Journal of Imaging

26 pages, 10909 KiB

Open AccessArticle

Super Resolution of Magnetic Resonance Images

by Prabhjot Kaur, Anil Kumar Sao and Chirag Kamal Ahuja

J. Imaging 2021, 7(6), 101; https://doi.org/10.3390/jimaging7060101 - 21 Jun 2021

Cited by 3 | Viewed by 2213

In this work, novel denoising and super resolution (SR) approaches for magnetic resonance (MR) images are addressed, and are integrated in a unified framework, which do not require example low resolution (LR)/high resolution (HR)/cross-modality/noise-free images and prior information of noise–noise variance. The proposed [...] Read more.

In this work, novel denoising and super resolution (SR) approaches for magnetic resonance (MR) images are addressed, and are integrated in a unified framework, which do not require example low resolution (LR)/high resolution (HR)/cross-modality/noise-free images and prior information of noise–noise variance. The proposed method categorizes the patches as either smooth or textured and then denoises them by deploying different denoising strategies for efficient denoising. The denoising algorithm is integrated into the SR approach, which uses a gradient profile-based constraint in a sparse representation-based framework to improve the resolution of MR images with reduced smearing of image details. This constraint regularizes the estimation of HR images such that the estimated HR image has gradient profiles similar to the gradient profiles of the original HR image. For this, the gradient profile sharpness (GPS) values of an unknown HR image are estimated using an approximated piece-wise linear relation among GPS values of LR and upsampled LR images. The experiments are performed on three different publicly available datasets. The proposed SR approach outperforms the existing unsupervised SR approach addressed for real MR images that exploits low rank and total variation (LRTV) regularization, by an average peak signal to noise ratio (PSNR) of 0.73 dB and 0.38 dB for upsampling factors 2 and 3, respectively. For the super resolution of noisy real MR images (degraded with 2% noise), the proposed approach outperforms the LRTV approach by an average PSNR of 0.54 dB and 0.46 dB for upsampling factors 2 and 3, respectively. The qualitative analysis is shown for real MR images from healthy subjects and subjects with Alzheimer’s disease and structural deformity, i.e., cavernoma. Full article

(This article belongs to the Special Issue Intelligent Strategies for Medical Image Analysis)

► Show Figures

Figure 1

24 pages, 1142 KiB

Open AccessArticle

Comparing Stacking Ensemble Techniques to Improve Musculoskeletal Fracture Image Classification

by Ibrahem Kandel, Mauro Castelli and Aleš Popovič

J. Imaging 2021, 7(6), 100; https://doi.org/10.3390/jimaging7060100 - 21 Jun 2021

Cited by 15 | Viewed by 3278

Abstract

Bone fractures are among the main reasons for emergency room admittance and require a rapid response from doctors. Bone fractures can be severe and can lead to permanent disability if not treated correctly and rapidly. Using X-ray imaging in the emergency room to [...] Read more.

Bone fractures are among the main reasons for emergency room admittance and require a rapid response from doctors. Bone fractures can be severe and can lead to permanent disability if not treated correctly and rapidly. Using X-ray imaging in the emergency room to detect fractures is a challenging task that requires an experienced radiologist, a specialist who is not always available. The availability of an automatic tool for image classification can provide a second opinion for doctors operating in the emergency room and reduce the error rate in diagnosis. This study aims to increase the existing state-of-the-art convolutional neural networks’ performance by using various ensemble techniques. In this approach, different CNNs (Convolutional Neural Networks) are used to classify the images; rather than choosing the best one, a stacking ensemble provides a more reliable and robust classifier. The ensemble model outperforms the results of individual CNNs by an average of 10%. Full article

► Show Figures

Figure 1

18 pages, 5669 KiB

Open AccessArticle

Directional TGV-Based Image Restoration under Poisson Noise

by Daniela di Serafino, Germana Landi and Marco Viola

J. Imaging 2021, 7(6), 99; https://doi.org/10.3390/jimaging7060099 - 16 Jun 2021

Cited by 12 | Viewed by 1931

Abstract

We are interested in the restoration of noisy and blurry images where the texture mainly follows a single direction (i.e., directional images). Problems of this type arise, for example, in microscopy or computed tomography for carbon or glass fibres. In order to deal [...] Read more.

We are interested in the restoration of noisy and blurry images where the texture mainly follows a single direction (i.e., directional images). Problems of this type arise, for example, in microscopy or computed tomography for carbon or glass fibres. In order to deal with these problems, the Directional Total Generalized Variation (DTGV) was developed by Kongskov et al. in 2017 and 2019, in the case of impulse and Gaussian noise. In this article we focus on images corrupted by Poisson noise, extending the DTGV regularization to image restoration models where the data fitting term is the generalized Kullback–Leibler divergence. We also propose a technique for the identification of the main texture direction, which improves upon the techniques used in the aforementioned work about DTGV. We solve the problem by an ADMM algorithm with proven convergence and subproblems that can be solved exactly at a low computational cost. Numerical results on both phantom and real images demonstrate the effectiveness of our approach. Full article

(This article belongs to the Special Issue Inverse Problems and Imaging)

► Show Figures

Figure 1

20 pages, 601 KiB

Open AccessReview

Breast Cancer Risk Assessment: A Review on Mammography-Based Approaches

by João Mendes and Nuno Matela

J. Imaging 2021, 7(6), 98; https://doi.org/10.3390/jimaging7060098 - 12 Jun 2021

Cited by 9 | Viewed by 2814

Abstract

Breast cancer affects thousands of women across the world, every year. Methods to predict risk of breast cancer, or to stratify women in different risk levels, could help to achieve an early diagnosis, and consequently a reduction of mortality. This paper aims to [...] Read more.

Breast cancer affects thousands of women across the world, every year. Methods to predict risk of breast cancer, or to stratify women in different risk levels, could help to achieve an early diagnosis, and consequently a reduction of mortality. This paper aims to review articles that extracted texture features from mammograms and used those features along with machine learning algorithms to assess breast cancer risk. Besides that, deep learning methodologies that aimed for the same goal were also reviewed. In this work, first, a brief introduction to breast cancer statistics and screening programs is presented; after that, research done in the field of breast cancer risk assessment are analyzed, in terms of both methodologies used and results obtained. Finally, considerations about the analyzed papers are conducted. The results of this review allow to conclude that both machine and deep learning methodologies provide promising results in the field of risk analysis, either in a stratification in risk groups, or in a prediction of a risk score. Although promising, future endeavors in this field should consider the possibility of the implementation of the methodology in clinical practice. Full article

(This article belongs to the Special Issue Advanced Computational Methods for Oncological Image Analysis)

► Show Figures

Figure 1

10 pages, 1669 KiB

Open AccessCommunication

Immersive Molecular Dynamics in Virtual Reality: Increasing Efficiency of Educational Process with Companion Converter for NarupaXR

by Polina Pereshivkina, Nadezhda Karandasheva, Maria Mikhaylenko and Mikhail Kurushkin

J. Imaging 2021, 7(6), 97; https://doi.org/10.3390/jimaging7060097 - 08 Jun 2021

Cited by 2 | Viewed by 2032

Abstract

Visualization has always been a crucial part of the educational process. Implementing computer algorithms and virtual reality tools into it is vital for the new generation engineers, scientists and researchers. In the field of chemistry education, various software that allow dynamic molecular building [...] Read more.

Visualization has always been a crucial part of the educational process. Implementing computer algorithms and virtual reality tools into it is vital for the new generation engineers, scientists and researchers. In the field of chemistry education, various software that allow dynamic molecular building and viewing are currently available. These software are now used to enhance the learning process and ensure better understanding of the chemical processes from the visual perspective. The present short communication provides a summary of these applications based on the NarupaXR program, which is a great educational tool that combines the functionality and simple design necessary for an educational tool. NarupaXR is used with a companion application “Narupa Builder” which requires a different file format, therefore a converter that allows a simple transition between the two extensions has been developed. The converter sufficiently increases the efficiency of the educational process. The automatic converter is freely available on GitLab The current communication provides detailed written instructions that can simplify the installation process of the converter and facilitate the use of both the software and the hardware of the VR set. Full article

(This article belongs to the Section Mixed, Augmented and Virtual Reality)

► Show Figures

Graphical abstract

23 pages, 4126 KiB

Open AccessArticle

Robust Visibility Surface Determination in Object Space via Plücker Coordinates

by Alessandro Rossi, Marco Barbiero, Paolo Scremin and Ruggero Carli

J. Imaging 2021, 7(6), 96; https://doi.org/10.3390/jimaging7060096 - 03 Jun 2021

Viewed by 3305

Abstract

Industrial 3D models are usually characterized by a large number of hidden faces and it is very important to simplify them. Visible-surface determination methods provide one of the most common solutions to the visibility problem. This study presents a robust technique to address [...] Read more.

Industrial 3D models are usually characterized by a large number of hidden faces and it is very important to simplify them. Visible-surface determination methods provide one of the most common solutions to the visibility problem. This study presents a robust technique to address the global visibility problem in object space that guarantees theoretical convergence to the optimal result. More specifically, we propose a strategy that, in a finite number of steps, determines if each face of the mesh is globally visible or not. The proposed method is based on the use of Plücker coordinates that allows it to provide an efficient way to determine the intersection between a ray and a triangle. This algorithm does not require pre-calculations such as estimating the normal at each face: this implies the resilience to normals orientation. We compared the performance of the proposed algorithm against a state-of-the-art technique. Results showed that our approach is more robust in terms of convergence to the maximum lossless compression. Full article

(This article belongs to the Section Visualization and Computer Graphics)

► Show Figures

Figure 1

14 pages, 2337 KiB

Open AccessArticle

Postprocessing for Skin Detection

by Diego Baldissera, Loris Nanni, Sheryl Brahnam and Alessandra Lumini

J. Imaging 2021, 7(6), 95; https://doi.org/10.3390/jimaging7060095 - 03 Jun 2021

Cited by 2 | Viewed by 2017

Abstract

Skin detectors play a crucial role in many applications: face localization, person tracking, objectionable content screening, etc. Skin detection is a complicated process that involves not only the development of apposite classifiers but also many ancillary methods, including techniques for data preprocessing and [...] Read more.

Skin detectors play a crucial role in many applications: face localization, person tracking, objectionable content screening, etc. Skin detection is a complicated process that involves not only the development of apposite classifiers but also many ancillary methods, including techniques for data preprocessing and postprocessing. In this paper, a new postprocessing method is described that learns to select whether an image needs the application of various morphological sequences or a homogeneity function. The type of postprocessing method selected is learned based on categorizing the image into one of eleven predetermined classes. The novel postprocessing method presented here is evaluated on ten datasets recommended for fair comparisons that represent many skin detection applications. The results show that the new approach enhances the performance of the base classifiers and previous works based only on learning the most appropriate morphological sequences. Full article

► Show Figures

Figure 1

16 pages, 9652 KiB

Open AccessArticle

Determining Chess Game State from an Image

by Georg Wölflein and Ognjen Arandjelović

J. Imaging 2021, 7(6), 94; https://doi.org/10.3390/jimaging7060094 - 02 Jun 2021

Cited by 6 | Viewed by 6712

Abstract

Identifying the configuration of chess pieces from an image of a chessboard is a problem in computer vision that has not yet been solved accurately. However, it is important for helping amateur chess players improve their games by facilitating automatic computer analysis without [...] Read more.

Identifying the configuration of chess pieces from an image of a chessboard is a problem in computer vision that has not yet been solved accurately. However, it is important for helping amateur chess players improve their games by facilitating automatic computer analysis without the overhead of manually entering the pieces. Current approaches are limited by the lack of large datasets and are not designed to adapt to unseen chess sets. This paper puts forth a new dataset synthesised from a 3D model that is an order of magnitude larger than existing ones. Trained on this dataset, a novel end-to-end chess recognition system is presented that combines traditional computer vision techniques with deep learning. It localises the chessboard using a RANSAC-based algorithm that computes a projective transformation of the board onto a regular grid. Using two convolutional neural networks, it then predicts an occupancy mask for the squares in the warped image and finally classifies the pieces. The described system achieves an error rate of 0.23% per square on the test set, 28 times better than the current state of the art. Further, a few-shot transfer learning approach is developed that is able to adapt the inference system to a previously unseen chess set using just two photos of the starting position, obtaining a per-square accuracy of 99.83% on images of that new chess set. The code, dataset, and trained models are made available online. Full article

(This article belongs to the Section Computer Vision and Pattern Recognition)

► Show Figures

Figure 1

22 pages, 53242 KiB

Open AccessArticle

Volumetric Semantic Instance Segmentation of the Plasma Membrane of HeLa Cells

by Cefa Karabağ, Martin L. Jones and Constantino Carlos Reyes-Aldasoro

J. Imaging 2021, 7(6), 93; https://doi.org/10.3390/jimaging7060093 - 01 Jun 2021

Cited by 4 | Viewed by 3122

Abstract

In this work, an unsupervised volumetric semantic instance segmentation of the plasma membrane of HeLa cells as observed with serial block face scanning electron microscopy is described. The resin background of the images was segmented at different slices of a 3D stack of [...] Read more.

In this work, an unsupervised volumetric semantic instance segmentation of the plasma membrane of HeLa cells as observed with serial block face scanning electron microscopy is described. The resin background of the images was segmented at different slices of a 3D stack of 518 slices with 8192 × 8192 pixels each. The background was used to create a distance map, which helped identify and rank the cells by their size at each slice. The centroids of the cells detected at different slices were linked to identify them as a single cell that spanned a number of slices. A subset of these cells, i.e., the largest ones and those not close to the edges were selected for further processing. The selected cells were then automatically cropped to smaller regions of interest of 2000 × 2000 × 300 voxels that were treated as cell instances. Then, for each of these volumes, the nucleus was segmented, and the cell was separated from any neighbouring cells through a series of traditional image processing steps that followed the plasma membrane. The segmentation process was repeated for all the regions of interest previously selected. For one cell for which the ground truth was available, the algorithm provided excellent results in Accuracy (AC) and the Jaccard similarity Index (JI): nucleus: JI

= 0.9665

, AC

= 0.9975

, cell including nucleus JI

= 0.8711

, AC

= 0.9655

, cell excluding nucleus JI

= 0.8094

, AC

= 0.9629

. A limitation of the algorithm for the plasma membrane segmentation was the presence of background. In samples with tightly packed cells, this may not be available. When tested for these conditions, the segmentation of the nuclear envelope was still possible. All the code and data were released openly through GitHub, Zenodo and EMPIAR. Full article

(This article belongs to the Special Issue 2020 Selected Papers from Journal of Imaging Editorial Board Members)

► Show Figures

Figure 1

17 pages, 1781 KiB

Open AccessArticle

EffUnet-SpaGen: An Efficient and Spatial Generative Approach to Glaucoma Detection

by Venkatesh Krishna Adithya, Bryan M. Williams, Silvester Czanner, Srinivasan Kavitha, David S. Friedman, Colin E. Willoughby, Rengaraj Venkatesh and Gabriela Czanner

J. Imaging 2021, 7(6), 92; https://doi.org/10.3390/jimaging7060092 - 30 May 2021

Cited by 8 | Viewed by 3233

Abstract

Current research in automated disease detection focuses on making algorithms “slimmer” reducing the need for large training datasets and accelerating recalibration for new data while achieving high accuracy. The development of slimmer models has become a hot research topic in medical imaging. In [...] Read more.

Current research in automated disease detection focuses on making algorithms “slimmer” reducing the need for large training datasets and accelerating recalibration for new data while achieving high accuracy. The development of slimmer models has become a hot research topic in medical imaging. In this work, we develop a two-phase model for glaucoma detection, identifying and exploiting a redundancy in fundus image data relating particularly to the geometry. We propose a novel algorithm for the cup and disc segmentation “EffUnet” with an efficient convolution block and combine this with an extended spatial generative approach for geometry modelling and classification, termed “SpaGen” We demonstrate the high accuracy achievable by EffUnet in detecting the optic disc and cup boundaries and show how our algorithm can be quickly trained with new data by recalibrating the EffUnet layer only. Our resulting glaucoma detection algorithm, “EffUnet-SpaGen”, is optimized to significantly reduce the computational burden while at the same time surpassing the current state-of-art in glaucoma detection algorithms with AUROC 0.997 and 0.969 in the benchmark online datasets ORIGA and DRISHTI, respectively. Our algorithm also allows deformed areas of the optic rim to be displayed and investigated, providing explainability, which is crucial to successful adoption and implementation in clinical settings. Full article

(This article belongs to the Special Issue Frontiers in Retinal Image Processing)

► Show Figures

Figure 1

Journal Menu

Journal Browser

J. Imaging, Volume 7, Issue 6 (June 2021) – 10 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI