Weakly supervised histopathology cancer image segmentation and classification

By Yan Xu, Jun-Yan Zhu, Eric I-Chao Chang, Maode Lai, Zhuowen Tu. Medical Image Anal., 2014

312 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/342ce4663b1cbe2a1ca2f0e85bd362a3432635b8

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 Vision and Pattern Recognition

Citations in the corpus

Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis (2018, background): “, 2012; Kandemir and Hamprecht, 2015) and detection of cancerous regions in histopathology images (Kandemir and Hamprecht, 2015; Xu et al., 2014; Li et al., 2015).”
A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises (2020, methodology): “To relax the stringent pixelwise annotation for image segmentation, weakly supervised methods that use image-level annotations [66] or weak annotations, such as dots and scribbles [67], are proposed.”
Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles (2016, methodology): “…al., 1997; Sertel et al., 2010; Sparks and Madabhushi, 2013; Sudbø et al., 2000; Tabesh and Teverovskiy, 2006; Tabesh et al., 2007, 2005; Tahir and Bouridane, 2006; Tasoulis et al., 2003; Teverovskiy et al., 2004; Thiran and Macq, 1996; Tsai et al., 2009; Xu et al. 2014a, 2014b; Yang et al., 2009).”
Large scale tissue histopathology image classification, segmentation, and visualization via deep convolutional activation features (2017, methodology): “Medical image segmentation methods can be generally classified into three categories: supervised learning [29], weakly supervised [48] and unsupervised [32].”
Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification (2015, methodology): “Utilizing unlabeled patches has led to Multiple Instance Learning (MIL) based WSI classification [16, 51, 52].”
Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning (2020, methodology): “MIL has been successfully applied to computational histopathology for tasks such as cell segmentation and tumor detection [54, 20, 37, 22, 3, 7].”
Deep neural network models for computational histopathology: A survey (2019, background): “Weakly supervised learning dramatically reduces the annotation burden on a pathologist (Xu et al., 2014), and an overview of these models is provided in Table 2.”
MILCut: A Sweeping Line Multiple Instance Learning Paradigm for Interactive Image Segmentation (2014, methodology): “Following CCMIL [38], we explicitly model the structural information in the likelihood function in training and testing in a formulation named MILCut-Struct.”
Causability and explainability of artificial intelligence in medicine (2019, background): “Particularly, labeling a histopathological image is not only time-consuming but also a critical task for cancer diagnosis, as it is clinically important to segment the cancer tissues and cluster them into various classes (Xu, Zhu, Chang, Lai, & Tu, 2014).”
Machine Learning Methods for Histopathological Image Analysis (2017, methodology): “Variousmethods inmultiple instance learning have been applied to histopathological image analysis including boosting-based approach [49], support vector machine-based approach [52] and deep learning-based approach [51].”
Multiple instance learning: A survey of problem characteristics and applications (2016, background): “The iseases and image modalities used are very diverse; applications nclude classification of cancer in histopathology images [141] , diaetes in retinal images [142] , dementia in brain MR [143] , tubercuosis in X-ray images [144] , classification of a chronic lung disease n CT [145] and others.”
Multiple Instance Learning for Heterogeneous Images: Training a CNN for Histopathology (2018, background): “Most MI applications use the maximum, which works well for problems such as cancer diagnosis where, if there is a small amount of tumor, the sample is labeled as cancerous [6,16].”
Artificial intelligence in histopathology: enhancing cancer research and clinical oncology (2022, background): “As early as 2010, several groups experimented with MIL in pathology image analysis 112,113 , but it took several years for these ideas to be more broadly used 114 .”