S.M.R. Soroushmehr

Melanoma detection by analysis of clinical images using convolutional neural network

Melanoma, most threatening type of skin cancer, is on the rise. In this paper an implementation of a deep-learning system on a computer server, equipped with graphic processing unit (GPU), is proposed for detection of melanoma lesions. Clinical (non-dermoscopic) images are used in the proposed system, which could assist a dermatologist in early diagnosis of this type of skin cancer. In the proposed system, input clinical images, which could contain illumination and noise effects, are preprocessed in order to reduce such artifacts. Afterward, the enhanced images are fed to a pre-trained convolutional neural network (CNN) which is a member of deep learning models. The CNN classifier, which is trained by large number of training samples, distinguishes between melanoma and benign cases. Experimental results show that the proposed method is superior in terms of diagnostic accuracy in comparison with the state-of-the-art methods.

Skin lesion segmentation in clinical images using deep learning

Melanoma is the most aggressive form of skin cancer and is on rise. There exists a research trend for computerized analysis of suspicious skin lesions for malignancy using images captured by digital cameras. Analysis of these images is usually challenging due to existence of disturbing factors such as illumination variations and light reflections from skin surface. One important stage in diagnosis of melanoma is segmentation of lesion region from normal skin. In this paper, a method for accurate extraction of lesion region is proposed that is based on deep learning approaches. The input image, after being preprocessed to reduce noisy artifacts, is applied to a deep convolutional neural network (CNN). The CNN combines local and global contextual information and outputs a label for each pixel, producing a segmentation mask that shows the lesion region. This mask will be further refined by some post processing operations. The experimental results show that our proposed method can outperform the existing state-of-the-art algorithms in terms of segmentation accuracy.

Vessel extraction in X-ray angiograms using deep learning

Coronary artery disease (CAD) is the most common type of heart disease which is the leading cause of death all over the world. X-ray angiography is currently the gold standard imaging technique for CAD diagnosis. These images usually suffer from low quality and presence of noise. Therefore, vessel enhancement and vessel segmentation play important roles in CAD diagnosis. In this paper a deep learning approach using convolutional neural networks (CNN) is proposed for detecting vessel regions in angiography images. Initially, an input angiogram is preprocessed to enhance its contrast. Afterward, the image is evaluated using patches of pixels and the network determines the vessel and background regions. A set of 1,040,000 patches is used in order to train the deep CNN. Experimental results on angiography images of a dataset show that our proposed method has a superior performance in extraction of vessel regions.

Vessel region detection in coronary X-ray angiograms

X-ray angiography is a standard method for diagnosing coronary artery diseases. In order to show coronary arteries, contrast agent and X-ray imaging are used but the produced images are not always of adequate quality for visual examination. The low quality is caused by different artifacts. The presence of catheter and also the surrounding tissues make the processing of these images more difficult. In this paper, we propose a fully automated method to enhance the angiogram images and detect the arteries. Our proposed method contains three main steps which are Hessian filter enhancement, feature extraction and vessel region detection. To further enhance the visual quality of the image, non-vessel areas are blurred. The enhanced images can be utilized for better diagnosis of coronary diseases such as stenosis. Subjective evaluation of the enhanced images shows the effectiveness and accuracy of the proposed method.

A Game Theoretic Predictive Modeling Approach to Reduction of False Alarm

False alarm is one of the main concerns in intensive care units which could result in care disruption, sleep deprivation, insensitivity of care---givers to alarms and so on. Many approaches such as improving the quality of physiological signals by filtering and developing more accurate sensors have been proposed in the last two decades to suppress the rate of false alarm. Moreover, some multi---parameter/feature methods have been developed to classify the alarms more accurately. One of the main problems facing these methods is that they neglect those features that individually have low impact on the accuracy. In this paper, we propose a model based on coalition game that considers the inter---features mutual information which results in gaining the accuracy of the classification. Simulation results on a database produced by four hospitals shows the superior performance of the proposed method compared to other existing methods.

Automatic detection of melanoma using broad extraction of features from digital images

Automatic and reliable diagnosis of skin cancer, as a smartphone application, is of great interest. Among different types of skin cancers, melanoma is the most dangerous one which causes most deaths. Meanwhile, melanoma is curable if it were diagnosed in its early stages. In this paper we propose an efficient system for prescreening of pigmented skin lesions for malignancy using general-purpose digital cameras. These images can be captured by a smartphone or a digital camera. This could be beneficial in different applications, such as computer aided diagnosis and telemedicine applications. It could assist dermatologists, or smartphone users, evaluate risk of suspicious moles. The proposed method enhances borders and extracts a broad set of dermatologically important features. These discriminative features allow classification of lesions into two groups of melanoma and benign. This method is computationally appropriate as a smartphone application. Experimental results show that our proposed method is superior in diagnosis accuracy compared to state-of-the-art methods.

Set of descriptors for skin cancer diagnosis using non-dermoscopic color images

Melanoma is the deadliest form of skin cancer. Diagnosis of melanoma in early stages significantly enhances the survival rate. Recently there has been a rising trend in web-based and mobile applications for early detection of melanoma using images captured by conventional cameras. These images usually contain fewer detailed information in comparison with dermoscopic (microscopic) images. Meanwhile, non-dermoscopic images have the advantage of broad availability. In this paper a set of ten features is proposed which cover different color characteristics of melanoma visible in skin images. The first 5 features are extracted using Fuzzy C-means clustering based on color variations and color spatial distributions of pigmented skin. These features are shown to be discriminative for melanoma lesions. The next 5 features consider colors and intensity of the colors. Hence, a 10 dimensional color feature space is formed. Experimental results show that classification accuracy of suspicious moles, by the proposed set of features, outperforms comparable state-of-the-art methods.

Vessel segmentation in low contrast X-ray angiogram images

Coronary artery disease is one of the major causes of death throughout the world. An effective method for diagnosing this disease is X-ray angiography. The images are usually of poor quality and low contrast. This is due to non-uniform illumination, appearance of other body organs and artifacts, low SNR values, etc. Accurate segmentation of arteries is a challenging and important task. In this paper we first extract coronary arteries region of interest (ROI) using Hessian filter. Then, we combine these results with the flux flow measurements for accurate identification of vessel pixels. Post processing is performed to eliminate falsely identified vessel pixels. Finally, we segment the coronary arteries by selecting the largest connected component. Qualitative and quantitative evaluations of our method show high effectiveness of the proposed method. In terms of capturing major vessels our method is successful in 96% of cases.

Segmentation of vessels in angiograms using convolutional neural networks

Abstract Coronary artery disease (CAD) is the most common type of heart disease and it is the leading cause of death in most parts of the world. About fifty percent of all middle-aged men and thirty percent of all middle-aged women in North America develop some type of CAD. The main tool for diagnosis of CAD is the X-ray angiography. Usually these images lack high quality and they contain noise. Accurate segmentation of vessels in these images could help physicians in accurate CAD diagnosis. Many image processing techniques have been used by researchers for vessel segmentation but achieving high accuracy is still a challenge in this regard. In this paper a method for detecting vessel regions in angiography images is proposed which is based on deep learning approach using convolutional neural networks (CNN). The intended angiogram is first processed to enhance the image quality. Then a patch around each pixel is fed into a trained CNN to determine whether the pixel is of vessel or background regions. Different elements of the proposed method, including the image enhancement method, the architecture of the CNN, and the training procedure of the CNN, all lead to a highly accurate mechanism. Experiments performed on angiograms of a dataset show that the proposed algorithm has a Dice score of 81.51 and an accuracy of 97.93. Results of the proposed algorithm show its superiority in extraction of vessel regions in comparison to state of the art methods.

Framework for robust blind image watermarking based on classification of attacks

With the widespread internet usage, digital contents are easily distributed throughout the world. To eliminate concerns of producers and owners of digital contents, watermarking techniques are extensively being used. Robustness against intentional and unintentional attacks is a major quality of watermarking systems. Since different attacks tend to target different parts of the frequency spectrum, in this paper we propose a framework for blind watermarking which determines the type of attack that the image has gone through before extracting the watermark. Within this framework, we propose an attack classification method to identify the region of the frequency spectrum that is less damaged. The watermark which is redundantly spread throughout the spectrum can be extracted from the less damaged regions. Experimental results show functionality of the framework by producing better results in comparison with well-known blind watermarking techniques.