Journal of Imaging最新文献

Recent advances in laser scanning systems have enabled the acquisition of 3D point cloud representations of scenes, revolutionizing the fields of Architecture, Engineering, and Construction (AEC). This paper presents a novel pipeline for the automatic generation of 3D semantic models of multi-level buildings from indoor point clouds. The architectural components are extracted hierarchically. After segmenting the point clouds into potential building floors, a wall detection process is performed on each floor segment. Then, room, ground, and ceiling extraction are conducted using the walls 2D constellation obtained from the projection of the walls onto the ground plan. The identification of the openings in the walls is performed using a deep learning-based classifier that separates doors and windows from non-consistent holes. Based on the geometric and semantic information from previously detected elements, the final model is generated in IFC format. The effectiveness and reliability of the proposed pipeline are demonstrated through extensive experiments and visual inspections. The results reveal high precision and recall values in the extraction of architectural elements, ensuring the fidelity of the generated models. In addition, the pipeline's efficiency and accuracy offer valuable contributions to future advancements in point cloud processing.

This study investigates the feasibility of employing an in-house-developed physical phantom dedicated to the weekly quality control testing of radiographic systems, performed by radiographers. For this purpose, a 3D phantom was fabricated, featuring test objects, including a model representing a lesion. Alongside this phantom, a commercial phantom, specifically, IBA's Primus L, was utilized. Weekly imaging of both phantoms was conducted over a span of four weeks, involving different imaging protocols and anode voltages. Subsequently, the obtained data underwent visual evaluation, as well as measurement of the intensity of selected regions of interest. The average values for three incident kilovoltages remained consistently stable over the four weeks, with the exception of the "low energy" case, which exhibited variability during the first week of measurements. Following experiments in "Week 1", the X-Ray unit was identified as malfunctioning and underwent necessary repairs. The in-house-developed phantom demonstrated its utility in assessing the performance of the X-Ray system.

State-of-the-art object detection models need large and diverse datasets for training. As these are hard to acquire for many practical applications, training images from simulation environments gain more and more attention. A problem arises as deep learning models trained on simulation images usually have problems generalizing to real-world images shown by a sharp performance drop. Definite reasons and influences for this performance drop are not yet found. While previous work mostly investigated the influence of the data as well as the use of domain adaptation, this work provides a novel perspective by investigating the influence of the object detection model itself. Against this background, first, a corresponding measure called sim-to-real generalizability is defined, comprising the capability of an object detection model to generalize from simulation training images to real-world evaluation images. Second, 12 different deep learning-based object detection models are trained and their sim-to-real generalizability is evaluated. The models are trained with a variation of hyperparameters resulting in a total of 144 trained and evaluated versions. The results show a clear influence of the feature extractor and offer further insights and correlations. They open up future research on investigating influences on the sim-to-real generalizability of deep learning-based object detection models as well as on developing feature extractors that have better sim-to-real generalizability capabilities.

The evaluation of hemodynamic conditions in critical limb-threatening ischemia (CLTI) patients is inevitable in endovascular interventions. In this study, the performance of color-coded digital subtraction angiography (ccDSA) and the recently developed color-coded digital variance angiography (ccDVA) was compared in the assessment of key time parameters in lower extremity interventions. The observational study included 19 CLTI patients who underwent peripheral vascular intervention at our institution in 2020. Pre- and post-dilatational images were retrospectively processed and analyzed by a commercially available ccDSA software (Kinepict Medical Imaging Tool 6.0.3; Kinepict Health Ltd., Budapest, Hungary) and by the recently developed ccDVA technology. Two protocols were applied using both a 4 and 7.5 frames per second acquisition rate. Time-to-peak (TTP) parameters were determined in four pre- and poststenotic regions of interest (ROI), and ccDVA values were compared to ccDSA read-outs. The ccDVA technology provided practically the same TTP values as ccDSA (r = 0.99, R² = 0.98, p < 0.0001). The correlation was extremely high independently of the applied protocol or the position of ROI; the r value was 0.99 (R² = 0.98, p < 0.0001) in all groups. A similar correlation was observed in the change in passage time (r = 0.98, R² = 0.96, p < 0.0001). The color-coded DVA technology can reproduce the same hemodynamic data as a commercially available DSA-based software; therefore, it has the potential to be an alternative decision-supporting tool in catheter labs.

The most difficult diagnostic challenge in neck imaging is the differentiation between benign and malignant neoplasms. The purpose of this work was to study the role of the ADC (apparent diffusion coefficient) value in discriminating benign from malignant neck neoplastic lesions. The study was conducted on 53 patients with different neck pathologies (35 malignant and 18 benign/inflammatory). In all of the subjects, conventional MRI (magnetic resonance imaging) sequences were performed apart from DWI (diffusion-weighted imaging). The mean ADC values in the benign and malignant groups were compared using the Mann-Whitney test. The ADCs of malignant lesions (mean 0.86 ± 0.28) were significantly lower than the benign lesions (mean 1.43 ± 0.57), and the mean ADC values of the inflammatory lesions (1.19 ± 0.75) were significantly lower than those of the benign lesions. The cutoff value of 1.1 mm²/s effectively differentiated benign and malignant lesions with a 97.14% sensitivity, a 77.78% specificity, and an 86.2% accuracy. There were also statistically significant differences between the ADC values of different malignant tumors of the neck (p, 0.001). NHL (0.59 ± 0.09) revealed significantly lower ADC values than SCC (0.93 ± 0.15). An ADC cutoff point of 0.7 mm²/s was the best for differentiating NHL (non-Hodgkin lymphoma) from SCC (squamous cell carcinoma); it provided a diagnostic ability of 100.0% sensitivity and 89.47% specificity. ADC mapping may be an effective MRI tool for the differentiation of benign and inflammatory lesions from malignant tumors in the neck.

This study explores the intersection of personality, attention and task performance in traditional 2D and immersive virtual reality (VR) environments. A visual search task was developed that required participants to find anomalous images embedded in normal background images in 3D space. Experiments were conducted with 30 subjects who performed the task in 2D and VR environments while their eye movements were tracked. Following an exploratory correlation analysis, we applied machine learning techniques to investigate the predictive power of gaze features on human data derived from different data collection methods. Our proposed methodology consists of a pipeline of steps for extracting fixation and saccade features from raw gaze data and training machine learning models to classify the Big Five personality traits and attention-related processing speed/accuracy levels computed from the Group Bourdon test. The models achieved above-chance predictive performance in both 2D and VR settings despite visually complex 3D stimuli. We also explored further relationships between task performance, personality traits and attention characteristics.

Breast cancer persists as a critical global health concern, emphasizing the advancement of reliable diagnostic strategies to improve patient survival rates. To address this challenge, a computer-aided diagnostic methodology for breast cancer classification is proposed. An architecture that incorporates a pre-trained EfficientNet-B0 model along with channel and spatial attention mechanisms is employed. The efficiency of leveraging attention mechanisms for breast cancer classification is investigated here. The proposed model demonstrates commendable performance in classification tasks, particularly showing significant improvements upon integrating attention mechanisms. Furthermore, this model demonstrates versatility across various imaging modalities, as demonstrated by its robust performance in classifying breast lesions, not only in mammograms but also in ultrasound images during cross-modality evaluation. It has achieved accuracy of 99.9% for binary classification using the mammogram dataset and 92.3% accuracy on the cross-modality multi-class dataset. The experimental results emphasize the superiority of our proposed method over the current state-of-the-art approaches for breast cancer classification.

The early detection of the acute deterioration of escalating illness severity is crucial for effective patient management and can significantly impact patient outcomes. Ambient sensing technology, such as computer vision, may provide real-time information that could impact early recognition and response. This study aimed to develop a computer vision model to quantify the number and type (clinician vs. visitor) of people in an intensive care unit (ICU) room, study the trajectory of their movement, and preliminarily explore its relationship with delirium as a marker of illness severity. To quantify the number of people present, we implemented a counting-by-detection supervised strategy using images from ICU rooms. This was accomplished through developing three methods: single-frame, multi-frame, and tracking-to-count. We then explored how the type of person and distribution in the room corresponded to the presence of delirium. Our designed pipeline was tested with a different set of detection models. We report model performance statistics and preliminary insights into the relationship between the number and type of persons in the ICU room and delirium. We evaluated our method and compared it with other approaches, including density estimation, counting by detection, regression methods, and their adaptability to ICU environments.

With the advancement of deep learning (DL) technology, DL-based intrusion detection models have emerged as a focal point of research within the domain of cybersecurity. This paper provides an overview of the datasets frequently utilized in the research. This article presents an overview of the widely utilized datasets in the research, establishing a basis for future investigation and analysis. The text subsequently summarizes the prevalent data preprocessing methods and feature engineering techniques utilized in intrusion detection. Following this, it provides a review of seven deep learning-based intrusion detection models, namely, deep autoencoders, deep belief networks, deep neural networks, convolutional neural networks, recurrent neural networks, generative adversarial networks, and transformers. Each model is examined from various dimensions, highlighting their unique architectures and applications within the context of cybersecurity. Furthermore, this paper broadens its scope to include intrusion detection techniques facilitated by the following two large-scale predictive models: the BERT series and the GPT series. These models, leveraging the power of transformers and attention mechanisms, have demonstrated remarkable capabilities in understanding and processing sequential data. In light of these findings, this paper concludes with a prospective outlook on future research directions. Four key areas have been identified for further research. By addressing these issues and advancing research in the aforementioned areas, this paper envisions a future in which DL-based intrusion detection systems are not only more accurate and efficient but also better aligned with the dynamic and evolving landscape of cybersecurity threats.

Both pathology and cytopathology still rely on recognizing microscopical morphologic features, and image analysis plays a crucial role, enabling the identification, categorization, and characterization of different tissue types, cell populations, and disease states within microscopic images. Historically, manual methods have been the primary approach, relying on expert knowledge and experience of pathologists to interpret microscopic tissue samples. Early image analysis methods were often constrained by computational power and the complexity of biological samples. The advent of computers and digital imaging technologies challenged the exclusivity of human eye vision and brain computational skills, transforming the diagnostic process in these fields. The increasing digitization of pathological images has led to the application of more objective and efficient computer-aided analysis techniques. Significant advancements were brought about by the integration of digital pathology, machine learning, and advanced imaging technologies. The continuous progress in machine learning and the increasing availability of digital pathology data offer exciting opportunities for the future. Furthermore, artificial intelligence has revolutionized this field, enabling predictive models that assist in diagnostic decision making. The future of pathology and cytopathology is predicted to be marked by advancements in computer-aided image analysis. The future of image analysis is promising, and the increasing availability of digital pathology data will invariably lead to enhanced diagnostic accuracy and improved prognostic predictions that shape personalized treatment strategies, ultimately leading to better patient outcomes.