Dense networks with relative location awareness for thorax disease identification.

PURPOSE: Chest X-ray is one of the most common examinations for diagnosing heart and lung diseases. Due to the existing of a large number of clinical cases, many automated diagnosis algorithms based on chest X-ray images have been proposed. To our knowledge, almost none of the previous auto-diagnosis algorithms consider the effect of relative location information on disease incidence. In this study, we propose to use relative location information to assist the identification of thorax diseases. METHOD: In this work, U-Net is used to segment lung and heart from chest image. The relative location maps are computed through Euclidean distance transformation from segmented masks. By introducing the relative location information into the network, the usual location of disease is combined with the incidence. The proposed network is the fusion of two branches: mask branch and image branch. A mask branch is designed to be a bottom-up and top-down structure to extract relative location information. The structure has a large receptive field, which can extract more information for large lesion and contextual information for small lesion. The features learned from mask branch are fused with image branch, which is a 121-layers DenseNet. RESULTS: We compare our proposed method with four state-of-the-art methods on the largest public chest X-ray dataset: ChestX-ray14. The proposed method achieves the area under a curve of 0.820, which outperforms all the existing models and algorithms. CONCLUSION: This paper proposed a dense network with relative location information to identify thorax disease. The method combines the usual location of disease with the incidence for the first time and performs good.

Leveraging tuberculosis case relative locations to enhance case detection and linkage to care in Swaziland.

BACKGROUND: In Swaziland, as in many high HIV/TB burden settings, there is not information available regarding the household location of TB cases for identifying areas of increased TB incidence, limiting the development of targeted interventions. Data from "Butimba", a TB REACH active case finding project, was re-analyzed to provide insight into the location of TB cases surrounding Mbabane, Swaziland. OBJECTIVE: The project aimed to identify geographical areas with high TB burdens to inform active case finding efforts. METHODS: Butimba implemented household contact tracing; obtaining landmark based, informal directions, to index case homes, defined here as relative locations. The relative locations were matched to census enumeration areas (known location reference areas) using the Microsoft Excel Fuzzy Lookup function. Of 403 relative locations, an enumeration area reference was detected in 388 (96%). TB cases in each census enumeration area and the active case finders in each Tinkhundla, a local governmental region, were mapped using the geographic information system, QGIS 2.16. RESULTS: Urban Tinkhundla predictably accounted for most cases; however, after adjusting for population, the highest density of cases was found in rural Tinkhundla. There was no correlation between the number of active case finders currently assigned to the 7 Tinkhundla surrounding Mbabane and the total number of TB cases (Spearman rho = -0.57, p = 0.17) or the population adjusted TB cases (Spearman rho = 0.14, p = 0.75) per Tinkhundla. DISCUSSION: Reducing TB incidence in high-burden settings demands novel analytic approaches to study TB case locations. We demonstrated the feasibility of linking relative locations to more precise geographical areas, enabling data-driven guidance for National Tuberculosis Programs' resource allocation. In collaboration with the Swazi National Tuberculosis Control Program, this analysis highlighted opportunities to better align the active case finding national strategy with the TB disease burden.

Relative location prediction in CT scan images using convolutional neural networks.

BACKGROUND AND OBJECTIVE: Relative location prediction in computed tomography (CT) scan images is a challenging problem. Many traditional machine learning methods have been applied in attempts to alleviate this problem. However, the accuracy and speed of these methods cannot meet the requirement of medical scenario. In this paper, we propose a regression model based on one-dimensional convolutional neural networks (CNN) to determine the relative location of a CT scan image both quickly and precisely. METHODS: In contrast to other common CNN models that use a two-dimensional image as an input, the input of this CNN model is a feature vector extracted by a shape context algorithm with spatial correlation. Normalization via z-score is first applied as a pre-processing step. Then, in order to prevent overfitting and improve model's performance, 20% of the elements of the feature vectors are randomly set to zero. This CNN model consists primarily of three one-dimensional convolutional layers, three dropout layers and two fully-connected layers with appropriate loss functions. RESULTS: A public dataset is employed to validate the performance of the proposed model using a 5-fold cross validation. Experimental results demonstrate an excellent performance of the proposed model when compared with contemporary techniques, achieving a median absolute error of 1.04 cm and mean absolute error of 1.69 cm. The time taken for each relative location prediction is approximately 2 ms. CONCLUSION: Results indicate that the proposed CNN method can contribute to a quick and accurate relative location prediction in CT scan images, which can improve efficiency of the medical picture archiving and communication system in the future.