2018
DOI: 10.1007/978-3-030-00934-2_29
|View full text |Cite
|
Sign up to set email alerts
|

Multiple Instance Learning for Heterogeneous Images: Training a CNN for Histopathology

Abstract: Multiple instance (MI) learning with a convolutional neural network enables end-to-end training in the presence of weak imagelevel labels. We propose a new method for aggregating predictions from smaller regions of the image into an image-level classification by using the quantile function. The quantile function provides a more complete description of the heterogeneity within each image, improving image-level classification. We also adapt image augmentation to the MI framework by randomly selecting cropped reg… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
32
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 49 publications
(32 citation statements)
references
References 14 publications
0
32
0
Order By: Relevance
“…Our approaches still work because classifiers can tolerate some error in the training data 52 . In the machine learning literature, this corresponds to the general problem of multi-label, multi-instance supervised learning with imbalanced data, an active area of research including for medical image data 28,[53][54][55] .…”
Section: Discussionmentioning
confidence: 99%
“…Our approaches still work because classifiers can tolerate some error in the training data 52 . In the machine learning literature, this corresponds to the general problem of multi-label, multi-instance supervised learning with imbalanced data, an active area of research including for medical image data 28,[53][54][55] .…”
Section: Discussionmentioning
confidence: 99%
“…For NLP or sentiment analysis, saliency map can also take the form of "heat" scores over words in texts, as demonstrated by Arras et al [62] using LRP and by Karpathy et al [63]. In the medical field (see later section), Irvin et al [6], Zhao et al [44], Paschali et al [64], Couture et al [65], Li et al [66], Qin et al [67], Tang et al [68], Papanastasopoulos et al [69], and Lee et al [70] have studied methods employing saliency and visual explanations. It is noted that we also subcategorize LIME as a method that uses optimization and sensitivity as its underlying mechanisms, and many researches on interpretability span more than one subcategories.…”
Section: A Perceptive Interpretabilitymentioning
confidence: 99%
“…Multilayer CAM (MLCAM) is introduced in [91] for glioma (a type of brain tumor) localization. Multiinstance (MI) aggregation method is used with CNN to classify breast tumor tissue microarray (TMA) image's for five different tasks [65], for example the classification of the histologic subtype. Super-pixel maps indicate the region in each TMA image where the tumor cells are; each label corresponds to a class of tumor.…”
Section: A Perceptive Interpretabilitymentioning
confidence: 99%
“…When only weak annotations are available for images, such as in heterogeneous images, it is often useful to turn to multiple instance learning (MIL). Courture et al [237] described a CNN using quantile function for the classification of 5 types of breast tumor histology. They finetuned AlexNet [23].…”
Section: Breastmentioning
confidence: 99%