UNCERTAINTY MODELING AND INTERPRETABILITY IN CONVOLUTIONAL NEURAL NETWORKS FOR POLYP SEGMENTATION

By Kristoffer Wickstrøm, Michael C. Kampffmeyer, Robert Jenssen. 2018

77 citations recorded by the source corpus.

Convolutional Neural Networks (CNNs) are propelling advances in a range of different computer vision tasks such as object detection and object segmentation. Their success has motivated research in applications of such models for medical image analysis. If CNN-based models are to be helpful in a medical context, they need to be precise, interpretable, and uncertainty in predictions must be well understood. In this paper, we develop and evaluate recent advances in uncertainty estimation and model interpretability in the context of semantic segmentation of polyps from colonoscopy images. We evaluate and enhance several architectures of Fully Convolutional Networks (FCNs) for semantic segmentation of colorectal polyps and provide a comparison between these models. Our highest performing model achieves a 76.06% mean IOU accuracy on the EndoScene dataset, a considerable improvement over the previous state-of-the-art.

Subfields: Oncology, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Oncology

1. Arvid Lundervold
2. Shuguang Cui
3. Yingyan Yu
4. Ruixin Yang

In Radiology, Nuclear Medicine and Imaging

1. Guanbin Li
2. Arvid Lundervold
3. Xiaochun Cao
4. Yizhou Yu
5. Yingyan Yu
6. Ruixin Yang
7. Florian Tramèr
8. Dan Boneh

Citations in the corpus

• An overview of deep learning in medical imaging focusing on MRI (2018, background): “In addition to producing valuable measures that function as uncertainty measures [65,355,356], these techniques can also lessen deep neural networks susceptibility to adversarial attacks [354,357].”
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges (2020, background): “[50] 2018 FCN [51] and SehNet [44] polyps segmentation ×”
• Adaptive Context Selection for Polyp Segmentation (2020, methodology): “We compare our ACSNet with FCN8s [1], UNet [14], UNet++ [21], SegNet [19] and SFANet [3] on the test set.”
• Artificial Convolutional Neural Network in Object Detection and Semantic Segmentation for Medical Imaging Analysis (2021, methodology): “The result showed that the FCN performed better than other two models (39).”
• Medical Image Segmentation Using Deep Learning: A Survey (2020, background): “[137] explored the uncertainty and interpretability of semantic segmentation of colorectal polyps in convolutional neural networks, and the authors developed the central idea of guided back propagation [138] for the”