Collaborative Enhancement of Consistency and Accuracy in US Diagnosis of Thyroid Nodules Using Large Language Models.

Background Large language models (LLMs) hold substantial promise for medical imaging interpretation. However, there is a lack of studies on their feasibility in handling reasoning questions associated with medical diagnosis. Purpose To investigate the viability of leveraging three publicly available LLMs to enhance consistency and diagnostic accuracy in medical imaging based on standardized reporting, with pathology as the reference standard. Materials and Methods US images of thyroid nodules with pathologic results were retrospectively collected from a tertiary referral hospital between July 2022 and December 2022 and used to evaluate malignancy diagnoses generated by three LLMs-OpenAI's ChatGPT 3.5, ChatGPT 4.0, and Google's Bard. Inter- and intra-LLM agreement of diagnosis were evaluated. Then, diagnostic performance, including accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC), was evaluated and compared for the LLMs and three interactive approaches: human reader combined with LLMs, image-to-text model combined with LLMs, and an end-to-end convolutional neural network model. Results A total of 1161 US images of thyroid nodules (498 benign, 663 malignant) from 725 patients (mean age, 42.2 years ± 14.1 [SD]; 516 women) were evaluated. ChatGPT 4.0 and Bard displayed substantial to almost perfect intra-LLM agreement (κ range, 0.65-0.86 [95% CI: 0.64, 0.86]), while ChatGPT 3.5 showed fair to substantial agreement (κ range, 0.36-0.68 [95% CI: 0.36, 0.68]). ChatGPT 4.0 had an accuracy of 78%-86% (95% CI: 76%, 88%) and sensitivity of 86%-95% (95% CI: 83%, 96%), compared with 74%-86% (95% CI: 71%, 88%) and 74%-91% (95% CI: 71%, 93%), respectively, for Bard. Moreover, with ChatGPT 4.0, the image-to-text-LLM strategy exhibited an AUC (0.83 [95% CI: 0.80, 0.85]) and accuracy (84% [95% CI: 82%, 86%]) comparable to those of the human-LLM interaction strategy with two senior readers and one junior reader and exceeding those of the human-LLM interaction strategy with one junior reader. Conclusion LLMs, particularly integrated with image-to-text approaches, show potential in enhancing diagnostic medical imaging. ChatGPT 4.0 was optimal for consistency and diagnostic accuracy when compared with Bard and ChatGPT 3.5. © RSNA, 2024 Supplemental material is available for this article.

US-based Sequential Algorithm Integrating an AI Model for Advanced Liver Fibrosis Screening.

Background Noninvasive tests can be used to screen patients with chronic liver disease for advanced liver fibrosis; however, the use of single tests may not be adequate. Purpose To construct sequential clinical algorithms that include a US deep learning (DL) model and compare their ability to predict advanced liver fibrosis with that of other noninvasive tests. Materials and Methods This retrospective study included adult patients with a history of chronic liver disease or unexplained abnormal liver function test results who underwent B-mode US of the liver between January 2014 and September 2022 at three health care facilities. A US-based DL network (FIB-Net) was trained on US images to predict whether the shear-wave elastography (SWE) value was 8.7 kPa or higher, indicative of advanced fibrosis. In the internal and external test sets, a two-step algorithm (Two-step#1) using the Fibrosis-4 Index (FIB-4) followed by FIB-Net and a three-step algorithm (Three-step#1) using FIB-4 followed by FIB-Net and SWE were used to simulate screening scenarios where liver stiffness measurements were not or were available, respectively. Measures of diagnostic accuracy were calculated using liver biopsy as the reference standard and compared between FIB-4, SWE, FIB-Net, and European Association for the Study of the Liver guidelines (ie, FIB-4 followed by SWE), along with sequential algorithms. Results The training, validation, and test data sets included 3067 (median age, 42 years [IQR, 33-53 years]; 2083 male), 1599 (median age, 41 years [IQR, 33-51 years]; 1124 male), and 1228 (median age, 44 years [IQR, 33-55 years]; 741 male) patients, respectively. FIB-Net obtained a noninferior specificity with a margin of 5% (P < .001) compared with SWE (80% vs 82%). The Two-step#1 algorithm showed higher specificity and positive predictive value (PPV) than FIB-4 (specificity, 79% vs 57%; PPV, 44% vs 32%) while reducing unnecessary referrals by 42%. The Three-step#1 algorithm had higher specificity and PPV compared with European Association for the Study of the Liver guidelines (specificity, 94% vs 88%; PPV, 73% vs 64%) while reducing unnecessary referrals by 35%. Conclusion A sequential algorithm combining FIB-4 and a US DL model showed higher diagnostic accuracy and improved referral management for all-cause advanced liver fibrosis compared with FIB-4 or the DL model alone. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Ghosh in this issue.

Biomimetic Liquid Metal-Elastomer Composited Foam with Adjustable Thermal Conductivity for Heat Control.

The application of traditional materials with constant thermal conductivity in time-varying thermal environments poses great challenges due to their inability of adjusting thermal conductivity according to different requirements, for which reason materials with adjustable thermal conductivity have attracted much attention. However, certain limitations induced by those materials' low softness or harsh adjustment conditions restrict them from being applied in heat dissipation and heat transfer scenarios. In this study, we report a biomimetic liquid metal-elastomer composited foam with adjustable thermal conductivity (B-LM-ECF). Inspired by the rationale of homeothermic animals regulating the thermal conductivity of their subcutaneous tissue, the prepared material adjusts its thermal conductivity via adjusting the volume proportion of liquid metal within it. The thermal conductivity of B-LM-ECF can be adjusted within the range of 0.11-8.4 W·m-1K-1. The adjustment factor η of B-LM-ECF is 76, which is defined as the ratio of the highest to the lowest thermal conductivity of the material. The material enabling reversible switching for itself from thermal insulation to heat dissipation. The prepared material exhibits 45 KPa of Young's modulus with the maximum fracture tensile rate of 600%, facilitating better covering for thermal management objects. We selected a power lithium battery and a smartphone as specific thermal management objects to demonstrate its practical application in thermal management experiment.

Preoperative Survival Prediction in Intrahepatic Cholangiocarcinoma Using an Ultrasound-Based Radiographic-Radiomics Signature.

OBJECTIVES: To construct a preoperative model for survival prediction in intrahepatic cholangiocarcinoma (ICC) patients using ultrasound (US) based radiographic-radiomics signatures. METHODS: Between April 2010 and September 2015, 170 patients with ICC who underwent curative resection were retrospectively recruited. Overall survival (OS)-related radiographic signatures and radiomics signatures based on preoperative US were built and assessed through a time-dependent receiver operating characteristic curve analysis. A nomogram was developed based on the selected predictors from the radiographic-radiomics signatures and clinical and laboratory results of the training cohort (n = 127), validated in an independent testing cohort (n = 43) by the concordance index (C-index), and compared with the Tumor Node Metastasis (TNM) cancer staging system as well as the radiographic and radiomics nomograms. RESULTS: The median areas under the curve of the radiomics signature and radiographic signature were higher than that of the TNM staging system in the testing cohort, although the values were not significantly different (0.76-0.82 versus 0.62, P = .485 and .264). The preoperative nomogram with CA 19-9, sex, ascites, radiomics signature, and radiographic signature had C-indexes of 0.72 and 0.75 in the training and testing cohorts, respectively, and it had significantly higher predictive performance than the 8th TNM staging system in the testing cohort (C-index: 0.75 versus 0.67, P = .004) and a higher C-index than the radiomics nomograms (0.75 versus 0.68, P = .044). CONCLUSIONS: The preoperative nomogram integrated with the radiographic-radiomics signature demonstrated good predictive performance for OS in ICC and was superior to the 8th TNM staging system.

Contrast-Enhanced Ultrasound-Based Nomogram: A Potential Predictor of Individually Postoperative Early Recurrence for Patients With Combined Hepatocellular-Cholangiocarcinoma.

PURPOSES: To evaluate the postsurgical prognostic implication of contrast-enhanced ultrasound (CEUS) for combined hepatocellular-cholangiocarcinoma (CHC). To build a CEUS-based early recurrence prediction classifier for CHC, in comparison with tumor-node-metastasis (TNM) staging. METHODS: The CEUS features and clinicopathological findings of each case were analyzed, and the Liver Imaging Reporting and Data System categories were assigned. The recurrence-free survival associated factors were evaluated by Cox proportional hazard model. Incorporating the independent factors, nomograms were built to estimate the possibilities of 3-month, 6-month, and 1-year recurrence and whose prognostic value was determined by time-dependent receiver operating characteristics, calibration curves, and hazard layering efficiency validation, comparing with TNM staging system. RESULTS: In the multivariable analysis, the levels of carbohydrate antigen 19-9, prothrombin time and total bilirubin, and tumor shape, the Liver Imaging Reporting and Data System category were independent factors for recurrence-free survival. The LR-M category showed longer recurrence-free survival than did the LR-4/5 category. The 3-month, 6-month, and 1-year area under the curves of the CEUS-clinical nomogram, clinical nomogram, and TNM staging system were 0.518, 0.552, and 0.843 versus 0.354, 0.240, and 0.624 (P = .048, .049, and .471) vs. 0.562, 0.545, and 0.843 (P = .630, .564, and .007), respectively. The calibration curves of the CEUS-clinical model at different prediction time pionts were all close to the ideal line. The CEUS-clinical model effectively stratified patients into groups of high and low risk of recurrence in both training and validation set, while the TNM staging system only works on the training set. CONCLUSIONS: Our CEUS-clinical nomogram is a reliable early recurrence prediction tool for hepatocellular-cholangiocarcinoma and helps postoperative risk stratification.

High Sensitivity Flexible Electronic Skin Based on Graphene Film.

Electronic skin with high sensitivity, rapid response, and long-term stability has great value in robotics, biomedicine, and in other fields. However, electronic skin still has challenges in terms of sensitivity and response time. In order to solve this problem, flexible electronic skin with high sensitivity and the fast response was proposed, based on piezoresistive graphene films. The electronic skin was a pressure sensor array, composed of a 4 × 4 tactile sensing unit. Each sensing unit contained three layers: The underlying substrate (polyimide substrate), the middle layer (graphene/polyethylene terephthalate film), and the upper substrate bump (polydimethylsiloxane). The results of the measurement and analysis experiments, designed in this paper, indicated that the flexible electronic skin achieved a positive resistance characteristic in the range of 0 kPa⁻600 kPa, a sensitivity of 10.80 Ω /kPa in the range of 0 kPa⁻4 kPa, a loading response time of 10 ms, and a spatial resolution of 5 mm. In addition, the electronic skin realized shape detection on a regular-shaped object, based on the change in the resistance value of each unit. The high sensitivity flexible electronic skin designed in this paper has important application prospects in medical diagnosis, artificial intelligence, and other fields.

Sensitivity-Compensated Micro-Pressure Flexible Sensor for Aerospace Vehicle.

When flight vehicles (e.g., aerospace vehicles, Low Earth Orbit (LEO) satellites, near-space aircrafts, Unmanned Aerial Vehicles (UAVs) and drones) fly at high speed, their surfaces suffer the micro-pressure from high-altitude thin air. The long-term effect of this pressure causes the surface components of flight vehicle to deform or fall off, which can lead to a serious accident. To solve this problem, this paper proposes a sensitivity-compensated micro-pressure flexible sensor based on hyper-elastic plastic material and plate parallel capacitance. The sensor is able to measure a range of 0⁻6 kPa micro-pressure suffered by the flight vehicle's surface with high sensitivity and flexible devices. In this paper, we propose the principle, structure design and fabrication of the sensitivity-compensated micro-pressure flexible sensor. We carried out experiments to obtain the static characteristic curve between micro-pressure and the output capacitance of the sensor devices, and investigated the relationship between sensitivity and geometric parameters. We also compared the performance of the flexible sensor before and after sensitivity compensation. The result shows that the sensor can measure a range of 0⁻2 kPa and 2⁻6 kPa with a sensitivity of 0.27 kPa-1 and 0.021 kPa-1, which are 80% and 141.38% higher than the sensor before compensation; a linearity of 1.39% and 2.88%, which are 51.7% and 13.1% higher than the sensor before compensation; and a hysteresis and repeatability of 4.95% and 2.38%, respectively. The sensor has potential applications in flight vehicles to measure the micro-pressure with high sensitivity and flexibility.

Thermal Protection Performance of Biomimetic Flexible Skin for Deformable High-Speed Vehicles (DHSV-bio-FS) under Uniaxial Tensile Strain.

Vehicle skin is the key component in maintaining the aerodynamic shape of the vehicle. A deformable high-speed vehicle needs to adjust its shape in real time to realize optimum aerodynamic efficiency and to withstand extreme heat flow induced by high-speed flight, which requires the skin to possess large strain and high-temperature resistance. Traditional vehicle skin cannot satisfy both of the requirements. Biomimetic flexible skin for deformable high-speed vehicles (DHSV-bio-FS) combines flexible material fabrication with transpiration cooling technology, which can simulate human skin sweat cooling, and has the characteristics of large strain and high-temperature resistance. The thermal protection performance of the prepared prototype of DHSV-bio-FS was evaluated by simulation and wind tunnel experiments at 40% tensile strain with liquid water as coolant. Simulation results suggest that the surface temperature of the DHSV-bio-FS at 40% tensile strain is consistent with the temperature of the coolant (350 K) in a 3,000 K high-temperature gas environment. In addition, the prepared prototype DHSV-bio-FS survived for 1,200 s in a high-temperature gas environment of 200 kW/m2 in wind tunnel experiments. This paper verifies the reliability of DHSV-bio-FS in a high-temperature gas environment and can be deployed in applications of flexible skin for deformable high-speed vehicles (DHSV-FS).

Weakly mutually uncorrelated codes with maximum run length constraint for DNA storage.

DNA storage systems have begun to attract considerable attention as next-generation storage technologies due to their high densities and longevity. However, efficient primer design for random-access in synthesized DNA strands is still an issue that needs to be solved. Although previous studies have explored various constraints for primer design in DNA storage systems, there is no attention paid to the combination of weakly mutually uncorrelated codes with the maximum run length constraint. In this paper, we first propose a code design by combining weakly mutually uncorrelated codes with the maximum run length constraint. Moreover, we also explore the weakly mutually uncorrelated codes to satisfy combinations of maximum run length constraint with more constraints such as being almost-balanced and having large Hamming distance, which are also efficient constraints for random-access in DNA storage systems. To guarantee that the proposed codes can be adapted to primer design with variable length, we present modified code construction methods to achieve different lengths of the code. Then, we provide an analysis of the size of the proposed codes, which indicates the capacity to support primer design. Finally, we compare the codes with those of previous works to show that the proposed codes can always guarantee the maximum run length constraint, which is helpful for random-access for DNA storage.

Social Anxiety and Subjective Quality of Life Among Chinese Left-Behind Children: The Mediating Role of Social Support.

The issue of left-behind children has become a key focus in China. In this study, we investigate the mediating role of social support between social anxiety and the subjective quality of life among left-behind children in China (N = 379, M age = 13.65). A total of 710 junior high school students were recruited using clustering random sampling from five middle schools in China and investigated using the Social Anxiety Scale for Children, Social Support Rating Scale for Adolescents, and Inventory of Subjective Life Quality. The results show that social anxiety is negatively associated with social support and subjective quality of life, and social support is positively correlated with subjective quality of life. In addition, social support partially mediates the relationship between social anxiety and subjective quality of life. In conclusion, these findings provide new insights to improve the subjective quality of life of left-behind children. The focus should be on alleviating social anxiety and increasing social support in order to help left-behind children improve their subjective quality of life.

High Sensitivity and Wide Range Biomimetic Tactile-Pressure Sensor Based on 2D Graphene Film and 3D Graphene Foam.

Bionic electronic skin is a system that simulates human skin and has multiple perceptions. For pressure sensors, high measurement accuracy and wide measurement range restrict each other, and it is difficult to achieve high measurement accuracy and wide measurement range simultaneously. Therefore, the research and application of bionic tactile-pressure sensors are limited due to the mutual constraints of measurement accuracy and range. In this work, a flexible graphene piezoresistive tactile sensor based on a biomimetic structure that utilizes the piezoresistive properties of graphene was reported. The novel tactile-pressure sensor consists of a 2D graphene film tactile sensor and a 3D graphene foam pressure sensor that could achieve high accuracy and a wide-range measurement simultaneously. The testing results show that the measurement range of this sensor was in two intervals of 0-2 N and 2-40 N. For the 0-2 N measurement range, the sensitivity was 472.2 Ω/kPa, the force resolution was 0.01 N, and the response time was less than 40 ms. For the 2-40 N measurement range, the sensitivity was 5.05 kΩ/kPa, the force resolution was 1 N, and the response time was less than 20 ms. The new sensor can realize high-precision and large-scale force measurements and shows great application value in the field of medical instruments and artificial limbs.

Social Support and Job Satisfaction in Kindergarten Teachers: The Mediating Role of Coping Styles.

This study explored the relationship between social support and job satisfaction in kindergarten teachers, and the mediating role of coping styles in this relationship. A sample of 617 kindergarten teachers (M age = 25.13 years, SD = 5.66 years) from kindergartens in mainland China completed questionnaires measuring social support, job satisfaction, and coping style. The results showed that social support was positively related to job satisfaction and positive coping style was positively associated with social support and job satisfaction. Furthermore, the results revealed that positive coping style, but not negative coping style, had a mediating effect on the relationship between kindergarten teachers' social support and job satisfaction. This study provides initial evidence that coping style mediates the link between social support and job satisfaction in kindergarten teachers, and suggests that increasing social support and encouraging positive coping style could improve kindergarten teachers' job satisfaction.

Flexible Capacitive Pressure Sensor Based on Microstructured Composite Dielectric Layer for Broad Linear Range Pressure Sensing Applications.

Flexible pressure sensors have attracted a considerable amount of attention in various fields including robotics and healthcare applications, among others. However, it remains significantly challenging to design and fabricate a flexible capacitive pressure sensor with a quite broad linearity detection range due to the nonlinear stress-strain relation of the hyperelastic polymer-based dielectric material. Along these lines, in this work, a novel flexible capacitive pressure sensor with microstructured composite dielectric layer (MCDL) is demonstrated. The MCDL was prepared by enforcing a solvent-free planetary mixing and replica molding method, while the performances of the flexible capacitive pressure sensor were characterized by performing various experimental tests. More specifically, the proposed capacitive pressure sensor with 4.0 wt % cone-type MCDL could perceive external pressure loads with a broad detection range of 0-1.3 MPa, which yielded a high sensitivity value of 3.97 × 10-3 kPa-1 in a relative wide linear range of 0-600 kPa. Moreover, the developed pressure sensor exhibited excellent repeatability during the application of 1000 consecutive cycles and a fast response time of 150 ms. Finally, the developed sensor was utilized for wearable monitoring and spatial pressure distribution sensing applications, which indicates the great perspectives of our approach for potential use in the robotics and healthcare fields.

Articles That Use Artificial Intelligence for Ultrasound: A Reader's Guide.

Artificial intelligence (AI) transforms medical images into high-throughput mineable data. Machine learning algorithms, which can be designed for modeling for lesion detection, target segmentation, disease diagnosis, and prognosis prediction, have markedly promoted precision medicine for clinical decision support. There has been a dramatic increase in the number of articles, including articles on ultrasound with AI, published in only a few years. Given the unique properties of ultrasound that differentiate it from other imaging modalities, including real-time scanning, operator-dependence, and multi-modality, readers should pay additional attention to assessing studies that rely on ultrasound AI. This review offers the readers a targeted guide covering critical points that can be used to identify strong and underpowered ultrasound AI studies.

Ultra-Sensitive Flexible Tactile Sensor Based on Graphene Film.

Flexible tactile sensor can be integrated into artificial skin and applied in industrial robot and biomedical engineering. However, the presented tactile sensors still have challenge in increasing sensitivity to expand the sensor's application. Aiming at this problem, this paper presents an ultra-sensitive flexible tactile sensor. The sensor is based on piezoresistive effect of graphene film and is composed of upper substrate (PDMS bump with a size of 5 mm × 7 mm and a thickness of 1 mm), medial Graphene/PET film (Graphene/PET film with a size of 5 mm × 7 mm, PET with a hardness of 2H) and lower substrate (PI with fabricated electrodes). We presented the structure and reduced the principle of the sensor. We also fabricated several sample devices of the sensor and carried out experiment to test the performance. The results show that the sensor performed an ultra high sensitivity of 10.80/kPa at the range of 0-4 kPa and have a large measurement range up to 600 kPa. The sensor has 4 orders of magnitude between minimum resolution and maximum measurement range which have great advantage compared with state of the art. The sensor is expected to have great application prospect in robot and biomedical.