XU, Wen-tao XIA, Hui-ming ZHOU, Xiao-meng HAN, Xiao-ying YU, Yan-liang SHENG. Frontiers and Perspectives of Artificial Intelligence in Forensic Research on CT Imaging Diagnosis of Rib Fractures[J]. Journal of Forensic Medicine, 2025, 41(6): 593-600.

References 35

[1]	DOGRUL B N， KILICCALAN I， ASCI E S， et al. Blunt trauma related chest wall and pulmonary injuries： An overview[J]. Chin J Traumatol，2020，23（3）：125-138. doi：10.1016/j.cjtee.2020.04.003 .
[2]	Expert Panel on Major Trauma Imaging， SHYU J Y， KHURANA B， et al. ACR Appropriateness Criteria^® major blunt trauma[J]. J Am Coll Radiol，2020，17（5S）：S160-S174. doi：10.1016/j.jacr.2020.01.024 .
[3]	AWAIS M， SALAM B， NADEEM N， et al. Diagnostic accuracy of computed tomography scout film and chest X-ray for detection of rib fractures in patients with chest trauma： A cross-sectional study[J]. Cureus，2019，11（1）：e3875. doi：10.7759/cureus.3875 .
[4]	倪伟勇，钱昭军. 肋骨骨折鉴定时间研究[J].刑事技术，2015，40（2）：114-117. doi：10.16467/j.1008-3650.2015.02.007 .
	NI W Y， QIAN Z J. Forensic evaluation of the time of rib fracture[J]. Xingshi Jishu，2015，40（2）：114-117.
[5]	吕铭，黄建松，张运阁，等. 薄层螺旋CT扫描在肋骨骨折法医学鉴定中的应用分析[J].中国司法鉴定，2021（1）：54-59. doi：10.3969/j.issn.1671-2072.2021.01.007 .
	LÜ M， HUANG J S， ZHANG Y G， et al. Application of thin-slice spiral CT scan in forensic identification of rib fractures[J]. Zhongguo Sifa Jianding，2021（1）：54-59.
[6]	邓振华. 肩负法治中国建设重任，推进我国法医临床学全面发展[J].法医学杂志，2025，41（5）：407-420. doi：10.12116/j.issn.1004-5619.2025.250808 .
	DENG Z H. Shouldering the responsibility of building a law-based china and advancing the comprehensive development of forensic clinical medicine[J]. Fayixue Zazhi，2025，41（5）：407-420.
[7]	黄美莎，张恒，李姝璇，等. 影像组学在法医骨关节损伤鉴定中的应用展望[J].中国法医学杂志，2024，39（1）：95-100. doi：10.13618/j.issn.1001-5728.2024.01.016 .
	HUANG M S， ZHANG H， LI S X， et al. Application prospect of radiomics in forensic examination on bone and joint injury[J]. Zhongguo Fayixue Zazhi，2024，39（1）：95-100.
[8]	邱锡鹏. 神经网络与深度学习[M].北京：机械工业出版社，2020：23.
	QIU X P. Neural networks and deep learning[M]. Beijing： China Machine Press，2020：23.
[9]	ERICKSON B J. Basic artificial intelligence techniques： Machine learning and deep learning[J]. Radiol Clin North Am，2021，59（6）：933-940. doi：10.1016/j.rcl.2021.06.004 .
[10]	DREIZIN D， ZHOU Y， ZHANG Y， et al. Performance of a deep learning algorithm for automated segmentation and quantification of traumatic pelvic hematomas on CT[J]. J Digit Imaging，2020，33（1）：243-251. doi：10.1007/s10278-019-00207-1 .
[11]	RAJAMANI K T， RANI P， SIEBERT H， et al. Attention-augmented U-Net （AA-U-Net） for semantic segmentation[J]. Signal Image Video Process，2023，17（4）：981-989. doi：10.1007/s11760-022-02302-3 .
[12]	BHANDARY S， KUHN D， BABAIEE Z， et al. Investigation and benchmarking of U-Nets on prostate segmentation tasks[J]. Comput Med Imaging Graph，2023，107：102241. doi：10.1016/j.compmedimag.2023. 102241 .
[13]	ZHOU Z， FU Z， JIA J， et al. Rib fracture detection with dual-attention enhanced U-Net[J]. Comput Math Methods Med，2022，2022：8945423. doi：10.1155/ 2022/8945423 .
[14]	WANG S， WU D， YE L， et al. Assessment of automatic rib fracture detection on chest CT using a deep learning algorithm[J]. Eur Radiol，2023，33（3）：1824-1834. doi：10.1007/s00330-022-09156-w .
[15]	WANG X， WANG Y. Composite attention residual U-Net for rib fracture detection[J]. Entropy （Basel），2023，25（3）：466. doi：10.3390/e25030466 .
[16]	ZHANG B， JIA C， WU R， et al. Improving rib fracture detection accuracy and reading efficiency with deep learning-based detection software： A clinical evaluation[J]. Br J Radiol，2021，94（1118）：20200870. doi：10.1259/bjr.20200870 .
[17]	YAO L， GUAN X， SONG X， et al. Rib fracture detection system based on deep learning[J]. Sci Rep，2021，11（1）：23513. doi：10.1038/s41598-021-03002-7 .
[18]	白洁，孙晶，程晓光，等. 基于YOLOv3算法的肋骨骨折诊断模型的构建及应用[J].法医学杂志，2023，39（4）：343-349，359. doi：10.12116/j.issn.1004-5619.2023.230308 .
	BAI J， SUN J， CHENG X G， et al. Construction and application of rib fracture diagnosis model based on YOLOv3 algorithm[J]. Fayixue Zazhi，2023，39（4）：343-349，359.
[19]	ZHOU Q Q， TANG W， WANG J， et al. Automatic detection and classification of rib fractures based on patients’ CT images and clinical information via convolutional neural network[J]. Eur Radiol，2021，31（6）：3815-3825. doi：10.1007/s00330-020-07418-z .
[20]	EDAMADAKA S， BROWN D W， SWAROOP R， et al. FasterRib： A deep learning algorithm to automate identification and characterization of rib fractures on chest computed tomography scans[J]. J Trauma Acute Care Surg，2023，95（2）：181-185. doi：10.1097/TA.0000000000003913 .
[21]	WU M， CHAI Z， QIAN G， et al. Development and evaluation of a deep learning algorithm for rib segmentation and fracture detection from multicenter chest CT images[J]. Radiol Artif Intell，2021，3（5）：e200248. doi：10.1148/ryai.2021200248 .
[22]	MENG X H， WU D J， WANG Z， et al. A fully automated rib fracture detection system on chest CT images and its impact on radiologist performance[J]. Skeletal Radiol，2021，50（9）：1821-1828. doi：10.1007/s00256-021-03709-8 .
[23]	ZHOU Q Q， HU Z C， TANG W， et al. Precise anatomical localization and classification of rib fractures on CT using a convolutional neural network[J]. Clin Imaging，2022，81：24-32. doi：10.1016/j.clinimag. 2021.09.010 .
[24]	YANG C， WANG J， XU J， et al. Development and assessment of deep learning system for the location and classification of rib fractures via computed tomography[J]. Eur J Radiol，2022，154：110434. doi：10.1016/j.ejrad.2022.110434 .
[25]	REN S， HE K， GIRSHICK R， et al. Faster R-CNN： Towards real-time object detection with region proposal networks[J]. IEEE Trans Pattern Anal Mach Intell，2017，39（6）：1137-1149. doi：10.1109/TPAMI.2016.2577031 .
[26]	何俊，王东建，王泽飞，等. 影像检查鉴别肋骨陈旧与新鲜骨折1例[J].中国法医学杂志，2025，40（S1）：277-278. doi：10.13618/j.issn.1001-5728.2025.S.149 .
	HE J， WANG D J， WANG Z F， et al. Differentiation between old and fresh rib fractures using imaging examination： A case report[J]. Zhongguo Fayixue Zazhi，2025，40（S1）：277-278.
[27]	ARREDONDO-GÓMEZ E. Treatment of traumatic clavicular pseudoarthrosis with the Hunec Colchero nail[J]. Acta Ortop Mex，2007，21（2）：63-68.
[28]	吴新宝，姜钰. 陈旧性骨折[J].中华外科杂志，2015，53（6）：460-463. doi：10.3760/cma.j.issn.0529-5815.2015.06.014 .
	WU X B， JIANG Y. Old fracture[J]. Zhonghua Waike Zazhi，2015，53（6）：460-463.
[29]	TANG Y， JIN L， JI W， et al. Determining rib fracture age from CT scans with a radiomics-based combined model： A multicenter retrospective study[J]. Insights Imaging，2023，14（1）：214. doi：10.1186/s13 244-023-01546-y .
[30]	JIN L， SUN Y， MA Z， et al. Radiomics-based machine learning for predicting the injury time of rib fractures in gemstone spectral imaging scans[J]. Bioengineering （Basel），2022，10（1）：8. doi：10.3390/bioengineering10010008 .
[31]	BEHESHTIAN E， PUTMAN K， SANTOMARTINO S M， et al. Generalizability and bias in a deep learning pediatric bone age prediction model using hand radiographs[J]. Radiology，2023，306（2）：e220505. doi：10.1148/radiol.220505 .
[32]	IMWINKELRIED E J，杜春鹏（译，李尧（译. 计算机源代码：自动化法庭科技可靠性争议日盛之缘由[J].证据科学，2019，27（4）：491-513. doi：10.3969/j.issn.1674-1226.2019.04.009 .
	IMWINKELRIED E J， DU C P transl）， LI Y transl）. Computer source code： A source of the growing controversy over the reliability of automated forensic techniques[J]. Zhengju Kexue，2019，27（4）：491-513.
[33]	FAN F， LIU H， DAI X， et al. Automated bone age assessment from knee joint by integrating deep learning and MRI-based radiomics[J]. Int J Legal Med，2024，138（3）：927-938. doi：10.1007/s00414-023-03148-1 .
[34]	苏青. 鉴定意见概念之比较与界定[J].法律科学（西北政法大学学报），2016，34（1）：154-161. doi：10.16290/j.cnki.1674-5205.2016.01.016 .
	SU Q. A comparative study on definition of forensic appraisal opinion[J]. Falü Kexue （Xibei Zhengfa Da-xue Xuebao），2016，34（1）：154-161.
[35]	TOURNOIS L， TROUSSET V， HATSCH D， et al. Artificial intelligence in the practice of forensic medicine： A scoping review[J]. Int J Legal Med，2024，138（3）：1023-1037. doi：10.1007/s00414-023-03140-9 .