Search results

This paper aims to propose a solution for detecting and grading diabetic retinopathy (DR) in retinal images using a convolutional neural network (CNN)-based approach. It could classify input retinal images into a normal class or an abnormal class, which would be further split into four stages of abnormalities automatically.

The proposed solution is developed based on a newly proposed CNN architecture, namely, DeepRoot. It consists of one main branch, which is connected by two side branches. The main branch is responsible for the primary feature extractor of both high-level and low-level features of retinal images. Then, the side branches further extract more complex and detailed features from the features outputted from the main branch. They are designed to capture details of small traces of DR in retinal images, using modified zoom-in/zoom-out and attention layers.

The proposed method is trained, validated and tested on the Kaggle dataset. The regularization of the trained model is evaluated using unseen data samples, which were self-collected from a real scenario from a hospital. It achieves a promising performance with a sensitivity of 98.18% under the two classes scenario.

The new CNN-based architecture (i.e. DeepRoot) is introduced with the concept of a multi-branch network. It could assist in solving a problem of an unbalanced dataset, especially when there are common characteristics across different classes (i.e. four stages of DR). Different classes could be outputted at different depths of the network.

Mouth segmentation is one of the challenging tasks of development in lip reading applications due to illumination, low chromatic contrast and complex mouth appearance. Recently, deep learning methods effectively solved mouth segmentation problems with state-of-the-art performances. This study presents a modified Mobile DeepLabV3 based technique with a comprehensive evaluation based on mouth datasets.

This paper presents a novel approach to mouth segmentation by Mobile DeepLabV3 technique with integrating decode and auxiliary heads. Extensive data augmentation, online hard example mining (OHEM) and transfer learning have been applied. CelebAMask-HQ and the mouth dataset from 15 healthy subjects in the department of rehabilitation medicine, Ramathibodi hospital, are used in validation for mouth segmentation performance.

Extensive data augmentation, OHEM and transfer learning had been performed in this study. This technique achieved better performance on CelebAMask-HQ than existing segmentation techniques with a mean Jaccard similarity coefficient (JSC), mean classification accuracy and mean Dice similarity coefficient (DSC) of 0.8640, 93.34% and 0.9267, respectively. This technique also achieved better performance on the mouth dataset with a mean JSC, mean classification accuracy and mean DSC of 0.8834, 94.87% and 0.9367, respectively. The proposed technique achieved inference time usage per image of 48.12 ms.

The modified Mobile DeepLabV3 technique was developed with extensive data augmentation, OHEM and transfer learning. This technique gained better mouth segmentation performance than existing techniques. This makes it suitable for implementation in further lip-reading applications.

The cardiomegaly can be determined by the cardiothoracic ratio (CTR) which can be measured in a chest x-ray image. It is calculated based on a relationship between a size of heart and a transverse dimension of chest. The cardiomegaly is identified when the ratio is larger than a cut-off threshold. This paper aims to propose a solution to calculate the ratio for classifying the cardiomegaly in chest x-ray images.

The proposed method begins with constructing lung and heart segmentation models based on U-Net architecture using the publicly available datasets with the groundtruth of heart and lung masks. The ratio is then calculated using the sizes of segmented lung and heart areas. In addition, Progressive Growing of GANs (PGAN) is adopted here for constructing the new dataset containing chest x-ray images of three classes including male normal, female normal and cardiomegaly classes. This dataset is then used for evaluating the proposed solution. Also, the proposed solution is used to evaluate the quality of chest x-ray images generated from PGAN.

In the experiments, the trained models are applied to segment regions of heart and lung in chest x-ray images on the self-collected dataset. The calculated CTR values are compared with the values that are manually measured by human experts. The average error is 3.08%. Then, the models are also applied to segment regions of heart and lung for the CTR calculation, on the dataset computed by PGAN. Then, the cardiomegaly is determined using various attempts of different cut-off threshold values. With the standard cut-off at 0.50, the proposed method achieves 94.61% accuracy, 88.31% sensitivity and 94.20% specificity.

The proposed solution is demonstrated to be robust across unseen datasets for the segmentation, CTR calculation and cardiomegaly classification, including the dataset generated from PGAN. The cut-off value can be adjusted to be lower than 0.50 for increasing the sensitivity. For example, the sensitivity of 97.04% can be achieved at the cut-off of 0.45. However, the specificity is decreased from 94.20% to 79.78%.

This paper proposes a solution for recognizing human faces under mask-wearing. The lower part of human face is occluded and could not be used in the learning process of face recognition. So, the proposed solution is developed to recognize human faces on any available facial components which could be varied depending on wearing or not wearing a mask.

The proposed solution is developed based on the FaceNet framework, aiming to modify the existing facial recognition model to improve the performance of both scenarios of mask-wearing and without mask-wearing. Then, simulated masked-face images are computed on top of the original face images, to be used in the learning process of face recognition. In addition, feature heatmaps are also drawn out to visualize majority of parts of facial images that are significant in recognizing faces under mask-wearing.

The proposed method is validated using several scenarios of experiments. The result shows an outstanding accuracy of 99.2% on a scenario of mask-wearing faces. The feature heatmaps also show that non-occluded components including eyes and nose become more significant for recognizing human faces, when compared with the lower part of human faces which could be occluded under masks.

The convolutional neural network based solution is tuned up for recognizing human faces under a scenario of mask-wearing. The simulated masks on original face images are augmented for training the face recognition model. The heatmaps are then computed to prove that features generated from the top half of face images are correctly chosen for the face recognition.

This study aimed to examine the effects of a three-month mobile health diabetes self-management program (MHDSMP) on glycemic control, diabetes self-management (DSM) behaviors and patient satisfaction in adults with uncontrolled type 2 diabetes (T2DM) in Thailand.

This was a three-arm, parallel-group, randomized controlled trial among 129 adults with uncontrolled T2DM who attended the medical outpatient department in a medical center. The participants were randomly assigned to the three study groups (n = 43 per group), including MHDSMP, telephone follow-up (TF) and usual care (UC). MHDSMP encompassed four components, including DSM engagement, DSM mobile application, motivational text messages and telephone coaching. Outcomes were evaluated at three-month end-of-study by using HbA1C and response to the Summary of Diabetes Self-Care Activities (SDSCA) and the Client Satisfaction Questionnaire (CSQ-8). Data were analyzed by using descriptive statistics and multivariate analysis of covariance (MANCOVA).

The findings revealed that at the end-of-study, HbA1C decreased from 7.80 to 7.17% (p < 0.001) in MHDSMP group, from 7.72 to 7.65% (p = 0.468) in TF group, and from 7.89 to 7.72% (p = 0.074) in UC group. Significantly higher SDSCA and CSQ-8 scores were also observed in MHDSMP compared to TF and UC groups (F = 12.283, F = 19.541, F = 8.552, p < 0.001, respectively).

This study demonstrated that MHDSMP adjunct with usual care is beneficial for patient outcomes in adults with uncontrolled T2DM in Thailand, compared to TF and UC groups.