Journal of Imaging最新文献

In CT-guided percutaneous punctures-an image-guided puncture method using CT images-physicians treat targets such as lung tumors, liver tumors, renal tumors, and intervertebral abscesses by inserting a puncture needle into the body from the exterior while viewing images. By recognizing two-dimensional CT images prior to a procedure, a physician determines the least invasive puncture route for the patient. Therefore, the candidate puncture route is limited to a two-dimensional region along the cross section of the human body. In this paper, we aim to construct a three-dimensional puncture space based on multiple two-dimensional CT images to search for a safer and shorter puncture route for a given patient. If all puncture routes starting from a target in the three-dimensional space were examined from all directions (the brute-force method), the processing time to derive the puncture route would be very long. We propose a more efficient method for three-dimensional puncture route selection in CT-guided percutaneous punctures. The proposed method extends the ray-tracing method, which quickly derives a line segment from a given start point to an end point on a two-dimensional plane, and applies it to three-dimensional space. During actual puncture route selection, a physician can use CT images to derive a three-dimensional puncture route that is safe for the patient and minimizes the puncture time. The main novelty is that we propose a method for deriving a three-dimensional puncture route within the allowed time in an actual puncture. The main goal is for physicians to select the puncture route they will use in the actual surgery from among the multiple three-dimensional puncture route candidates derived using the proposed method. The proposed method derives a three-dimensional puncture route within the allowed time in an actual puncture. Physicians can use the proposed method to derive a new puncture route, reducing the burden on patients and improving physician skills. In the evaluation results of a computer simulation, for a 3D CT image created by combining 170 two-dimensional CT images, the processing time for deriving the puncture route using the proposed method was approximately 59.4 s. The shortest length of the puncture route from the starting point to the target was between 20 mm and 22 mm. The search time for a three-dimensional human body consisting of 15 CT images was 4.77 s for the proposed method and 2599.0 s for a brute-force method. In a questionnaire, physicians who actually perform puncture treatments evaluated the candidate puncture routes derived by the proposed method. We confirmed that physicians could actually use these candidates as a puncture route.

The global spread of Coronavirus (COVID-19) has prompted imperative research into scalable and effective detection methods to curb its outbreak. The early diagnosis of COVID-19 patients has emerged as a pivotal strategy in mitigating the spread of the disease. Automated COVID-19 detection using Chest X-ray (CXR) imaging has significant potential for facilitating large-scale screening and epidemic control efforts. This paper introduces a novel approach that employs state-of-the-art Convolutional Neural Network models (CNNs) for accurate COVID-19 detection. The employed datasets each comprised 15,000 X-ray images. We addressed both binary (Normal vs. Abnormal) and multi-class (Normal, COVID-19, Pneumonia) classification tasks. Comprehensive evaluations were performed by utilizing six distinct CNN-based models (Xception, Inception-V3, ResNet50, VGG19, DenseNet201, and InceptionResNet-V2) for both tasks. As a result, the Xception model demonstrated exceptional performance, achieving 98.13% accuracy, 98.14% precision, 97.65% recall, and a 97.89% F1-score in binary classification, while in multi-classification it yielded 87.73% accuracy, 90.20% precision, 87.73% recall, and an 87.49% F1-score. Moreover, the other utilized models, such as ResNet50, demonstrated competitive performance compared with many recent works.

Phase Retrieval is defined as the recovery of a signal when only the intensity of its Fourier Transform is known. It is a non-linear and non-convex optimization problem with a multitude of applications including X-ray crystallography, microscopy and blind deconvolution. In this study, we address the problem of Phase Retrieval from the perspective of variable splitting and alternating minimization for real signals and seek to develop algorithms with improved convergence properties. An exploration of the underlying geometric relations led to the conceptualization of an algorithmic step aiming to refine the estimate at each iteration via recombination of the separated variables. Following this, a theoretical analysis to study the convergence properties of the proposed method and justify the inclusion of the recombination step was developed. Our experiments showed that the proposed method converges substantially faster compared to other state-of-the-art analytical methods while demonstrating equivalent or superior performance in terms of quality of reconstruction and ability to converge under various setups.

With the rapid advancement of deep learning technologies, computer vision has shown immense potential in retail automation. This paper presents a novel self-checkout system for retail based on an improved YOLOv10 network, aimed at enhancing checkout efficiency and reducing labor costs. We propose targeted optimizations for the YOLOv10 model, incorporating the detection head structure from YOLOv8, which significantly improves product recognition accuracy. Additionally, we develop a post-processing algorithm tailored for self-checkout scenarios, to further enhance the application of the system. Experimental results demonstrate that our system outperforms existing methods in both product recognition accuracy and checkout speed. This research not only provides a new technical solution for retail automation but offers valuable insights into optimizing deep learning models for real-world applications.

Time-of-Flight (ToF) cameras are subject to high levels of noise and errors due to Multi-Path-Interference (MPI). To correct these errors, algorithms and neuronal networks require training data. However, the limited availability of real data has led to the use of physically simulated data, which often involves simplifications and computational constraints. The simulation of such sensors is an essential building block for hardware design and application development. Therefore, the simulation data must capture the major sensor characteristics. This work presents a learning-based approach that leverages high-quality laser scan data to generate realistic ToF camera data. The proposed method employs MCW-Net (Multi-Level Connection and Wide Regional Non-Local Block Network) for domain transfer, transforming laser scan data into the ToF camera domain. Different training variations are explored using a real-world dataset. Additionally, a noise model is introduced to compensate for the lack of noise in the initial step. The effectiveness of the method is evaluated on reference scenes to quantitatively compare to physically simulated data.

Color is an important cue in object recognition and classification problems. In underwater imagery, colors undergo strong distortion due to light propagation through an absorbing and scattering medium. Distortions depend on a number of complex phenomena, the most important being wavelength-dependent absorption and the sensitivity of sensors in trichromatic cameras. It has been shown previously that unique reconstruction in this case is not possible-at least for a simplified image formation model. In this paper, the authors use numerical simulations to demonstrate that this statement also holds for the underwater image formation model that is currently the most sophisticated.

Anemia diagnosis is crucial for pediatric patients due to its impact on growth and development. Traditional methods, like blood tests, are effective but pose challenges, such as discomfort, infection risk, and frequent monitoring difficulties, underscoring the need for non-intrusive diagnostic methods. In light of this, this study proposes a novel method that combines image processing with learning-driven data representation and model behavior for non-intrusive anemia diagnosis in pediatric patients. The contributions of this study are threefold. First, it uses an image-processing pipeline to extract 181 features from 13 categories, with a feature-selection process identifying the most crucial data for learning. Second, a deep multilayered network based on long short-term memory (LSTM) is utilized to train a model for classifying images into anemic and non-anemic cases, where hyperparameters are optimized using Bayesian approaches. Third, the trained LSTM model is integrated as a layer into a learning model developed based on recurrent expansion rules, forming a part of a new deep network called a recurrent expansion network (RexNet). RexNet is designed to learn data representations akin to traditional deep-learning methods while also understanding the interaction between dependent and independent variables. The proposed approach is applied to three public datasets, namely conjunctival eye images, palmar images, and fingernail images of children aged up to 6 years. RexNet achieves an overall evaluation of 99.83 ± 0.02% across all classification metrics, demonstrating significant improvements in diagnostic results and generalization compared to LSTM networks and existing methods. This highlights RexNet's potential as a promising alternative to traditional blood-based methods for non-intrusive anemia diagnosis.

Vertebral compression fractures (VCFs) affect 1.4 million patients every year, especially among the globally aging population, leading to increased morbidity and mortality. Often characterized with symptoms of sudden onset back pain, decreased vertebral height, progressive kyphosis, and limited mobility, VCFs can significantly impact a patient's quality of life and are a significant public health concern. Imaging modalities in radiology, including radiographs, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET) studies and bone scans, play crucial and evolving roles in the diagnosis, assessment, and management of VCFs. An understanding of anatomy, and the extent to which each imaging modality serves to elucidate that anatomy, is crucial in understanding and providing guidance on fracture severity, classification, associated soft tissue injuries, underlying pathologies, and bone mineral density, ultimately guiding treatment decisions, monitoring treatment response, and predicting prognosis and long-term outcomes. This article thus explores the important role of radiology in illuminating the underlying anatomy and pathophysiology, classification, diagnosis, treatment, and management of patients with VCFs. Continued research and advancements in imaging technologies will further enhance our understanding of VCFs and pave the way for personalized and effective management strategies.

Conventional radiography is widely used for postmortem foetal imaging, but its role in diagnosing congenital anomalies is debated. This study aimed to assess the effectiveness of X-rays in detecting skeletal abnormalities and guiding genetic analysis and counselling. This is a retrospective analysis of all post-abortion diagnostic imaging studies conducted at a centre serving a population of over 300,000 inhabitants from 2008 to 2023. The data were analysed using descriptive statistics. X-rays of 81 aborted foetuses (total of 308 projections; mean: 3.8 projections/examination; SD: 1.79) were included. We detected 137 skeletal anomalies. In seven cases (12.7%), skeletal anomalies identified through radiology were missed by prenatal sonography. The autopsy confirmed radiological data in all cases except for two radiological false positives. Additionally, radiology failed to identify a case of syndactyly, which was revealed by anatomopathology. X-ray is crucial for accurately classifying skeletal abnormalities, determining the causes of spontaneous abortion, and guiding the request for genetic counselling. Formal training for both technicians and radiologists, as well as multidisciplinary teamwork, is necessary to perform X-ray examinations on aborted foetuses and interpret the results effectively.

In this study, we investigated joint effusion in patients with temporomandibular disorders (TMDs) with disc displacement. The magnetic resonance (MR) images of 97 temporomandibular joints (TMJs) were evaluated, and the appearance of joint effusion was investigated. Myofascial pain and TMJ pain were considered in addition to the duration from manifestation. Disc displacement with and without reduction, as well as the region and the area of joint effusion, were investigated using the MR images. Fisher's test was used for the analyses. Joint effusion was recognized in 70 TMJs, including 55 in the superior articular cavity, 1 in the inferior articular cavity, and 14 in both the superior and inferior articular cavities. The appearance of joint effusion did not differ with the existence of myofascial pain or TMJ pain. The region of joint effusion did not differ between disc displacement with and without reduction. A larger area of joint effusion was recognized in disc displacement without reduction (p < 0.05). The results showed that the amount of synovial fluid in the joint effusion did not change with the existence of myofascial pain or TMJ pain. Joint effusion commonly appeared in disc displacement without reduction.