Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

Deep learning has been applied to saliency detection in recent years. The superior performance has proved that deep networks can model the semantic properties of salient objects. Yet it is difficult for a deep network to discriminate pixels belonging to similar receptive fields around the object boundaries, thus deep networks may output maps with blurred saliency and inaccurate boundaries. To tackle such an issue, in this work, we propose a deep Level Set network to produce compact and uniform saliency maps. Our method drives the network to learn a Level Set function for salient objects so it can output more accurate boundaries and compact saliency. Besides, to propagate saliency information among pixels and recover full resolution saliency map, we extend a superpixel-based guided filter to be a layer in the network. The proposed network has a simple structure and is trained end-to-end. During testing, the network can produce saliency maps by efficiently feedforwarding testing images at a speed over 12FPS on GPUs. Evaluations on benchmark datasets show that the proposed method achieves state-of-the-art performance.

/pdf/deep-level-sets-for-salient-object-detection-2ma9dboer7.pdf

Deep Level Sets for Salient Object Detection

There is increasing interest in paravertebral muscle composition as a potential prognostic and diagnostic element in lumbar spine health. As a consequence, it is becoming popular to use magnetic resonance imaging (MRI) to examine muscle volume and fatty infiltration in lumbar paravertebral muscles to assess both age-related change and their clinical relevance in low back pain (LBP). A variety of imaging methods exist for both measuring key variables (fat, muscle) and for defining regions of interest, making pooled comparisons between studies difficult and rendering post-production analysis of MRIs confusing. We therefore propose and define a method as an option for use as a standardized MRI procedure for measuring lumbar paravertebral muscle composition, and to stimulate discussion towards establishing consensus for the analysis of skeletal muscle composition amongst clinician researchers. In this descriptive methodological study we explain our method by providing an examination of regional lumbar morphology, followed by a detailed description of the proposed technique. Identification of paravertebral muscles and vertebral anatomy includes axial E12 sheet-plastinates from cadaveric material, combined with a series of axial MRIs that encompass sequencing commonly used for investigations of muscle quality (fat-water DIXON, T1-, and T2-weighted) to illustrate regional morphology; these images are shown for L1 and L4 levels to highlight differences in regional morphology. The method for defining regions of interest (ROI) for multifidus (MF), and erector spinae (ES) is then described. Our method for defining ROIs for lumbar paravertebral muscles on axial MRIs is outlined and discussed in relation to existing literature. The method provides a foundation for standardising the quantification of muscle quality that particularly centres on examining fatty infiltration and composition. We provide recommendations relating to imaging parameters that should additionally inform a priori decisions when planning studies examining lumbar muscle tissues with MRI. We intend this method to provide a platform towards developing and delivering meaningful comparisons between MRI data on lumbar paravertebral muscle quality.

/pdf/manually-defining-regions-of-interest-when-quantifying-1371o31no3.pdf

Manually defining regions of interest when quantifying paravertebral muscles fatty infiltration from axial magnetic resonance imaging: a proposed method for the lumbar spine with anatomical cross-reference

The visual exploration of retinal blood vessels assists ophthalmologists in the diagnoses of different abnormalities of the eyes such as diabetic retinopathy, glaucoma, cardiovascular ailment, high blood pressure, arteriosclerosis, and age-related macular degeneration. The manual inspection of retinal vasculature is an extremely challenging and tedious task for medical experts due to the complex structure of an eye, tiny blood vessels, and variation in vessels width. Several automatic retinal vessels extraction techniques have been proposed in contemporary literature, which assist ophthalmologists in the timely identification of an eye disorders. However, due to the fast evolution of such techniques, a comprehensive survey is needed. This survey presents a comprehensive review of such techniques, strategies, and algorithms presented to date. The techniques are classified into logical groups based on the underlying methodology employed for retinal vessel extraction. The performance of existing techniques is reported on the publicly accessible datasets in term of various performance measures, providing a valuable comparison among the techniques. Thus, this survey presents a valuable resource for researchers working toward automatic extraction of retinal vessels.

A review of retinal blood vessels extraction techniques: challenges, taxonomy, and future trends

Deep virtual adversarial self-training with consistency regularization for semi-supervised medical image classification.

Level set methods are a popular way to solve the image segmentation problem. The solution contour is found by solving an optimization problem where a cost functional is minimized. Gradient descent methods are often used to solve this optimization problem since they are very easy to implement and applicable to general nonconvex functionals. They are, however, sensitive to local minima and often display slow convergence. Traditionally, cost functionals have been modified to avoid these problems. In this paper, we instead propose using two modified gradient descent methods, one using a momentum term and one based on resilient propagation. These methods are commonly used in the machine learning community. In a series of 2-D/3-D-experiments using real and synthetic data with ground truth, the modifications are shown to reduce the sensitivity for local optima and to increase the convergence rate. The parameter sensitivity is also investigated. The proposed methods are very simple modifications of the basic method, and are directly compatible with any type of level set implementation. Downloadable reference code with examples is available online.

/pdf/modified-gradient-search-for-level-set-based-image-3nvkr7ka7g.pdf

Modified Gradient Search for Level Set Based Image Segmentation

PURPOSE:To quantitatively and qualitatively evaluate the water-signal performance of the consistent intensity inhomogeneity correction (CIIC) method to correct for intensity inhomogeneities METHODS ...

/pdf/consistent-intensity-inhomogeneity-correction-in-water-fat-2jzg2lz8jc.pdf

Consistent intensity inhomogeneity correction in water-fat MRI.

Level set methods are a popular way to solve the image segmentation problem in computer image analysis. A contour is implicitly represented by the zero level of a signed distance function, and evolved according to a motion equation in order to minimize a cost function. This function defines the objective of the segmentation problem and also includes regularization constraints. Gradient descent search is the de facto method used to solve this optimization problem. Basic gradient descent methods, however, are sensitive for local optima and often display slow convergence. Traditionally, the cost functions have been modified to avoid these problems. In this work, we instead propose using a modified gradient descent search based on resilient propagation (Rprop), a method commonly used in the machine learning community. Our results show faster convergence and less sensitivity to local optima, compared to traditional gradient descent.

/pdf/a-fast-optimization-method-for-level-set-segmentation-342q41fp7u.pdf

A Fast Optimization Method for Level Set Segmentation

This paper presents a novel method for atlas-based segmentation of medical images. The method uses semi-supervised learning of a graph describing a manifold of anatomical variations of whole-body images, where unlabelled data are used to find a path with small deformations from the labelled atlas to the target image. The method is evaluated on 36 whole-body magnetic resonance images with manually segmented livers as ground truth. Significant improvement (p < 0.001) was obtained compared to direct atlas-based registration.

Semi-supervised learning of anatomical manifolds for atlas-based segmentation of medical images

Fig. 1 Top: Liver using standard scaling, Middle: Liver using MANA. Note the more homogenous liver intensities, Bottom: Mean time series with standard deviations SELFCALIBRATED DCE MRI USING MULTI SCALE ADAPTIVE NORMALIZED AVERAGING (MANA) Thord Andersson, Thobias Romu, Bengt Norén, Mikael Fredrik Forsgren, Örjan Smedby, Stergios Kechagias, Sven Almer, Peter Lundberg, Magnus Borga, and Olof Dahlqvist Leinhard Dept of Biomedical Engineering (IMT), Linköping University, Linköping, Sweden, Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden, Dept of Medical and Health Sciences (IMH), Div of Radiological Sciences, Linköping University, Linköping, Sweden, Dept of Radiation Physics, Linköping University and Radiation Physics, UHL County Council of Ostergotland, Linköping, Sweden, Dept of Medical and Health Sciences (IMH), Div of Cardiovascular Medicine, Linköping University, Linköping, Sweden, Dept of Endocrinology and Gastroenterology, UHL County Council of Ostergotland, Linköping, Sweden, Dept of Clinical and Experimental Medicine (IKE), Div of Gastroenterology and Hepatology, Linköping University, Linköping, Sweden

Self-calibrated DCE MRI using Multi Scale Adaptive Normalized Averaging (MANA)

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Thord Andersson

Author Tools

Chat about Author