计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 220200063-10.doi: 10.11896/jsjkx.220200063
王笑天1, 李博2, 康晓东1, 刘汉卿1, 韩俊玲1, 杨靖怡1
WANG Xiaotian1, LI Bo2, KANG Xiaodong1, LIU Hanqing1, HAN Junling1, YANG Jingyi1
摘要: CT是临床最常用的影像学检查之一,CT影像的计算机辅助诊断技术具有重要的临床意义。为优化CT影像目标检测,分别采用8种不同目标检测算法对肝血管瘤增强CT的图像、脑动脉狭窄CTA图像和结肠息肉CT图像进行检测研究,比较不同算法的适用性。首先,对肝血管瘤增强CT图像、脑动脉狭窄CTA和结肠息肉CT图像进行标注并制作数据集。其次,采用不同参数优化算法,并绘制AP-epoch和AP-FPS曲线以比较不同算法的检测性能。实验结果表明,PPYOLOv2在不同数据集中的AP,AP50,AP75和Recall均达到最优,预测边界框紧贴待检目标,预测置信度较高,并且具有良好的泛化能力和鲁棒性。
中图分类号:
[1]VIOLA P,JONES M.Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR 2001).IEEE,2001. [2]VIOLA P,JONES M J J I J O C V.Robust real-time face detection[J].International Journal of Computer Visio,2004,57(2):137-154. [3]YUAN X P,CHEN X F,LIAN M.Multi-feature Fusion Target Detection algorithm based on Haar-like and LBP[J].Computer Science,2021,48(11):219-255. [4]DALAL N,TRIGGS B.Histograms of oriented gradients forhuman detection[C]//Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR’05).IEEE,2005:886-893. [5]FELZENSZWALB P,MCALLESTER D,RAMANAN D.A discriminatively trained,multiscale,deformable part model[C]//Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2008:1-8. [6]GIRSHICK R,FELZENSZWALB P,MCALLESTER D.Object detection with grammar models[J].Advances in Neural Information Processing Systems,2011,24:442-450. [7]GIRSHICK R B.From rigid templates to grammars:Object detection with structured models[M].The University of Chicago,2012. [8]GIRSHICK R,DONAHUE J,DARRELL T,et al.Region-based convolutional networks for accurate object detection and segmentation[J].IEEE Transactions on Pattern Analysis Machine Intelligence,2015,38(1):142-158. [9]HE K,ZHANG X,REN S,et al.Spatial pyramid pooling in deepconvolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis Machine Intelligence,2015,37(9):1904-1916. [10]GIRSHICK R.Fast r-cnn[C]//Proceedings of the 2015 Proceedings of the IEEE International Conference on Computer Vision.2015:1440-1448. [11]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towardsreal-time object detection with region proposal networks[J].2016,39(6):1137-1149. [12]CAI Z,VASCONCELOS N J I T O P A,INTELLIGENCE M.Cascade r-cnn:High quality object detection and instance segmentation[J].IEEE Transactions on Pattern Analysis Machine Intelligence,2019,43(5):1483-1498. [13]DAI J,LI Y,HE K,et al.R-fcn:Object detection via region-based fully convolutional networks[C]//Proceedings of the 2016 Advances in Neural Information Processing Systems.2016:379-387. [14]REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:779-788. [15]REDMON J,FARHADI A.YOLO9000:better,faster,stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:7263-7271. [16]FARHADI A,REDMON J.Yolov3:An incremental improvement[C]//Proceedings of the 2018 Computer Vision and Pattern Recognition:Springer Berlin/Heidelberg,Germany,2018:1-6. [17]LONG X,DENG K,WANG G,et al.PP-YOLO:An effectiveand efficient implementation of object detector[J/OL].https://arxiv.org/abs/2007.12099. [18]HUANG X,WANG X,LV W,et al.PP-YOLOv2:A Practical Object Detector[J/OL].https://arxiv.org/abs/2104.10419. [19]LIU W,ANGUELOV D,ERHAN D,et al.Ssd:Single shotmultibox detector[C]//Proceedings of the 2016 European Conference on Computer Vision.Springer,2016:21-37. [20]LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:2980-2988. [21]PANG S,DING T,QIAO S,et al.A novel YOLOv3-arch model for identifying cholelithiasis and classifying gallstones on CT images[J].PLoS One,2019,14(6):e0217647. [22]LEMAY A J A P A.Kidney recognition in CT using YOLOv3[J/O].https://arxiv.org/abs/1910.01268. [23]FURUZUKI M,LU H,KIM H,et al.A Detection Method for Liver Cancer Region Based on Faster R-CNN[C]//2019 19th International Conference on Control,Automation and Systems(ICCAS).IEEE,2019:808-811. [24]CHEN Y,CHEN J,XIAO B,et al.Volume R-CNN:UnifiedFramework for CT Object Detection and Instance Segmentation[C]//2019 IEEE 16th International Symposium on Biomedical Imaging(ISBI 2019).IEEE,2019:872-876. [25]PENG X,YANG X J P I M,BIOLOGY.Liver tumor detection based on objects as points[J].Physics in Medicine and Biology,2021,66(23):235009. [26]GEORGE J,SKARIA S,VARUN V.Using YOLO based deep learning network for real time detection and localization of lung nodules from low dose CT scans[C]//Proceedings of the 2018 Medical Imaging 2018:Computer-Aided Diagnosis:International Society for Optics and Photonics.2018. [27]KETKAR N.Stochastic gradient descent[J/OL].Deep Learning with Python:A hands-on introduction,2017:113-132.https://link.springer.com/chapter/10.1007/978-1-4842-2766-4_8. |
|