Classification of mitotic figures with convolutional neural networks and seeded blob features
Tóm tắt
Background: The mitotic figure recognition contest at the 2012 International Conference on Pattern Recognition (ICPR) challenges a system to identify all mitotic figures in a region of interest of hematoxylin and eosin stained tissue, using each of three scanners (Aperio, Hamamatsu, and multispectral). Methods: Our approach combines manually designed nuclear features with the learned features extracted by convolutional neural networks (CNN). The nuclear features capture color, texture, and shape information of segmented regions around a nucleus. The use of a CNN handles the variety of appearances of mitotic figures and decreases sensitivity to the manually crafted features and thresholds. Results: On the test set provided by the contest, the trained system achieves F1 scores up to 0.659 on color scanners and 0.589 on multispectral scanner. Conclusions: We demonstrate a powerful technique combining segmentation-based features with CNN, identifying the majority of mitotic figures with a fair precision. Further, we show that the approach accommodates information from the additional focal planes and spectral bands from a multi-spectral scanner without major redesign.
Từ khóa
#Mitosis #digital pathology #convolutional neural networkTài liệu tham khảo
1 CW Elston IO Ellis Pathological prognostic factors in breast cancer. I. The value of histological grade in breast cancer: Experience from a large studywith long-term follow-up Histopathology 19 1991 403 410 Elston CW, Ellis IO. Pathological prognostic factors in breast cancer. I. The value of histological grade in breast cancer: Experience from a large studywith long-term follow-up. Histopathology 1991;19:403-10.
2 JS Meyer C Alvarez C Milikowski N Olson I Russo J Russo Breast carcinoma malignancy grading by Bloom-Richardson system vs proliferation index: Reproducibility of grade and advantages of proliferation index Mod Pathol 18 2005 1067 1078 Meyer JS, Alvarez C, Milikowski C, Olson N, Russo I, Russo J, et al. Breast carcinoma malignancy grading by Bloom-Richardson system vs proliferation index: Reproducibility of grade and advantages of proliferation index. Mod Pathol 2005;18:1067-78.
3 Liu A, Li K, Kanade T. Mitosis sequence detection using hidden conditional random fields. IIn Proc. IEEE Intl. Symp. on Biomedical Imaging (ISBI) 2010, Rotterdam, Netherlands. p. 580-3. Liu A, Li K, Kanade T. Mitosis sequence detection using hidden conditional random fields. IIn Proc. IEEE Intl. Symp. on Biomedical Imaging (ISBI) 2010, Rotterdam, Netherlands. p. 580-3.
4 F Yang MA Mackey F Ianzini G Gallardo M Sonka Cell segmentation, tracking, and mitosis detection using temporal context Med Image Comput Comput Assist Interv 8 2005 302 309 Yang F, Mackey MA, Ianzini F, Gallardo G, Sonka M. Cell segmentation, tracking, and mitosis detection using temporal context. Med Image Comput Comput Assist Interv 2005;8:302-9.
5 CY Tao J Hoyt Y Feng A support vector machine classifier for recognizing mitotic subphases using high-content screening data J Biomol Screen 12 2007 490 496 Tao CY, Hoyt J, Feng Y. A support vector machine classifier for recognizing mitotic subphases using high-content screening data. J Biomol Screen 2007;12:490-6.
6 C Malon E Brachtel E Cosatto HP Graf A Kurata M Kuroda Mitotic figure recognition: Agreement among pathologists and computerized detector Anal Cell Pathol (Amst) 35 2012 97 100 Malon C, Brachtel E, Cosatto E, Graf HP, Kurata A, Kuroda M, et al. Mitotic figure recognition: Agreement among pathologists and computerized detector. Anal Cell Pathol (Amst) 2012;35:97-100.
7 N Elie V Becette B Plancoulaine H Pezeril M Brecin Y Denoux Automatic analysis of virtual slides to help in the determination of well established prognostic parameters in breast carcinomas (abstract) Anal Cell Pathol 34 2011 187 188 Elie N, Becette V, Plancoulaine B, Pezeril H, Brecin M, Denoux Y, et al. Automatic analysis of virtual slides to help in the determination of well established prognostic parameters in breast carcinomas (abstract). Anal Cell Pathol 2011;34:187-8.
8 R Weinstein AR Graham F Lian AK Bhattacharyya Z-axis challenges in whole slide imaging (WSI) telepathology (abstract) Anal Cell Pathol 34 2011 175 Weinstein R, Graham AR, Lian F, Bhattacharyya AK. Z-axis challenges in whole slide imaging (WSI) telepathology (abstract). Anal Cell Pathol 2011;34:175.
9 LE Boucheron Z Bi NR Harvey B Manjunath DL Rimm Utility of multispectral imaging for nuclear classification of routine clinical histopathology imagery BMC Cell Biol 8 Suppl 1 2007 S8 Boucheron LE, Bi Z, Harvey NR, Manjunath B, Rimm DL. Utility of multispectral imaging for nuclear classification of routine clinical histopathology imagery. BMC Cell Biol 2007;8 Suppl 1:S8.
10 K Masood NM Rajpoot Spatial analysis for colon biopsy classification from hyperspectral imagery Ann Br Mach Vis Assoc 4 2008 1 16 Masood K, Rajpoot NM. Spatial analysis for colon biopsy classification from hyperspectral imagery. Ann Br Mach Vis Assoc 2008;4:1-16.
11 Y Le Cun L Bottou Y Bengio P Haffner Gradient-based learning applied to document recognition Proc IEEE 86 1998 2278 2324 Le Cun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE 1998;86:2278-324.
12 C Garcia M Delakis Convolutional face finder: A neural architecture for fast and robust face detection IEEE Trans Pattern Anal Mach Intell 26 2004 1408 1423 Garcia C, Delakis M. Convolutional face finder: A neural architecture for fast and robust face detection. IEEE Trans Pattern Anal Mach Intell 2004;26:1408-23.
13 M Osadchy Y Le Cun ML Miller Synergistic face detection and pose estimation with energy-based models J Mach Learn Res 8 2007 1197 1215 Osadchy M, Le Cun Y, Miller ML. Synergistic face detection and pose estimation with energy-based models. J Mach Learn Res 2007;8:1197-1215.
14 SB Lo SA Lou JS Lin MT Freedman MV Chien SK Mun Artificial convolution neural network techniques and applications for lung nodule detection IEEE Trans Med Imaging 14 1995 711 718 Lo SB, Lou SA, Lin JS, Freedman MT, Chien MV, Mun SK. Artificial convolution neural network techniques and applications for lung nodule detection. IEEE Trans Med Imaging 1995;14:711-8.
15 K Jarrett K Kavukcuoglu MA Ranzato Y LeCun What is the best multi-stage architecture for object recognition? In Proc Intl Conf on Comput Vis 2009 2146 2153 Jarrett K, Kavukcuoglu K, Ranzato MA, LeCun Y. What is the best multi-stage architecture for object recognition? In Proc Intl Conf on Comput Vis 2009;2146-53.
16 Y Le Cun L Bottou GB Orr KR Muller Efficient backprop. In neural networks, tricks of the trade Lect Notes Comput Sci 1524 1998 9 50 Le Cun Y, Bottou L, Orr GB, Muller KR. Efficient backprop. In neural networks, tricks of the trade. Lect Notes Comput Sci 1524, 1998, p. 9-50.
17 Ahmed A, Yu K, Xu W, Gong Y, Xing E. Training hierarchical feed-forward visual recognition models using transfer learning from pseudo tasks. In: European Conference on Computer Vision. Part 3. Lect Notes in Comput Sci 5304; 2008. p. 69-82. Ahmed A, Yu K, Xu W, Gong Y, Xing E. Training hierarchical feed-forward visual recognition models using transfer learning from pseudo tasks. In: European Conference on Computer Vision. Part 3. Lect Notes in Comput Sci 5304; 2008. p. 69-82.
18 Ranzato M, Huang F, Boureau YL, LeCun Y. Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: IEEE Conference on Computer Vision and Pattern Recognition 2007. p. 1-8. Ranzato M, Huang F, Boureau YL, LeCun Y. Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: IEEE Conference on Computer Vision and Pattern Recognition 2007. p. 1-8.