RESUMEN
INTRODUCTION: Timely diagnosis and prognostication of Alzheimer's disease (AD) and mild cognitive impairment (MCI) are pivotal for effective intervention. Artificial intelligence (AI) in neuroradiology may aid in such appropriate diagnosis and prognostication. This study aimed to evaluate the potential of novel diffusion model-based AI for enhancing AD and MCI diagnosis through superresolution (SR) of brain magnetic resonance (MR) images. METHODS: 1.5T brain MR scans of patients with AD or MCI and healthy controls (NC) from Alzheimer's Disease Neuroimaging Initiative 1 (ADNI1) were superresolved to 3T using a novel diffusion model-based generative AI (d3T*) and a convolutional neural network-based model (c3T*). Comparisons of image quality to actual 1.5T and 3T MRI were conducted based on signal-to-noise ratio (SNR), naturalness image quality evaluator (NIQE), and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE). Voxel-based volumetric analysis was then conducted to study whether 3T* images offered more accurate volumetry than 1.5T images. Binary and multiclass classifications of AD, MCI, and NC were conducted to evaluate whether 3T* images offered superior AD classification performance compared to actual 1.5T MRI. Moreover, CNN-based classifiers were used to predict conversion of MCI to AD, to evaluate the prognostication performance of 3T* images. The classification performances were evaluated using accuracy, sensitivity, specificity, F1 score, Matthews correlation coefficient (MCC), and area under the receiver-operating curves (AUROC). RESULTS: Analysis of variance (ANOVA) detected significant differences in image quality among the 1.5T, c3T*, d3T*, and 3T groups across all metrics. Both c3T* and d3T* showed superior image quality compared to 1.5T MRI in NIQE and BRISQUE with statistical significance. While the hippocampal volumes measured in 3T* and 3T images were not significantly different, the hippocampal volume measured in 1.5T images showed significant difference. 3T*-based AD classifications showed superior performance across all performance metrics compared to 1.5T-based AD classification. Classification performance between d3T* and actual 3T was not significantly different. 3T* images offered superior accuracy in predicting the conversion of MCI to AD than 1.5T images did. CONCLUSIONS: The diffusion model-based MRI SR enhances the resolution of brain MR images, significantly improving diagnostic and prognostic accuracy for AD and MCI. Superresolved 3T* images closely matched actual 3T MRIs in quality and volumetric accuracy, and notably improved the prediction performance of conversion from MCI to AD.
Asunto(s)
Enfermedad de Alzheimer , Disfunción Cognitiva , Humanos , Enfermedad de Alzheimer/diagnóstico por imagen , Enfermedad de Alzheimer/clasificación , Disfunción Cognitiva/diagnóstico por imagen , Disfunción Cognitiva/clasificación , Anciano , Femenino , Masculino , Pronóstico , Anciano de 80 o más Años , Inteligencia Artificial , Imagen por Resonancia Magnética/métodos , Interpretación de Imagen Asistida por Computador/métodos , Encéfalo/diagnóstico por imagen , Encéfalo/patología , Persona de Mediana Edad , Imagen de Difusión por Resonancia Magnética/métodos , Neuroimagen/métodos , Neuroimagen/normasRESUMEN
This study developed a new convolutional neural network model to detect and classify gastric lesions as malignant, premalignant, and benign. We used 10,181 white-light endoscopy images from 2606 patients in an 8:1:1 ratio. Lesions were categorized as early gastric cancer (EGC), advanced gastric cancer (AGC), gastric dysplasia, benign gastric ulcer (BGU), benign polyp, and benign erosion. We assessed the lesion detection and classification model using six-class, cancer versus non-cancer, and neoplasm versus non-neoplasm categories, as well as T-stage estimation in cancer lesions (T1, T2-T4). The lesion detection rate was 95.22% (219/230 patients) on a per-patient basis: 100% for EGC, 97.22% for AGC, 96.49% for dysplasia, 75.00% for BGU, 97.22% for benign polyps, and 80.49% for benign erosion. The six-class category exhibited an accuracy of 73.43%, sensitivity of 80.90%, specificity of 83.32%, positive predictive value (PPV) of 73.68%, and negative predictive value (NPV) of 88.53%. The sensitivity and NPV were 78.62% and 88.57% for the cancer versus non-cancer category, and 83.26% and 89.80% for the neoplasm versus non-neoplasm category, respectively. The T stage estimation model achieved an accuracy of 85.17%, sensitivity of 88.68%, specificity of 79.81%, PPV of 87.04%, and NPV of 82.18%. The novel CNN-based model remarkably detected and classified malignant, premalignant, and benign gastric lesions and accurately estimated gastric cancer T-stages.
Asunto(s)
Aprendizaje Profundo , Neoplasias Gástricas , Humanos , Neoplasias Gástricas/patología , Neoplasias Gástricas/diagnóstico , Masculino , Femenino , Persona de Mediana Edad , Anciano , Adulto , Redes Neurales de la Computación , Sensibilidad y Especificidad , Anciano de 80 o más AñosRESUMEN
Muscle strength assessments are vital in rehabilitation, orthopedics, and sports medicine. However, current methods used in clinical settings, such as manual muscle testing and hand-held dynamometers, often lack reliability, and isokinetic dynamometers (IKD), while reliable, are not easily portable. The aim of this study was to design and validate a wearable dynamometry system with high accessibility, accuracy, and reliability, and to validate the device. Therefore, we designed a wearable dynamometry system (WDS) equipped with knee joint torque sensors. To validate this WDS, we measured knee extension and flexion strength in 39 healthy adults using both the IKD and WDS. Comparing maximal isometric torque measurements, WDS and IKD showed strong correlation and good reliability for extension (Pearson's r: 0.900; intraclass correlation coefficient [ICC]: 0.893; standard error of measurement [SEM]: 9.85%; minimal detectable change [MDC]: 27.31%) and flexion (Pearson's r: 0.870; ICC: 0.857; SEM: 11.93%; MDC: 33.07%). WDS demonstrated excellent inter-rater (Pearson's r: 0.990; ICC: 0.993; SEM: 4.05%) and test-retest (Pearson's r: 0.970; ICC: 0.984; SEM: 6.15%) reliability during extension/flexion. User feedback from 35 participants, including healthcare professionals, underscores WDS's positive user experience and clinical potential. The proposed WDS is a suitable alternative to IKD, providing high accuracy, reliability, and potentially greater accessibility.
Asunto(s)
Articulación de la Rodilla , Dinamómetro de Fuerza Muscular , Fuerza Muscular , Torque , Dispositivos Electrónicos Vestibles , Humanos , Masculino , Adulto , Femenino , Articulación de la Rodilla/fisiología , Fuerza Muscular/fisiología , Reproducibilidad de los Resultados , Rango del Movimiento Articular/fisiología , Adulto Joven , Diseño de EquipoRESUMEN
Sonic vibration (SV), or vibroacoustic therapy, is applied to enhance local and systemic blood circulation and alleviate pain using low-frequency sine wave vibrations. However, there is limited scientific data on the mechanisms through which the benefits are achieved. In this study, we investigated the impact of SV on inflammatory responses by assessing cytokine secretion in both in vivo and in vitro models. After inducing inflammatory responses in mice and macrophages, we studied cytokine expression and the symptoms of inflammatory diseases in response to three frequencies (14, 45, or 90â Hz) of SV stimulation at 0.5â m/s2 of amplitude. The results showed that SV at 90 Hz significantly increased interelukin-10 (IL-10) secretion in mice who were administered lipopolysaccharides (LPS) and increased the expression of IL-10 transcripts in peritoneal exudate cells and macrophages. Furthermore, SV at 90â Hz improved LPS-induced lethality and alleviated symptoms in a colitis model. In conclusion, this study scientifically proves the anti-inflammatory effects of vibration therapy through its ability to increase IL-10 expression.
RESUMEN
BACKGROUND: Patient isolation units (PIUs) can be an effective method for effective infection control. Computational fluid dynamics (CFD) is commonly used for PIU design; however, optimizing this design requires extensive computational resources. Our study aims to provide data-driven models to determine the PIU settings, thereby promoting a more rapid design process. METHOD: Using CFD simulations, we evaluated various PIU parameters and room conditions to assess the impact of PIU installation on ventilation and isolation. We investigated particle dispersion from coughing subjects and airflow patterns. Machine-learning models were trained using CFD simulation data to estimate the performance and identify significant parameters. RESULTS: Physical isolation alone was insufficient to prevent the dispersion of smaller particles. However, a properly installed fan filter unit (FFU) generally enhanced the effectiveness of physical isolation. Ventilation and isolation performance under various conditions were predicted with a mean absolute percentage error of within 13%. The position of the FFU was found to be the most important factor affecting the PIU performance. CONCLUSION: Data-driven modeling based on CFD simulations can expedite the PIU design process by offering predictive capabilities and clarifying important performance factors. Reducing the time required to design a PIU is critical when a rapid response is required.
Asunto(s)
Hidrodinámica , Aislamiento de Pacientes , Humanos , Simulación por Computador , Control de Infecciones/métodos , Servicio de Urgencia en HospitalRESUMEN
Robot-assisted surgery platforms are utilized globally thanks to their stereoscopic vision systems and enhanced functional assistance. However, the necessity of ergonomic improvement for their use by surgeons has been increased. In surgical robots, issues with chronic fatigue exist owing to the fixed posture of the conventional stereo viewer (SV) vision system. A head-mounted display was adopted to alleviate the inconvenience, and a virtual vision platform (VVP) is proposed in this study. The VVP can provide various critical data, including medical images, vital signs, and patient records, in three-dimensional virtual reality space so that users can access medical information simultaneously. An availability of the VVP was investigated based on various user evaluations by surgeons and novices, who executed the given tasks and answered questionnaires. The performances of the SV and VVP were not significantly different; however, the craniovertebral angle of the VVP was 16.35° higher on average than that of the SV. Survey results regarding the VVP were positive; participants indicated that the optimal number of displays was six, preferring the 2 × 3 array. Reflecting the tendencies, the VVP can be a neoconceptual candidate to be customized for medical use, which opens a new prospect in a next-generation surgical robot.
Asunto(s)
Procedimientos Quirúrgicos Robotizados , Robótica , Realidad Virtual , Humanos , Interfaz Usuario-Computador , Procedimientos Quirúrgicos Robotizados/métodos , Visión OcularRESUMEN
Recognizing anatomical sections during colonoscopy is crucial for diagnosing colonic diseases and generating accurate reports. While recent studies have endeavored to identify anatomical regions of the colon using deep learning, the deformable anatomical characteristics of the colon pose challenges for establishing a reliable localization system. This study presents a system utilizing 100 colonoscopy videos, combining density clustering and deep learning. Cascaded CNN models are employed to estimate the appendix orifice (AO), flexures, and "outside of the body," sequentially. Subsequently, DBSCAN algorithm is applied to identify anatomical sections. Clustering-based analysis integrates clinical knowledge and context based on the anatomical section within the model. We address challenges posed by colonoscopy images through non-informative removal preprocessing. The image data is labeled by clinicians, and the system deduces section correspondence stochastically. The model categorizes the colon into three sections: right (cecum and ascending colon), middle (transverse colon), and left (descending colon, sigmoid colon, rectum). We estimated the appearance time of anatomical boundaries with an average error of 6.31 s for AO, 9.79 s for HF, 27.69 s for SF, and 3.26 s for outside of the body. The proposed method can facilitate future advancements towards AI-based automatic reporting, offering time-saving efficacy and standardization.
Asunto(s)
Enfermedades del Colon , Aprendizaje Profundo , Humanos , Colonoscopía , Algoritmos , Análisis por ConglomeradosRESUMEN
The intraoperative estimated blood loss (EBL), an essential parameter for perioperative management, has been evaluated by manually weighing blood in gauze and suction bottles, a process both time-consuming and labor-intensive. As the novel EBL prediction platform, we developed an automated deep learning EBL prediction model, utilizing the patch-wise crumpled state (P-W CS) of gauze images with texture analysis. The proposed algorithm was developed using animal data obtained from a porcine experiment and validated on human intraoperative data prospectively collected from 102 laparoscopic gastric cancer surgeries. The EBL prediction model involves gauze area detection and subsequent EBL regression based on the detected areas, with each stage optimized through comparative model performance evaluations. The selected gauze detection model demonstrated a sensitivity of 96.5% and a specificity of 98.0%. Based on this detection model, the performance of EBL regression stage models was compared. Comparative evaluations revealed that our P-W CS-based model outperforms others, including one reliant on convolutional neural networks and another analyzing the gauze's overall crumpled state. The P-W CS-based model achieved a mean absolute error (MAE) of 0.25 g and a mean absolute percentage error (MAPE) of 7.26% in EBL regression. Additionally, per-patient assessment yielded an MAE of 0.58 g, indicating errors < 1 g/patient. In conclusion, our algorithm provides an objective standard and streamlined approach for EBL estimation during surgery without the need for perioperative approximation and additional tasks by humans. The robust performance of the model across varied surgical conditions emphasizes its clinical potential for real-world application.
Asunto(s)
Pérdida de Sangre Quirúrgica , Aprendizaje Profundo , Humanos , Animales , Porcinos , Redes Neurales de la Computación , Algoritmos , VendajesRESUMEN
Monitoring ankle strength is crucial for assessing daily activities, functional ability, and preventing lower extremity injuries. However, the current methods for measuring ankle strength are often unreliable or not easily portable to be used in clinical settings. Therefore, this study proposes a portable dynamometer with high reliability capable of measuring ankle dorsiflexion and plantar flexion. The proposed portable dynamometer comprised plates made of aluminum alloy 6061 and a miniature tension-compression load cell. A total of 41 healthy adult participants applied maximal isometric dorsiflexor and plantar flexor forces on a Lafayette Handheld Dynamometer (HHD) and the portable dynamometer. The results were cross-validated, using change in mean, and two independent examiners evaluated the inter-rater and test-retest reliabilities in separate sessions using intraclass correlation coefficients, standard error of measurement, and minimal detectable change. Both dorsiflexion and plantar flexion measurements demonstrated a strong correlation with the HHD (r = 0.827; r = 0.973) and showed high inter-rater and test-retest reliabilities. Additionally, the participant responses to the user experience questionnaire survey indicated vastly superior positive experiences with the portable dynamometer. The study findings suggest that the designed portable dynamometer can provide accurate and reliable measurements of ankle strengths, making it a potential alternative to current methods in clinical settings.
Asunto(s)
Tobillo , Fenómenos Fisiológicos Musculoesqueléticos , Adulto , Humanos , Reproducibilidad de los Resultados , Dinamómetro de Fuerza Muscular , Extremidad Inferior , Fuerza Muscular/fisiologíaRESUMEN
Objective: Endotracheal intubation (ETI) is critical to secure the airway in emergent situations. Although artificial intelligence algorithms are frequently used to analyze medical images, their application to evaluating intraoral structures based on images captured during emergent ETI remains limited. The aim of this study is to develop an artificial intelligence model for segmenting structures in the oral cavity using video laryngoscope (VL) images. Methods: From 54 VL videos, clinicians manually labeled images that include motion blur, foggy vision, blood, mucus, and vomitus. Anatomical structures of interest included the tongue, epiglottis, vocal cord, and corniculate cartilage. EfficientNet-B5 with DeepLabv3+, EffecientNet-B5 with U-Net, and Configured Mask R-Convolution Neural Network (CNN) were used; EffecientNet-B5 was pretrained on ImageNet. Dice similarity coefficient (DSC) was used to measure the segmentation performance of the model. Accuracy, recall, specificity, and F1 score were used to evaluate the model's performance in targeting the structure from the value of the intersection over union between the ground truth and prediction mask. Results: The DSC of tongue, epiglottis, vocal cord, and corniculate cartilage obtained from the EfficientNet-B5 with DeepLabv3+, EfficientNet-B5 with U-Net, and Configured Mask R-CNN model were 0.3351/0.7675/0.766/0.6539, 0.0/0.7581/0.7395/0.6906, and 0.1167/0.7677/0.7207/0.57, respectively. Furthermore, the processing speeds (frames per second) of the three models stood at 3, 24, and 32, respectively. Conclusions: The algorithm developed in this study can assist medical providers performing ETI in emergent situations.
RESUMEN
OBJECTIVE: To develop an alert/verbal/painful/unresponsive (AVPU) scale assessment system based on automated video and speech recognition technology (AVPU-AVSR) that can automatically assess a patient's level of consciousness and evaluate its performance through clinical simulation. METHODS: We developed an AVPU-AVSR system with a whole-body camera, face camera, and microphone. The AVPU-AVSR system automatically extracted essential audiovisual features to assess the AVPU score from the recorded video files. Arm movement, pain stimulus, and eyes-open state were extracted using a rule-based approach using landmarks estimated from pre-trained pose and face estimation models. Verbal stimuli were extracted using a pre-trained speech-recognition model. Simulations of a physician examining the consciousness of 12 simulated patients for 16 simulation scenarios (4 for each of "Alert", "Verbal", "Painful", and "Unresponsive") were conducted under the AVPU-AVSR system. The accuracy, sensitivity, and specificity of the AVPU-AVSR system were assessed. RESULTS: A total of 192 cases with 12 simulated patients were assessed using the AVPU-AVSR system with a multi-class accuracy of 0.95 (95% confidence interval [CI] (0.92-0.98). The sensitivity and specificity (95% CIs) for detecting impaired consciousness were 1.00 (0.97-1.00) and 0.88 (0.75-0.95), respectively. The sensitivity and specificity of each extracted feature ranged from 0.88 to 1.00 and 0.98 to 1.00. CONCLUSIONS: The AVPU-AVSR system showed good accuracy in assessing consciousness levels in a clinical simulation and has the potential to be implemented in clinical practice to automatically assess mental status.
Asunto(s)
Estado de Conciencia , Percepción del Habla , Humanos , Habla , Escala de Coma de Glasgow , DolorRESUMEN
BACKGROUND: Alzheimer's disease (AD) is the most common form of dementia, which makes the lives of patients and their families difficult for various reasons. Therefore, early detection of AD is crucial to alleviating the symptoms through medication and treatment. OBJECTIVE: Given that AD strongly induces language disorders, this study aims to detect AD rapidly by analyzing the language characteristics. MATERIALS AND METHODS: The mini-mental state examination for dementia screening (MMSE-DS), which is most commonly used in South Korean public health centers, is used to obtain negative answers based on the questionnaire. Among the acquired voices, significant questionnaires and answers are selected and converted into mel-frequency cepstral coefficient (MFCC)-based spectrogram images. After accumulating the significant answers, validated data augmentation was achieved using the Densenet121 model. Five deep learning models, Inception v3, VGG19, Xception, Resnet50, and Densenet121, were used to train and confirm the results. RESULTS: Considering the amount of data, the results of the five-fold cross-validation are more significant than those of the hold-out method. Densenet121 exhibits a sensitivity of 0.9550, a specificity of 0.8333, and an accuracy of 0.9000 in a five-fold cross-validation to separate AD patients from the control group. CONCLUSIONS: The potential for remote health care can be increased by simplifying the AD screening process. Furthermore, by facilitating remote health care, the proposed method can enhance the accessibility of AD screening and increase the rate of early AD detection.
RESUMEN
Muscle strength assessment is important in predicting clinical and functional outcomes in many disorders. Manual muscle testing, although commonly used, offers suboptimal accuracy and reliability. Isokinetic dynamometers (IKDs) have excellent accuracy and reliability; but are bulky and expensive, offering limited accessibility. This study aimed to design a portable dynamometer that is accessible, accurate and reliable, and to validate the device in a general population. The portable articulated dynamometry system (PADS) is a portable device with an embedded high-precision load cell, designed to measure muscle strength with optimal accuracy. Seventy-two participants underwent maximal isometric and isokinetic knee extensor torque measurement with the PADS and IKD, respectively. The PADS results were cross-validated against IKD results using change in mean (CIM). Interrater and intra-rater reliabilities were assessed using intraclass correlation coefficients, standard error of measurement, and minimal detectable change. The PADS maximal knee extensor strength results were not significantly different from those by IKD (CIM: - 2.13 Nm; 95% CI - 4.74, 0.49 Nm). The PADS showed interrater reliability (Pearson's r: 0.958; ICC: 0.979; SEM: 5.51%) and excellent intra-rater reliability (Pearson's r: 0.912; ICC: 0.954; SEM: 8.38%). The proposed PADS may be an effective alternative to IKD, offering good accuracy, reliability, and potentially better accessibility.
Asunto(s)
Articulación de la Rodilla , Rodilla , Humanos , Reproducibilidad de los Resultados , Dinamómetro de Fuerza Muscular , Articulación de la Rodilla/fisiología , Rodilla/fisiología , Músculo Esquelético/fisiología , Fuerza Muscular/fisiología , Contracción Isométrica/fisiologíaRESUMEN
This study proposes the possibility of employing metal iodates as novel gas-sensing materials synthesized using a facile chemical precipitation method. An extensive survey of a library of metal iodates reveals that cobalt, nickel, and copper iodates are useful for gas sensor applications. Material analysis conducted using scanning electron microscopy, X-ray diffraction, X-ray photoelectron spectroscopy, thermal gravity differential temperature analysis, and Raman spectroscopy enables us to understand the thermal behavior and optimize post-annealing conditions. The evaluation of the gas-sensing performance of the specified metal iodates indicates that all of them display p-type sensing behavior and exhibit a high gas response toward different gases: a gas response of 18.6 by cobalt iodate to 1.8 ppm of acetone, a gas response of 4.3 by nickel iodate to 1 ppm of NO2, and a gas response of 6.6 by copper iodate to 1.8 ppm of H2S. Further investigation of the temperature-programmed reduction of H2 and polarization-electric field hysteresis analyses elucidates that the high gas response originates from the inherent characteristics of metal iodates, such as the high oxygen-reduction ability of iodine, highlighting the potential of the iodates as novel gas-sensing materials.
RESUMEN
BACKGROUND: Accurate interpretation of chest radiographs requires years of medical training, and many countries face a shortage of medical professionals to meet such requirements. Recent advancements in artificial intelligence (AI) have aided diagnoses; however, their performance is often limited due to data imbalance. The aim of this study was to augment imbalanced medical data using generative adversarial networks (GANs) and evaluate the clinical quality of the generated images via a multi-center visual Turing test. METHODS: Using six chest radiograph datasets, (MIMIC, CheXPert, CXR8, JSRT, VBD, and OpenI), starGAN v2 generated chest radiographs with specific pathologies. Five board-certified radiologists from three university hospitals, each with at least five years of clinical experience, evaluated the image quality through a visual Turing test. Further evaluations were performed to investigate whether GAN augmentation enhanced the convolutional neural network (CNN) classifier performances. RESULTS: In terms of identifying GAN images as artificial, there was no significant difference in the sensitivity between radiologists and random guessing (result of radiologists: 147/275 (53.5%) vs result of random guessing: 137.5/275, (50%); p = .284). GAN augmentation enhanced CNN classifier performance by 11.7%. CONCLUSION: Radiologists effectively classified chest pathologies with synthesized radiographs, suggesting that the images contained adequate clinical information. Furthermore, GAN augmentation enhanced CNN performance, providing a bypass to overcome data imbalance in medical AI training. CNN based methods rely on the amount and quality of training data; the present study showed that GAN augmentation could effectively augment training data for medical AI.
Asunto(s)
Inteligencia Artificial , Redes Neurales de la Computación , Humanos , Certificación , Hospitales Universitarios , RadiografíaRESUMEN
OBJECTIVE: Smart hospitals involve the application of recent information and communications technology (ICT) innovations to medical services; however, the concept of a smart hospital has not been rigorously defined. In this study, we aimed to derive the definition and service types of smart hospitals and investigate cases of each type. METHODS: A literature review was conducted regarding the background and technical characteristics of smart hospitals. On this basis, we conducted a focus group interview with experts in hospital information systems, and ultimately derived eight smart hospital service types. RESULTS: Smart hospital services can be classified into the following types: services based on location recognition and tracking technology that measures and monitors the location information of an object based on short-range communication technology; high-speed communication network-based services based on new wireless communication technology; Internet of Things-based services that connect objects embedded with sensors and communication functions to the internet; mobile health services such as mobile phones, tablets, and wearables; artificial intelligence-based services for the diagnosis and prediction of diseases; robot services provided on behalf of humans in various medical fields; extended reality services that apply hyper-realistic immersive technology to medical practice; and telehealth using ICT. CONCLUSIONS: Smart hospitals can influence health and medical policies and create new medical value by defining and quantitatively measuring detailed indicators based on data collected from existing hospitals. Simultaneously, appropriate government incentives, consolidated interdisciplinary research, and active participation by industry are required to foster and facilitate smart hospitals.
RESUMEN
Computer-aided detection (CADe) systems have been actively researched for polyp detection in colonoscopy. To be an effective system, it is important to detect additional polyps that may be easily missed by endoscopists. Sessile serrated lesions (SSLs) are a precursor to colorectal cancer with a relatively higher miss rate, owing to their flat and subtle morphology. Colonoscopy CADe systems could help endoscopists; however, the current systems exhibit a very low performance for detecting SSLs. We propose a polyp detection system that reflects the morphological characteristics of SSLs to detect unrecognized or easily missed polyps. To develop a well-trained system with imbalanced polyp data, a generative adversarial network (GAN) was used to synthesize high-resolution whole endoscopic images, including SSL. Quantitative and qualitative evaluations on GAN-synthesized images ensure that synthetic images are realistic and include SSL endoscopic features. Moreover, traditional augmentation methods were used to compare the efficacy of the GAN augmentation method. The CADe system augmented with GAN synthesized images showed a 17.5% improvement in sensitivity on SSLs. Consequently, we verified the potential of the GAN to synthesize high-resolution images with endoscopic features and the proposed system was found to be effective in detecting easily missed polyps during a colonoscopy.
Asunto(s)
Pólipos del Colon/patología , Colonoscopía , Neoplasias Colorrectales/patología , Detección Precoz del Cáncer , Interpretación de Imagen Asistida por Computador , Redes Neurales de la Computación , Bases de Datos Factuales , Humanos , Valor Predictivo de las Pruebas , Estudios Prospectivos , Reproducibilidad de los Resultados , Estudios RetrospectivosRESUMEN
Recently, HD maps have become important parts of autonomous driving, from localization to perception and path planning. For the practical application of HD maps, it is significant to regularly update environmental changes in HD maps. Conventional approaches require expensive mobile mapping systems and considerable manual work by experts, making it difficult to achieve frequent map updates. In this paper, we show how frequent and automatic updates of lane marking in HD maps are made possible with enormous crowdsourced data. Crowdsourced data is acquired from onboard low-cost sensing devices installed on many city buses and taxis in Seoul, South Korea. A large amount of crowdsourced data is daily accumulated on the server. The quality of sensor measurement is not very high due to the limited performance of low-cost devices. Therefore, the technical challenge is to overcome the uncertainty of the crowdsourced data. Appropriately filtering out a large amount of low-quality data is a significant problem. The proposed HD map update strategy comprises several processing steps including pose correction, observation assignment, observation clustering, and landmark classification. The proposed HD map update strategy is experimentally verified using crowdsourced data. If the changed environments are successfully extracted, then precisely updated HD maps are generated.
Asunto(s)
Colaboración de las Masas , Seúl , República de Corea , Incertidumbre , Vehículos a MotorRESUMEN
BACKGROUND: Cecal intubation time is an important component for quality colonoscopy. Cecum is the turning point that determines the insertion and withdrawal phase of the colonoscope. For this reason, obtaining information related with location of the cecum in the endoscopic procedure is very useful. Also, it is necessary to detect the direction of colonoscope's movement and time-location of the cecum. METHODS: In order to analysis the direction of scope's movement, the Horn-Schunck algorithm was used to compute the pixel's motion change between consecutive frames. Horn-Schunk-algorithm applied images were trained and tested through convolutional neural network deep learning methods, and classified to the insertion, withdrawal and stop movements. Based on the scope's movement, the graph was drawn with a value of +1 for insertion, -1 for withdrawal, and 0 for stop. We regarded the turning point as a cecum candidate point when the total graph area sum in a certain section recorded the lowest. RESULTS: A total of 328,927 frame images were obtained from 112 patients. The overall accuracy, drawn from 5-fold cross-validation, was 95.6%. When the value of "t" was 30 s, accuracy of cecum discovery was 96.7%. In order to increase visibility, the movement of the scope was added to summary report of colonoscopy video. Insertion, withdrawal, and stop movements were mapped to each color and expressed with various scale. As the scale increased, the distinction between the insertion phase and the withdrawal phase became clearer. CONCLUSION: Information obtained in this study can be utilized as metadata for proficiency assessment. Since insertion and withdrawal are technically different movements, data of scope's movement and phase can be quantified and utilized to express pattern unique to the colonoscopist and to assess proficiency. Also, we hope that the findings of this study can contribute to the informatics field of medical records so that medical charts can be transmitted graphically and effectively in the field of colonoscopy.
RESUMEN
ReS2 nanosheets are grown on the surface of carbon black (CB) via an efficient hydrothermal method. We confirmed the ultra-thin ReS2 nanosheets with ≈1-4 layers on the surface of the CB (ReS2@CB) by using analytical techniques of field emission scanning electron microscopy (FESEM) and high-resolution transmission electron microscopy (HRTEM). The ReS2@CB nanocomposite showed high specific capacities of 760, 667, 600, 525, and 473 mAh/g at the current densities of 0.1 (0.23 C), 0.2 (0.46 C), 0.3 (0.7 C), 0.5 (1.15 C) and 1.0 A/g (2.3 C), respectively, in conjunction with its excellent cycling performance (432 mAh/g at 2.3 C; 91.4% capacity retention) after 100 cycles. Such LIB performance is greatly higher than pure CB and ReS2 powder samples. These results could be due to the following reasons: (1) the low-cost CB serves as a supporter enabling the formation of ≈1-4 layered nanosheets of ReS2, thus avoiding its agglomeration; (2) the CB enhances the electrical conductivity of the ReS2@CB nanocomposite; (3) the ultra-thin (1-4 layers) ReS2 nanosheets with imperfect structure can function as increasing the number of active sites for reaction of Li+ ions with electrolytes. The outstanding performance and unique structural characteristics of the ReS2@CB anodes make them promising candidates for the ever-increasing development of advanced LIBs.