Deep-learning-based gestational sac detection in ultrasound images using modified YOLOv7-E6E model.

As the population and income levels rise, meat consumption steadily increases annually. However, the number of farms and farmers producing meat decrease during the same period, reducing meat sufficiency. Information and Communications Technology (ICT) has begun to be applied to reduce labor and production costs of livestock farms and improve productivity. This technology can be used for rapid pregnancy diagnosis of sows; the location and size of the gestation sacs of sows are directly related to the productivity of the farm. In this study, a system proposes to determine the number of gestation sacs of sows from ultrasound images. The system used the YOLOv7-E6E model, changing the activation function from sigmoid-weighted linear unit (SiLU) to a multi-activation function (SiLU + Mish). Also, the upsampling method was modified from nearest to bicubic to improve performance. The model trained with the original model using the original data achieved mean average precision of 86.3%. When the proposed multi-activation function, upsampling, and AutoAugment were applied, the performance improved by 0.3%, 0.9%, and 0.9%, respectively. When all three proposed methods were simultaneously applied, a significant performance improvement of 3.5% to 89.8% was achieved.

An intelligent method for pregnancy diagnosis in breeding sows according to ultrasonography algorithms.

Pig breeding management directly contributes to the profitability of pig farms, and pregnancy diagnosis is an important factor in breeding management. Therefore, the need to diagnose pregnancy in sows is emphasized, and various studies have been conducted in this area. We propose a computer-aided diagnosis system to assist livestock farmers to diagnose sow pregnancy through ultrasound. Methods for diagnosing pregnancy in sows through ultrasound include the Doppler method, which measures the heart rate and pulse status, and the echo method, which diagnoses by amplitude depth technique. We propose a method that uses deep learning algorithms on ultrasonography, which is part of the echo method. As deep learning-based classification algorithms, Inception-v4, Xception, and EfficientNetV2 were used and compared to find the optimal algorithm for pregnancy diagnosis in sows. Gaussian and speckle noises were added to the ultrasound images according to the characteristics of the ultrasonography, which is easily affected by noise from the surrounding environments. Both the original and noise added ultrasound images of sows were tested together to determine the suitability of the proposed method on farms. The pregnancy diagnosis performance on the original ultrasound images achieved 0.99 in accuracy in the highest case and on the ultrasound images with noises, the performance achieved 0.98 in accuracy. The diagnosis performance achieved 0.96 in accuracy even when the intensity of noise was strong, proving its robustness against noise.

A deep learning-based approach for feeding behavior recognition of weanling pigs.

Feeding is the most important behavior that represents the health and welfare of weanling pigs. The early detection of feed refusal is crucial for the control of disease in the initial stages and the detection of empty feeders for adding feed in a timely manner. This paper proposes a real-time technique for the detection and recognition of small pigs using a deep-leaning-based method. The proposed model focuses on detecting pigs on a feeder in a feeding position. Conventional methods detect pigs and then classify them into different behavior gestures. In contrast, in the proposed method, these two tasks are combined into a single process to detect only feeding behavior to increase the speed of detection. Considering the significant differences between pig behaviors at different sizes, adaptive adjustments are introduced into a you-only-look-once (YOLO) model, including an angle optimization strategy between the head and body for detecting a head in a feeder. According to experimental results, this method can detect the feeding behavior of pigs and screen non-feeding positions with 95.66%, 94.22%, and 96.56% average precision (AP) at an intersection over union (IoU) threshold of 0.5 for YOLOv3, YOLOv4, and an additional layer and with the proposed activation function, respectively. Drinking behavior was detected with 86.86%, 89.16%, and 86.41% AP at a 0.5 IoU threshold for YOLOv3, YOLOv4, and the proposed activation function, respectively. In terms of detection and classification, the results of our study demonstrate that the proposed method yields higher precision and recall compared to conventional methods.

Energy-Efficient and Reliable Face-Routing Scheme in Wireless Networks.

Face-routing is one of the reliable recovery schemes when geographic routing fails to transmit data packets. Although studies on face-routing can overcome the failure of the data transmission, they lead to much energy consumption due to frequent data transmissions between adjacent nodes for carrying out the rule of face-routing. To avoid the frequent data transmissions, several face-routing schemes have been recently proposed to transmit data packets to the farthest-neighbor node. However, they happen with many data retransmissions because the farthest-neighbor node has a relatively low transmission success ratio. To solve this problem, we propose a new face-routing scheme that determines the most appropriate neighbor node to balance the trade-off between energy efficiency and transmission reliability with two viewpoints. The first viewpoint focuses on how to increase the distance progress of the data delivery in one-hop range to enhance energy efficiency. After that, the second viewpoint focuses on how to increase the success ratio of the data delivery to enhance the transmission reliability. As a result of the simulation, it was confirmed that the proposed method achieves better performance in terms of energy efficiency than existing face-routing research, and it is better than recent face-routing research in terms of reliability and retransmission.

A Hierarchical Routing Graph for Supporting Mobile Devices in Industrial Wireless Sensor Networks.

As many industrial applications require real-time and reliability communication, a variety of routing graph construction schemes were proposed to satisfy the requirements in Industrial Wireless Sensor Networks (IWSNs). Each device transmits packet through a route which is designated based on the graph. However, as existing studies consider a network consists of static devices only, they cannot cope with the network changes by movement of mobile devices considered important in the recent industrial environment. Thus, the communication requirements cannot be guaranteed because the existing path is broken by the varying network topology. The communication failure could cause critical problems such as malfunctioning equipment. The problem is caused repeatedly by continuous movement of mobile devices, even if a new graph is reconstructed for responding the changed topology. To support mobile devices exploited in various industrial environments, we propose a Hierarchical Routing Graph Construction (HRGC). The HRGC is consisted of two phases for hierarchical graph construction: In first phase, a robust graph called skeleton graph consisting only of static devices is constructed. The skeleton graph is not affected by network topology changes and does not suffer from packet loss. In second phase, the mobile devices are grafted into the skeleton graph for seamless communication. Through the grafting process, the routes are established in advance for mobile device to communicate with nearby static devices in anywhere. The simulation results show that the packet delivery ratio is improved when the graph is constructed through the HRGC.

An Energy Efficient Sink Location Service for Continuous Objects in Wireless Sensor Networks.

In wireless sensor networks (WSNs), detection and report of continuous object, such as forest fire and toxic gas leakage, is one of the major applications. In large-scale continuous object tracking in WSNs, there might be many source nodes simultaneously, detecting the continuous object. Each nodes reports its data to both a base station and mobile workers in the industry field. For communication between the source nodes and a mobile worker, sink location service is needed to continuously notify the location of the mobile worker. But, as the application has a large number of sources, it causes a waste of energy consumption. To address this issue, in this paper, we propose a two-phase sink location service scheme. In the first phase, the proposed scheme constructs a virtual grid structure for merging the source nodes. Then, the proposed scheme aggregates the merging points from an originated merging point as the second phase. Simulation results show that the proposed scheme is superior to other schemes in terms of energy consumption.

Ultrasound shear wave simulation of wave propagation at oblique angles.

Shear wave elasticity imaging (SWEI) has been used to measure the local tissue elasticity. The local tissue shear modulus can be reconstructed from the displacement field of shear waves using an algebraic Helmholtz inversion (AHI) equation or a time-of-flight (TOF)-based algorithm. The shear waves, which are generated by successive focusing of ultrasonic beams at different depths, propagate at oblique angles rather than along the lateral position. The wave propagation at oblique angles can result in bias in shear modulus reconstruction using the AHI equation or the TOF-based algorithm. In this study, the effect of wave propagation at oblique angles on the tissue shear modulus reconstruction was investigated using in silico finite element (FE) simulation. An FE elastic tissue with a hard inclusion model was designed. The shear waves with propagation angles of 0°, 5°, and 10° were applied to the model. The shear modulus and the percentage error in the model were computed using the AHI equation and the TOF-based algorithm at each propagation angle from 0° to 10°. For the AHI equation, the percentage error was 0% at propagation angles of 0° and 5°, and 1% at a propagation angle of 10° in the inclusion. In the surrounding tissue, the percentage error was 0% at propagation angles of 0°, 5°, and 10°. For the TOF-based algorithm, the percentage error was 0% at propagation angles of 0° and 5°, and 40% at a propagation angle of 10° in the inclusion. In the surrounding tissue, the percentage error was 0% at propagation angles of 0° and 5°, and 35% at a propagation angle of 10° in the inclusion. Therefore, whereas the TOF-based algorithm produced critical bias in shear modulus reconstruction by the shear wave propagation at oblique angles, the AHI equation was not affected by the propagation.

A similarity study of content-based image retrieval system for breast cancer using decision tree.

PURPOSE: We are developing a decision tree content-based image retrieval (DTCBIR) CADx system to assist radiologists in characterization of breast masses on ultrasound images. METHODS: Three DTCBIR configurations, including decision tree with boosting (DTb), decision tree with full leaf features (DTL), and decision tree with selected leaf features (DTLs) were compared. For DTb, features of a query mass were combined first into a merged feature score and then masses with similar scores were retrieved. For DTL and DTLs, similar masses were retrieved based on the Euclidean distance between feature vectors of the query and those of selected references. For each DTCBIR configuration, we investigated the use of full feature set and subset of features selected by the stepwise linear discriminant analysis (LDA) and simplex optimization method, resulting in six retrieval methods and selected five, DTb-lda, DTL-lda, DTb-full, DTL-full, and DTLs-full, for the observer study. Three MQSA radiologists rated similarities between the query mass and computer-retrieved three most similar masses using nine-point similarity scale (9 = very similar). RESULTS: For DTb-lda, DTL-lda, DTb-full, DTL-full, and DTLs-full, average A(z) values were 0.90 ± 0.03, 0.85 ± 0.04, 0.87 ± 0.04, 0.79 ± 0.05, and 0.71 ± 0.06, respectively, and average similarity ratings were 5.00, 5.41, 4.96, 5.33, and 5.13, respectively. CONCLUSIONS: The DTL-lda is a promising DTCBIR CADx configuration which had simple tree structure, good classification performance, and highest similarity rating.

Similarity evaluation in a content-based image retrieval (CBIR) CADx system for characterization of breast masses on ultrasound images.

PURPOSE: The authors are developing a content-based image retrieval (CBIR) CADx system to assist radiologists in characterization of breast masses on ultrasound images. In this study, the authors compared seven similarity measures to be considered for the CBIR system. The similarity between the query and the retrieved masses was evaluated based on radiologists' visual similarity assessments. METHODS: The CADx system retrieves masses that are similar to a query mass from a reference library based on computer-extracted features using a k-nearest neighbor (k-NN) approach. Among seven similarity measures evaluated for the CBIR system, four similarity measures including linear discriminant analysis (LDA), Bayesian neural network (BNN), cosine similarity measure (Cos), and Euclidean distance (ED) similarity measure were compared by radiologists' visual assessment. For LDA and BNN, the features of a query mass were combined first into a malignancy score and then masses with similar scores were retrieved. For Cos and ED, similar masses were retrieved based on the normalized dot product and the Euclidean distance, respectively, between two feature vectors. For the observer study, three most similar masses were retrieved for a given query mass with each method. All query-retrieved mass pairs were mixed and presented to the radiologists in random order. Three Mammography Quality Standards Act (MQSA) radiologists rated the similarity between each pair using a nine-point similarity scale (1 = very dissimilar, 9 = very similar). The accuracy of the CBIR CADx system using the different similarity measures to characterize malignant and benign masses was evaluated by ROC analysis. RESULTS: The BNN measure used with the k-NN classifier provided slightly higher performance for classification of malignant and benign masses (A(z) values of 0.87) than those with the LDA, Cos, and ED measures (A(z) of 0.86, 0.84, and 0.81, respectively). The average similarity ratings of all radiologists for LDA, BNN, Cos, and ED were 4.71, 4.95, 5.18, and 5.32, respectively. The k-NN with the ED measures retrieved masses of significantly higher similarity (p < 0.008) than LDA and BNN. CONCLUSIONS: Similarity measures using the resemblance of individual features in the multidimensional feature space can retrieve visually more similar masses than similarity measures using the resemblance of the classifier scores. A CBIR system that can most effectively retrieve similar masses to the query may not have the best A(z).