Multiscale generative model using regularized skip-connections and perceptual loss for anomaly detection in toxicologic histopathology

Zehnder, Philip; Feng, Jeffrey; Fuji, Reina N.; Sullivan, Ruth; Hu, Fangyao

doi:10.1016/j.jpi.2022.100102

Cited by 4 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One such limitation is the prediction of rare disease, for which it is hard to gather enough annotated examples to train any ML model. This long tail of disease can be approached by anomaly detection (119,120), an ML concept that revolves around detecting data that are not similar to most of the data at hand and, therefore, allows the model to train on naturally distributed data and promises to flag data that are uncommon to it. This orthogonal approach is fundamental to AI in real-world scenarios in order to catch potential fail cases that should be referred to human experts.…”

Section: Unsupervised Learningmentioning

confidence: 99%

Toward Explainable Artificial Intelligence for Precision Pathology

Klauschen,

Dippel,

Keyl

et al. 2024

Annu. Rev. Pathol. Mech. Dis.

View full text Add to dashboard Cite

The rapid development of precision medicine in recent years has started to challenge diagnostic pathology with respect to its ability to analyze histological images and increasingly large molecular profiling data in a quantitative, integrative, and standardized way. Artificial intelligence (AI) and, more precisely, deep learning technologies have recently demonstrated the potential to facilitate complex data analysis tasks, including clinical, histological, and molecular data for disease classification; tissue biomarker quantification; and clinical outcome prediction. This review provides a general introduction to AI and describes recent developments with a focus on applications in diagnostic pathology and beyond. We explain limitations including the black-box character of conventional AI and describe solutions to make machine learning decisions more transparent with so-called explainable AI. The purpose of the review is to foster a mutual understanding of both the biomedical and the AI side. To that end, in addition to providing an overview of the relevant foundations in pathology and machine learning, we present worked-through examples for a better practical understanding of what AI can achieve and how it should be done. Expected final online publication date for the Annual Review of Pathology: Mechanisms of Disease, Volume 19 is January 2024. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

show abstract

Section: Unsupervised Learningmentioning

confidence: 99%