Search

BACKGROUND Photographs or videos taken from a mobile phone with a +20-D lens can be an alternative to indirect ophthalmoscopy in mass screening and telemedicine. OBJECTIVE To develop a mobile fundus camera (MFC) that ensures eye screening with safety, ease of use, and high accuracy in detecting fundus lesions. METHODS From October 1st, 2021, to September 30th, 2022, we developed an MFC based on Samsung S21 and iPhone 12 mobile phones with four different types of connecting lenses. Ten ophthalmology personnel were trained to use the MFC on schematic eyes and evaluate the developed systems. The four schematic eyes had a normal fundus, diabetic retinopathy (DR), normal optic disc, and glaucomatous optic disc. The system safety was assessed based on the ISO 15004-2 Visible wavelength (400–700 nm). All users completed the Thai version of the Usability Experience Questionnaire (UEQ). The evaluation of image quality was based on the sharpness index (SI), disc-to-image ratio, and color discrimination, which included relative redness, red-green difference, and red-blue difference. RESULTS Our system satisfied the safety criteria. The mean UEQ scores for the overall MFCs were above average in the domains of attractiveness, dependability, stimulation, and novelty. However, the efficiency and perspicuity were below average. The MFC based on the Samsung S21 had a significantly better overall SI but poorer overall color discrimination power than that of the iPhone 12 (p < 0.05). The best SI was achieved using Samsung S21+Volk 28D, whereas iPhone 12+oDocs 20D provided the best color discrimination. Interparticipant differences were not statistically significant. CONCLUSIONS All the developed MFCs tested were safe and usable. Based on the SI criteria, the Samsung S21+ Volk 28D should be used for further development.

Obesity is a significant factor in health information and increases the risk of health problems. Hence, an application that can help users to monitor their body mass index (BMI) timelines is needed. The simulation of a personalized 3D body shape may encourage women to control their BMI for a healthy body and pleasant appearance. Therefore, this paper aims to develop computerized 3D models of female shapes for various weights and heights, and consists of three important parts. First, the preparation of six avatars is described. Second, the body proportions of 6767 female datasets are analyzed to find the relationship of variables in various weights and heights. Last, 3D morphing of different female shapes is developed and analyzed experimentally for appropriate morphing parameters. Accuracy tests are carried out in three ways. First, body proportions calculated using the Z-Size Ladies application, called “Z-Size calculations,” are compared with the body proportions of data obtained from 3D scanners. Second, the Z-Size calculations are compared with tape measurements. Last, the Z-Size calculations are compared with measurements of Z-Size 3D morph models. The results of accuracy tests are shown as the relationship graphs between the BMI and body proportion measurements of chest, waist, hip, and inseam. Bland–Altman plots and Pearson correlation calculation show high correlation. In conclusion, the data obtained from the Z-Size calculations, 3D Scanner, tape measurements, and Z-Size morph models’ measurements are in good agreement and are highly correlated. The simulation of 3D female shapes for different weights and heights as proposed shows good performance and high accuracy.

Robotic process automation (RPA) is a specialized software robot widely used for facilitating repeated tasks. The RPA can augment medical staff in data gathering, analysis, and reporting process. This chapter presents an RPA framework for a mobile glaucoma screening system. With the RPA, fundus images and clinical history of patients are gathered and submitted to the machine learning-based glaucoma diagnosis. If the preliminary diagnosis results in a severe condition, the application directly prompts the eye specialists for timely verification and treatments. The application facilitates the specialists in adjusting clinical parameters, making final diagnosis decision remotely, gathering and reporting information and decision, and scheduling the next hospital visit or re-imaging. The integration of the RPA framework within the eye screening system significantly reduces costs and time of operations, allows timely treatments, improves customer experiences, and promotes feasibility in large-scale population glaucoma screening.

In this paper, the mannequin for each individual person is constructed using information obtained from 3D body scanner. The collected measurements data are standardized for SizeThailand body shape sizing. The created mannequin represents each size of Thai women body shapes. The problems are that these collected 3D data of these sizes are asymmetry and have un-pleasant rough surface. In practical application, asymmetry body adjustment is solved manually but time-consuming and cumber-some. Hence, we explore the simple and automatically methods that are able to solve these problems and easily implemented. Our methods consist of 6 steps as follows: data rearrangement, symmetric plane construction, the template side selection, symmetric torso creation, torso trimming and mannequin surface smoothing. The 30 women samples data were tested by measuring chests, waists and hips of created mannequins comparing with the corresponding original 3D model. Processing time for each sample is approximately 894 milliseconds. The results show that the created mannequins have the accuracy of 98–99% with the SD of 0.5–1.1 for measurements of the chests, waists and hips. In overall, the sizes of 30 created mannequins are compared with their original 3D scanned sizes categorized based on SizeThailand size chart and the accuracy is calculated to be 90%. There are errors found in 3 of 30 mannequins as they are ± 1 size from their original sizes.

To improve the classification performance in object recognition, many different features have been created from various techniques. However, these features may be redundant or irrelevant to implement the classification model. So, feature selection is considered one of the important tools that can be employed to select a subset of relevant features for specific model. In this paper, we applied feature selection method to form a new subset of features obtained from different feature extraction algorithms so that we can improve the object's classification performance. In the experiments, we demonstrated the use of filter method and wrapper methods for RGB-D object dataset and the results were promising.

Object category and instance recognition have received much attention in this era of modern technologies. Advanced image sensing technologies provide high resolution color and depth synchronized videos such as RGB-D (Kinect style) camera. At present, various features extraction schemes are introduced to improve classification performance. Extracting useful features from both color and depth images have recently gained much attention in this research area. In this paper, we proposed an approach to create new features using a feature combination of various feature extraction techniques: color autrocorrelogram, wavelet moments, local binary pattern (LBP) and principal component analysis (PCA) for RGB-D data. The experiments on benchmark dataset shows that the new features obtained by the proposed method using k-nearest neighbor (k-NN) classifier provide promising classification results.

The purpose of the study was to design a hybrid decision support system (HDSS) that could simulate the embolized coil selection pattern of the radiologists in aneurysms treatment. As the longest available length of the coils should be used in most cases, therefore only the shape diameter (SD) selection was modeled and varied. Ninety-eight aneurysms successfully treated by a radiologist with coil embolization were divided into two groups (86 for training and 12 randomly selected for validating). Eight aneurysms treated by another radiologist were also used to cross validate the proposed HDSS. The HDSS was developed using the classification and the linear regression methods (LRM). The dome and the width of an aneurysm were used as the system inputs. The system outputs were the SDs of the first three coils indexed according to the insertion order. The HDSS that consisted of Bagging classification and LRM achieved the highest accuracy for all cases. The errors were within 1 mm for the SD selection of the first two coils. For the third coil, the SD selection within 1 mm bound had 80 % accuracy. The experimental results indicated the feasibility of using the HDSS as the guidance for selecting the SDs of the first two coils. The selection of the third coil required more training data for the rarely used SD. Moreover, the cross validation with another radiologist showed the feasibility of using the proposed HDSS as the guidance, however further validation with more data is recommended.

The purpose of this study is to develop a texture-based algorithm for breast cancer classification in Thermography and performance evaluation for the purposed method. The aim of screening a disease is early detection in order to decrease the rate of mortality. CAD systems can be reckonable diagnostic tools for this importance and Infra-red imaging is expressed as a portable, non-invasive, non-contact and radiation-free diagnostic tool among them.

This paper discusses interactive 3D reconstruction of ultrasonography model. The proposed scheme can be divided into three modules, consisting of Image Segmentation, 3D Model Reconstruction and Interactive Model Editing.More specifically, a set of 2D radial scans acquired from ultrasonography were segmented using Active Contour, resulting in an unorganized set of 3D points delineating an object of interest on multi-planar images. These points were subsequently fitted with a 3D surface model by an expansion of Spherical Harmonics. As accurately segmenting ultrasound images with low SNR can be challenging, this fitted model will be later interactively adjusted to be more properly coincided with underlying structure subject to expert’s opinion. The contribution of this paper is therefore the algorithm and the organizing of related data structure which lend to responsive rendition of the parametric surface being edited.

The Lorentzian norm of robust statistics is often applied in the reconstruction of the sparse signal from a compressed measurement signal in an impulsive noise environment. The optimization of the robust statistic function is iterative and usually requires complex parameter adjustments. In this article, the impulsive noise rejection for the compressed measurement signal with the design for image reconstruction is proposed. It is used as the preprocessing for any compressed sensing reconstruction given that the sparsified version of the signal is obtained by utilizing octave-tree discrete wavelet transform with db8 as the mother wavelet. The presence of impulsive noise is detected from the energy distribution of the reconstructed sparse signal. After the noise removal, the noise corrupted coefficients are estimated. The proposed method requires neither complex optimization nor complex parameter adjustments. The performance of the proposed method was evaluated on 60 images. The experimental results indicated that the proposed method effectively rejected the impulsive noise. Furthermore, at the same impulsive noise corruption level, the reconstruction with the proposed method as the preprocessing required much lower measurement rate than the model-based Lorentzian iterative hard thresholding.

The compressed signal in compressed sensing (CS) may be corrupted by noise during transmission. The effect of Gaussian noise can be reduced by averaging, hence a robust reconstruction method using compressed signal ensemble from one compressed signal is proposed. The compressed signal is subsampled for L times to create the ensemble of L compressed signals. Orthogonal matching pursuit with partially known support (OMP-PKS) is applied to each signal in the ensemble to reconstruct L noisy outputs. The L noisy outputs are then averaged for denoising. The proposed method in this article is designed for CS reconstruction of image signal. The performance of our proposed method was compared with basis pursuit denoising, Lorentzian-based iterative hard thresholding, OMP-PKS and distributed compressed sensing using simultaneously orthogonal matching pursuit. The experimental results of 42 standard test images showed that our proposed method yielded higher peak signal-to-noise ratio at low measurement rate and better visual quality in all cases.

In image stitching, parallax is key challenge that leads to inaccurate registration and ghosting effect of objects in the result. A novel foreground rejection method is proposed in this paper to remove parallax in video sequence. Firstly, the global motion is estimated between two frames using SIFT feature matching. The logical OR operators are then applied to the pixels that have high displaced frame difference for foreground extraction. There are two sets of foreground calculated from the near frames and far frames. Voting scheme is applied in the way that only the near-frame foreground appears inside the area of far-frame foreground that is considered as the actual foreground. The extracted foreground at this stage is mostly the edges of objects. Therefore, the foreground rejection method proposed in this paper aims to provide better motion vector estimation and ghosting effect reduction. The removal of the major parts of the high difference foreground is sufficient; hence the simple two-stage rendering is applied. The implemented results indicate that more accurate registration is achieved by including our proposed foreground rejection method. Moreover, the background of the stitched video sequence does not have the visible ghosting effect.

Product integration (PI) is considered as one of important processes for complex system development. The purpose of the PI process is to ensure that interfaces of components are compatible and able to work properly through the product life cycle. In case of changes, the cooperation between interfaces should be carefully managed and controlled for the completeness and compatibility of the overall system. In this research we propose a method for verifying interface compatibility of components from design document by extracting interface description from Unified Modeling Language (UML) component diagram and class diagram. Interface description is then used for constructing component dependency graph of which the traversal will automate the verification of component interface compatibility.