Showing papers in "Medical Image Analysis in 2021"

TL;DR: The analysis shows that the performance of DL models for single modality (CT / MR) can show reliable volumetric analysis performance, but the best MSSD performance remains limited, and multi-tasking DL models designed to segment all organs are observed to perform worse compared to organ-specific ones.

TL;DR: A comprehensive review of state-of-the-art deep learning approaches that have been used in the context of histopathological image analysis can be found in this paper, where a survey of over 130 papers is presented.

TL;DR: The role that humans might play in the development and deployment of deep learning enabled diagnostic applications is investigated and techniques that will retain a significant input from a human end user are focused on.

TL;DR: This work proposes a deep convolutional neural network model, Simple Fully Convolutional Network (SFCN), for accurate prediction of brain age using T1-weighted structural MRI data, which achieved state-of-the-art performance in UK Biobank data.

TL;DR: The 2019 Kidney and Kidney Tumor Segmentation challenge (KiTS19) was a competition held in conjunction with the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) which sought to address issues and stimulate progress on this automatic segmentation problem.

TL;DR: In this paper, the authors present a comprehensive review of segmentation loss functions in an organized manner and conduct the first large-scale analysis of 20 general loss functions on four typical 3D segmentation tasks involving six public datasets from 10+ medical centers.

TL;DR: This large-scale benchmarking study makes a significant step towards much-improved segmentation methods for atrial LGE-MRIs, and will serve as an important benchmark for evaluating and comparing the future works in the field.

TL;DR: Experimental results based on a clinical dataset of 170 3D ABUS volumes collected from 107 patients indicate that the proposed multi-task framework improves tumor segmentation and classification over the single-task learning counterparts.

TL;DR: Faster Mean-Shift as discussed by the authors proposes a new online seed optimization policy to adaptively determine the minimal number of seeds, accelerate computation, and save GPU memory, which achieved 7-10 times speedup compared to the state-of-the-art embedding based cell instance segmentation and tracking algorithm.

TL;DR: In this article, a review of deep learning on chest X-ray images is presented, focusing on image-level prediction (classification and regression), segmentation, localization, image generation and domain adaptation.

TL;DR: In this paper, a review of the recent developments in deep learning for fundus images with a review paper is presented, where the authors introduce 143 application papers with a carefully designed hierarchy.

TL;DR: In this paper, a comparative study of unsupervised anomaly detection in brain MRI is presented, where a single architecture, a single resolution and the same dataset(s) are used.

TL;DR: A dual-branch combination network for COVID-19 diagnosis that can simultaneously achieve individual-level classification and lesion segmentation and good interpretability on the loci of infection compared to other deep models due to its classification guided by high-level semantic information.

TL;DR: This survey summarizes the current progress on integrating medical domain knowledge into deep learning models for various tasks, such as disease diagnosis, lesion, organ and abnormality detection, lesions and organ segmentation, and systematically categorizes different kinds of medical domainknowledge that have been utilized and their corresponding integrating methods.

TL;DR: The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations.

TL;DR: In this paper, a federated semi-supervised learning framework was proposed to handle the variability in both the data and annotations for detecting Coronavirus Disease 2019 (COVID-19) in chest CT scans.

TL;DR: In this paper, a graph neural network (GNN) framework was proposed to analyze functional magnetic resonance images (fMRI) and discover neurological biomarkers, which leveraged the topological and functional information of fMRI.

TL;DR: This approach relies on automatic deep learning-based disease quantification using an ensemble of architectures, and a data-driven consensus for the staging and outcome prediction of the patients fusing imaging biomarkers with clinical and biological attributes.

TL;DR: Wang et al. as discussed by the authors proposed a self-attention mechanism in the encoder and decoder to learn rich hierarchical representations of curvilinear structures and employed a 1×3 and a 3×1 convolutional kernel to capture boundary features.

TL;DR: In this article, the authors propose a boundary loss, which takes the form of a distance metric on the space of contours, not regions, to mitigate the difficulties of highly unbalanced problems.

TL;DR: This work proposes a novel neural network model that is trained with only image-level labels and can generate pixel-level saliency maps indicating possible malignant findings in screening mammography interpretation: predicting the presence or absence of benign and malignant lesions.

TL;DR: The experimental results demonstrate that the proposed CO VID-AL outperforms the state-of-the-art active learning approaches in the diagnosis of COVID-19 and the qualitative and quantitative analysis proves the effectiveness and efficiency of the proposedCOVID-AL framework.

TL;DR: A framework to design and train HookNet for achieving high-resolution semantic segmentation and introduce constraints to guarantee pixel-wise alignment in feature maps during hooking is described and the superiority of HookNet when compared with single-resolution U-Net models working at different resolutions is shown.

TL;DR: The triple-attention learning (A 3Net) model is proposed, which uses the pre-trained DenseNet-121 as the backbone network for feature extraction, and integrates three attention modules in a unified framework for channel-wise, element- wise, and scale-wise attention learning.

TL;DR: A review of methods based on machine and deep learning for automatic vessel segmentation and classification for fundus camera images between 2012 and 2020, and an attempt to assess the quantitative merit of DL methods in terms of accuracy improvement compared to other methods.

TL;DR: Wang et al. as discussed by the authors proposed a novel scale and context sensitive network (a.k.a., SCS−Net) for retinal vessel segmentation, which dynamically adjusts the receptive fields to extract multi-scale features.

TL;DR: In this article, a concatenation of two sub-networks, a relatively shallow image normalization network and a deep CNN segmentation network, is proposed for medical image segmentation.

TL;DR: Characterising the tissue by classifying it into 12 meaningful dermatological classes, including hair follicles, sweat glands as well as identifying the well-defined stratified layers of the skin helps inform ways in which future computer aided diagnosis systems could be applied usefully in a clinical setting with human interpretable outcomes.

TL;DR: This study is the first work to jointly predict the disease progression and the conversion time, which could help clinicians to deal with the potential severe cases in time or even save the patients’ lives.

TL;DR: In this article, the authors combine 35,320 magnetic resonance images of the brain from 17 studies to examine bias in neuroimaging, and propose methods for dataset harmonization and study their ability to remove bias in imaging features.