基于HOG特征和滑动窗口的乳腺病理图像细胞检测

doi:10.6040/j.issn.1672-3961.2.2014.048

山东大学学报(工学版) ›› 2015, Vol. 45 ›› Issue (1): 37-44.doi: 10.6040/j.issn.1672-3961.2.2014.048

基于HOG特征和滑动窗口的乳腺病理图像细胞检测

项磊, 徐军

南京信息工程大学信息与控制学院, 江苏南京 210044

收稿日期:2014-05-23 修回日期:2014-12-11 发布日期:2014-05-23
作者简介:项磊(1990-),男,江苏南京人,硕士研究生,主要研究方向为深度学习,模式识别.Email:xianglei19900125@163.com
基金资助:
国家自然科学基金资助项目(61273259);江苏省"六大人才高峰"高层次人才资助项目(2013-XXRJ-019)

Nuclei detection of breast histopathology based on HOG feature and sliding window

XIANG Lei, XU Jun

School of Information and Control, Nanjing University of Information Science & Technology, Najing 210044, Jiangsu, China

Received:2014-05-23 Revised:2014-12-11 Published:2014-05-23

摘要/Abstract

摘要： 提出一种基于方向梯度直方图(histograms of oriented gradient, HOG) 特征和滑动窗口的细胞检测方法,能快速、高效、准确地检测高分辨率病理组织图像中的细胞。该检测算法首先对训练集中的细胞样本块和非细胞样本块提取HOG特征,然后运用HOG特征训练分类器。训练好的分类器用于在整幅病理图像中自动检测细胞。先运用滑动窗的方法在整幅高分辨率病理图像中选取相同尺寸的所有可能的细胞块,被滑动窗选定的图像块提取HOG特征后,送到训练好的分类器中判断是否是细胞块。为了验证提出方法的有效性,将此方法运用于17名乳腺患者的共37张H&E(hematoxylin & eosin)染色高分辨率穿刺切片病理图像上自动检测细胞, 通过与softmax(SM)分类器、稀疏自编码器+SM、局部二值模式+SM、支持向量机(support vector machine, SVM)、HOG+SVM、以及 HOG+SVM 多个模型对细胞检测的准确率、召回率以及综合评价指标的对比表明,本研究提出的方法分别为71.5%,82.3%和76.5%,具有更高的准确率。

关键词: 滑动窗口, 非最大值抑制, 细胞检测, 方向梯度直方图特征, 组织病理图像

Abstract: A new method was presented which integrated histograms of oriented gradient (HOG) feature and sliding window for rapid, efficient and accurate detection of nuclei from high resolution pathological images. HOG feature was extracted from the training samples which include both nuclei and non-nuclei patches. The supervised classifier were trained with HOG features. The trained classifier was employed for automated nuclei detection from input patches that selected from histopathological images. During the detection, sliding window was used to select patches. In order to verify the effectiveness of the method on detecting nuclei from histopathological images, this article compared the proposed method with softmax (SM) classifier, sparse autoencoder(SAE)+SM, local binary pattern (LBP)+SM, support vector machine(SVM), HOG+SM, and HOG+SVM models. The experiments on 37 pieces of H&E staining histopathological images showed that the proposed method achieved highest precision, recall and F₁-measure values, which were 71.5%, 82.3% and 76.5% respectively.

Key words: non-maxima suppression, histopathological image, HOG feature, sliding window, nuclei detection

中图分类号:

TP 18

项磊, 徐军. 基于HOG特征和滑动窗口的乳腺病理图像细胞检测[J]. 山东大学学报(工学版), 2015, 45(1): 37-44.

XIANG Lei, XU Jun. Nuclei detection of breast histopathology based on HOG feature and sliding window[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2015, 45(1): 37-44.

参考文献

[1] LERMAN C, TROCK B, RIMER B K, et al. Psychological side effects of breast cancer screening[J]. Health Psychology, 1991, 10(4):259.
[2] FATAKDAWALA H, XU J, BASAVANHALLY A, et al. Expectation—maximization-driven geodesic active contour with overlap resolution (emagacor):application to lymphocyte segmentation on breast cancer histopathology[J]. Biomedical Engineering, IEEE Transactions on, 2010, 57(7):1676-1689.
[3] MOUELHI A, SAYADI M, FNAIECH F, et al. Automatic image segmentation of nuclear stained breast tissue sections using color active contour model and an improved watershed method[J]. Biomedical Signal Processing and Control, 2013, 8(5):421-436.
[4] XU J, JANOWCZYK A, CHANDRAN S, et al. A high-throughput active contour scheme for segmentation of histopathological imagery[J]. Medical Image Analysis, 2011, 15(6):851-862.
[5] BASAVANHALLY A, XU J, MADABHUSHI A, et al. Computer-aided prognosis of ER+breast cancer histopathology and correlating survival outcome with oncotype DX assay[C]//Biomedical Imaging:From Nano to Macro. [S.l.]:IEEE, 2009:851-854.
[6] GHAZNAVI F, EVANS A, MADABHUSHI A, et al. Digital imaging in pathology:whole-slide imaging and beyond[J]. Annual Review of Pathology:Mechanisms of Disease, 2013, 8:331-359.
[7] CIREŞAN D C, GIUSTI A, GAMBARDELLA L M, et al. Mitosis detection in breast cancer histology images with deep neural networks[C]//Medical Image Computing and Computer-Assisted Intervention. Germany:Springer Berlin Heidelberg, 2013:411-418.
[8] WOLBERG W H, STREET W N, MANGASARIAN O L. Machine learning techniques to diagnose breast cancer from image-processed nuclear features of fine needle aspirates[J]. Cancer Letters, 1994, 77(2):163-171.
[9] BASAVANHALLY A N, GANESAN S, AGNER S, et al. Computerized image-based detection and grading of lymphocytic infiltration in HER2+breast cancer histopathology[J]. Biomedical Engineering, IEEE Transactions on, 2010, 57(3):642-653.
[10] PETUSHI S, GARCIA F U, HABER M M, et al. Large-scale computations on histology images reveal grade-differentiating parameters for breast cancer[J]. BMC Medical Imaging, 2006, 6(1):14.
[11] DI Cataldo S, FICARRA E, ACQUAVIVA A, et al. Automated segmentation of tissue images for computerized IHC analysis[J]. Computer Methods and Programs in Biomedicine, 2010, 100(1):1-15.
[12] DI Cataldo S, FICARRA E, ACQUAVIVA A, et al. Achieving the way for automated segmentation of nuclei in cancer tissue images through morphology-based approach:a quantitative evaluation[J]. Computerized Medical Imaging and Graphics, 2010, 34(6):453-461.
[13] IRSHAD H, VEILLARD A, ROUX L, et al. Methods for nuclei detection, segmentation and classification in digital histopathology:a review [J].Current Status and Future Potential, 2013.
[14] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Computer Vision and Pattern Recognition. [S.l.]:IEEE, 2005:886-893.
[15] LAMPERT C H, BLASCHKO M B, HOFMANN T. Beyond sliding windows: object localization by efficient subwindow search[C]//Computer Vision and Pattern Recognition.[S.l.]:IEEE Conference on. IEEE, 2008:1-8.
[16] BOSCH A, ZISSERMAN A, MUNOZ X. Representing shape with a spatial pyramid kernel[C]//Proceedings of the 6th ACM international conference on Image and video retrieval.[S.l.]:[S.n.], 2007:401-408.
[17] OJALA T, PIETIKAINEN M, MAENPAA T, et al. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2002, 24(7):971-987.
[18] LIENHART R, MAYDT J. An extended set of haar-like features for rapid object detection[C]//Image Processing.[S.l.]: IEEE, 2002.
[19] VIOLA P, JONES M J, HU X. Robust real-time face detection[J]. International Journal of Computer Vision, 2004, 57(2):137-154.
[20] CRISTIANINI N, SHAWE-TAYLOR J. An introduction to support vector machines and other kernel-based learning methods[M]. London:Cambridge University Press, 2000:331-346.
[21] BARINOVA O, LEMPITSKY V, KHOLI P. On detection of multiple object instances using hough transforms[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2012, 34(9):1773-1784.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于HOG特征和滑动窗口的乳腺病理图像细胞检测

Nuclei detection of breast histopathology based on HOG feature and sliding window

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

多维度评价

本文评价

推荐阅读 10

[1]	王斌,常发亮,刘春生. 基于多特征融合的交通标志分类[J]. 山东大学学报(工学版), 2016, 46(4): 34-40.
[2]	朱全银1,严云洋1,周培1,谷天峰2. 一种线性插补与自适应滑动窗口价格预测模型[J]. 山东大学学报(工学版), 2012, 42(5): 53-58.
[3]	刘文亮,朱维红,陈涤,张泓泉. 基于雷达图像的运动目标形态检测及跟踪技术[J]. 山东大学学报(工学版), 2010, 40(3): 31-36.