We develop progressive alternating attention dense (PAAD) blocks, which construct a guiding attention map (GAM) after every convolutional layer in the dense blocks using features from all scales.
To explore the generalization capability of ResUNet++ on different publicly available polyp datasets, so that it could be used in a real-world setting, we performed an extensive cross-dataset evaluation.
Ranked #1 on Medical Image Segmentation on CVC-VideoClinicDB
Minimally invasive surgery is a surgical intervention used to examine the organs inside the abdomen and has been widely used due to its effectiveness over open surgery.
Ranked #1 on Medical Image Segmentation on ROBUST-MIS
The proposed MSRF-Net allows to capture object variabilities and provides improved results on different biomedical datasets.
Ranked #3 on Medical Image Segmentation on 2018 Data Science Bowl
To utilize automated methods in clinical settings, it is crucial to design lightweight models with low latency such that they can be integrated with low-end endoscope hardware devices.
Ranked #1 on Medical Image Segmentation on KvasirCapsule-SEG
We propose a novel architecture called feedback attention network (FANet) that unifies the previous epoch mask with the feature map of the current training epoch.
Ranked #1 on Medical Image Segmentation on EM
Deep Neural Networks (DNNs) have become the de-facto standard in computer vision, as well as in many other pattern recognition tasks.
Colonoscopy is the gold standard for examination and detection of colorectal polyps.
Colorectal cancer is the third most common cause of cancer worldwide.
The trade-off is a slightly lower precision compared to the current state-of-the-art, which has higher latency and performs better when a less accurate time estimation can be accepted.
Ranked #7 on Action Spotting on SoccerNet
1 code implementation • 23 Oct 2020 • Debesh Jha, Sharib Ali, Krister Emanuelsen, Steven A. Hicks, VajiraThambawita, Enrique Garcia-Ceja, Michael A. Riegler, Thomas de Lange, Peter T. Schmidt, Håvard D. Johansen, Dag Johansen, Pål Halvorsen
Additionally, we provide a baseline for the segmentation of the GI tools to promote research and algorithm development.
Ranked #2 on Medical Image Segmentation on Kvasir-Instrument
The encouraging results, produced on various medical image segmentation datasets, show that DoubleU-Net can be used as a strong baseline for both medical image segmentation and cross-dataset evaluation testing to measure the generalizability of Deep Learning (DL) models.
A clear understanding of evaluation metrics and machine learning models with cross datasets is crucial to bring research in the field to a new quality level.
In this paper, we present Kvasir-SEG: an open-access dataset of gastrointestinal polyp images and corresponding segmentation masks, manually annotated by a medical doctor and then verified by an experienced gastroenterologist.
Ranked #1 on Polyp Segmentation on Kvasir-SEG (DSC metric)
Accurate computer-aided polyp detection and segmentation during colonoscopy examinations can help endoscopists resect abnormal tissue and thereby decrease chances of polyps growing into cancer.
In this paper, we present our approach for the 2018 Medico Task classifying diseases in the gastrointestinal tract.