AggNet: Deep Learning From Crowds for Mitosis Detection in Breast Cancer Histology Images

By Shadi Albarqouni, Christoph Baur, Felix Achilles, Vasileios Belagiannis, Stefanie Demirci, Nassir Navab. IEEE Transactions on Medical Imaging, 2016

502 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Science Applications, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/f15a6caf0d6062fc6e100c3ed64e2634e5f9949f

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

In Computer Science Applications

Aditya Khosla

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Medical Image Analysis using Convolutional Neural Networks: A Review (2017, methodology): “In [92], a CNN based deep learning framework is presented for detection of mitosis in histopathology breast cancer images using crowd based learning on a publicly available dataset, MICCAI-AMID13 having histology images of 23 patients.”
Deep Learning and Its Applications in Biomedicine (2018, background): “On the other hand, crowdsourcing approaches have begun to pave the way in collecting annotations [191,192], which may be an important tool in the next few years.”
Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification (2018, background): “The noticeable progress in deep learning has beneﬁted many trials in medical image analysis, such as lesion segmentation or detection [1], [2], [3], [4], [5], diseases classiﬁcation [6], [7], [8], [9], noise induction [10], image annotation [11], [12], registration [13], regression [14] and so on.”
The impact of pre- and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis (2020, methodology): “Finally, Albarqouni et al. [163] implemented a multi-scale CNN for mitosis detection, combining the output probability of three different CCNs.”
Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets. (2017, methodology): “Previously deep learning has been used mostly for unsupervised learning and noisy data 28–34 .”
Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer (2017, background): “Test (n=129 slides and images) RUMC 23 6 50 14 15 2 (1-14) 79”
Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis (2018, methodology): “Methods which use the crowdsourced labels inside machine learning methods, are less common, for example [Albarqouni et al., 2016].”
Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review (2017, methodology): “widely used in brain MRI for preprocessing data [15], detecting and segmenting lesions [16, 17, 18, 19, 20, 21] and segmenting tumours [22, 23, 24], whole tissue [25, 26, 27] and sub-cortical structures [28, 29].”
A review on deep learning in medical image analysis (2021, methodology): “Random projection is a more computationally effective dimensionality reduction approach than principal component analysis [45].”
Deep learning with noisy labels: exploring techniques and remedies in medical image analysis (2019, background): “There have also been studies that have used crowd-sourcing methods to obtain labels from non-experts [24], [25].”