Visualizing histopathologic deep learning classification and anomaly detection using nonlinear feature space dimensionality reduction

Faust, Kevin; Xie, Quin; Han, Dominick; Goyle, Kartikay; Volynskaya, Zoya; Djuric, Ugljesa; Diamandis, Phedias

doi:10.1186/s12859-018-2184-4

Cited by 60 publications

(39 citation statements)

References 21 publications

(3 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, there has been a surge of interest in developing deep learning approaches for AD. This is motivated by a lack of effective methods for AD tasks that involve complex data, for instance, cancer detection from multigigapixel whole-slide images in histopathology [124]. As in other adoptions of deep learning, the goal of deep AD is to mitigate the burden of manual feature engineering and to enable effective, scalable solutions.…”

Section: Introductionmentioning

confidence: 99%

A Unifying Review of Deep and Shallow Anomaly Detection

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

A Unifying Review of Deep and Shallow Anomaly Detection

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Dimensionality reduction techniques are commonly used to visualize network representations of data and gain intuition into how the network separates classes, but they can also be used to identify outlier data. In ( Faust et al , 2018 ), the authors apply a k nearest neighbors approach to tSNE-produced representations of patches drawn from whole slide histology images of CNS tissue samples. They find that tSNE representations of new glioma patches fall close to glioma patches in their training data.…”

Section: Discussionmentioning

confidence: 99%

“…It can thus be used for several applications, for example visualizing patterns and clusters across classes and detecting outliers. This technique has been applied to the classification of abdominal ultrasound images ( Cheng and Malhi, 2017 ) as well as classification and anomaly detection in histopathology images ( Faust et al , 2018 ). An example of tSNE images generated from ( Faust et al , 2018 ) is shown in Figure 4A .…”

Section: Understanding Model Structure and Functionmentioning

confidence: 99%

“…This technique has been applied to the classification of abdominal ultrasound images ( Cheng and Malhi, 2017 ) as well as classification and anomaly detection in histopathology images ( Faust et al , 2018 ). An example of tSNE images generated from ( Faust et al , 2018 ) is shown in Figure 4A . In ( Yu et al , 2018 ), tSNE was performed not only on the components of the fully connected layers but also on vectorized 2D ultrasound images.…”

Section: Understanding Model Structure and Functionmentioning

confidence: 99%

See 1 more Smart Citation

Interpretation and visualization techniques for deep learning models in medical imaging

2021

View full text Add to dashboard Cite

Deep learning approaches to medical image analysis tasks have recently become popular; however, they suffer from a lack of human interpretability critical for both increasing understanding of the methods’ operation and enabling clinical translation. This review summarizes currently available methods for performing image model interpretation and critically evaluates published uses of these methods for medical imaging applications. We divide model interpretation in two categories: (1) understanding model structure and function and (2) understanding model output. Understanding model structure and function summarizes ways to inspect the learned features of the model and how those features act on an image. We discuss techniques for reducing the dimensionality of high-dimensional data and cover autoencoders, both of which can also be leveraged for model interpretation. Understanding model output covers attribution-based methods, such as saliency maps and class activation maps, which produce heatmaps describing the importance of different parts of an image to the model prediction. We describe the mathematics behind these methods, give examples of their use in medical imaging, and compare them against one another. We summarize several published toolkits for model interpretation specific to medical imaging applications, cover limitations of current model interpretation methods, provide recommendations for deep learning practitioners looking to incorporate model interpretation into their task, and offer general discussion on the importance of model interpretation in medical imaging contexts.

show abstract

“…A class-activation map technique was employed to provide a heat map to identify the location of the lung nodule. 58 …”

Section: Interpretability Improvement For Deep Learningmentioning

confidence: 99%

Balancing accuracy and interpretability of machine learning approaches for radiation treatment outcomes modeling

Luo

Tseng

Cui³

et al. 2019

BJR|Open

View full text Add to dashboard Cite

Radiation outcomes prediction (ROP) plays an important role in personalized prescription and adaptive radiotherapy. A clinical decision may not only depend on an accurate radiation outcomes’ prediction, but also needs to be made based on an informed understanding of the relationship among patients’ characteristics, radiation response and treatment plans. As more patients’ biophysical information become available, machine learning (ML) techniques will have a great potential for improving ROP. Creating explainable ML methods is an ultimate task for clinical practice but remains a challenging one. Towards complete explainability, the interpretability of ML approaches needs to be first explored. Hence, this review focuses on the application of ML techniques for clinical adoption in radiation oncology by balancing accuracy with interpretability of the predictive model of interest. An ML algorithm can be generally classified into an interpretable (IP) or non-interpretable (NIP) (“black box”) technique. While the former may provide a clearer explanation to aid clinical decision-making, its prediction performance is generally outperformed by the latter. Therefore, great efforts and resources have been dedicated towards balancing the accuracy and the interpretability of ML approaches in ROP, but more still needs to be done. In this review, current progress to increase the accuracy for IP ML approaches is introduced, and major trends to improve the interpretability and alleviate the “black box” stigma of ML in radiation outcomes modeling are summarized. Efforts to integrate IP and NIP ML approaches to produce predictive models with higher accuracy and interpretability for ROP are also discussed.

show abstract

Visualizing histopathologic deep learning classification and anomaly detection using nonlinear feature space dimensionality reduction

Cited by 60 publications

References 21 publications

A Unifying Review of Deep and Shallow Anomaly Detection

A Unifying Review of Deep and Shallow Anomaly Detection

Interpretation and visualization techniques for deep learning models in medical imaging

Balancing accuracy and interpretability of machine learning approaches for radiation treatment outcomes modeling

Contact Info

Product

Resources

About