Search

Background: Female breast cancer has surpassed lung cancer as the most common cancer, and is also the main cause of cancer death for women worldwide. Breast cancer <1 cm showed excellent survival rate. However, the diagnosis of minimal breast cancer (MBC) is challenging. Objective: The purpose of our research is to develop and validate an radiomics model based on ultrasound images for early recognition of MBC. Methods: 302 breast masses with a diameter of <10 mm were retrospectively studied, including 159 benign and 143 malignant breast masses. The radiomics features were extracted from the gray‐scale ultrasound image of the largest face of each breast mass. The maximum relevance minimum reduncancy and recursive feature elimination methods were used to screen. Finally, 10 features with the most discriminating value were selected for modeling. The random forest was used to establish the prediction model, and the rad‐score of each mass was calculated. In order to evaluate the effectiveness of the model, we calculated and compared the area under the curve (AUC) value, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of the model and three groups with different experience in predicting small breast masses, and drew calibration curves and decision curves to test the stability and consistency of the model. Results: When we selected 10 radiomics features to calculate the rad‐score, the prediction efficiency was the best, the AUC values for the training set and testing set were 0.840 and 0.793, which was significantly better than the insufficient experience group (AUC = 0.673), slightly better than the moderate experience group (AUC = 0.768), and was inferior to the experienced group (AUC = 0.877). The calibration curve and decision curve also showed that the radiomics model had satisfied stability and clinical application value. Conclusion: The radiomics model based on ultrasound image features has a satisfied predictive ability for small breast masses, and is expected to become a potential tool for the diagnosis of MBC, and it is a zero cost (in terms of patient participation and imaging time). [ABSTRACT FROM AUTHOR]

Purpose: By constructing a prediction model of carpal tunnel syndrome (CTS) based on ultrasound images, it can automatically and accurately diagnose CTS without measuring the median nerve cross‐sectional area (CSA). Methods: A total of 268 wrists ultrasound images of 101 patients diagnosed with CTS and 76 controls in Ningbo NO.2 Hospital from December 2021 to August 2022 were retrospectively analyzed. The radiomics method was used to construct the Logistic model through the steps of feature extraction, feature screening, reduction, and modeling. The area under the receiver operating characteristic curve was calculated to evaluate the performance of the model, and the diagnostic efficiency of the radiomics model was compared with two radiologists with different experience. Results: The 134 wrists in the CTS group included 65 mild CTS, 42 moderate CTS, and 17 severe CTS. In the CTS group, 28 wrists median nerve CSA were less than the cut‐off value, 17 wrists were missed by Dr. A, 26 wrists by Dr. B, and only 6 wrists were missed by radiomics model. A total of 335 radiomics features were extracted from each MN, of which 10 features were significantly different between compressed and normal nerves, and were used to construct the model. The area under curve (AUC) value, sensitivity, specificity, and accuracy of the radiomics model in the training set and testing set were 0.939, 86.17%, 87.10%, 86.63%, and 0.891, 87.50%, 80.49%, and 83.95%, respectively. The AUC value, sensitivity, specificity, and accuracy of the two doctors in the diagnosis of CTS were 0.746, 75.37%, 73.88%, 74.63% and 0.679, 68.66%, 67.16%, and 67.91%, respectively. The radiomics model was superior to the two‐radiologist diagnosis, especially when there was no significant change in CSA. Conclusion: Radiomics based on ultrasound images can quantitatively analyze the subtle changes in the median nerve, and can automatically and accurately diagnose CTS without measuring CSA, especially when there was no significant change in CSA, which was better than radiologists. [ABSTRACT FROM AUTHOR]

Objectives: The ultrasound diagnosis of mild carpal tunnel syndrome (CTS) is challenging. Radiomics can identify image information that the human eye cannot recognize. The purpose of our study was to explore the value of ultrasound image‐based radiomics in the diagnosis of mild CTS. Methods: This retrospective study included 126 wrists in the CTS group and 88 wrists in the control group. The radiomics features were extracted from the cross‐sectional ultrasound images at the entrance of median nerve carpal tunnel, and the modeling was based on robust features. Two radiologists with different experiences diagnosed CTS according to two guidelines. The area under receiver (AUC) operating characteristic curve, sensitivity, specificity, and accuracy were used to evaluate the diagnostic efficacy of the two radiologists and the radiomics model. Results: According to guideline one, the AUC values of the two radiologists for CTS were 0.72 and 0.67, respectively; according to guideline two, the AUC were 0.73 and 0.68, respectively. The radiomics model achieved the best accuracy when 16 important robust features were selected. The AUC values of training set and test set were 0.92 and 0.90, respectively. Conclusions: The radiomics label based on ultrasound images had excellent diagnostic efficacy for mild CTS. It is expected to help radiologists to identify early CTS patients as soon as possible, especially for inexperienced doctors. [ABSTRACT FROM AUTHOR]

Background: In the recent years, artificial intelligence (AI) algorithms have been used to accurately diagnose musculoskeletal diseases. However, it is not known whether the particular regions of interest (ROI) delineation method would affect the performance of the AI algorithm. Purpose: The purpose of this study was to investigate the influence of ROI delineation methods on model performance and observer consistency. Methods: In this retrospective analysis, ultrasound (US) measures of median nerves affected with carpal tunnel syndrome (CTS) were compared to median nerves in a control group without CTS. Two methods were used for delineation of the ROI: (1) the ROI along the hyperechoic medial edge of the median nerve but not including the epineurium (MN) (ROI1); and (2) the ROI including the hyperechoic epineurium (ROI2), respectively. The intra group correlation coefficient (ICC) was used to compare the observer consistency of ROI features (i.e. the corresponding radiomics parameters). Parameters α1 and α2 were obtained based on the ICC of ROI1 features and ROI2 features. The ROC analysis was used to determine the area under the curve (AUC) and evaluate the performance of the radiologists and network. In addition, four indices, namely sensitivity, specificity, positive prediction and negative prediction were analyzed too. Results: A total of 136 wrists of 77 CTS group and 136 wrists of 74 control group were included in the study. Control group was matched to CTS group according to the age and sex. The observer consistency of ROI features delineated by the two schemes was different, and the consistency of ROI1 features was higher (α1 ˃ α2). The intra‐observer consistency was higher than the inter‐observer consistency regardless of the scheme, and the intra‐observer consistency was higher when chose scheme one. The performances of models based on the two ROI features were different, although the AUC of each model was greater than 0.8.The model performed better when the MN epineurium was included in the ROI. Among five artificial intelligence algorithms, the Forest models (model1 achieved an AUC of 0.921 in training datasets and 0.830 in testing datasets; model2 achieved an AUC of 0.967 in training datasets and 0.872 in testing datasets.) obtained the highest performance, followed by the support vector machine (SVM) models and the Logistic models. The performances of the models were significantly better than the inexperienced radiologist (Dr. B. Z. achieved an AUC of 0.702). Conclusion: Different ROI delineation methods may affect the performance of the model and the consistency of observers. Model performance was better when the ROI contained the MN epineurium, and observer consistency was higher when the ROI was delineated along the hyperechoic medial border of the MN. [ABSTRACT FROM AUTHOR]

Logo detection is a technology that identifies logos in images and returns their locations. With logo detection technology, brands can check how often their logos are displayed on social media platforms and elsewhere online and how they appear. It has received a lot of attention for its wide applications across different sectors, such as brand identity protection, product brand management, and logo duration monitoring. Particularly, logo detection technology can offer various benefits for companies to help brands measure their logo coverage, track their brand perception, secure their brand value, increase the effectiveness of their marketing campaigns and build brand awareness more effectively. However, compared with the general object detection, logo detection is more challenging due to the existence of both small logo objects and large aspect ratio logo objects. In this paper, we propose a novel approach, named Discriminative Semantic Feature Pyramid Network with Guided Anchoring (DSFP-GA), which can address these challenges via aggregating the semantic information and generating different aspect ratio anchor boxes. More specifically, our approach mainly consists of two components, namely Discriminative Semantic Feature Pyramid (DSFP) and Guided Anchoring (GA). The former is proposed to fuse semantic features into low-level feature maps to obtain discriminative representation of small logo objects, while the latter is further integrated into DSFP to generate large aspect ratio anchor boxes for detecting large aspect ratio logo objects. Extensive experimental results on four benchmarks demonstrate the effectiveness of the proposed DSFP-GA. Moreover, we further conduct visual analysis and ablation studies to illustrate the strength of the proposed DSFP-GA when detecting both small logo objects and large aspect logo objects. [ABSTRACT FROM AUTHOR]

Logo detection is one of the crucial branches in computer vision due to various real-world applications, such as automatic logo detection and recognition, intelligent transportation, and trademark infringement detection. Compared with traditional handcrafted-feature-based methods, deep learning-based convolutional neural networks (CNNs) can learn both low-level and high-level image features. Recent decades have witnessed the great feature representation capabilities of deep CNNs and their variants, which have been very good at discovering intricate structures in high-dimensional data and are thereby applicable to many domains including logo detection. However, logo detection remains challenging, as existing detection methods cannot solve well the problems of a multiscale and large aspect ratios. In this paper, we tackle these challenges by developing a novel long-range dependence involutional network (LDI-Net). Specifically, we designed a strategy that combines a new operator and a self-attention mechanism via rethinking the intrinsic principle of convolution called long-range dependence involution (LD involution) to alleviate the detection difficulties caused by large aspect ratios. We also introduce a multilevel representation neural architecture search (MRNAS) to detect multiscale logo objects by constructing a novel multipath topology. In addition, we implemented an adaptive RoI pooling module (ARM) to improve detection efficiency by addressing the problem of logo deformation. Comprehensive experiments on four benchmark logo datasets demonstrate the effectiveness and efficiency of the proposed approach. [ABSTRACT FROM AUTHOR]

Solution-processed colloidal lead halide perovskite quantum dots (QDs) are considered one of the promising candidates for next-generation photovoltaics (PVs) due to the excellent optoelectronic properties and low-cost synthetic process. In particular, all-inorganic perovskite (AIP) QDs exhibit better prospects due to their better stability. Although remarkable breakthroughs have been made in bulk perovskite solar cells (SCs), the AIP QD-based SCs (AIPQDSCs) are still on their way to catch up. A lot of reports have summarized the development of perovskite SCs, but few have focused on AIPQDSCs. In this review, we focus on the latest development of AIPQDSCs, and analyze the current bottlenecks they are facing. Also, various optimization means have been discussed to improve the performance of AIPQDSCs from two perspectives of QD materials and device structure, including compositional regulation, surface engineering, interface engineering, and optimization of the carrier transport layer. In addition, AIP QDs as converter for SCs are also presented. Since the stability of perovskite SCs is currently the most pressing issue, the device stability is also highlighted. In the end, a brief summary and perspectives are presented to look forward to the future development of AIPQDSCs. [ABSTRACT FROM AUTHOR]

Lead halide perovskite, as an emerging semiconductor, provides a fire‐new opportunity for high‐definition display and solid‐state lighting. Earthshaking improvements are implemented in green, red, and near‐infrared perovskite light‐emitting diodes (PeLEDs). However, blue PeLEDs are still far behind in performance, which restricts the development of PeLEDs in practical applications. Herein, a facile energy cascade channel strategy via one‐step self‐organized and controllable 2D/3D perovskite preparation by introducing guanidine hydrobromide (GABr) is developed that greatly improves the efficiency of blue PeLEDs. The 2D/3D perovskite structure boosts the energy cascade to induce energy transfer from the wide into the narrow bandgap domains and inhibit free charge diffusion, which increases the density of electrons and holes, and enhances the radiative recombination. Profiting from this energy cascade channels, the external quantum efficiency of blue PeLEDs, emitting at 492 nm, is considerably enhanced from 1.5% of initial blue device to 8.2%. In addition, device operating stability under ambient conditions is also improved by 2.6‐fold. The one‐step self‐organized 2D/3D hybrid perovskites induced by GABr pave a new and simple route toward high‐performance blue emission PeLEDs. [ABSTRACT FROM AUTHOR]

Recent investigations found that hydrothermal activity and sulfide mineralization occurs along the Southwest Indian Ridge (SWIR). The Longqi and Duanqiao hydrothermal fields between 49° E and 53° E of the SWIR are two prospective mineralization areas discovered by Chinese scientists. With the aim to determine the mineralogical and chemical characteristics of sulfide minerals, we have conducted detailed studies for samples from the two areas using an optical microscope, X‐ray diffractometer, scanning electron microscope, and electron microprobe. The mineralization processes in the Longqi area are divided into three main stages: (1) the low‐medium‐temperature stage: colloform pyrite (Py I) + marcasite → euhedral pyrite (Py II), (2) the high‐temperature stage: isocubanite (±exsolved chalcopyrite) + pyrrhotite → coarse‐grained chalcopyrite (Ccp I), and (3) the medium–low‐temperature stage: sphalerite + fine‐grained chalcopyrite inclusions (Ccp II) → aggregates of anhedral pyrite (Py III) ± marcasite → Fe‐oxide (‐hydroxide) + amorphous silica. The mineralization processes in the Duanqiao area are divided into two main stages: (1) the medium–high‐temperature stage: subhedral and euhedral pyrite (Py I′) → coarse‐grained chalcopyrite (Ccp I′) and (2) the medium–low‐temperature stage: sphalerite → fine‐grained chalcopyrite (Ccp II′) + chalcopyrite inclusions (Ccp II′) → silica‐cemented pyrite (Py II′) + marcasite → Fe‐oxide + amorphous silica. We suggest that the fine‐grained chalcopyrite inclusions in sphalerite from Longqi and Duanqiao were formed by co‐precipitation and replacement mechanisms, respectively. Primary sphalerites from both fields are enriched in Fe (avg. 5.84 wt% for the Longqi field vs. avg. 3.69 wt% for the Duanqiao field), Co (avg. 185.56 ppm for the Longqi field vs. 160.53 ppm for the Duanqiao field), and Cd (avg. 1950 ppm for the Longqi field vs. avg. 525.26 ppm for the Duanqiao field). Cu contents in pyrite from the Duanqiao field (Py I′: avg. 849.23 ppm and Py II′: avg. 1191.11 ppm) tend to be higher than those from the Longqi field (Py I: avg. 26.67 ppm, Py II: avg. 445 ppm, and Py III: avg. 179.29 ppm). Chalcopyrite from both fields is enriched in Zn (Ccp I: avg. 3226.67 ppm, Ccp II: avg. 9280 ppm, Ccp I′: avg. 848 ppm, Ccp II′ (inclusions): avg. 1098 ppm, and Ccp II′ (fine‐grained): avg. 1795 ppm). The varying contents of Zn in the different pyrite and chalcopyrite generations may result from the zone refining process. An integrated study of the mineralogy and mineralogical chemistry suggests that the hydrothermal fluids of the Longqi area are likely conditioned with higher temperatures and relatively lower fO2 and fS2 than those of the Duanqiao area, but in contrast to the former, the latter is much affected by the compositions of the surrounding rocks. [ABSTRACT FROM AUTHOR]

To study the effects of different storage methods and time on content of nutrients in biogas slurry of straw, two storage methods were carried out on biogas slurry between open storage and airtight storage conditions at normal atmospheric temperature. The contents of N, P, K, and organic matter in biogas slurry of straw were determined in different storage times. The results showed that; during the process of biogas slurry storage, little change occurred in the content of the organic matter while the total content of N. P. K significantly declined; up to 50 days, the total content of N. P. K reduced to nearly 80%-90%. Because the contents of N, P. K in biogas slurry reduced less in airtight storage conditions so that a better result was found on airtight storage methods than open storage methods in fertilizer field of biogas slurry of straw. [ABSTRACT FROM AUTHOR]

The article focuses on a research paper on geology of hot spring geyserite cesium deposit in Targejia in Tibet, China. It discusses the geochemical analysis of the acidic and alkaline spring water area in Targejia. It also reflects on the geological setting of the deposits whcih suggests eruptive fountains, hot springs and sediments of the springs the mining area.

An eco-friendly material, activated carbon cloth (ACC) was used as the heterogeneous catalyst in activation of peroxydisulfate (PDS) for the efficient degradation of organic pollutant in water. Besides, the effects of several parameters in the ACC/PDS process including initial pH, PDS concentration, reaction temperature, stirring speed and co-existing anions were investigated. Under optimum conditions, almost complete removal (98.6%) of AO7 in 60 min and 67.4% of total organic carbon (TOC) removal within 180 min were obtained, accompanied by the remarkable destruction of azo band and naphthalene ring on AO7. The electron paramagnetic resonance and radical quenching experiments were carried out to identify the reactive radicals in the ACC/PDS process. Surface characteristic techniques such as XRD, BET, SEM, FTIR, XPS were applied to analysis the change of crystal structure, surface area, surface morphology, functional groups on the surface of fresh and spent ACC samples. Hydroxyl groups (C‒OH) and π-π transitions significantly affected the catalytic activity of ACC. The intermediate products of AO7 oxidation were identified by LC-MS and the corresponding degradation pathway was proposed. Image 1 • Activated carbon cloth (ACC) in monolithic form was applied to catalyze PDS. • Effects of reaction parameters on AO7 removal were evaluated. • SO 4.•−, HO• and •C were identified in ACC/PDS system • Surface function groups are responsible for the adsorption and activation of ACC. [ABSTRACT FROM AUTHOR]

Objectives: The aim of this study was to assess the quality of tuberculosis (TB) care for the whole course and assess factors that affect completing treatment., Design: This is an observational retrospective study using chart abstraction for the whole course of TB care conducted at two underserved provinces in China., Setting: The study was conducted from June 2021 to July 2021. All medical records (outpatient and inpatient) for the whole course (6-8 months) of patients with TB newly registered from July 2020 to December 2020 were reviewed and abstracted using predetermined checklists., Participants: A total of 268 outpatient medical records and 126 inpatient records were included., Primary and Secondary Outcome Measures: The primary outcome included diagnostic quality, treatment quality and management quality. The secondary outcome was completing treatment., Results: For diagnostic quality, 94.2% of the diagnosis were based on adequate evidence. For treatment quality, 240 (91.6%) outpatients and 100 (85.5%) inpatients took the standard chemotherapy regimens. 234 (87.3%) patients completed treatment. 85.1% of the inpatients prescribed with second-line drugs were inappropriate. For management quality, 128 (47.9%) patients received midterm assessments, but only 47 (19.7%) received sufficient services for the whole course. Patients with TB symptoms were 1.8 times more likely to complete treatment (p=0.011)., Conclusion: Patients with TB received high-quality diagnosis and treatment services, but low-quality whole-course management. Integration of medical and public health services should be strengthened to improve whole-course quality., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Background: The consistency of Breast Imaging Reporting and Data System (BI-RADS) classification among experienced radiologists is different, which is difficult for inexperienced radiologists to master. This study aims to explore the value of computer-aided diagnosis (CAD) (AI-SONIC breast automatic detection system) in the BI-RADS training for residents., Methods: A total of 12 residents who participated in the first year and the second year of standardized resident training in Ningbo No. 2 Hospital from May 2020 to May 2021 were randomly divided into 3 groups (Group 1, Group 2, Group 3) for BI-RADS training. They were asked to complete 2 tests and questionnaires at the beginning and end of the training. After the first test, the educational materials were given to the residents and reviewed during the breast imaging training month. Group 1 studied independently, Group 2 studied with CAD, and Group 3 was taught face-to-face by experts. The test scores and ultrasonographic descriptors of the residents were evaluated and compared with those of the radiology specialists. The trainees' confidence and recognition degree of CAD were investigated by questionnaire., Results: There was no statistical significance in the scores of residents in the first test among the 3 groups (P=0.637). After training and learning, the scores of all 3 groups of residents were improved in the second test (P=0.006). Group 2 (52±7.30) and Group 3 (54±5.16) scored significantly higher than Group 1 (38±3.65). The consistency of ultrasonographic descriptors and final assessments between the residents and senior radiologists were improved (κ3 > κ2 > κ1), with κ2 and κ3 >0.4 (moderately consistent with experts), and κ1 =0.225 (fairly agreed with experts). The results of the questionnaire showed that the trainees had increased confidence in BI-RADS classification, especially Group 2 (1.5 to 3.5) and Group 3 (1.25 to 3.75). All trainees agreed that CAD was helpful for BI-RADS learning (Likert scale score: 4.75 out of 5) and were willing to use CAD as an aid (4.5, max. 5)., Conclusions: The AI-SONIC breast automatic detection system can help residents to quickly master BI-RADS, improve the consistency between residents and experts, and help to improve the confidence of residents in the classification of BI-RADS, which may have potential value in the BI-RADS training for radiology residents., Trial Registration: Chinese Clinical Trial Registry (ChiCTR2400081672)., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://tcr.amegroups.com/article/view/10.21037/tcr-23-2122/coif). The authors have no conflicts of interest to declare., (2024 Translational Cancer Research. All rights reserved.)

Objective: The accurate diagnosis of superficial lymphadenopathy is challenging. We aim to explore a non-invasive and accurate machine-learning method for distinguishing benign lymph nodes, lymphoma, and metastatic lymph nodes., Methods: The clinical data and ultrasound images of 160 patients with superficial lymphadenopathy (58 benign lymph nodes, 62 lymphoma, 40 metastatic lymph nodes) admitted to our hospital from January 2020 to November 2022 were retrospectively studied. Patients were randomly divided into a training set and test set according to the ratio of 6:4. Firstly, the radiomics features of each lymph node were extracted, and then a series of statistical methods were used to avoid over-fitting. Then, the gradient boosting machine(GBM) was used to build the model. The area under receiver(AUC) operating characteristic curve, precision, recall rate and F1 value were calculated to evaluate the effectiveness of the model., Results: Ten robust features were selected to build the model. The AUC values of benign lymph nodes, lymphoma and metastatic lymph nodes in the training set were 1.00, 0.98 and 0.99, and the AUC values of the test set were 0.96, 0.84 and 0.90, respectively., Conclusion: It was a reliable and non-invasive method for the differential diagnosis of lymphadenopathy based on the model constructed by machine learning., (Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.net.)

Background: Up to 15.3% of papillary thyroid microcarcinoma (PTMC) patients with negative clinical lymph node metastasis (cN0) were confirmed to have pathological lymph node metastasis in level VI. Conventional ultrasound (US) focuses on the characteristics of tumor capsule and the periphery to determine whether the tumor has invasive growth. However, due to its small size, the typical features of invasiveness shown by conventional 2-dimensional (2D) US are not well visualized. US-based radiomics makes use of artificial intelligence and big data to build a model that can help improving diagnostic accuracy and providing prognostic implication of the disease. We hope to establish and assess the value of a nomogram based on US radiomics combined with independent risk factors in predicting the invasiveness of a single PTMC without clinical lymph node metastasis (cN0)., Methods: A total of 317 patients with cN0 single PTMC who underwent US examination and operation were included in this retrospective cohort study. Patients were randomly divided into training and testing set in the ratio of 8:2. The US images of all patients were segmented, and the radiomics features were extracted. In the training dataset, the US with features of minimum redundancy maximum relevance (mRMR) and the least absolute shrinkage and selection operator (LASSO) were selected and radiomics signatures were then established according to their respective weighting coefficients. Univariate and multivariate logistic regression analyses were employed to generate the risk factors of possible invasive PTMC. The nomogram is then made by combining high risk factors and the radiomics signature. The efficiency of the nomogram was evaluated by the receiver operating characteristic (ROC) curve and calibration curve, and its clinical application value was assessed by decision curve analysis (DCA). The testing dataset was used to validate the model., Results: In the model, seven radiomics features were selected to establish the radiomics signature. A nomogram was made by incorporating clinically independent risk factors and the radiomics signature. Both the ROC curve and calibration curve showed good prediction efficiency. The area under the curve (AUC), accuracy, sensitivity, and specificity of the nomogram in the training data were 0.76 [95% confidence interval (CI): 0.71-0.82], 0.811, 0.914, and 0.727, respectively whereas the results of the testing dataset were 0.71 (95% CI: 0.58-0.84), 0.841, 0.533, and 0.868. As such, the efficacy of the nomogram in predicting the invasiveness of PTMC was subsequently validated by the DCA., Conclusions: Nomogram based on thyroid US radiomics has an excellent predictive value of the potential invasiveness of a single PTMC without clinical lymph node metastasis. With these promising results, it can potentially be the imaging marker used in daily clinical practice., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://gs.amegroups.com/article/view/10.21037/gs-23-473/coif). The authors have no conflicts of interest to declare., (2023 Gland Surgery. All rights reserved.)

Purpose: To evaluate the value of preoperative ultrasound (US) radiomics nomogram of primary papillary thyroid carcinoma (PTC) for predicting large-number cervical lymph node metastasis (CLNM)., Materials and Methods: A retrospective study was conducted to collect the clinical and ultrasonic data of primary PTC. 645 patients were randomly divided into training and testing datasets according to the proportion of 7:3. Minimum redundancy-maximum relevance (mRMR) and least absolution shrinkage and selection operator (LASSO) were used to select features and establish radiomics signature. Multivariate logistic regression was used to establish a US radiomics nomogram containing radiomics signature and selected clinical characteristics. The efficiency of the nomogram was evaluated by the receiver operating characteristic (ROC) curve and calibration curve, and the clinical application value was assessed by decision curve analysis (DCA). Testing dataset was used to validate the model., Results: TG level, tumor size, aspect ratio, and radiomics signature were significantly correlated with large-number CLNM (all P< 0.05). The ROC curve and calibration curve of the US radiomics nomogram showed good predictive efficiency. In the training dataset, the AUC, accuracy, sensitivity, and specificity were 0.935, 0.897, 0.956, and 0.837, respectively, and in the testing dataset, the AUC, accuracy, sensitivity, and specificity were 0.782, 0.910, 0.533 and 0.943 respectively. DCA showed that the nomogram had some clinical benefits in predicting large-number CLNM., Conclusion: We have developed an easy-to-use and non-invasive US radiomics nomogram for predicting large-number CLNM with PTC, which combines radiomics signature and clinical risk factors. The nomogram has good predictive efficiency and potential clinical application value., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Zhang, Zhang, Wei, Yang, Liu, Zhang and Lyu.)

Background: Since 2010, China has implemented a national programme to train general practitioners for rural areas. The programme enrolled medical students with a rural background who signed a contract for 6 years' compulsory rural service after graduation. China is transitioning its national COVID-19 strategies in view of the features of coronavirus Omicron variant, the vaccination coverage, and the need for socioeconomic development. Strengthening primary health care, especially the health workforce in rural areas, should be an important consideration during the policy transition. This study aims to evaluate the implementation process of enrolling medical students in the programme, their willingness to work in the rural settings and their actual job choice after graduation., Methods: The study chose four medical universities in central and western China. A total of 2,041 medical graduates who have signed a contract for compulsory rural service and 1,576 medical graduates enrolled "as usual" (no compulsory rural service) were recruited in five campaigns-every June from 2015 to 2019. A survey was conducted 1 week before their graduation ceremony., Results: The top three reasons for choosing this programme were: a recommendation of a family member or teacher, a guaranteed job after graduation and the waiver of the tuition fee. 23.0-29.7% of the study participants were not familiar with the policy details. 39.1% of the medical students signed a contract with a county other than that of their hometown. Medical graduates on the compulsory rural service programme had very low willingness (1.9%) to work in rural areas but 86.1% of them actually worked at township health centers. In contrast, the willingness to work at township health centers was 0.2% for the comparison group (medical graduates without the contract), and their actual job choice at township health centers was 0%., Conclusions: Although the well-trained medical graduates on the compulsory rural service programme have low willingness to work in the township health centers, 86.1% of them choose to do so following their contract. This programme will strengthen the primary health workforce to deal with the increasing disease burden as China is transitioning its national COVID-19 strategies., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Hu, Zhang, Huang, Liu, Xia, Zuo and Liu.)

Background: China started a national program in 2010 to train qualified general practitioners with compulsory services program (CSP) in rural and remote areas. While the program has shown positive effects on staffing primary healthcare (PHC) in rural areas, very little is known about how well they perform. This study aims to evaluate the job performance of medical graduates from this program and the influence of program design on job performance., Methods: A cohort study was conducted with graduates from CSP and non-CSP (NCSP) from four medical universities in central and western China. Baseline and three waves of follow-up surveys were conducted from 2015-2020. The pass rate of China National Medical Licensing Examinations (NMLE) and self-reported job performance were used as measurements. Multivariable regressions were used to identify factors affecting job performance., Results: 2154 medical graduates were included, with 1586 CSP and 568 NCSP graduates. CSP (90.6%) and NCSP (87.5%) graduates showed no difference in passing the NMLE ( P =.153). CSP graduates reported similar job performance with NCSP graduates (CSP, 63.7; NCSP, 64.2); in the multivariable regression, CSP graduates scored 0.32 and 1.36 points lower in the total sample and graduates of 2015-2017, respectively, but not significantly. Having formally funded positions improved the job performance of CSP (β coefficient=4.87, P <.05). After controlling for Qinghai which adopted a different contracting strategy, "working in hometown" showed significant influence on job performance (β coefficient = 1.48, P <.05)., Conclusion: CSP graduates have demonstrated as good job performance as NCSP, proving the competency to provide high-quality care for remote and rural areas. The contracted township health centers (THCs) should provide guidance for CSP graduates, especially in the first few years after graduation. The local government should provide formally funded positions on time and prioritize signing contracts with hometowns or places nearby., (© 2022 The Author(s); Published by Kerman University of Medical Sciences This is an open-access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.)