Assessment of algorithms for mitosis detection in breast cancer histopathology images

By M. Veta, P. Diest, S. Willems, Haibo Wang, Anant Madabhushi, Angel Cruz-Roa, Fabio A. González, A. Larsen, Jacob S. Vestergaard, Anders Bjorholm Dahl and 19 more. Medical Image Anal., 2014

464 citations recorded by the source corpus.

The proliferative activity of breast tumors, which is routinely estimated by counting of mitotic figures in hematoxylin and eosin stained histology sections, is considered to be one of the most important prognostic markers. However, mitosis counting is laborious, subjective and may suffer from low inter-observer agreement. With the wider acceptance of whole slide images in pathology labs, automatic image analysis has been proposed as a potential solution for these issues. In this paper, the results from the Assessment of Mitosis Detection Algorithms 2013 (AMIDA13) challenge are described. The challenge was based on a data set consisting of 12 training and 11 testing subjects, with more than one thousand annotated mitotic figures by multiple observers. Short descriptions and results from the evaluation of eleven methods are presented. The top performing method has an error rate that is comparable to the inter-observer agreement among pathologists.

Subfields: Artificial Intelligence, Biophysics, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/edf931d8d22c024ec558b06f798f69ebb5764d8b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. P. Heng
2. Qi-Yan Dou
3. Hao Chen
4. Yoshua Bengio
5. Mohit Bansal
6. Lorenzo Torresani
7. Quoc V. Le
8. Lequan Yu

In Biophysics

1. Peter Naylor
2. Thomas Walter
3. Fabien Reyal
4. Marick Lae
5. Andrew Janowczyk
6. Fuyong Xing
7. Lin F. Yang
8. Anant Madabhushi

In Radiology, Nuclear Medicine and Imaging

1. P. Heng
2. Hao Chen
3. Qi-Yan Dou
4. Jing Qin
5. Lequan Yu
6. Lin F. Yang
7. Andrew Janowczyk
8. Fuyong Xing

Citations in the corpus

• Emerging role of deep learning‐based artificial intelligence in tumor pathology (2020, methodology): “The Assessment of Mitosis Detection Algorithms 2013 (AMIDA13) generated a good algorithm recognizing mitoses with the F1-score of 0.611 on 1000 images at high power fields (HPFs) from breast cancers, which was comparable to the performance of inter-observers [57].”
• Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (2017, unknown): “The performances of the mitosis detection models were evaluated with the F 1 - score as described in [2,9,1].”
• Deep neural network models for computational histopathology: A survey (2019, background): “, 2019) and if possible, a consensus between pathologists reached (Veta et al., 2015).”
• Structure-Preserving Color Normalization and Sparse Stain Separation for Histological Images (2016, background): “This can also help in computational pathology, for example in quantification of cancer-related structure information, such as the count of certain nuclei and shape of glands [7], [8], and in custom visualization of the structure information using false colors.”
• Deep Learning for Classification of Colorectal Polyps on Whole-slide Images (2017, background): “t dierentiation between hyperplastic polyps and sessile serrated polyp is another major source of mistakes for our model, which is aligned with gastrointestinal pathologists’ experience in this task [45, 16, 44]. Although our proposed histopathology characterization system is based on strong deep-le”
• Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases (2016, background): “DL algorithms also have the potential for being the unifying approach for the many tasks in DP, having previously been shown to produce state-of-the-art results across varied domains, including mitosis detection,[6-8] tissue classification,[9] and immunohistochemical staining.”
• Detecting Cancer Metastases on Gigapixel Pathology Images (2017, methodology): “CNNs were also used to detect mitosis, winning the ICPR12 [6] and AMIDA13 [22] mitosis detection competitions.”
• Segmentation of Nuclei in Histopathology Images by Deep Regression of the Distance Map (2019, background): “states, such as mitoses [8], [9] or the classification of tissue regions, such as glands [10] and necrotic or metastatic regions [11], [12] and prediction of tumor type and grade [13]–[15].”
• AggNet: Deep Learning From Crowds for Mitosis Detection in Breast Cancer Histology Images (2016, background): “reader is referred to [32] for more information about the dataset”