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.

Most local adaptive image binarization techniques have been inspired by Niblack's method and thus use local thresholding. Niblack's and the NICK methods that is based on it introduce a parameter k to determine the object boundaries in a given window, but one of the deficiencies of local thresholding is that the k value is constant. In this paper, we propose a new approach to calculating k values for the NICK binarization method: we set the k value based on the standard deviation of the image. For our experiments, we used the DIBCO 2013 dataset and a privately held ancient Jawi manuscript dataset. The results were evaluated using the F-measure, pseudo F-measure, peak signal-to-noise ratio, misclassication penalty metrics (MPM), distance reciprocal distortion (DRD), and overall rank score. The proposed method achieved result of 91.09% for the DIBCO dataset and 87.07% for the Jawi dataset, which were higher than those with earlier methods that used fixed k values ranging from - 0.2 to - 0.1. These results indicate that the k values produced by the proposed method can adapt to the state of the manuscript and that using them for NICK thresholding can increase binarization performance.

Breast cancer is one of the diseases with the highest mortality rate among women. Early detection is the key to decreasing the rate. Cancerous cell increases the blood circulation, thus temperature around skin surface. Thermography is a potential screening method for early detection of breast cancer because it is non-invasive, radiation-free and can identify cell metabolism activity, i.e., the heat around the cancerous area. This paper presents an analysis of healthy and cancerous breast based on intensity value of grayscale thermograms. We use histogram statistics features, and gray level co-occurrence matrix (GLCM) features. We inspect 18 healthy and 21 cancerous breast images from Database for Mastology Research (DMR) dataset. Experiment results showed that mean, entropy and skewness values are the statistical features that can indicate whether the thermograms contains cancerous cell. Furthermore, the energy, homogeneity and contrast of healthy and malignant cells of the GLCM features are significantly distinctive, thus can also be used as discriminative features.