Developing a breast cancer screening method is very important to facilitate early breast cancer detection and treatment. Building a screening method using medical imaging modality that does not cause body tissue damage (non-invasive) and does not involve physical touch is challenging. Thermography, a non-invasive and non-contact cancer screening method, can detect tumors at an early stage even under precancerous conditions by observing temperature distribution in both breasts. The thermograms obtained on thermography can be interpreted using deep learning models such as convolutional neural networks (CNNs). CNNs can automatically classify breast thermograms into categories such as normal and abnormal. Despite their demostrated utility, CNNs have not been widely used in breast thermogram classification. In this study, we aimed to summarize the current work and progress in breast cancer detection based on thermography and CNNs. We first discuss of breast thermography potential in early breast cancer detection, providing an overview of the availability of breast thermal datasets together with publicly accessible. We also discuss characteristics of breast thermograms and the differences between healthy and cancerous thermographic patterns. Breast thermogram classification using a CNN model is described step by step including a simulation example illustrating feature learning. We cover most research related to the implementation of deep neural networks for breast thermogram classification and propose future research directions for developing representative datasets, feeding the segmented image, assigning a good kernel, and building a lightweight CNN model to improve CNN performance.

Diabetes mellitus (DM) is one of the major diseases that cause death worldwide and lead to complications of diabetic foot ulcers (DFU). Improper and late handling of a diabetic foot patient can result in an amputation of the patient’s foot. Early detection of DFU symptoms can be observed using thermal imaging with a computer-assisted classifier. Previous study of DFU detection using thermal image only achieved 97% of accuracy, and it has to be improved. This article proposes a novel framework for DFU classification based on thermal imaging using deep neural networks and decision fusion. Here, decision fusion combines the classification result from a parallel classifier. We used the convolutional neural network (CNN) model of ShuffleNet and MobileNetV2 as the baseline classifier. In developing the classifier model, firstly, the MobileNetV2 and ShuffleNet were trained using plantar thermogram datasets. Then, the classification results of those two models were fused using a novel decision fusion method to increase the accuracy rate. The proposed framework achieved 100% accuracy in classifying the DFU thermal images in binary classes of positive and negative cases. The accuracy of the proposed Decision Fusion (DF) was increased by about 3.4% from baseline ShuffleNet and MobileNetV2. Overall, the proposed framework outperformed in classifying the images compared with the state-of-the-art deep learning and the traditional machine-learning-based classifier.

This paper discusses the initial experiments on fine-tuning the convolutional neural network (CNN) models of ResNet101, DenseNet, MobileNetV2, and ShuffleNetV2 for breast cancer detection. These models have been tested using the ImageNet database and shown their high performance on the image classification. Here, the dataset used to train the model are thermal breast images downloaded from the Database for Mastology Research (DMR). There are only two classification classes here, cancer and healthy. During the training, we used three epochs for the training iteration, 10, 20, and 30. For this preliminary study, we set the learning rate to 0.001, momentum to 0.9, learning rate factor for weight and bias each to 10, and minibatch size to 10. The training results showed that ResNet101 and DenseNet with deep networks have 100% accuracy only in 10 epochs. Whereas, MobileNetV2 and ShuffleNetV2 respectively need 20 epochs and 30 epochs of training to achieve 100% accuracy. Finally, we evaluated the performance of each pretrained model using testing results. The DenseNet was able to classify all the testing dataset correctly. ResNet101 and MobileNetV2 have the same performance, correctly classified static dataset while slightly missed in classifying dynamic dataset with 0.996 of accuracy. ShuffleNetV2 has a little lower performance with only 0.98 of accuracy. In term of training time, ShuffleNetV2 spent a short duration, but MobileNetV2 with competitive elapse time was able to show equal performance to ResNet101.

Objective: Routine dialysis is stressful. It has the possibility of leading to depression and anxiety and also reducing patients’ quality of life. Despite these significant consequences, these comorbidities have been rarely studied among Indonesian patients. This study aims to examine the rate of depression, anxiety, and the role of acceptance of their illness on patients’ quality of life. Method: A total of 213 patients undergoing hemodialysis in three general hospitals in Aceh, Indonesia, were included in the study. The presence of depression, anxiety, and the quality of life of each patient was assessed using the hospital anxiety and depression scale and WHO quality of life-BREF questionnaires. Results: The prevalence of depression and anxiety was 46% and 30.5%, respectively. Depression was only associated with the presence of anxiety and the duration of hemodialysis. Anxiety was negatively associated with quality of life but positively associated with depression and the prescription of an anxiolytic. Overall quality of life was associated with age, body mass index, the presence of anxiety, and acceptance of the illness. Acceptance of the illness was also independently associated with almost every domain of patients’ quality of life. Conclusions: The rates of depression and anxiety among patients undergoing hemodialysis in the current study setting are relatively similar to the rates in other settings. Patients’ acceptance of their illnesses is significantly associated with the occurrence of anxiety and quality of life. Therefore, health practitioners should help patients accept their illnesses and the administration of regular hemodialysis.

Indonesian universal health coverage was implemented in 2013 and hemodialysis services became universally accessible, yet few studies have examined patient adherence to hemodialysis schedules. We examined the rates of missed in-center hemodialysis sessions in Banda Aceh and the factors associated with non-attendance. This cross-sectional questionnaire survey included 193 patients receiving in-center hemodialysis. Approximately 28% of the patients missed ≥ 1 hemodialysis session in the month prior to the questionnaire’s administration. About 65% reported attending religious activities as the reason for missing hemodialysis. The level of health literacy was generally low with a mean score of 14.38 out of 26 (55.3%). Multivariate logistic regression analyses showed that patients with educational levels higher than elementary school were less likely to miss hemodialysis sessions. Participants who performed more self-care behaviors had lower odds of missing hemodialysis sessions. Every unit increase in the health literacy score was associated with increased odds of missing hemodialysis sessions. Emphasizing the importance of attending hemodialysis sessions and modifying hemodialysis schedules based on patients’ needs is essential. Patients who miss hemodialysis sessions should be reminded of all self-care behaviors. Health literacy among hemodialysis patients should be improved, with emphasis on patient safety, advanced knowledge, and critical health literacy.

BACKGROUND: Sodium glucose co-transporter-2 inhibitor (SGLT2-i), a new oral antidiabetic drug, has been recommended for its morbidity and mortality benefits in patients with heart failure. This study aimed to determine the effect of acute SGLT2-i therapy on the relative ratio expression of microRNA-21 (miR-21), transforming growth factor-β1 (TGF-β1), and matrix metalloproteinase-2 (MMP-2) in the process of cardiac fibrosis in the hyperglycemia Wistar rat models compared to biguanide (metformin) therapy. METHODS: We used Streptozotocin (STZ) to induce hyperglycemia in Wistar rats (n=31), randomly divided into four groups: negative control (NC, n=4), positive control (PC, n=10), hyperglycemia plus metformin (M, n=8), and hyperglycemia plus empagliflozin (E, n=9). After seven weeks, the rats were sacrificed and the heart tissue was taken for microRNA and messenger RNA (mRNA) extraction, followed by reverse transcription quantitative real time polymerase chain reaction (RT-qPCR) examination. The data was analyzed using One-way ANOVA. RESULTS: Results showed a decreasing trend in the gene expression relative ratio of miR-21 (1.0 vs. 1.9; p=0.079) and TGF-β1 (0.9 vs. 3.2; p=0.145), but a significant increase in MMP-2 gene expression (1.3 vs. 0.7; p=0.002) in the SGLT2-i (empagliflozin) vs. biguanide (metformin) groups. CONCLUSION: Empagliflozin administration may play a significant role in preventing the occurrence of cardiac fibrosis in hyperglycemia. KEYWORDS: sodium glucose co-transporter-2 inhibitor, microRNA-21, transforming growth factor-β1, matrix metalloproteinase-2, cardiac fibrosis