Olivier Rukundo

Olivier Rukundo, Andrea Behanova, Riccardo De Feo et al.

Regular monitoring of the primary particles and purity profiles of a drug product during development and manufacturing processes is essential for manufacturers to avoid product variability and contamination. Transmission electron microscopy (TEM) imaging helps manufacturers predict how changes affect particle characteristics and purity for virus-based gene therapy vector products and intermediates. Since intact particles can characterize efficacious products, it is beneficial to automate the detection of intact adenovirus against a non-intact-viral background mixed with debris, broken, and artefact particles. In the presence of such particles, detecting intact adenoviruses becomes more challenging. To overcome the challenge, due to such a presence, we developed a software tool for semi-automatic annotation and segmentation of adenoviruses and a software tool for automatic segmentation and detection of intact adenoviruses in TEM imaging systems. The developed semi-automatic tool exploited conventional image analysis techniques while the automatic tool was built based on convolutional neural networks and image analysis techniques. Our quantitative and qualitative evaluations showed outstanding true positive detection rates compared to false positive and negative rates where adenoviruses were nicely detected without mistaking them for real debris, broken adenoviruses, and/or staining artefacts.

Olivier Rukundo

Current mask processing operations rely on interpolation algorithms that do not produce extra pixels, such as nearest neighbor (NN) interpolation, as opposed to algorithms that do produce extra pixels, like bicubic (BIC) or bilinear (BIL) interpolation. In our previous study, the author proposed an alternative approach to NN-based mask processing and evaluated its effects on deep learning training outcomes. In this study, the author evaluated the effects of both BIC-based image and mask processing and BIC-and-NN-based image and mask processing versus NN-based image and mask processing. The evaluation revealed that the BIC-BIC model/network was an 8.9578 % (with image size 256 x 256) and a 1.0496 % (with image size 384 x 384) increase of the NN-NN network compared to the NN-BIC network which was an 8.3127 % (with image size 256 x 256) and a 0.2887 % (with image size 384 x 384) increase of the NN-NN network.

Olivier Rukundo

Avoiding the risk of undefined categorical labels using nearest neighbor interpolation overlooks the risk of exacerbating pixel level annotation errors in data augmentation. To simultaneously avoid these risks, the author modified convolutional neural networks data transformation functions by incorporating a modified geometric transformation function to improve the quality of augmented data by removing the reliance on nearest neighbor interpolation and integrating a mean based class filtering mechanism to handle undefined categorical labels with alternative interpolation algorithms. Experiments on semantic segmentation tasks using three medical image datasets demonstrated both qualitative and quantitative improvements with alternative interpolation algorithms.

Olivier Rukundo, Samuel Emil Schmidt

The stochastic rounding (SR) function is proposed to evaluate and demonstrate the effects of stochastically rounding row and column subscripts in image interpolation and scan conversion. The proposed SR function is based on a pseudorandom number, enabling the pseudorandom rounding up or down any non-integer row and column subscripts. Also, the SR function exceptionally enables rounding up any possible cases of subscript inputs that are inferior to a pseudorandom number. The algorithm of interest is the nearest-neighbor interpolation (NNI) which is traditionally based on the deterministic rounding (DR) function. Experimental simulation results are provided to demonstrate the performance of NNI-SR and NNI-DR algorithms before and after applying smoothing and sharpening filters of interest. Additional results are also provided to demonstrate the performance of NNI-SR and NNI-DR interpolated scan conversion algorithms in cardiac ultrasound videos.

Olivier Rukundo, Hanqiang Cao

This paper presents an advance on image interpolation based on ant colony algorithm (AACA) for high-resolution image scaling. The difference between the proposed algorithm and the previously proposed optimization of bilinear interpolation based on ant colony algorithm (OBACA) is that AACA uses global weighting, whereas OBACA uses a local weighting scheme. The strength of the proposed global weighting of the AACA algorithm depends on employing solely the pheromone matrix information present on any group of four adjacent pixels to decide which case deserves a maximum global weight value or not. Experimental results are further provided to show the higher performance of the proposed AACA algorithm with reference to the algorithms mentioned in this paper.

Olivier Rukundo, Marius Pedersen, Øistein Hovde

This paper proposes an advanced method for contrast enhancement of capsule endoscopic images, with the main objective to obtain sufficient information about the vessels and structures in more distant (or darker) parts of capsule endoscopic images. The proposed method (PM) combines two algorithms for the enhancement of darker and brighter areas of capsule endoscopic images, respectively. The half-unit weighted bilinear algorithm (HWB) proposed in our previous work is used to enhance darker areas according to the darker map content of its HSV's component V. Enhancement of brighter areas is achieved thanks to the novel thresholded weighted-bilinear algorithm (TWB) developed to avoid overexposure and enlargement of specular highlight spots while preserving the hue, in such areas. The TWB performs enhancement operations following a gradual increment of the brightness of the brighter map content of its HSV's component V. In other words, the TWB decreases its averaged-weights as the intensity content of the component V increases. Extensive experimental demonstrations were conducted, and based on evaluation of the reference and PM enhanced images, a gastroenterologist (ØH) concluded that the PM enhanced images were the best ones based on the information about the vessels, contrast in the images, and the view or visibility of the structures in more distant parts of the capsule endoscopy images.

Olivier Rukundo

Essential for improving the accuracy and reliability of bowel cancer screening, three-dimensional (3D) surface reconstruction using capsule endoscopy (CE) images remains challenging due to CE hardware and software limitations. This report generally focuses on challenges associated with 3D visualization and specifically investigates the impact of the indeterminate selection of the angle of the line of sight on 3D surfaces. Furthermore, it demonstrates that impact through 3D surfaces viewed at the same azimuth angles and different elevation angles of the line of sight. The report concludes that 3D printing of reconstructed 3D surfaces can potentially overcome line of sight indeterminate selection and 2D screen visual restriction-related errors.

Olivier Rukundo

In this work, the best size for late gadolinium enhancement (LGE) magnetic resonance imaging (MRI) images in the training dataset was determined to optimize deep learning training outcomes. Non-extra pixel and extra pixel interpolation algorithms were used to determine the new size of the LGE-MRI images. A novel strategy was introduced to handle interpolation masks and remove extra class labels in interpolated ground truth (GT) segmentation masks. The expectation maximization, weighted intensity, a priori information (EWA) algorithm was used for quantification of myocardial infarction (MI) in automatically segmented LGE-MRI images. Arbitrary threshold, comparison of the sums, and sums of differences are methods used to estimate the relationship between semi-automatic or manual and fully automated quantification of myocardial infarction (MI) results. The relationship between semi-automatic and fully automated quantification of MI results was found to be closer in the case of bigger LGE MRI images (55.5% closer to manual results) than in the case of smaller LGE MRI images (22.2% closer to manual results).

Olivier Rukundo

This work evaluates deep learning-based myocardial infarction (MI) quantification using Segment cardiovascular magnetic resonance (CMR) software. Segment CMR software incorporates the expectation-maximization, weighted intensity, a priori information (EWA) algorithm used to generate the infarct scar volume, infarct scar percentage, and microvascular obstruction percentage. Here, Segment CMR software segmentation algorithm is updated with semantic segmentation with U-net to achieve and evaluate fully automated or deep learning-based MI quantification. The direct observation of graphs and the number of infarcted and contoured myocardium are two options used to estimate the relationship between deep learning-based MI quantification and medical expert-based results.

Olivier Rukundo

The extent to which the arbitrarily selected L2 regularization hyperparameter value affects the outcome of semantic segmentation with deep learning is demonstrated. Demonstrations rely on training U-net on small LGE-MRI datasets using the arbitrarily selected L2 regularization values. The remaining hyperparameters are to be manually adjusted or tuned only when 10 % of all epochs are reached before the training validation accuracy reaches 90%. Semantic segmentation with deep learning outcomes are objectively and subjectively evaluated against the manual ground truth segmentation.

Olivier Rukundo

Image interpolation algorithms pervade many modern image processing and analysis applications. However, when their weighting schemes inefficiently generate very unrealistic estimates, they may negatively affect the performance of the end user applications. Therefore, in this work, the author introduced four weighting schemes based on some geometric shapes for digital image interpolation operations. And, the quantity used to express the extent of each shape weight was the normalized area, especially when the sums of areas exceeded a unit square size. The introduced four weighting schemes are based on the minimum side based diameter (MD) of a regular tetragon, hypotenuse based radius (HR), the virtual pixel length based height for the area of the triangle (AT), and the virtual pixel length for hypotenuse based radius for the area of the circle (AC). At the smaller scaling ratio, the image interpolation algorithm based on the HR scheme scored the highest at 66.6 % among non traditional image interpolation algorithms presented. But, at the higher scaling ratio, the AC scheme based image interpolation algorithm scored the highest at 66.6 % among non traditional algorithms presented and, here, its image interpolation quality was generally superior or comparable to the quality of images interpolated by both non traditional and traditional algorithms.

Olivier Rukundo

A novel evaluation study of the most appropriate round function for nearest-neighbor (NN) image interpolation is presented. Evaluated rounding functions are selected among the five rounding rules defined by the Institute of Electrical and Electronics Engineers (IEEE) 754-2008 standard. Both full- and no-reference image quality assessment (IQA) metrics are used to study and evaluate the influence of rounding functions on NN interpolation image quality. The concept of achieved occurrences over targeted occurrences is used to determine the percentage of achieved occurrences based on the number of test images used. Inferential statistical analysis is applied to deduce from a small number of images and draw a conclusion of the behavior of each rounding function on a bigger number of images. Under the normal distribution and at the level of confidence equals to 95%, the maximum and minimum achievable occurrences by each evaluated rounding function are both provided based on the inferential analysis-based experiments.

Olivier Rukundo

This paper proposes a 4X4 Census Transform (4X4CT) to encourage further research in computer vision and visual computing. Unlike the traditional 3X3 CT which uses a nine pixels kernel, the proposed 4X4CT uses a sixteen pixels kernel with four overlapped groups of 3X3 kernel size. In each overlapping group, a reference input pixel profits from its nearest eight pixels to produce an eight bits binary string convertible to a grayscale integer of the 4X4CT's output pixel. Preliminary experiments demonstrated more image textural crispness and contrast than the CT as well as alternativeness to enable meaningful solutions to be achieved.