2020
DOI: 10.21203/rs.3.rs-48727/v1
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

An Annotation-free Whole-slide Training Approach to Pathological Classification of Lung Cancer Types by Deep Neural Network

Abstract: Deep learning for digital pathology is hindered by the extremely high spatial resolution of whole slide images (WSIs). Most studies adopt patch-based methods which, however, require well annotated data for training. These are typically done by laboriously free-hand contouring on the WSI by experts. To both alleviate annotation burdens of experts and enjoy benefits from scaling up amounts of data, we develop a whole-slide training method for entire WSIs to classify types of lung cancers using slide-level diagno… Show more

Help me understand this report
View published versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2021
2021
2021
2021

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 17 publications
0
1
0
Order By: Relevance
“…To analyze which parts of an image a neural network focuses on while making a classification decision, class activation maps (CAMs) are used for various applications, including cancer classification [ 39 ], grading [ 40 ], and diagnosis [ 41 ]. CAM is generated for each class of the network by obtaining the weighted sum of the last convolutional features (activation maps) using the fully connected layer weights [ 42 ].…”
Section: Methodsmentioning
confidence: 99%
“…To analyze which parts of an image a neural network focuses on while making a classification decision, class activation maps (CAMs) are used for various applications, including cancer classification [ 39 ], grading [ 40 ], and diagnosis [ 41 ]. CAM is generated for each class of the network by obtaining the weighted sum of the last convolutional features (activation maps) using the fully connected layer weights [ 42 ].…”
Section: Methodsmentioning
confidence: 99%