A multi-Task Learning based applicable AI model simultaneously predicts stage, histology, grade and LNM for cervical cancer before surgery.

PURPOSE: To build an Mult-Task Learning (MTL) based Artificial Intelligence(AI) model that can simultaneously predict clinical stage, histology, grade and LNM for cervical cancer before surgery. METHODS: This retrospective and prospective cohort study was conducted from January 2001 to March 2014 for the training set and from January 2018 to November 2021 for the validation set at Beijing Chaoyang Hospital, Capital Medical University. Preoperative clinical information of cervical cancer patients was used. An Artificial Neural Network (ANN) algorithm was used to build the MTL-based AI model. Accuracy and weighted F1 scores were calculated as evaluation indicators. The performance of the MTL model was compared with Single-Task Learning (STL) models. Additionally, a Turing test was performed by 20 gynecologists and compared with this AI model. RESULTS: A total of 223 cervical cancer cases were retrospectively enrolled into the training set, and 58 cases were prospectively collected as independent validation set. The accuracy of this cervical cancer AI model constructed with ANN algorithm in predicting stage, histology, grade and LNM were 75%, 95%, 86% and 76%, respectively. And the corresponding weighted F1 score were 70%, 94%, 86%, and 76%, respectively. The average time consumption of AI simultaneously predicting stage, histology, grade and LNM for cervical cancer was 0.01s (95%CI: 0.01-0.01) per 20 patients. The mean time consumption doctor and doctor with AI were 581.1s (95%CI: 300.0-900.0) per 20 patients and 534.8s (95%CI: 255.0-720.0) per 20 patients, respectively. Except for LNM, both the accuracy and F-score of the AI model were significantly better than STL AI, doctors and AI-assisted doctors in predicting stage, grade and histology. (P < 0.05) The time consumption of AI was significantly less than that of doctors' prediction and AI-assisted doctors' results. (P < 0.05 CONCLUSION: A multi-task learning AI model can simultaneously predict stage, histology, grade, and LNM for cervical cancer preoperatively with minimal time consumption. To improve the conditions and use of the beneficiaries, the model should be integrated into routine clinical workflows, offering a decision-support tool for gynecologists. Future studies should focus on refining the model for broader clinical applications, increasing the diversity of the training datasets, and enhancing its adaptability to various clinical settings. Additionally, continuous feedback from clinical practice should be incorporated to ensure the model's accuracy and reliability, ultimately improving personalized patient care and treatment outcomes.

Photodynamically Tumor Vessel Destruction Amplified Tumor Targeting of Nanoparticles for Efficient Chemotherapy.

Efficient tumor-targeted drug delivery is still a challenging and currently unbreakable bottleneck in chemotherapy for tumors. Nanomedicines based on passive or active targeting strategy have not yet achieved convincing chemotherapeutic benefits in the clinic due to the tumor heterogeneity. Inspired by the efficient inflammatory-cell recruitment to acute clots, we constructed a two-component nanosystem, which is composed of an RGD-modified pyropheophorbide-a (Ppa) micelle (PPRM) that mediates the tumor vascular-targeted photodynamic reaction to activate local coagulation and subsequently transmits the coagulation signals to the circulating clot-targeted CREKA peptide-modified camptothecin (CPT)-loaded nanodiscs (CCNDs) for amplifying tumor targeting. PPRM could effectively bind with the tumor vasculature and induce sufficient local thrombus by a photodynamic reaction. Local photodynamic reaction-induced tumor target amplification greatly increased the tumor accumulation of CCND by 4.2 times, thus significantly enhancing the chemotherapeutic efficacy in the 4T1 breast tumor model. In other words, this study provides a powerful platform to amplify tumor-specific drug delivery by taking advantage of the efficient crosstalk between the PPRM-activated coagulation cascade and clot-targeted CCND.

Risk factors for postpartum stress urinary incontinence: a prospective study.

PURPOSE: Postpartum stress urinary incontinence (SUI) is a common occurrence in women, and it has a profound effect on women's health and quality of life. This study aimed to investigate the risk factors for postpartum SUI and the relative importance of each factor, including pelvic floor ultrasound measurement data and clinical data. METHOD: Pregnant women who delivered in our hospital from March 2021 to January 2022 were selected as the study population. The clinical and anatomical Data from women with SUI and those without SUI were collected and analyzed. The clinical and anatomical risk factors associated with postpartum SUI were identified using univariate and multivariate analyses. RESULTS: A total of 255 participants were recruited. Logistic regression analysis indicated that age (OR:1.215, 95% CI:1.097-1.346, P < 0.001), vaginal delivery (OR:3.05, 95% CI:1.328-7.016, P < 0.009), parity (OR:3.059, 95% CI:1.506-6.216, P < 0.002), bladder neck descent (OR:4.159, 95% CI: 2.010-8.605, P < 0.001), the angle of the internal urethral orifice funnel (OR:1.133, 95% CI:1.091-1.176, P < 0.001) were important independent risk factors for postpartum SUI (all P < 0.05). The AUC was 0.883 (95% CI: 0.839-0.926) in the model. CONCLUSIONS: Age, vaginal delivery, parity, bladder neck descent and the angle of the internal urethral orifice funnel are independent risk factors for postpartum SUI. To prevent the occurrence of postpartum SUI, high-risk factors of postpartum SUI should be identified as early as possible during pregnancy and after delivery, and postpartum pelvic floor rehabilitation training should be promoted.

Assessing the role of GPT-4 in thyroid ultrasound diagnosis and treatment recommendations: enhancing interpretability with a chain of thought approach.

Background: As artificial intelligence (AI) becomes increasingly prevalent in the medical field, the effectiveness of AI-generated medical reports in disease diagnosis remains to be evaluated. ChatGPT is a large language model developed by open AI with a notable capacity for text abstraction and comprehension. This study aimed to explore the capabilities, limitations, and potential of Generative Pre-trained Transformer (GPT)-4 in analyzing thyroid cancer ultrasound reports, providing diagnoses, and recommending treatment plans. Methods: Using 109 diverse thyroid cancer cases, we evaluated GPT-4's performance by comparing its generated reports to those from doctors with various levels of experience. We also conducted a Turing Test and a consistency analysis. To enhance the interpretability of the model, we applied the Chain of Thought (CoT) method to deconstruct the decision-making chain of the GPT model. Results: GPT-4 demonstrated proficiency in report structuring, professional terminology, and clarity of expression, but showed limitations in diagnostic accuracy. In addition, our consistency analysis highlighted certain discrepancies in the AI's performance. The CoT method effectively enhanced the interpretability of the AI's decision-making process. Conclusions: GPT-4 exhibits potential as a supplementary tool in healthcare, especially for generating thyroid gland diagnostic reports. Our proposed online platform, "ThyroAIGuide", alongside the CoT method, underscores the potential of AI to augment diagnostic processes, elevate healthcare accessibility, and advance patient education. However, the journey towards fully integrating AI into healthcare is ongoing, requiring continuous research, development, and careful monitoring by medical professionals to ensure patient safety and quality of care.

Prospective comparison of an 18-gauge versus 16-gauge needle for percutaneous liver core-needle biopsy in children.

PURPOSE: The objective of this study was to analyzed the impact of needle gauge (G) on the adequacy of specimens and hemorrhagic complications in pediatric patients undergoing ultrasound (US)-guided transplanted liver biopsies. METHODS: The study included 300 consecutive biopsies performed in 282 pediatric patients (mean age 6.75 ± 3.82 years, range 0.84-17.90) between December 2020 and April 2022. All pediatric patients that referred to our institution for US-guided core-needle liver biopsy (CNLB) were randomized to undergo 16-G or 18-G CNLB. Hemorrhagic complications were qualitatively evaluated. The number of complete portal tracts (CPTs) per specimen was counted and specimen adequacy was assessed based on the American Association for the Study of Liver Diseases guidelines. RESULTS: The incidence of bleeding was 7.00% (n = 21) and adequate specimens for accurate pathological diagnosis were obtained from 98.33% (n = 295) of patients. There was no significant difference in the incidence or amount of bleeding between the 16-G and 18-G groups (11 vs 10, p = 0.821; 35.0 mL vs 31.3 mL, p = 0.705). Although biopsies obtained using a 16-G needle contained more complete portal tracts than those obtained using an 18-G needle (20.0 vs 18.0, p = 0.029), there was no significant difference in specimen inadequacy according to needle gauge (2 vs 3, p = 1.000). CONCLUSIONS: Biopsy with a 16-G needle was associated with a greater number of CPTs but did not increase the adequate specimen rate. There was no significant difference in the complication rate between 16-G biopsy and 18-G biopsy.

Real-time auto-segmentation of the ureter in video sequences of gynaecological laparoscopic surgery.

BACKGROUND: Ureteral injury is common during gynaecological laparoscopic surgery. Real-time auto-segmentation can assist gynaecologists in identifying the ureter and reduce intraoperative injury risk. METHODS: A deep learning segmentation model was crafted for ureter recognition in surgical videos, utilising 3368 frames from 11 laparoscopic surgeries. Class activation maps enhanced the model's interpretability, showing its areas. The model's clinical relevance was validated through an End-User Turing test and verified by three gynaecological surgeons. RESULTS: The model registered a Dice score of 0.86, a Hausdorff 95 distance of 22.60, and processed images in 0.008 s on average. In complex surgeries, it pinpointed the ureter's position in real-time. Fifty five surgeons across eight institutions found the model's accuracy, specificity, and sensitivity comparable to human performance. Yet, artificial intelligence experience influenced some subjective ratings. CONCLUSIONS: The model offers precise real-time ureter segmentation in laparoscopic surgery and can be a significant tool for gynaecologists to mitigate ureteral injuries.

Risk factors for unresectable pancreatic cancer following high-intensity focused ultrasound treatment.

PURPOSE: Pancreatic cancer is one of the most aggressive malignant tumors with poor prognosis. High-intensity focused ultrasound (HIFU) is an effective and safe treatment option for advanced pancreatic cancer, however, the survival time of patients after the treatment was different. So, the purpose of this study was to evaluate the relationship between the high-risk characteristics and prognosis of unresectable pancreatic cancer after HIFU treatment. PATIENTS AND METHODS: This prospective study included 30 patients with unresectable pancreatic cancer who received HIFU at Beijing Friendship Hospital. Data on patients' tumor size, pain scores, peripheral blood lymphocyte subsets, CA19-9 and contrast enhanced ultrasound (CEUS) features were collected to assess the relationship with overall survival (OS) after HIFU. RESULTS: The median OS from the start of HIFU treatment was 159 days, 95% confidence interval (95% CI): 108-210. The levels of pain were determined by visual analogue scale (VAS) score, and the quartile of the score decreased from 6 (2, 7) to 4 (2, 5) immediately after one session of the treatment (p = 0.001). The diagnostic model showed that high post VAS score and decreasing of peripheral CD4+ T cells were significantly correlated with poor prognosis (p < 0.05), and showed good discrimination ability (AUC = 0.848, 95% CI = 0.709-0.987). CONCLUSION: HIFU can effectively relieve pain in patients with unresectable pancreatic cancer. Post treatment VAS and change of peripheral CD4+ T cells are independent risk factors affecting the prognosis in patients with unresectable pancreatic cancer after HIFU treatment.

Manipulating Neovasculature-Targeting Capability of Biomimetic Nanodiscs for Synergistic Photoactivatable Tumor Infarction and Chemotherapy.

Tumor infarction therapy is a promising antitumor strategy with the advantages of taking a short therapy duration, less risk of resistance, and effectiveness against a wide range of tumor types. However, its clinical application is largely hindered by tumor recurrence in the surviving rim and the potential risk of thromboembolic events due to nonspecific vasculature targeting. Herein, a neovasculature-targeting synthetic high-density lipoprotein (sHDL) nanodisc loaded with pyropheophorbide-a and camptothecin (CPN) was fabricated for photoactivatable tumor infarction and synergistic chemotherapy. By manipulating the anisotropy in ligand modification of sHDL nanodiscs, CPN modified with neovaculature-targeting peptide on the planes (PCPN) shows up to 7-fold higher cellular uptake compared with that around the edge (ECPN). PCPN can efficiently bind to endothelial cells of tumor vessels, and upon laser irradiation, massive local thrombus can be induced by the photodynamic reaction to deprive nutrition supply. Meanwhile, CPT could be released in response to the tumor reductive environment, thus killing residual tumor cells in the surviving rim to inhibit recurrence. These findings not only offer a powerful approach of synergistic cancer therapy but also suggest the potential of plane-modified sHDL nanodiscs as a versatile drug delivery nanocarrier.

Development and validation of a dynamic nomogram based on conventional ultrasound and contrast-enhanced ultrasound for stratifying the risk of central lymph node metastasis in papillary thyroid carcinoma preoperatively.

Purpose: The aim of this study was to develop and validate a dynamic nomogram by combining conventional ultrasound (US) and contrast-enhanced US (CEUS) to preoperatively evaluate the probability of central lymph node metastases (CLNMs) for patients with papillary thyroid carcinoma (PTC). Methods: A total of 216 patients with PTC confirmed pathologically were included in this retrospective and prospective study, and they were divided into the training and validation cohorts, respectively. Each cohort was divided into the CLNM (+) and CLNM (-) groups. The least absolute shrinkage and selection operator (LASSO) regression method was applied to select the most useful predictive features for CLNM in the training cohort, and these features were incorporated into a multivariate logistic regression analysis to develop the nomogram. The nomogram's discrimination, calibration, and clinical usefulness were assessed in the training and validation cohorts. Results: In the training and validation cohorts, the dynamic nomogram (https://clnmpredictionmodel.shinyapps.io/PTCCLNM/) had an area under the receiver operator characteristic curve (AUC) of 0.844 (95% CI, 0.755-0.905) and 0.827 (95% CI, 0.747-0.906), respectively. The Hosmer-Lemeshow test and calibration curve showed that the nomogram had good calibration (p = 0.385, p = 0.285). Decision curve analysis (DCA) showed that the nomogram has more predictive value of CLNM than US or CEUS features alone in a wide range of high-risk threshold. A Nomo-score of 0.428 as the cutoff value had a good performance to stratify high-risk and low-risk groups. Conclusion: A dynamic nomogram combining US and CEUS features can be applied to risk stratification of CLNM in patients with PTC in clinical practice.

Safety and efficacy of microwave ablation for abdominal wall endometriosis: A retrospective study.

Objectives: This retrospective study aimed to evaluate the safety and feasibility of ultrasound-guided microwave ablation in the treatment of abdominal wall endometriosis (AWE). Background: AWE is a rare form of endometriosis that often results in cyclic abdominal pain. The current treatment algorithm for AWE is not well established. Microwave ablation technology is a promising new thermal ablation technique for treating AWE. Methods: This was a retrospective study of nine women with pathologically proven endometriosis of the abdominal wall. All patients were treated with ultrasound-guided microwave ablation. Grey-scale and color Doppler flow ultrasonography, contrast-enhanced ultrasonography, and MRI were used to observe the lesions before and after treatment. The complications, pain relief, AWE lesion volume, and volume reduction rate were recorded 12 months after treatment to evaluate the treatment efficacy. Complications were classified according to the Common Terminology Criteria for Adverse Events and the Society of Interventional Radiology classification system. Results: Contrast-enhanced ultrasound showed that all lesions underwent successful treatment with microwave ablation. The average initial nodule volume was 7.11 ± 5.75 cm3, which decreased significantly to 1.85 ± 1.02 cm3 at the 12-month follow-up with a mean volume reduction rate of 68.77 ± 12.50%. Periodic abdominal incision pain disappeared at 1 month after treatment in all nine patients. The adverse events and complications were Common Terminology Criteria for Adverse Events grade 1 or Society of Interventional Radiology classification grade A. Conclusions: Ultrasound-guided microwave ablation is a safe and effective technique for the treatment of AWE, and further study is warranted.

Evaluation of Early Diabetic Kidney Disease Using Ultrasound Localization Microscopy: A Feasibility Study.

OBJECTIVE: The purpose of this study is to detect the hemodynamic changes of microvessels in the early stage of diabetic kidney disease (DKD) and to test the feasibility of ultrasound localization microscopy (ULM) in early diagnosis of DKD. METHODS: In this study, streptozotocin (STZ) induced DKD rat model was used. Normal rats served as the control group. Conventional ultrasound, contrast-enhanced ultrasound (CEUS), and ULM data were collected and analyzed. The kidney cortex was divided into four segments, which are 0.25-0.5 mm (Segment 1), 0.5-0.75 mm (Segment 2), 0.75-1 mm (Segment 3), and 1-1.25 mm (Segment 4) away from the renal capsule, respectively. The mean blood flow velocities of arteries and veins in each segment were separately calculated, and also the velocity gradients and overall mean velocities of arteries and veins. Mann-Whitney U test was used for comparison of the data. RESULTS: Quantitative results of microvessel velocity obtained by ULM show that the arterial velocity of Segments 2, 3, and 4, and the overall mean arterial velocity of the four segments in the DKD group are significantly lower than those in the normal group. The venous velocity of Segment 3 and the overall mean venous velocity of the four segments in the DKD group are higher than those in the normal group. The arterial velocity gradient in the DKD group is lower than that in the normal group. CONCLUSION: ULM can visualize and quantify the blood flow and may be used for early diagnosis of DKD.

Evaluation of early arterial wall lesions by elastography parameters in spontaneously hypertensive rats.

BACKGROUND: Arterialsclerosis caused by hypertension can lead to many complications, such as heart attack, stroke and so on. Early diagnosis and treatment of arterialsclerosis can prevent cardiovascular and cerebrovascular diseases and improve the prognosis. The present study aimed to explore the value of ultrasonography in evaluating the early lesion of the local arterial wall in hypertensive rats and identify useful elastography parameters. METHODS: A total of 24 spontaneously hypertensive rats (SHR), 10-, 20-, 30-, and 40-weeks-old, were used in this study, with 6 rats in each group. Blood pressure was recorded using the Animal Noninvasive Blood Pressure Measurement System (Kent company, model CODA, USA), and the local elasticity of the abdominal aorta of rats was measured using a ultrasound diagnostic instrument (VINNO, Suzhou city, China). According to the histopathological results, SHR were divided into two groups: the normal arterial elasticity and the early arterial wall lesions. Mann-Whitney U test was used to compare the differences in elastic parameters and influencing factors between the above two groups, and receiver operating characteristic curve (ROC) was used to analyze and judge the value of each elastic parameter in evaluating early arterial lesions. RESULTS: A total of 22 cases were divided into two groups: 14 in the normal arterial elasticity and 8 in the early arterial wall lesions. The differences in age, blood pressure, pulse wave velocity (PWV), compliance coefficient (CC), distensibility coefficient (DC), and elasticity parameter (EP) between the two groups were compared. The differences in PWV, CC, DC and EP were statistically significant. Subsequently, the ROC curve analysis was performed for the above four evaluation indexes of arterial elasticity; the results were as follows: the area under the curve of PWV, CC, DC, and EP was 0.946, 0.781, 0.946, and 0.911, respectively. CONCLUSIONS: Early arterial wall lesions can be evaluated by ultrasound measurement of local PWV. PWV and DC can accurately evaluate the early arterial wall lesions in SHR, and the combined application of the two can improve the sensitivity and specificity of the approach.

Excessive iodine induces thyroid follicular epithelial cells apoptosis by activating HIF-1α-mediated hypoxia pathway in Hashimoto thyroiditis.

BACKGROUND: Hashimoto thyroiditis (HT) is considered the most common autoimmune thyroid disease. A growing body of evidence suggests that HT incidence correlates with excessive iodine intake. We should probe the effects of excessive iodine intake in HT development and its possible mechanism. METHODS AND RESULTS: The study recruited 20 patients: 10 with HT and 10 with nodular goiter. We detected the expression of an apoptosis-related protein caspase-3 by immunohistochemistry. In vitro study, we explored the proliferation and apoptosis status in thyroid follicular cells (TFCs) stimulated with different iodine concentrations by MTT and flow cytometry. Then we performed RNA sequence analysis of Nthy-ori3-1 cells treated for 48 h with KI to probe the underlying mechanism. Finally, we used RT-PCR and siRNA interference to verify the results. We identified apoptosis in thyroid tissue obtained from HT patients coincides with the increase of caspase-3 levels. In vitro study, iodine suppressed proliferation of TFCs and promoted TFCs apoptosis in a dose-dependent manner with regulating caspase-3 activation. HIF-1α-NDRG1 mediated hypoxia pathway activation promoted the transmission of essential apoptosis signals in TFCs. CONCLUSION: Our study confirmed that excessive iodine adsorption activates the HIF-1α-mediated hypoxia pathway to promote apoptosis of TFCs, which may be an important risk factor contributing to HT development.

Virtual elastography ultrasound via generative adversarial network for breast cancer diagnosis.

Elastography ultrasound (EUS) imaging is a vital ultrasound imaging modality. The current use of EUS faces many challenges, such as vulnerability to subjective manipulation, echo signal attenuation, and unknown risks of elastic pressure in certain delicate tissues. The hardware requirement of EUS also hinders the trend of miniaturization of ultrasound equipment. Here we show a cost-efficient solution by designing a deep neural network to synthesize virtual EUS (V-EUS) from conventional B-mode images. A total of 4580 breast tumor cases were collected from 15 medical centers, including a main cohort with 2501 cases for model establishment, an external dataset with 1730 cases and a portable dataset with 349 cases for testing. In the task of differentiating benign and malignant breast tumors, there is no significant difference between V-EUS and real EUS on high-end ultrasound, while the diagnostic performance of pocket-sized ultrasound can be improved by about 5% after V-EUS is equipped.

Deep learning diagnostic performance and visual insights in differentiating benign and malignant thyroid nodules on ultrasound images.

This study aims to construct and evaluate a deep learning model, utilizing ultrasound images, to accurately differentiate benign and malignant thyroid nodules. The objective includes visualizing the model's process for interpretability and comparing its diagnostic precision with a cohort of 80 radiologists. We employed ResNet as the classification backbone for thyroid nodule prediction. The model was trained using 2096 ultrasound images of 655 distinct thyroid nodules. For performance evaluation, an independent test set comprising 100 cases of thyroid nodules was curated. In addition, to demonstrate the superiority of the artificial intelligence (AI) model over radiologists, a Turing test was conducted with 80 radiologists of varying clinical experience. This was meant to assess which group of radiologists' conclusions were in closer alignment with AI predictions. Furthermore, to highlight the interpretability of the AI model, gradient-weighted class activation mapping (Grad-CAM) was employed to visualize the model's areas of focus during its prediction process. In this cohort, AI diagnostics demonstrated a sensitivity of 81.67%, a specificity of 60%, and an overall diagnostic accuracy of 73%. In comparison, the panel of radiologists on average exhibited a diagnostic accuracy of 62.9%. The AI's diagnostic process was significantly faster than that of the radiologists. The generated heat-maps highlighted the model's focus on areas characterized by calcification, solid echo and higher echo intensity, suggesting these areas might be indicative of malignant thyroid nodules. Our study supports the notion that deep learning can be a valuable diagnostic tool with comparable accuracy to experienced senior radiologists in the diagnosis of malignant thyroid nodules. The interpretability of the AI model's process suggests that it could be clinically meaningful. Further studies are necessary to improve diagnostic accuracy and support auxiliary diagnoses in primary care settings.

A radiomics nomogram for the ultrasound-based evaluation of central cervical lymph node metastasis in papillary thyroid carcinoma.

Purpose: To develop and validate a radiomics nomogram based on ultrasound (US) to predict central cervical lymph node (LN) metastasis in patients with papillary thyroid carcinoma (PTC). Methods: PTC patients with pathologically confirmed presence or absence of central cervical LN metastasis in our hospital between March 2021 and November 2021 were enrolled as the training cohort. Radiomics features were extracted from the preoperative US images, and a radiomics signature was constructed. Univariate and multivariate logistic regression analyses were used to screen out the independent risk factors, and a radiomics nomogram was established. The performance of the model was verified in the independent test cohort of PTC patients who underwent thyroidectomy and cervical LN dissection in our hospital from December 2021 to March 2022. Results: In the independent test cohort, the radiomics model based on long-axis cross-section and short-axis cross-section images outperformed the radiomics models based on either one of these sections (the area under the curve (AUC), 0.69 vs. 0.62 and 0.66). The radiomics signature consisted of 4 selected features. The US radiomics nomogram included the radiomics signature, age, gender, BRAF V600E mutation status, and extrathyroidal extension (ETE) status. In the independent test cohort, the AUC of the receiver operating curve(ROC) of this nomogram was 0.76, outperformingthe clinical model and the radiomics model (0.63 and 0.69, respectively), and also much better than preoperative US examination (AUC, 0.60). Decision curve analysis indicated that the radiomics nomogram was clinically useful. Conclusions: This study presents an efficient and useful US radiomics nomogram that can provide comprehensive information to assist clinicians in the individualized preoperative prediction of central cervical LN metastasis in PTC patients.

HIF-1α and Caspase-3 expression in aggressive papillary thyroid carcinoma.

BACKGROUND: Tumor cells adapt to hypoxia by regulating transcription factors that involved in regulation of metabolism, angiogenesis, cell proliferation, and apoptosis. Under hypoxic conditions, hypoxia-inducible factor-1 (HIF-1), consisting of HIF-1α and HIF-1ß subunits, acts as a key transcription factor mediating the adaptive cellular responses. Caspase-3 is a key apoptosis-related protease that plays a role in tumor growth and development. Studies have shown that caspase-3 could be regulated by HIF-1α under pathological conditions. Therefore, HIF-1α and caspase-3 expression may be related to the poor prognosis of tumors. In this study, we analyzed the possible relationships between these two signaling factors in correlation with the clinical behavior of PTC. METHODS: We detected the expression levels of HIF-1α and caspase-3 in 70 samples of PTC and para-cancerous tissues (control group) by immunohistochemistry (IHC). Furthermore, various clinicopathological parameters were assessed to determine their correlations with HIF-1α and caspase-3 expressions. RESULTS: First, HIF-1α and caspase-3 expressions (60% and 37.1%, respectively) increased significantly in the PTC samples as compared to normal tissues (2.9% for both HIF-1α and caspase-3) (p < 0.05) as determined by IHC. Second, although there was no significant difference between the expression of HIF-1α and caspase-3 in regard to gender, age distribution, tumor size, lymph node metastasis, and BRAFV600E mutation (all p > 0.05), HIF-1α and caspase-3 expressions were associated with capsule invasion and cell subtypes of PTC (p < 0.05). The percent positivity of caspase-3 expression in tall-cell variant (TCV) was the highest (63.6%). Third, HIF-1α expression was positively correlated with that of caspase-3 (rs = 0.326; p < 0.05). CONCLUSIONS: Overexpression of HIF-1α and caspase-3 is associated with carcinogenesis. These factors might serve as promising predictors of aggressive PTC. These findings also suggest their potential as therapeutic targets.

An AI model of sonographer's evaluation+ S-Detect + elastography + clinical information improves the preoperative identification of benign and malignant breast masses.

Purpose: The purpose of the study was to build an AI model with selected preoperative clinical features to further improve the accuracy of the assessment of benign and malignant breast nodules. Methods: Patients who underwent ultrasound, strain elastography, and S-Detect before ultrasound-guided biopsy or surgical excision were enrolled. The diagnosis model was built using a logistic regression model. The diagnostic performances of different models were evaluated and compared. Results: A total of 179 lesions (101 benign and 78 malignant) were included. The whole dataset consisted of a training set (145 patients) and an independent test set (34 patients). The AI models constructed based on clinical features, ultrasound features, and strain elastography to predict and classify benign and malignant breast nodules had ROC AUCs of 0.87, 0.81, and 0.79 in the test set. The AUCs of the sonographer and S-Detect were 0.75 and 0.82, respectively, in the test set. The AUC of the combined AI model with the best performance was 0.89 in the test set. The combined AI model showed a better specificity of 0.92 than the other models. The sonographer's assessment showed better sensitivity (0.97 in the test set). Conclusion: The combined AI model could improve the preoperative identification of benign and malignant breast masses and may reduce unnecessary breast biopsies.

Establishment and validation of a risk prediction model for postpartum stress urinary incontinence based on pelvic floor ultrasound and clinical data.

INTRODUCTION AND HYPOTHESIS: This study aimed to establish a risk prediction model for postpartum stress urinary incontinence (SUI) based on pelvic floor ultrasound measurement data and certain clinical data. METHODS: Singleton pregnant women aged ≥ 18 years who underwent delivery were selected. All participants were followed up to determine the symptoms of SUI, and pregnancy-related data were collected at the time of registration. Pelvic floor ultrasound was performed at 6-12 weeks postpartum to obtain ultrasonic measurement data. Logistic regression analysis was used to select predictors and establish a nomogram to predict the risk of postpartum SUI. Area under the ROC curve (AUC) values and calibration curves were used for discrimination and calibration, respectively. Finally, external verification of the model was carried out. RESULTS: A total of 255 participants were included in the analysis, comprising 105 in the postpartum SUI group and 150 in the non-SUI group. Logistic regression analysis identified age, parity, vaginal delivery, bladder neck descent (BND), and angle of internal urethral orifice funnel as risk factors for postpartum SUI (all P < 0.05). CONCLUSIONS: We constructed a prediction model for postpartum SUI based on pelvic floor ultrasound measurement data and certain clinical data. In clinical practice, this convenient and reliable tool can provide a basis for formulation of treatment strategies for patients with postpartum SUI.