
浏览全部资源
扫码关注微信
1.牡丹江医学院附属红旗医院,黑龙江牡丹江 157011
2.牡丹江医学院第一临床医学院,黑龙江牡丹江 157011
3.牡丹江医学院医学影像学院,黑龙江牡丹江 157011
4.牡丹江医学院生命科学学院,黑龙江牡丹江 157011
廉洪宇 (1982—),男,主治医师,研究生学历,研究方向:临床数据挖掘。
沈翔 (1996—),男,研究生在读,研究方向:临床医学。
陈广新 (1978—),男,讲师,研究方向:临床大数据挖掘。
国威 (2001—),男,研究生在读,研究方向:临床预测模型。
才莹 (1996—),女,中级职称,研究方向:医学人工智能。
纸质出版日期:2024-05-15
移动端阅览
廉洪宇, 沈翔, 陈广新, 等. 基于残差神经网络的颅骨缺损识别研究[J]. 新一代信息技术, 2024, 7(5): 01-05
LIAN Hong-yu, SHEN Xiang, CHEN Guang-xin, et al. Research on skull defect recognition based on residual neural network[J]. New Generation of Information Technology, 2024, 7(5): 01-05
廉洪宇, 沈翔, 陈广新, 等. 基于残差神经网络的颅骨缺损识别研究[J]. 新一代信息技术, 2024, 7(5): 01-05 DOI: 10.12263/newIT.2024.05.001.
LIAN Hong-yu, SHEN Xiang, CHEN Guang-xin, et al. Research on skull defect recognition based on residual neural network[J]. New Generation of Information Technology, 2024, 7(5): 01-05 DOI: 10.12263/newIT.2024.05.001.
鉴于颅骨缺损可能引发的严重健康问题,本研究旨在通过残差神经网络,提高对颅骨缺损的诊断精准度,从而提升患者的治疗成效和生存质量。本研究采用ResNet50深度学习模型结合颅骨医学影像数据,利用残差网络结构来增强对颅骨缺损的识别能力,并与传统CNN模型进行比较。ResNet50模型在颅骨缺损识别任务中显著优于CNN,其AUC指标达到0.92,表明在学习和泛化骨骼断裂特征方面具有更高的准确性和效率。综合考虑模型的计算资源需求、泛化性能以及实际应用中的数据规模,ResNet50模型在颅骨缺损识别领域展现出显著优势,但为了更好地适应临床应用,仍需对模型进行进一步优化和调整。
In view of the serious health problems that may be caused by skull defects
this study aims to improve the accuracy of diagnosis of skull defects through residual neural networks
so as to improve the treatment effectiveness and quality of life of patients. In this study
ResNet50 deep learning model is combined with cranial medical image data
and residual network structure is used to enhance the recognition ability of skull defect
and the traditional CNN model is compared. ResNet50 model is significantly better than CNN in skull defect recognition task
and its AUC index reaches 0.92
indicating higher accuracy and efficiency in learning and generalizing bone fracture characteristics. Considering the computing resource requirements
generalization performance and data scale in practical applications
ResNet50 model shows significant advantages in skull defect recognition
but in order to better adapt to clinical applications
further optimization and adjustment of the model is still needed.
焦云琦 . 早期颅骨修补术治疗脑外伤合并颅骨缺损的临床效果 [J ] . 医药论坛杂志 , 2024 , 45 ( 2 ): 135 - 139 .
朱磊 , 尹海斌 . 早期颅骨修补术治疗颅脑外伤术后颅骨缺损的效果 [J ] . 中外医学研究 , 2022 , 20 ( 26 ): 135 - 137 .
李斌 , 邵天宇 . 早期颅骨修补术对颅脑创伤术后颅骨缺损的临床效果研究 [J ] . 浙江创伤外科 , 2024 , 29 ( 2 ): 270 - 272 .
薛冶 , 李媛 , 邓振华 等 . 基于CT影像学的颅骨缺损虚拟三维修复方法的研究进展 [J ] . 中国法医学杂志 , 2023 , 38 ( 6 ): 642 - 647 .
肖航 , 陈振兴 , 李斌 . 颅脑外伤术后颅骨缺损自体骨瓣回植修补术的临床效果分析 [J ] . 中外医疗 , 2024 , 43 ( 6 ): 41 - 44 .
CHILAMKURTHY S , GHOSH R , TANAMALA S , et al . Deep learning algorithms for detection of critical findings in head CT scans: A retrospective study [J ] . The Lancet , 2018 , 392 ( 10162 ): 2388 - 2396 .
GOLBIN D A , VECHERIN A V , CHEREKAEV V A , et al . Predictive model for preoperative risk calculation of cerebrospinal fluid leak after resection of midline craniofacial mass lesions [J ] . World Neurosurgery: X , 2023 , 18 : 100163 .
METCALFE D . The pathophysiology of osteoporotic hip fracture [J ] . McGill Journal of Medicine: MJM , 2008 , 11 ( 1 ): 51 .
SHEU A , DIAMOND T . Diagnostic tests: bone mineral density: Testing for osteoporosis [J ] . Australian Prescriber , 2016 , 39 ( 2 ): 35 .
KRUSE C , EIKEN P , VESTERGAARD P . Machine learning principles can improve hip fracture prediction [J ] . Calcified Tissue International , 2017 , 100 : 348 - 360 .
BIVER E , DUROSIER‐IZART C , CHEVALLEY T , et al . Evaluation of radius microstructure and areal bone mineral density improves fracture prediction in postmenopausal women [J ] . Journal of Bone and Mineral Research , 2018 , 33 ( 2 ): 328 - 337 .
LEVI R , GAROLI F , BATTAGLIA M , et al . CT-based radiomics can identify physiological modifications of bone structure related to subjects' age and sex [J ] . La Radiologia Medica , 2023 , 128 ( 6 ): 744 - 754 .
HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2016 : 770 - 778 .
PANTHAKKAN A , ANZAR S M , JAMAL S , et al . Concatenated Xception-ResNet50—A novel hybrid approach for accurate skin cancer prediction [J ] . Computers in Biology and Medicine , 2022 , 150 : 106170 .
XU W , FU Y L , ZHU D . ResNet and its application to medical image processing: Research progress and challenges [J ] . Computer Methods and Programs in Biomedicine , 2023 : 107660 .
HASANAH S A , PRAVITASARI A A , ABDULLAH A S , et al . A deep learning review of resnet architecture for lung disease Identification in CXR Image [J ] . Applied Sciences , 2023 , 13 ( 24 ): 13111 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621