Detecting mitotic figures in breast cancer histopathology images

Veta, Mitko; Diest, van; Pluim, Jpw Josien

doi:10.1117/12.2006626

Cited by 36 publications

(21 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other approaches [18,8,12,20] address this issue by first detecting all nuclei, then classifying each nucleus separately as mitotic or non-mitotic. We follow a different, simpler approach, which does not need any additional ground-truth information and relies on a single trained detector.…”

Section: Materials Experiments and Resultsmentioning

confidence: 99%

“…We also report the performance of faster but less accurate versions of our approach, namely: DNNf12, which averages the results of nets DNN1 and DNN2 without computing input variations (1 minute per image), and DNNf1, which is computed only from the result of DNN1 (31s per image). [12] 0.74 0.59 0.659 DREXEL 0.14 0.21 0.172 UTRECHT [20] 0.51 0.68 0.583 BII 0.10 0.32 0.156 WARWICK [10] 0.46 0.57 0.513 QATAR 0.00 0.94 0.005 Fig. 2.…”

Section: Performance and Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks

Cireşan

Giusti

Gambardella

et al. 2013

Lecture Notes in Computer Science

1,070

740

View full text Add to dashboard Cite

Abstract. We use deep max-pooling convolutional neural networks to detect mitosis in breast histology images. The networks are trained to classify each pixel in the images, using as context a patch centered on the pixel. Simple postprocessing is then applied to the network output. Our approach won the ICPR 2012 mitosis detection competition, outperforming other contestants by a significant margin.

show abstract

Section: Materials Experiments and Resultsmentioning

confidence: 99%

Section: Performance and Comparisonmentioning

confidence: 99%

Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks

Cireşan

Giusti

Gambardella

et al. 2013

Lecture Notes in Computer Science

1,070

740

View full text Add to dashboard Cite

show abstract

“…We study how top-performing mitosis detection algorithms [4,5,6,7,8] in the recent ICPR2012 mitosis detection contest [9] compare with the performance of humans which are new to the problem. We design an user test that places such humans in the same conditions as algorithms (i.e.…”

Section: Introductionmentioning

confidence: 99%

A comparison of algorithms and humans for mitosis detection

Giusti

Caccia

Cireşan

et al. 2014

2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

We consider the problem of detecting mitotic figures in breast cancer histology slides. We investigate whether the performance of stateof-the-art detection algorithms is comparable to the performance of humans, when they are compared under fair conditions: our test subjects were not previously exposed to the task, and were required to learn their own classification criteria solely by studying the same training set available to algorithms. We designed and implemented a standardized web-based test based on the publicly-available MITOS dataset, and compared results with the performance of the 6 topscoring algorithms in the ICPR 2012 Mitosis Detection Contest. The problem is presented as a classification task on a balanced dataset. 45 different test subjects produced a total of 3009 classifications. The best individual (accuracy = 0.859 ± 0.012), is outperformed by the most accurate algorithm (accuracy = 0.873 ± 0.004). This suggests that state-of-the-art detection algorithms are likely limited by the size of the training set, rather than by lack of generalization ability.

show abstract

“…The NEC team [21] and CCIPD/MINDLAB team [19] employed the learned CNN-derived features for mitosis detection. The UTRECHT team extracted size, shape, color and texture features of candidate objects for automatically detecting mitotic figures [66]. The WARWICK approach modeled the pixel intensities of mitosis by a Gamma-Gaussian mixture model in conjunction with the SVM classifier [44].…”

Section: Comparative Strategiesmentioning

confidence: 99%

Automated mitosis detection in histopathology based on non-gaussian modeling of complex wavelet coefficients

et al. 2017

View full text Add to dashboard Cite

General rightsThis document is made available in accordance with publisher policies. Please cite only the published version using the reference above. AbstractTo diagnose breast cancer, the number of mitotic cells present in histology sections is an important indicator for examining and grading biopsy specimen. This study aims at improving the accuracy of automated mitosis detection by characterizing mitotic cells in wavelet based multi-resolution representations via a non-Gaussian modeling method. The potential mitosis candidates were decomposed into multi-scale forms by an undecimated dual-tree complex wavelet transform. Two non-Gaussian models (the generalized Gaussian distribution (GGD) and the symmetric alpha-stable (SαS) distributions) were used to accurately model the heavy-tailed behavior of wavelet marginal distributions. The method was evaluated on two independent data cohorts, including the benchmark dataset (MITOS), via a support vector machine classifier.

show abstract

Detecting mitotic figures in breast cancer histopathology images

Cited by 36 publications

References 2 publications

Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks

Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks

A comparison of algorithms and humans for mitosis detection

Automated mitosis detection in histopathology based on non-gaussian modeling of complex wavelet coefficients

Contact Info

Product

Resources

About