Unsupervised Detection of Cancerous Regions in Histology Imagery using Image-to-Image Translation

  title={Unsupervised Detection of Cancerous Regions in Histology Imagery using Image-to-Image Translation},
  author={Dejan {\vS}tepec and Danijel Sko{\vc}aj},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  • Dejan Štepec, D. Skočaj
  • Published 2021
  • Computer Science, Engineering
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Detection of visual anomalies refers to the problem of finding patterns in different imaging data that do not conform to the expected visual appearance and is a widely studied problem in different domains. Due to the nature of anomaly occurrences and underlying generating processes, it is hard to characterize them and obtain labeled data. Obtaining labeled data is especially difficult in biomedical applications, where only trained domain experts can provide labels, which often come in large… Expand
1 Citations

Figures and Tables from this paper

Artificial intelligence in computational pathology – challenges and future directions
The future of the computational pathology is the combination of weak label strategies with active learning and crowdsourcing scenarios since it would remove some of the workload from clinical experts and manual annotation obtaining clinically satisfactory performance with minimal annotation effort. Expand


Image Synthesis as a Pretext for Unsupervised Histopathological Diagnosis
This work evaluates a crucial part of the unsupervised visual anomaly detection pipeline, that is needed for normal appearance modelling, as well as the ability to reconstruct closest looking normal and tumor samples, and adapt and evaluate state-of-the-art generative models from the face synthesis domain and demonstrate their superiority over currently used approaches on a challenging domain of digital pathology. Expand
Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images
This work shows that deep spatial autoencoding models can be efficiently used to capture normal anatomical variability of entire 2D brain MR images and shows that constraints on the latent space and adversarial training can further improve the segmentation performance over standard deep representation learning. Expand
Biomedical Image Segmentation via Representative Annotation
The proposed representative annotation (RA) scheme uses unsupervised networks for feature extraction and selects representative image patches for annotation in the latent space of learned feature descriptors, which implicitly characterizes the underlying data while minimizing redundancy. Expand
Few-Shot Anomaly Detection for Polyp Frames from Colonoscopy
A new few-shot anomaly detection method based on an encoder trained to maximise the mutual information between feature embeddings and normal images, followed by a few- shot score inference network, trained with a large set of inliers and a substantially smaller set of outliers is proposed. Expand
Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
AnoGAN, a deep convolutional generative adversarial network is proposed to learn a manifold of normal anatomical variability, accompanying a novel anomaly scoring scheme based on the mapping from image space to a latent space. Expand
Manifolds for Unsupervised Visual Anomaly Detection
This work develops a novel hyperspherical Variational Auto-Encoder via stereographic projections with a gyroplane layer - a complete equivalent to the Poincare VAE and presents state-of-the-art results on visual anomaly benchmarks in precision manufacturing and inspection, demonstrating real-world utility in industrial AI scenarios. Expand
Scale-Space Autoencoders for Unsupervised Anomaly Segmentation in Brain MRI
The modeling of the laplacian pyramid enables the delineation and aggregation of lesions at multiple scales, which allows to effectively cope with different pathologies and lesion sizes using a single model. Expand
Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation
A deep active learning framework that combines fully convolutional network (FCN) and active learning to significantly reduce annotation effort by making judicious suggestions on the most effective annotation areas is presented. Expand
f‐AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks
Fast AnoGAN (f‐AnoGAN), a generative adversarial network (GAN) based unsupervised learning approach capable of identifying anomalous images and image segments, that can serve as imaging biomarker candidates is presented. Expand
Clinical-grade computational pathology using weakly supervised deep learning on whole slide images
A multiple instance learning-based deep learning system that uses only the reported diagnoses as labels for training, thereby avoiding expensive and time-consuming pixel-wise manual annotations, and has the ability to train accurate classification models at unprecedented scale. Expand