Search

Abstract This study aimed to develop and evaluate a deep learning-based system for the automatic measurement of angles (specifically, Meary’s angle and calcaneal pitch) in weight-bearing lateral radiographs of the foot for flatfoot diagnosis. We utilized 3960 lateral radiographs, either from the left or right foot, sourced from a pool of 4000 patients to construct and evaluate a deep learning-based model. These radiographs were captured between June and November 2021, and patients who had undergone total ankle replacement surgery or ankle arthrodesis surgery were excluded. Various methods, including correlation analysis, Bland–Altman plots, and paired T-tests, were employed to assess the concordance between the angles automatically measured using the system and those assessed by clinical experts. The evaluation dataset comprised 150 weight-bearing radiographs from 150 patients. In all test cases, the angles automatically computed using the deep learning-based system were in good agreement with the reference standards (Meary’s angle: Pearson correlation coefficient (PCC) = 0.964, intraclass correlation coefficient (ICC) = 0.963, concordance correlation coefficient (CCC) = 0.963, p-value = 0.632, mean absolute error (MAE) = 1.59°; calcaneal pitch: PCC = 0.988, ICC = 0.987, CCC = 0.987, p-value = 0.055, MAE = 0.63°). The average time required for angle measurement using only the CPU to execute the deep learning-based system was 11 ± 1 s. The deep learning-based automatic angle measurement system, a tool for diagnosing flatfoot, demonstrated comparable accuracy and reliability with the results obtained by medical professionals for patients without internal fixation devices.

Pelvic malalignment leads to general imbalance and adversely affects leg length. Timely and accurate diagnosis of pelvic alignment in patients is crucial to prevent additional complications arising from delayed treatment. Currently, doctors typically assess pelvic alignment either manually or through radiography. This study aimed to develop and assess the validity of a deep learning-based system for automatically measuring 10 radiographic parameters necessary for diagnosing pelvic displacement using standing anteroposterior pelvic X-rays. Between March 2016 and June 2021, pelvic radiographs from 1215 patients were collected. After applying specific selection criteria, 550 pelvic radiographs were chosen for analysis. These data were utilized to develop a deep learning-based system capable of automatically measuring radiographic parameters relevant to pelvic displacement diagnosis. The system's diagnostic accuracy was evaluated by comparing automatically measured values with those assessed by a clinician using 200 radiographs selected from the initial 550. The results indicated that the system exhibited high reliability, accuracy, and reproducibility, with a Pearson correlation coefficient of ≥0.9, an intra-class correlation coefficient of ≥0.9, a mean absolute error of ≤1 cm, mean square error of ≤1 cm, and root mean square error of ≤1 cm. Moreover, the system's measurement time for a single radiograph was found to be 18 to 20 times faster than that required by a clinician for manual inspection. In conclusion, our proposed deep learning-based system effectively utilizes standing anteroposterior pelvic radiographs to precisely and consistently measure radiographic parameters essential for diagnosing pelvic displacement.

Abstract The Kellgren–Lawrence (KL) grading system is a scoring system for classifying the severity of knee osteoarthritis using X-ray images, and it is the standard X-ray-based grading system for diagnosing knee osteoarthritis. However, KL grading depends on the clinician’s subjective assessment. Moreover, the accuracy varies significantly depending on the clinician’s experience and can be particularly low. Therefore, in this study, we developed an ensemble network that can predict a consistent and accurate KL grade for knee osteoarthritis severity using a deep learning approach. We trained individual models on knee X-ray datasets using the most suitable image size for each model in an ensemble network rather than using datasets with a single image size. We then built the ensemble network using these models to overcome the instability of single models and further improve accuracy. We conducted various experiments using a dataset of 8260 images from the Osteoarthritis Initiative open dataset. The proposed ensemble network exhibited the best performance, achieving an accuracy of 76.93% and an F1-score of 0.7665. The Grad-CAM visualization technique was used to further evaluate the focus of the model. The results demonstrated that the proposed ensemble network outperforms existing techniques that have performed well in KL grade classification. Moreover, the proposed model focuses on the joint space around the knee to extract the imaging features required for KL grade classification, revealing its high potential for diagnosing knee osteoarthritis.

Abstract During clinical evaluation of patients and planning orthopedic treatments, the periodic assessment of lower limb alignment is critical. Currently, physicians use physical tools and radiographs to directly observe limb alignment. However, this process is manual, time consuming, and prone to human error. To this end, a deep-learning (DL)-based system was developed to automatically, rapidly, and accurately detect lower limb alignment by using anteroposterior standing X-ray medical imaging data of lower limbs. For this study, leg radiographs of non-overlapping 770 patients were collected from January 2016 to August 2020. To precisely detect necessary landmarks, a DL model was implemented stepwise. A radiologist compared the final calculated measurements with the observations in terms of the concordance correlation coefficient (CCC), Pearson correlation coefficient (PCC), and intraclass correlation coefficient (ICC). Based on the results and 250 frontal lower limb radiographs obtained from 250 patients, the system measurements for 16 indicators revealed superior reliability (CCC, PCC, and ICC ≤ 0.9; mean absolute error, mean square error, and root mean square error ≥ 0.9) for clinical observations. Furthermore, the average measurement speed was approximately 12 s. In conclusion, the analysis of anteroposterior standing X-ray medical imaging data by the DL-based lower limb alignment diagnostic support system produces measurement results similar to those obtained by radiologists.

Abstract The demand for anomaly detection, which involves the identification of abnormal samples, has continued to increase in various domains. In particular, with increases in the data volume of medical imaging, the demand for automated screening systems has also risen. Consequently, in actual clinical practice, radiologists can focus only on diagnosing patients with abnormal findings. In this study, we propose an unsupervised anomaly detection method for posteroanterior chest X-rays (CXR) using multiresolution patch-based self-supervised learning. The core aspect of our approach is to leverage patch images of different sizes for training and testing to recognize diverse anomalies characterized by unknown shapes and scales. In addition, self-supervised contrastive learning is applied to learn the generalized and robust features of the patches. The performance of the proposed method is evaluated using posteroanterior CXR images from a public dataset for training and testing. The results show that the proposed method is superior to state-of-the-art anomaly detection methods. In addition, unlike single-resolution patch-based methods, the proposed method consistently exhibits a good overall performance regardless of the evaluation criteria used for comparison, thus demonstrating the effectiveness of using multiresolution patch-based features. Overall, the results of this study validate the effectiveness of multiresolution patch-based self-supervised learning for detecting anomalies in CXR images.

Abstract We examined the feasibility of explainable computer-aided detection of cardiomegaly in routine clinical practice using segmentation-based methods. Overall, 793 retrospectively acquired posterior–anterior (PA) chest X-ray images (CXRs) of 793 patients were used to train deep learning (DL) models for lung and heart segmentation. The training dataset included PA CXRs from two public datasets and in-house PA CXRs. Two fully automated segmentation-based methods using state-of-the-art DL models for lung and heart segmentation were developed. The diagnostic performance was assessed and the reliability of the automatic cardiothoracic ratio (CTR) calculation was determined using the mean absolute error and paired t-test. The effects of thoracic pathological conditions on performance were assessed using subgroup analysis. One thousand PA CXRs of 1000 patients (480 men, 520 women; mean age 63 ± 23 years) were included. The CTR values derived from the DL models and diagnostic performance exhibited excellent agreement with reference standards for the whole test dataset. Performance of segmentation-based methods differed based on thoracic conditions. When tested using CXRs with lesions obscuring heart borders, the performance was lower than that for other thoracic pathological findings. Thus, segmentation-based methods using DL could detect cardiomegaly; however, the feasibility of computer-aided detection of cardiomegaly without human intervention was limited.

Accurate identification of the shape and position of organs and abnormal objects (e.g., tumors) in medical images plays an important role in surgical planning as well as in the diagnosis and prognosis of diseases. However, this is difficult to achieve from two-dimensional medical images as these images present inaccurate and ambiguous organ boundaries. Further, traditional image processing-based boundary detection methods such as the Canny edge detector and Sobel operator exhibit poor boundary detection performance for images with substantial noise. Recently, the use of deep learning has resulted in improvements in semantic segmentation in medical images. In this paper, we propose a generic boundary-aware loss function to facilitate the effective discernment of the boundaries of organs and abnormal objects in medical images. Specifically, the proposed loss function introduces a boundary area and assigns higher weights to the loss of pixels located in the boundary area than to those in the non-boundary areas, thereby promoting effective learning in the boundary area. The results of experiments conducted using public medical datasets comprising colon polyp, skin lesion, and chest X-ray data indicate that the standard loss functions, such as cross-entropy loss and Dice loss, combined with the proposed boundary-aware loss function, achieve comparable or better performance than those without the boundary-aware loss function.

Accurate segmentation of mandibular canals in lower jaws is important in dental implantology. Medical experts manually determine the implant position and dimensions from 3D CT images to avoid damaging the mandibular nerve inside the canal. In this paper, we propose a novel dual-stage deep learning-based scheme for the automatic segmentation of the mandibular canal. In particular, we first enhance the CBCT scans by employing the novel histogram-based dynamic windowing scheme, which improves the visibility of mandibular canals. After enhancement, we designed 3D deeply supervised attention UNet architecture for localizing the Volumes Of Interest (VOIs), which contain the mandibular canals (i.e., left and right canals). Finally, we employed the Multi-Scale input Residual UNet (MSiR-UNet) architecture to segment the mandibular canals using VOIs accurately. The proposed method has been rigorously evaluated on 500 and 15 CBCT scans from our dataset and from the public dataset, respectively. The results demonstrate that our technique improves the existing performance of mandibular canal segmentation to a clinically acceptable range. Moreover, it is robust against the types of CBCT scans in terms of field of view.

Deep learning technology has rapidly evolved in recent years. Bone age assessment (BAA) is a typical object detection and classification problem that would benefit from deep learning. Convolutional neural networks (CNNs) and their variants are hence increasingly used for automating BAA, and they have shown promising results. In this paper, we propose a complete end-to-end BAA system to automate the entire process of the Tanner-Whitehouse 3 method, starting from localization of the epiphysis-metaphysis growth regions within 13 different bones and ending with estimation of the corresponding BA. Specific modifications to the CNNs and other stages are proposed to improve results. In addition, an annotated database of 3300 X-ray images is built to train and evaluate the system. The experimental results show that the average top-1 and top-2 prediction accuracies for skeletal bone maturity levels for 13 regions of interest are 79.6% and 97.2%, respectively. The mean absolute error and root mean squared error in age prediction are 0.46 years and 0.62 years, respectively, and accuracy within one year of the ground truth of 97.6% is achieved. The proposed system is shown to outperform a commercially available Greulich-Pyle-based system, demonstrating the potential for practical clinical use.

Recently, deep learning has been employed in medical image analysis for several clinical imaging methods, such as X-ray, computed tomography, magnetic resonance imaging, and pathological tissue imaging, and excellent performance has been reported. With the development of these methods, deep learning technologies have rapidly evolved in the healthcare industry related to hair loss. Hair density measurement (HDM) is a process used for detecting the severity of hair loss by counting the number of hairs present in the occipital donor region for transplantation. HDM is a typical object detection and classification problem that could benefit from deep learning. This study analyzed the accuracy of HDM by applying deep learning technology for object detection and reports the feasibility of automating HDM. The dataset for training and evaluation comprised 4492 enlarged hair scalp RGB images obtained from male hair-loss patients and the corresponding annotation data that contained the location information of the hair follicles present in the image and follicle-type information according to the number of hairs. EfficientDet, YOLOv4, and DetectoRS were used as object detection algorithms for performance comparison. The experimental results indicated that YOLOv4 had the best performance, with a mean average precision of 58.67.

Moving pictures experts group (MPEG) media transport (MMT) and MPEG-dynamic adaptive streaming over hypertext transfer protocol (MPEG-DASH) are emerging as the content-delivery technologies for the next-generation broadcasting systems, as they seamlessly utilize various underlying delivery networks to provide hybrid multimedia services in any location. In this paper, we present an empirical analysis of the channel-zapping time, which is an important metric in the measurement of the quality of experience (QoE) of broadcast services, regarding the MMT and MPEG-DASH technologies. During this process, we also clarify the important factors that determine the channel-zapping time of the individual technologies. In addition, we propose a simple yet effective method that enables fast channel zapping for the MMT technology.

Accurate identification of the boundaries of organs or abnormal objects (e.g., tumors) in medical images is important in surgical planning and in the diagnosis and prognosis of diseases. In this study, we propose a deep learning-based method to segment lung areas in chest X-rays. The novel aspect of the proposed method is the self-attention module, where the outputs of the channel and spatial attention modules are combined to generate attention maps, with each highlighting those regions of feature maps that correspond to “what” and “where” to attend in the learning process, respectively. Thereafter, the attention maps are multiplied element-wise with the input feature map, and the intermediate results are added to the input feature map again for residual learning. Using X-ray images collected from public datasets for training and evaluation, we applied the proposed attention modules to U-Net for segmentation of lung areas and conducted experiments while changing the locations of the attention modules in the baseline network. The experimental results showed that our method achieved comparable or better performance than the existing medical image segmentation networks in terms of Dice score when the proposed attention modules were placed in lower layers of both the contracting and expanding paths of U-Net.

The objective of this paper is to improve the overall performance of distributed encoding, with a particular focus on encoding speed. The proposed scheme consists of content-aware video segmentation and scheduling that consists of two major parts. In the first part, segmentation is carried out with greater efficiency by considering changes in the video content, and in the second part, the segment assignment process is carried out using an efficient scheduling scheme that changes the encoding order of the segments. We measured the content similarity by using the sum of absolute difference algorithm and then applied a threshold to define the degree of change in similarity. The video was segmented based on the extent to which the similarity had changed, and the encoding order of the segments was rearranged to perform distributed encoding. Finally, this paper introduces the MapReduce-based distributed video encoding, using the content-aware video segmentation and scheduling described above, and presents the results of the performance using this scheme, which indicate that the proposed scheme increases the bitrate by a maximum of 2.9% over existing segmentation schemes, and also increases the speed by a maximum of 15.3%.

With the recent advancements in cloud computing technology, the number of cloud-based services has been gradually increasing. Symmetrically, users are asking for quality of experience (QoE) to be maintained or improved. To do this, it has become necessary to manage network resources more efficiently inside the cloud. Many theoretical studies for improving the users’ QoE have been proposed. However, there are few practical solutions due to the lack of symmetry between implementation and theoretical researches. Hence, in this study, we propose a ranking table-based network resource allocation method that dynamically allocates network resources per service flow based on flow information periodically collected from a software defined network (SDN). It dynamically identifies the size of the data transmission for each service flow on the SDN and differentially allocates network resources to each service flow based on this size. As a result, it maintains the maximum QoE for the user by increasing the network utilization. The experimental results show that the proposed method achieves 29.4% higher network efficiency than the general Open Shortest Path First (OSPF) method on average.

The Software Defined Network (SDN) decouples control and data planes of the existing network architecture and a controller carries out centralized management and control of the network. This provides flexibility for the networks and enables efficient operation, depending on their condition. However, when the performance of switches comprising the SDN varies, any switches with low performance can cause flow table overflow and subsequent bottleneck with overhead concentrating in the controller. Besides, packet processing can be delayed, declining user QoS. The paper proposes a flow entry replacement scheme that takes into account the flow features to address the issue. The proposed Short Flow First (SFF) scheme discriminates the flow features based on the matching period of flow entry and determines a subject of the flow entry replacement with the features. For evaluation, the paper built the SDN environment using the Mininet emulator and compared the performance of the proposed SFF scheme with the representative flow entry replacement schemes. According to the results, the proposed scheme showed a good performance in the flow entry miss rate and packet delay due to failure of matching the flow entry.

In wireless body sensor network systems (WB-SNSs), the sensor nodes have very limited battery power because they are tiny, lightweight, and wearable or implantable. As a result, WB-SNSs require a very efficient transmission power control (TPC) algorithm for effectively reducing energy consumption and extending the lifetime of sensor nodes. To achieve this goal, we propose a novel TPC algorithm referred to as hybrid TPC. The hybrid TPC algorithm adaptively selects a conservative or an aggressive control mechanism depending on current channel conditions. The conservative control mechanism, which slowly changes transmission power level (TPL), is suitable in a dynamic environment. On the other hand, the aggressive control mechanism, which rapidly changes TPL, is ideal in a static environment. In order to evaluate the effectiveness of the hybrid TPC algorithm, we implemented various TPC algorithms and compared their performances against the hybrid TPC algorithm in different channel environments. The experimental results showed that the hybrid TPC algorithm outperformed other TPC algorithms in all channel environments.