Deciphering the tumour microenvironment of clear cell renal cell carcinoma: Prognostic insights from programmed death genes using machine learning.

Clear cell renal cell carcinoma (ccRCC), a prevalent kidney cancer form characterised by its invasiveness and heterogeneity, presents challenges in late-stage prognosis and treatment outcomes. Programmed cell death mechanisms, crucial in eliminating cancer cells, offer substantial insights into malignant tumour diagnosis, treatment and prognosis. This study aims to provide a model based on 15 types of Programmed Cell Death-Related Genes (PCDRGs) for evaluating immune microenvironment and prognosis in ccRCC patients. ccRCC patients from the TCGA and arrayexpress cohorts were grouped based on PCDRGs. A combination model using Lasso and SuperPC was constructed to identify prognostic gene features. The arrayexpress cohort validated the model, confirming its robustness. Immune microenvironment analysis, facilitated by PCDRGs, employed various methods, including CIBERSORT. Drug sensitivity analysis guided clinical treatment decisions. Single-cell data enabled Programmed Cell Death-Related scoring, subsequent pseudo-temporal and cell-cell communication analyses. A PCDRGs signature was established using TCGA-KIRC data. External validation in the arrayexpress cohort underscored the model's superiority over traditional clinical features. Furthermore, our single-cell analysis unveiled the roles of PCDRG-based single-cell subgroups in ccRCC, both in pseudo-temporal progression and intercellular communication. Finally, we performed CCK-8 assay and other experiments to investigate csf2. In conclusion, these findings reveal that csf2 inhibit the growth, infiltration and movement of cells associated with renal clear cell carcinoma. This study introduces a PCDRGs prognostic model benefiting ccRCC patients while shedding light on the pivotal role of programmed cell death genes in shaping the immune microenvironment of ccRCC patients.

Evaluation of standard breast ultrasonography by adding two-dimensional and three-dimensional shear wave elastography: a prospective, multicenter trial.

OBJECTIVE: To reduce the number of biopsies performed on benign breast lesions categorized as BI-RADS 4-5, we investigated the diagnostic performance of combined two-dimensional and three-dimensional shear wave elastography (2D + 3D SWE) with standard breast ultrasonography (US) for the BI-RADS assessment of breast lesions. METHODS: A total of 897 breast lesions, categorized as BI-RADS 3-5, were subjected to standard breast US and supplemented by 2D SWE only and 2D + 3D SWE analysis. Based on the malignancy rate of less than 2% for BI-RADS 3, lesions assessed by standard breast US were reclassified with SWE assessment. RESULTS: After standard breast US evaluation, 268 (46.1%) participants underwent benign biopsies in BI-RADS 4-5 lesions. By using separated cutoffs for upstaging BI-RADS 3 at 120 kPa and downstaging BI-RADS 4a at 90 kPa in 2D + 3D SWE reclassification, 123 (21.2%) participants underwent benign biopsy, resulting in a 54.1% reduction (123 versus 268). CONCLUSION: Combining 2D + 3D SWE with standard breast US for reclassification of BI-RADS lesions may achieve a reduction in benign biopsies in BI-RADS 4-5 lesions without sacrificing sensitivity unacceptably. CLINICAL RELEVANCE STATEMENT: Combining 2D + 3D SWE with US effectively reduces benign biopsies in breast lesions with categories 4-5, potentially improving diagnostic accuracy of BI-RADS assessment for patients with breast lesions. TRIAL REGISTRATION: ChiCTR1900026556 KEY POINTS: • Reduce benign biopsy is necessary in breast lesions with BI-RADS 4-5 category. • A reduction of 54.1% on benign biopsies in BI-RADS 4-5 lesions was achieved using 2D + 3D SWE reclassification. • Adding 2D + 3D SWE to standard breast US improved the diagnostic performance of BI-RADS assessment on breast lesions: specificity increased from 54 to 79%, and PPV increased from 54 to 71%, with slight loss in sensitivity (97.2% versus 98.7%) and NPV (98.1% versus 98.7%).

Two-stage CNNs for computerized BI-RADS categorization in breast ultrasound images.

BACKGROUND: Quantizing the Breast Imaging Reporting and Data System (BI-RADS) criteria into different categories with the single ultrasound modality has always been a challenge. To achieve this, we proposed a two-stage grading system to automatically evaluate breast tumors from ultrasound images into five categories based on convolutional neural networks (CNNs). METHODS: This new developed automatic grading system was consisted of two stages, including the tumor identification and the tumor grading. The constructed network for tumor identification, denoted as ROI-CNN, can identify the region contained the tumor from the original breast ultrasound images. The following tumor categorization network, denoted as G-CNN, can generate effective features for differentiating the identified regions of interest (ROIs) into five categories: Category "3", Category "4A", Category "4B", Category "4C", and Category "5". Particularly, to promote the predictions identified by the ROI-CNN better tailor to the tumor, refinement procedure based on Level-set was leveraged as a joint between the stage and grading stage. RESULTS: We tested the proposed two-stage grading system against 2238 cases with breast tumors in ultrasound images. With the accuracy as an indicator, our automatic computerized evaluation for grading breast tumors exhibited a performance comparable to that of subjective categories determined by physicians. Experimental results show that our two-stage framework can achieve the accuracy of 0.998 on Category "3", 0.940 on Category "4A", 0.734 on Category "4B", 0.922 on Category "4C", and 0.876 on Category "5". CONCLUSION: The proposed scheme can extract effective features from the breast ultrasound images for the final classification of breast tumors by decoupling the identification features and classification features with different CNNs. Besides, the proposed scheme can extend the diagnosing of breast tumors in ultrasound images to five sub-categories according to BI-RADS rather than merely distinguishing the breast tumor malignant from benign.

[The perfusion pattern of lymphadenopathy in contrast-enhanced ultrasonograph. under different reference conditions ].

OBJECTIVE: To determine the perfusion pattern of lymphadenopathy in contrast-enhanced ultrasonography (CEUS) under different reference conditions. METHODS: The CEUS perfusion patterns of 78 superficial lymph node lesions were compared with their pathology results. Time-intensity curves were used for comparison between benign and malignant lymph nodes. RESULTS: Inhomogeneous hyperenhancement was the main perfusion pattern (7/17, 41. 2%) in metastatic lymph nodes; compared with homogeneous hyperenhancement (2/4, 50. 0%) in lymphoma, homogeneous hyperenhancement and isoenhancement (6/52, 11. 5%) in reactive lymph nodes, and circle enhancement (2/4,50. 0%) in tuberculosis. Benign lymph nodes showed different mean value, peak intensity and area under the curve compared with their surrounding arteries (P<0. 05). But the differences in mean value, rise time, time to peak, peak intensity and the area under the curve between benign lymphadenopathy and their surrounding tissues were not statistically significant (P>0. 05). Malignant lymph nodes showed different mean value and peak intensity compared with their surrounding arteries and tissues (P<0. 05). The differences in time to peak between malignant lymph nodes and their surrounding tissues were also statistically significant (P< 0. 05). CONCLUSION: Different CEUS perfusion patterns are associated with different types of lymph node lesions. Time intensity curves with surrounding tissues as reference condition offer great values for the differential diagnosis of superficial lymphadenopathy.

[Sonography of male breast lesions and the pathological diagnosis: a retrospective study of 10 years and literature review].

The sonographic features of male breast lesions, which underwent ultrasound examination in our hospital for the past 10 years, were retrospectively analyzed. Sonographic features of these lesions were standardized as BI RADS image lexicon. The differences in ultrasonic malignant signs were assessed between the benign and the malig nant diseases. Between the two groups, incomplete boundary was statistically different. The specificity was above 95% within the two groups in terms of speculated margin, echogenic halo, calcification, axillary lymphadenopathy, thickening of skin and eccentric of mass to the nipple. High-frequency sonographic examination has a high level of differential diagnosis for male breast lesions.

Ultrasound deep learning radiomics and clinical machine learning models to predict low nuclear grade, ER, PR, and HER2 receptor status in pure ductal carcinoma in situ.

Background: Low nuclear grade ductal carcinoma in situ (DCIS) patients can adopt proactive management strategies to avoid unnecessary surgical resection. Different personalized treatment modalities may be selected based on the expression status of molecular markers, which is also predictive of different outcomes and risks of recurrence. DCIS ultrasound findings are mostly non mass lesions, making it difficult to determine boundaries. Currently, studies have shown that models based on deep learning radiomics (DLR) have advantages in automatic recognition of tumor contours. Machine learning models based on clinical imaging features can explain the importance of imaging features. Methods: The available ultrasound data of 349 patients with pure DCIS confirmed by surgical pathology [54 low nuclear grade, 175 positive estrogen receptor (ER+), 163 positive progesterone receptor (PR+), and 81 positive human epidermal growth factor receptor 2 (HER2+)] were collected. Radiologists extracted ultrasonographic features of DCIS lesions based on the 5th Edition of Breast Imaging Reporting and Data System (BI-RADS). Patient age and BI-RADS characteristics were used to construct clinical machine learning (CML) models. The RadImageNet pretrained network was used for extracting radiomics features and as an input for DLR modeling. For training and validation datasets, 80% and 20% of the data, respectively, were used. Logistic regression (LR), support vector machine (SVM), random forest (RF), and eXtreme Gradient Boosting (XGBoost) algorithms were performed and compared for the final classification modeling. Each task used the area under the receiver operating characteristic curve (AUC) to evaluate the effectiveness of DLR and CML models. Results: In the training dataset, low nuclear grade, ER+, PR+, and HER2+ DCIS lesions accounted for 19.20%, 65.12%, 61.21%, and 30.19%, respectively; the validation set, they consisted of 19.30%, 62.50%, 57.14%, and 30.91%, respectively. In the DLR models we developed, the best AUC values for identifying features were 0.633 for identifying low nuclear grade, completed by the XGBoost Classifier of ResNet50; 0.618 for identifying ER, completed by the RF Classifier of InceptionV3; 0.755 for identifying PR, completed by the XGBoost Classifier of InceptionV3; and 0.713 for identifying HER2, completed by the LR Classifier of ResNet50. The CML models had better performance than DLR in predicting low nuclear grade, ER+, PR+, and HER2+ DCIS lesions. The best AUC values by classification were as follows: for low nuclear grade by RF classification, AUC: 0.719; for ER+ by XGBoost classification, AUC: 0.761; for PR+ by XGBoost classification, AUC: 0.780; and for HER2+ by RF classification, AUC: 0.723. Conclusions: Based on small-scale datasets, our study showed that the DLR models developed using RadImageNet pretrained network and CML models may help predict low nuclear grade, ER+, PR+, and HER2+ DCIS lesions so that patients benefit from hierarchical and personalized treatment.

Unexpected breast cancer mimicking benign lesions on ultrasound-guided vacuum-assisted excision biopsy: A retrospective cross-sectional study over a 20-year period.

Objectives: This study investigated the occurrence rate of unexpected breast cancer (UEBC) mimicking benign lesions [Breast Imaging Reporting and Data System (BI-RADS) category 3 or 4a] using ultrasound-guided vacuum-assisted excision biopsy (US-VAEB), and explored the factors responsible for late diagnosis of T2 stage UEBC. Materials and methods: We collected clinicopathologic data and preoperative US imaging features within 3 months before US-VAEB of patients who were diagnosed with UEBC from January 2002 to September 2022. The UEBC were divided into T1 and T2 stageUEBC. The US imaging features as well as clinical and pathological information of T1 and T2 stage UEBC were compared to explore the factors responsible for late diagnosis of T2 stage UEBC. Results: Breast cancer was diagnosed in 91 of 19 306 patients who underwent US-VAEB. We excluded eight patients with breast cancer assigned to BI-RADS 4b category by preoperative US, and two for whom US imaging records were unavailable. Finally, we enrolled 81 patients. The occurrence rate of UEBC after US-VAEB was 0.42%(81/19296). Of the 81 cases of UEBC, 22 were at T2 stage. The ratio of T2 stage UEBC was 27.2%. The differences in risk factor of breast cancer and routine breast US screening between T1 and T2 stage UEBC were significant[96.6% (57/59) vs 81.8% (18/22), 44.1% (26/59) vs 13.6% (3/22), respectively, P<0.05). Conclusion: UEBC was rarely detected by US-VAEB. Most cases of T2 stage UEBC were diagnosed late because of the absence of routine US screening and risk factors for breast cancer. Stricter clinical management regulations for breast lesions and performing regular US screening may be helpful to reduce T2 stage UEBC.

Identification and validation of neurotrophic factor-related gene signatures in glioblastoma and Parkinson's disease.

Background: Glioblastoma multiforme (GBM) is the most common cancer of the central nervous system, while Parkinson's disease (PD) is a degenerative neurological condition frequently affecting the elderly. Neurotrophic factors are key factors associated with the progression of degenerative neuropathies and gliomas. Methods: The 2601 neurotrophic factor-related genes (NFRGs) available in the Genecards portal were analyzed and 12 NFRGs with potential roles in the pathogenesis of Parkinson's disease and the prognosis of GBM were identified. LASSO regression and random forest algorithms were then used to screen the key NFRGs. The correlation of the key NFRGs with immune pathways was verified using GSEA (Gene Set Enrichment Analysis). A prognostic risk scoring system was constructed using LASSO (Least absolute shrinkage and selection operator) and multivariate Cox risk regression based on the expression of the 12 NFRGs in the GBM cohort from The Cancer Genome Atlas (TCGA) database. We also investigated differences in clinical characteristics, mutational landscape, immune cell infiltration, and predicted efficacy of immunotherapy between risk groups. Finally, the accuracy of the model genes was validated using multi-omics mutation analysis, single-cell sequencing, QT-PCR, and HPA. Results: We found that 4 NFRGs were more reliable for the diagnosis of Parkinson's disease through the use of machine learning techniques. These results were validated using two external cohorts. We also identified 7 NFRGs that were highly associated with the prognosis and diagnosis of GBM. Patients in the low-risk group had a greater overall survival (OS) than those in the high-risk group. The nomogram generated based on clinical characteristics and risk scores showed strong prognostic prediction ability. The NFRG signature was an independent prognostic predictor for GBM. The low-risk group was more likely to benefit from immunotherapy based on the degree of immune cell infiltration, expression of immune checkpoints (ICs), and predicted response to immunotherapy. In the end, 2 NFRGs (EN1 and LOXL1) were identified as crucial for the development of Parkinson's disease and the outcome of GBM. Conclusions: Our study revealed that 4 NFRGs are involved in the progression of PD. The 7-NFRGs risk score model can predict the prognosis of GBM patients and help clinicians to classify the GBM patients into high and low risk groups. EN1, and LOXL1 can be used as therapeutic targets for personalized immunotherapy for patients with PD and GBM.

Ultrasonographic Features, Nodule Size, Capsular Invasion, and Lymph Node Metastasis of Solitary Papillary Carcinoma of Thyroid Isthmus.

Objective: This retrospective study aimed to analyze the ultrasound (US) imaging features of solitary papillary thyroid carcinoma (PTC) located in the isthmus and to assess the risk factors for lymph node metastasis (LNM) and tumor capsular invasion. Methods: We included a total of 135 patients with solitary PTC located in the isthmus. All the cases underwent US, total thyroidectomy, and prophylactic central lymph node dissection. Patients' demographic and thyroid isthmus nodules' US characteristics, as well as risk factors associated with LNM and tumor capsular invasion, were analyzed. Results: It was revealed that the occurrence of LNM was higher in male patients than in female patients (P < 0.001). As risk factors, the size of PTC in the isthmus was found to be associated with LNM and tumor capsular invasion (P = 0.005 and 0.000, respectively). The area under the receiver operating characteristic curve (AUC) of the size of the isthmus PTC was 0.64 [95% confidence interval (CI) = 0.55-0.72], indicating a probability for LNM. The AUC value for tumor capsular invasion was 0.77 (95% CI: 0.68-0.83). When the threshold was set to 1.1 cm, the larger size indicated that there was a probability of occurrence of LNM with sensitivity and specificity of 47.4 and 73.7%, respectively. When the threshold was set to 0.7 cm, the larger size indicated that there was potentially a tumor capsular invasion, with sensitivity and specificity of 80.6 and 56.3%, respectively. Wider-than-tall nodules were found to be significantly different from those in LNM and tumor capsular invasion (P = 0.038 and 0.030, respectively). There were significant differences in tumor capsular invasion in extrathyroidal extension (ETE) compared with smooth or ill-defined and lobulated or irregular nodules (P = 0.017). Conclusions: This study showed that the incidence of LNM in male patients was higher than that in female ones. When a US image shows a thyroid isthmus nodule with a wider-than-tall shape, LNM and tumor capsular invasion were likely to occur. When a US image shows a thyroid isthmus nodule with an ETE, tumor capsular invasion was likely to occur. ETE and wider-than-tall may be indicators of FNA under US guidance, even though the size of thyroid isthmus nodule may be <1 cm.

Partially cystic thyroid cancer on conventional and elastographic ultrasound: a retrospective study and a machine learning-assisted system.

BACKGROUND: Thyroid carcinoma constitutes the vast majority of all thyroid cancer, most of which is the solid nodule type. No previous studies have examined combining both conventional and elastic sonography to evaluate the diagnostic performance of partially cystic thyroid cancer (PCTC). This retrospective study was designed to evaluate differentiation of PCTC from benign partially cystic nodules with a machine learning-assisted system based on ultrasound (US) and elastography. METHODS: Patients with suspicious partially cystic nodules and finally confirmed were included in the study. We performed conventional US and real-time elastography (RTE). The US features of nodules were recorded. The data set was entered into 6 machine-learning algorithms. Sensitivity, specificity, accuracy, and area under the curve (AUC) were calculated. RESULTS: A total of 177 nodules were included in this study. Among these nodules, 81 were malignant and 96 were benign. Wreath-shaped feature, micro-calcification, and strain ratio (SR) value were the most important imaging features in differential diagnosis. The random forest classifier was the best diagnostic model. CONCLUSIONS: US features of PCTC exhibited unique characteristics. Wreath-shaped partially cystic nodules, especially with the appearance of micro-calcifications and larger SR value, are more likely to be malignant. The random forest classifier might be useful to diagnose PCTC.

Semi-supervised segmentation of lesion from breast ultrasound images with attentional generative adversarial network.

BACKGROUND AND OBJECTIVE: Automatic segmentation of breast lesion from ultrasound images is a crucial module for the computer aided diagnostic systems in clinical practice. Large-scale breast ultrasound (BUS) images remain unannotated and need to be effectively explored to improve the segmentation quality. To address this, a semi-supervised segmentation network is proposed based on generative adversarial networks (GAN). METHODS: In this paper, a semi-supervised learning model, denoted as BUS-GAN, consisting of a segmentation base network-BUS-S and an evaluation base network-BUS-E, is proposed. The BUS-S network can densely extract multi-scale features in order to accommodate the individual variance of breast lesion, thereby enhancing the robustness of segmentation. Besides, the BUS-E network adopts a dual-attentive-fusion block having two independent spatial attention paths on the predicted segmentation map and leverages the corresponding original image to distill geometrical-level and intensity-level information, respectively, so that to enlarge the difference between lesion region and background, thus improving the discriminative ability of the BUS-E network. Then, through adversarial training, the BUS-GAN model can achieve higher segmentation quality because the BUS-E network guides the BUS-S network to generate more accurate segmentation maps with more similar distribution as ground truth. RESULTS: The counterpart semi-supervised segmentation methods and the proposed BUS-GAN model were trained with 2000 in-house images, including 100 annotated images and 1900 unannotated images, and tested on two different sites, including 800 in-house images and 163 public images. The results validate that the proposed BUS-GAN model can achieve higher segmentation accuracy on both the in-house testing dataset and the public dataset than state-of-the-art semi-supervised segmentation methods. CONCLUSIONS: The developed BUS-GAN model can effectively utilize the unannotated breast ultrasound images to improve the segmentation quality. In the future, the proposed segmentation method can be a potential module for the automatic breast ultrasound diagnose system, thus relieving the burden of a tedious image annotation process and alleviating the subjective influence of physicians' experiences in clinical practice. Our code will be made available on https://github.com/fiy2W/BUS-GAN.

Animal excrement: a potential biomonitor of heavy metal contamination in the marine environment.

To assess the feasibility of using animal excrement to biomonitor the extent of heavy metal contamination in the marine environment, concentrations of mercury (Hg), lead (Pb), copper (Cu) and zinc (Zn) in the fresh excrement of seabirds and marine mammals, along with other biomaterials, from the Arctic, Antarctica (West and East), and Xisha Archipelago of the South China Sea were determined. Results show that the excrement of marine animals at higher trophic levels generally contained high levels of Hg, demonstrating the biomagnification of Hg through food chains in different remote regions. Significant variations in metal accumulation in the excrements were observed among the distinctive geographical areas, with the highest Hg concentration in Xisha Archipelago and the highest Pb concentration in the Arctic, which reflects different levels of air metal pollution at various sampling locations. Concentrations of Cu in the excrements primarily correlate to the geochemical background levels in the regions. High Cu concentrations were found near the Great Wall Station in West Antarctica where a copper mineralized belt exists. No clear spatial variation pattern was found for Zn accumulation in the excrement. This study shows that animal excrement can be used as bioindicators for the level of metal contamination in the marine environment, with the advantages of easy sampling, accurate detection (i.e., with high levels of metal accumulation), and reconstructing historical metal contamination trends by long-term monitoring of sedimentary excrements.

Can continuous scans in orthogonal planes improve diagnostic performance of shear wave elastography for breast lesions?

BACKGROUND: Static shear wave elastography (SWE) is used to detect breast lesions, but slice and plane selections result in discrepancies. OBJECTIVE: To evaluate the intraobserver reproducibility of continuous SWE, and whether quantitative elasticities in orthogonal planes perform better in the differential diagnosis of breast lesions. METHOD: One hundred and twenty-two breast lesions scheduled for ultrasound-guided biopsy were recruited. Continuous SWE scans were conducted in orthogonal planes separately. Quantitative elasticities and histopathology results were collected. Reproducibility in the same plane and diagnostic performance in different planes were evaluated. RESULTS: The maximum and mean elasticities of the hardest portion, and standard deviation of whole lesion, had high inter-class correlation coefficients (0.87 to 0.95) and large areas under receiver operation characteristic curve (0.887 to 0.899). Without loss of accuracy, sensitivities had increased in orthogonal planes compared with single plane (from 73.17% up to 82.93% at most). Mean elasticity of whole lesion and lesion-to-parenchyma ratio were significantly less reproducible and less accurate. CONCLUSION: Continuous SWE is highly reproducible for the same observer. The maximum and mean elasticities of the hardest portion and standard deviation of whole lesion are most reliable. Furthermore, the sensitivities of the three parameters are improved in orthogonal planes without loss of accuracies.