Lung ultrasound (LUS) is an important imaging modality used by emergency physicians to assess pulmonary congestion at the patient bedside. B-line artifacts in LUS videos are key findings associated with pulmonary congestion. Not only can the interpretation of LUS be challenging for novice operators, but visual quantification of B-lines remains subject to observer variability. In this work, we investigate the strengths and weaknesses of multiple deep learning approaches for automated B-line detection and localization in LUS videos. We curate and publish,BEDLUS, a new ultrasound dataset comprising 1,419 videos from 113 patients with a total of 15,755 expert-annotated B-lines. Based on this dataset, we present a benchmark of established deep learning methods applied to the task of B-line detection. To pave the way for interpretable quantification of B-lines, we propose a novel “single-point” approach to B-line localization using only the point of origin. Our results show that (a) the area under the receiver operating characteristic curve ranges from 0.864 to 0.955 for the benchmarked detection methods, (b) within this range, the best performance is achieved by models that leverage multiple successive frames as input, and (c) the proposed single-point approach for B-line localization reaches an F$_{1}$-score of 0.65, performing on par with the inter-observer agreement. The dataset and developed methods can facilitate further biomedical research on automated interpretation of lung ultrasound with the potential to expand the clinical utility.

This paper presents U-LanD, a framework for automatic detection of landmarks on key frames of the video by leveraging the uncertainty of landmark prediction. We tackle a specifically challenging problem, where training labels are noisy and highly sparse. U-LanD builds upon a pivotal observation: a deep Bayesian landmark detector solely trained on key video frames, has significantly lower predictive uncertainty on those frames vs. other frames in videos. We use this observation as an unsupervised signal to automatically recognize key frames on which we detect landmarks. As a test-bed for our framework, we use ultrasound imaging videos of the heart, where sparse and noisy clinical labels are only available for a single frame in each video. Using data from 4,493 patients, we demonstrate that U-LanD can exceedingly outperform the state-of-the-art non-Bayesian counterpart by a noticeable absolute margin of 42% in${R}^{{2}}$score, with almost no overhead imposed on the model size.

Localization of anatomical landmarks to perform two-dimensional measurements in echocardiography is part of routine clinical workflow in cardiac disease diagnosis. Automatic localization of those landmarks is highly desirable to improve workflow and reduce interobserver variability. Training a machine learning framework to perform such localization is hindered given the sparse nature of gold standard labels; only few percent of cardiac cine series frames are normally manually labeled for clinical use. In this paper, we propose a new end-to-end reciprocal detection and tracking model that is specifically designed to handle the sparse nature of echocardiography labels. The model is trained using few annotated frames across the entire cardiac cine sequence to generate consistent detection and tracking of landmarks, and an adversarial training for the model is proposed to take advantage of these annotated frames. The superiority of the proposed reciprocal model is demonstrated using a series of experiments.

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.

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.