Search

Calcaneus is the bone in the foot that bears most of the body weight and calcaneus fracture is the most common type of tarsal bone fractures. Plain radiograph examination is usually the first step of calcaneus fracture diagnosis because of its convenience and low cost. A multi-task U-Net is proposed in this paper to develop a computer aided calcaneus fracture diagnosis system. Our approach is an end-to-end CNN for identification and segmentation of calcaneus fracture, which uses regularization of the two tasks for mutual performance enhancement. First, a novel radiograph normalization method to obtain scale rotation invariance under different monochrome type is employed. Second, a classification header with feature from decoder and encoder is added to U-Net for multitask. Finally, a conditional dice-loss which can promote model performance under rough-ground-truth supervision is adopted in training. Experiments show that the network predicts fracture regions more precise than the rough ground-truth and identifies fracture with sensitivity of 99.53% and specificity of 98.59%.

Background and objective Calcaneus is the largest tarsal bone to withstand the daily stresses of weight-bearing. The calcaneal fracture is the most common type in the tarsal bone fractures. After a fracture is suspected, plain radiographs should be taken first. Bohler's Angle (BA) and Critical Angle of Gissane (CAG), measured by four anatomic landmarks in lateral foot radiograph, can guide fracture diagnosis and facilitate operative recovery of the fractured calcaneus. This study aims to develop an analysis system that can automatically locate four anatomic landmarks, measure BA and CAG for fracture assessment, identify fractured calcaneus, and segment fractured regions. Methods For landmark detection, we proposed a coarse-to-fine Rotation-Invariant Regression-Voting (RIRV) landmark detection method based on regressive Multi-Layer Perceptron (MLP) and Scale Invariant Feature Transform (SIFT) patch descriptor, which solves the problem of fickle rotation of calcaneus. By implementing a novel normalization approach, the RIRV method is explicitly rotation-invariance comparing with traditional regressive methods. For fracture identification and segmentation, a convolution neural network (CNN) based on U-Net with auxiliary classification head (U-Net-CH) is designed. The input ROIs of the CNN are normalized by detected landmarks to uniform view, orientation, and scale. The advantage of this approach is the multi-task learning that combines classification and segmentation. Results Our system can accurately measure BA and CAG with a mean angle error of 3.8○ and 6.2○ respectively. For fracture identification and fracture region segmentation, our system presents good performance with an F1-score of 96.55%, recall of 94.99%, and segmentation IoU-score of 0.586. Conclusion A powerful calcaneal radiograph analysis system including anatomical angles measurement, fracture identification, and fracture segmentation can be built. The proposed analysis system can aid orthopedists to improve the efficiency and accuracy of calcaneus fracture diagnosis.

Coded-aperture imagers typically have a smaller field-of-view (FOV) than in un-collimated gamma imaging systems. However, sources out of the fully coded field-of-view (FCFOV) can cause pseudo hotspots on the wrong side of an image reconstructed using the cross-correlation method. In this work, we propose a neural network method to identify and localize the sources within the partially coded field-of-view (PCFOV). The model was trained using Monte Carlo simulation data and evaluated with both simulation and experimental data. The results showed that the proposed model can identify and localize sources with good classification accuracy, low positioning error, and strong robustness to the statistical noise.

The proportion of the rural population who live within 2 km of an all-season road is an indicator of the United Nations’ Sustainable Development Goals (SDGs) 9.1.1. This paper aims to calculate SDG indicator 9.1.1 in the proximity of five Algerian expressways. Three monitoring methods are proposed for different spatial regions based on the five expressways built by China’s Belt and Road Initiative Project. These methods are based on remote sensing and WorldPop and The High Resolution Settlement Layer (HRSL) population data. The results indicate that (1) the WorldPop population statistics show that the five expressways built by China’s Belt Project have increased the rural population of the 2 km buffer zone by 192,016 between the start of construction and eight years after its completion. By the end of 2019, the population increased by 329,291 accounting for 1.17% of the rural population. (2) Based on populations estimated form built-up index (NDBI) building areas, the rural populations within the 2 km buffer area of the Bejaia-Haniff Expressway in 2011, 2015, and 2019 were 273,118, 306,430, and 375,408, respectively. (3) HRSL population grid statistics indicate that, in 2015, the populations were: East-West Expressway = 911,549, Bejaia Expressway = 127,471, Tipaza Expressway = 71,411, North-South Expressway = 30,583, and Cherchell Ring Expressway = 41,657. (4) A visual interpretation method based on Google Earth imagery was used to count the number of buildings and number of building floors in the town of Tikhramtath. Based on the estimated population of each building and floor, the population of Tikhramtath town in 2011, 2015, 2017, and 2019 was estimated as 1,790, 2,785, 3,365, and 3,870, respectively. (5) Through analysis and accuracy assessment, the appropriate statistical methods for different regions were determined.