Ultrasound imaging is a standard examination during pregnancy that can be used for measuring specific biometric parameters towards prenatal diagnosis and estimating gestational age. Fetal head circumference (HC) is one of the significant factors to determine the fetus growth and health. In this paper, a multi-task deep convolutional neural network is proposed for automatic segmentation and estimation of HC ellipse by minimizing a compound cost function composed of segmentation dice score and MSE of ellipse parameters. Experimental results on fetus ultrasound dataset in different trimesters of pregnancy show that the segmentation results and the extracted HC match well with the radiologist annotations. The obtained dice scores of the fetal head segmentation and the accuracy of HC evaluations are comparable to the state-of-the-art. I. INTRODUCTION Ultrasound (US) imaging is a safe non-invasive procedure for diagnosing internal body organs. Ultrasound imaging as compared to other imaging tools, such as computed tomography (CT) and magnetic resonance imaging (MRI), is cheaper, portable and more prevalent [1]. It helps to diagnose the causes of pain, swelling, and infection in internal organs, for evaluation and treatment of medical conditions [2].Ultrasound imaging has turned into a general checkup method for prenatal diagnosis. It is used to investigate and measure fetal biometric parameters, such as the baby's abdominal circumference, head circumference, biparietal diameter, femur and humerus length, and crown-rump length. Furthermore, the fetal head circumference (HC) is measured for estimating the gestational age, size and weight, growth monitoring and detecting fetus abnormalities [3].Despite all the benefits and typical applications of US imaging, this imaging modality suffers from various artifacts such as motion blurring, missing boundaries, acoustic shadows, speckle noise, and low signal-to-noise ratio. This makes the US images very challenging to interpret, which requires expert operators. As shown in US image samples of

No abstract

Lesion segmentation in skin images is an important step in computerized detection of skin cancer. Melanoma is known as one of the most life threatening types of this cancer. Existing methods often fall short of accurately segmenting lesions with fuzzy boarders. In this paper, a new class of fully convolutional network is proposed, with new dense pooling layers for segmentation of lesion regions in non-dermoscopic images. Unlike other existing convolutional networks, this proposed network is designed to produce dense feature maps. This network leads to highly accurate segmentation of lesions. The produced dice score here is 91.6% which outperforms state-of-the-art algorithms in segmentation of skin lesions based on the Dermquest dataset.Index Terms-skin cancer, melanoma, deep neural networks, dense pooling layer. IntroductionComputerized diagnosis of skin cancer is of great necessity and interest [1]. About 5.4 million new cases of skin cancer are detected in the USA every year. Most fatal types of skin cancer are melanoma, where 75% of deaths are related to [2]. Recently the incidence pattern of melanoma has shown a rapid increase. The rate of melanoma occurrence has tripled in the past 30 years [3]. In the USA, an estimated 87,110 newly detected cases and an estimated 9,730 melanoma-related deaths occurred only in 2017. A key point in the survival of patients is early detection of malignant skin lesions [4][5]. Patients, with melanoma detected in the early stages, have a 98% of five-year relative chance of survival. The survival rate is shown to be only 18% when melanoma is spread to the other parts of the body, which results in a life expectancy with a median of less than one year [2][3].The importance and variety of computerized methods for melanoma early detection are reviewed in [6][7]. There exist two main categories of images applied for computerized diagnosis of melanoma: Dermoscopic images, also known as microscopic images, which are captured by a special instrument named dermoscope and non-dermoscopic images, which are captured by conventional digital cameras and smartphones. Dermoscopic images contain more detailed information, while the nondermoscopic images have the advantage of ease of access. Dermoscopic images are not easily accessible. Authors in [8] indicates that less than 50% of the dermatologists in the United States use dermatoscopy. Jafari et al. [9] have used deep learning to detect melanoma in non-dermoscopic images.One of the most critical stages in the computerized study of melanoma is the accurate segmentation of skin lesions. Captured images usually contain a lesion, which is surrounded by healthy skin. Proper extraction of the lesion region is critical for assessment of lesion's features. Lesion features include area, border irregularity, shape symmetry, and variation of color. There exist various methods for skin lesions segmentation, based on active contours, region merging [10], and thresholding [11]. Nondermoscopic images exhibit what is seen by the naked eye. There are some chal...

The need for CT scan analysis is growing for pre-diagnosis and therapy of abdominal organs. Automatic organ segmentation of abdominal CT scan can help radiologists analyze the scans faster and segment organ images with fewer errors. However, existing methods are not efficient enough to perform the segmentation process for victims of accidents and emergencies situations. In this paper we propose an efficient liver segmentation with our 3D to 2D fully convolution network (3D-2D-FCN). The segmented mask is enhanced by means of conditional random field on the organ's border. Consequently, we segment a target liver in less than a minute with Dice score of 93.52.

Histopathology images contain essential information for medical diagnosis and prognosis of cancerous disease. Segmentation of glands in histopathology images is a primary step for analysis and diagnosis of an unhealthy patient. Due to the widespread application and the great success of deep neural networks in intelligent medical diagnosis and histopathology, we propose a modified version of LinkNet for gland segmentation and recognition of malignant cases. We show that using specific handcrafted features such as invariant local binary pattern drastically improves the system performance. The experimental results demonstrate the competency of the proposed system against the state-of-the-art methods. We achieved the best results in testing on section B images of the Warwick-QU dataset and obtained comparable results on section A images.

No abstract

No abstract

No abstract