Angiodysplasia Detection and Localization Using Deep Convolutional Neural Networks
By Alexey A. Shvets, Vladimir I. Iglovikov, Alexander Rakhlin, Alexandr A Kalinin. 2018
75 citations recorded by the source corpus.
Accurate detection and localization for angiodysplasia lesions is an important problem in early stage diagnostics of gastrointestinal bleeding and anemia. Gold-standard for angiodysplasia detection and localization is performed using wireless capsule endoscopy. This pill-like device is able to produce thousand of high enough resolution images during one passage through gastrointestinal tract. In this paper we present our winning solution for MICCAI 2017 Endoscopic Vision SubChallenge: Angiodysplasia Detection and Localization its further improvements over the state-of-the-art results using several novel deep neural network architectures. It address the binary segmentation problem, where every pixel in an image is labeled as an angiodysplasia lesions or background. Then, we analyze connected component of each predicted mask. Based on the analysis we developed a classifier that predict angiodysplasia lesions (binary variable) and a detector for their localization (center of a component). In this setting, our approach outperforms other methods in every task subcategory for angiodysplasia detection and localization thereby providing state-of-the-art results for these problems. The source code for our solution is made publicly available at https://github.com/ternaus/angiodysplasia-segmentation
Subfields: Gastroenterology, Hematology, Pulmonary and Respiratory Medicine
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Gastroenterology
In Hematology
In Pulmonary and Respiratory Medicine
Citations in the corpus
- Albumentations: fast and flexible image augmentations (2018, background): “In medical computer vision tasks that deal with color images or videos, color transformations have also been shown to help deep networks to generalize better, for example, such for surgical [16] or endoscopic [17] video analysis.”
- TernausNetV2: Fully Convolutional Network for Instance Segmentation (2018, background): “This modification was called TernausNet [14] that we naturally extend in the current work (see also [20, 19]).”
- Camera Model Identification Using Convolutional Neural Networks (2018, background): “Problems in satellite [1], [2], [3], [4], medical [5], [6], [7], [8] or any other imagery are successfully tackled with these techniques, routinely beating human performance in many tasks, including classification, segmentation, and detection.”
- Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning (2018, methodology): “In this work we evaluate 4 different deep architectures for segmentation: modified U-Net [17], [18], 2 modifications of TernausNet [19], and a modification of LinkNet [20], [21].”
- Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection (2018, methodology): “Semantic segmentation algorithms, such as the U-Net architecture [22], constitute the de facto standard approach for detection of anatomical structures in clincial context [6, 14, 12, 26, 24].”
- Feature Pyramid Network for Multi-class Land Segmentation (2018, methodology): “This architecture shows significant improvement as a generic feature extractor in several applications such as object detection and instance object segmentation [15, 7, 21, 20].”
- Fully Convolutional Network for Automatic Road Extraction from Satellite Imagery (2018, background): “This type of network architecture proven themselves in binary image segmentation competitions for satellite image analyses [6, 7, 8, 15, 16] and other applications [13, 12].”