Special Issue "Image and Video Processing in Medicine"
A special issue of Journal of Imaging (ISSN 2313-433X).
Deadline for manuscript submissions: closed (30 October 2016)
Prof. Dr. Gonzalo Pajares Martinsanz
Department Software Engineering and Artificial Intelligence, Faculty of Informatics, University Complutense of Madrid, 28040 Madrid, Spain
Website | E-Mail
Interests: computer vision; image processing; pattern recognition; 3D image reconstruction, spatio-temporal image change detection and track movement; fusion and registering from imaging sensors; superresolution from low-resolution image sensors
Prof. Dr. Philip Morrow
School of Computing and Information Engineering, Faculty of Computing and Engineering, University of Ulster, BT52 1SA Northern Ireland, UK
Website | E-Mail
Fax: +44 (0)28 7012 4916
Interests: image processing, computer vision, medical and biomedical image analysis, 3D/4D image analytics, remote sensing
Dr. Kenji Suzuki
Associate Professor of Electrical and Computer Engineering, Medical Imaging Research Center, Illinois Institute of Technology, Chicago, IL 60616, USA
Website | E-Mail
Phone: +1 312 567 5232
Interests: machine learning in medical imaging, computation intelligence in medical imaging, computer-aided detection and diagnosis, medical image processing and analysis
Medical imaging and video analysis are oriented to extract information from structures in the human body. Prevention, diagnosis and monitoring of diseases, caused by different pathologies, are the main objective.
Image and video acquisition, processing and interpretation are oriented toward the efficiency of anatomy and physiology analysis, to achieve the above objectives.
The following is a list of the main topics covered by this Special Issue. The issue will, however, not be limited to these topics:
- Image and video acquisition instruments and technologies: visible cameras, radiography, tomography, magnetic resonance, nuclear-based devices, ultrasound (echocardiography), acoustic, thermography, neuroimaging.
- Image processing techniques: enhancement, segmentation, texture analysis, image fusion.
- Computing vision-based approaches: pattern recognition, 2D/3D structures.
Prof. Dr. Gonzalo Pajares Martinsanz
Prof. Dr. Philip Morrow
Dr. Kenji Suzuki
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Imaging is an international peer-reviewed open access quarterly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) is waived for well-prepared manuscripts submitted to this issue. Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.
Title: FPGA based Portable Medical Ultrasound Imaging System with Automatic Detection of Kidney in An Image
Authors: Raji Rajalakshmi and Uday Desai et al.
Abstract: Ultrasound scanning (US) is the most widely used Non-invasive, safest imaging system in healthcare. Lack of Radiologists and high form factor limits the benefits of US to use in remote diagnosis. To address this issues, we propose portable ultrasound scanning system with image processing algorithms to assist the semi-skilled sonographer. Portable Ultrasound system is realized with a single Xilinx Zync processor along with automatic region of interest detection for kidney images. Semi-skilled person can now emphasize more only in region of interest detection. These type of smart imaging systems will be very beneficial to treat the patients at their bedside with minimum skill needed for diagnosing.
Title: Dynamic analysis of upper limbs movements after breast cancer surgery
Authors: Hélder Oliveira et al.
Abstract: The quality of life of breast cancer patients has increasingly become an important factor of consideration in choosing the type of treatment used. However, common treatment techniques, as the case of radiation therapy or the surgical removal of the axillary lymphatic nodes, result in several impairments in women’s upperbody function. These impairments include restricted shoulder mobility and arm swelling, which usually precedes chronic lymphedema. As consequence, several daily life activities of the women will be affected and, consequently, contribute to a decreased QOL. Therefore, is of extreme importance to assess the functional restrictions caused by cancer treatment, in order to evaluate the quality of procedures and to avoid further complications. In this manner, the present work aims to develop an effective method for the evaluation of the upper-body function, suitable for breast cancer patients. For this purpose, it is investigated the use of both depth and skeleton data, provided by the Microsoft Kinect, to extract features that characterize the upper-limbs motion. Supervised classification algorithms are used to construct a predictive model of classification and very promising results are obtained, with high classification accuracy. Therefore, the developed method appears to be a proper solution for the proposed goal. After breast cancer treatment, it is essential for the women to maintain a continuous physical activity in order to recover the upper-limb mobility. In that way, a home-base exercise program is normally recommended, but the patients not always perform the exercises as they should. This highlights the importance of a surveillance rehabilitation model for breast cancer patients to promote and support physical activity and exercise behaviors. Further in this research, it was investigated a rehabilitation model for breast cancer patients. Taking advantage of the Kinect device, an application was developed in this direction that instructs the patient on how to execute the exercises and makes an evaluation of their performance. Preliminary results are quite satisfactory, but further work is still needed.
Title: An Approximate Method for characterizing Diffusion Anisotropy in HARDI Data
Authors: H.Z. Zhang, T.M. McGinnity, S.A. Coleman, and M. Jing
Abstract: This paper presents a novel approach for characterising diffusion anisotropy in diffusion weighted magnetic resonance imaging (DW-MRI). Usually, diffusion anisotropy is characterized by truncating the spherical harmonic (SH) series of reconstructed data in voxels. In our solution scheme, by considering Rician noise in DW-MRI, we employ an approximate strategy to construct a basis selection criterion in terms of the criterion in the Gaussian generalized linear model (GLM) so that it can alleviate the effect of Rician noise depending on the signal to noise ratio level and appropriately truncate the SH series of reconstructed data so as to characterize diffusion anisotropy in voxels. The proposed method is applied to various synthetic, phantom and real high angular resolution diffusion imaging (HARDI) datasets. The experimental results demonstrate the effectiveness and accuracy of the proposed method by comparing the approach with several traditional methods.
Title: Resting State Network Activity Estimation using Regression Mixture Analysis
Authors: Vangelis P. Oikonomou, Konstantinos Blekas and Loukas Astrakas
Abstract: Functional MRI (fMRI) is one of the most important techniques to study the human brain. A relatively new problem to the analysis of fMRI data is the identification of brain networks when the brain is at rest, i.e., no external stimulus is applied to the subject. In this work we present an advanced method to estimate the Resting State Networks (RSNs) based on mixture of regression models. An important advantage of it is its ability to incorporate spatial correlations of fMRI data by using a new functional for the responsibilities of the mixture. Another important feature of the proposed scheme is its flexibility to handle all the brain time series at once and not slice by slice. Several experiments were made where we evaluate the usefulness of the approach in comparison with other ordinary methods.
Title: Polyp Detection from Video Capsule Endoscopy: A Review
Author: Surya Prasath
Affiliation: Computational Imaging and Visualization Analysis Lab, Department of Computer Science, University of Missouri-Columbia, MO 65211, USA
Abstract: Video capsule endoscopy (VCE) is used widely nowadays for visualizing the gastrointestinal (GI) tract. Capsule endoscopy exams are prescribed usually as an additional monitoring mechanism and can help in identifying polyps, bleeding, etc. To analyze the large scale video data produced by VCE exams automatic image processing, computer vision, and learning algorithms are required. Recently, automatic polyp detection algorithms have been proposed with various degrees of success. Though polyp detection in CT colonoscopy and other traditional endoscopy procedure based images is becoming a mature field, due to its unique imaging characteristics detecting polyps automatically in VCE is a hard problem. We review different polyp detection approaches for VCE imagery and provide systematic analysis with challenges faced by standard image processing and computer vision methods.
Title: Optimized Distributed Hyperparameter Search and Simulation for Medical Tissue Texture Learning Using Hadoop
Author: Henning Müller, Roger Schaer et al.
Abstract: Many medical image analysis tasks require complex learning strategies to reach a quality of image-based decision support that is sufficient in clinical practice. The analysis of medical texture in tomographic images, for example of lung tissue, is no exception. Via a learning framework very good classification rates can be obtained but many parameters need to be optimized.
This article describes a framework for such pattern learning and optimization that can be applicable in many other research groups that have a heterogeneous computing infrastructure and no massive servers available.
We use the Hadoop framework to run and distribute the analysis on a mix of desktop computers and servers and show how good response times can be reached and which type of infrastructure is best adapted to which task.
The results are directly applicable in many scenarios and allow implementing an efficient and effective strategy for medical image analysis
Title: Wavelet Denoising and Medical Imaging: A Review
Author: Abdeldjalil OUAHABI et al.
Affiliation: Tours University, Tours, France
Abstract: The persistence of noise in imaging technologies has been one of the greatest challenges to the developments of digital imaging technologies in modern medicine, such as MRIs. In medical images, noise suppression is a particularly delicate and difficult task because noise removal introduces artifacts and causes blurring of the images. A tradeoff between noise reduction and the preservation of actual image features has to be made in a way that enhances the diagnostically relevant image content.
This review conveys the usefulness of wavelets in compact signal and image representations to denoise images and improve compression and feature detection processing. Standard imaging techniques are largely successful in modern medical practices, and denoising only aids the precision and accuracy of disease diagnoses.