Ultrasound-based radiomics XGBoost model to assess the risk of central cervical lymph node metastasis in patients with papillary thyroid carcinoma: Individual application of SHAP.

Objectives: A radiomics-based explainable eXtreme Gradient Boosting (XGBoost) model was developed to predict central cervical lymph node metastasis (CCLNM) in patients with papillary thyroid carcinoma (PTC), including positive and negative effects. Methods: A total of 587 PTC patients admitted at Binzhou Medical University Hospital from 2017 to 2021 were analyzed retrospectively. The patients were randomized into the training and test cohorts with an 8:2 ratio. Radiomics features were extracted from ultrasound images of the primary PTC lesions. The minimum redundancy maximum relevance algorithm and the least absolute shrinkage and selection operator regression were used to select CCLNM positively-related features and radiomics scores were constructed. Clinical features, ultrasound features, and radiomics score were screened out by the Boruta algorithm, and the XGBoost model was constructed from these characteristics. SHapley Additive exPlanations (SHAP) was used for individualized and visualized interpretation. SHAP addressed the cognitive opacity of machine learning models. Results: Eleven radiomics features were used to calculate the radiomics score. Five critical elements were used to build the XGBoost model: capsular invasion, radiomics score, diameter, age, and calcification. The area under the curve was 91.53% and 90.88% in the training and test cohorts, respectively. SHAP plots showed the influence of each parameter on the XGBoost model, including positive (i.e., capsular invasion, radiomics score, diameter, and calcification) and negative (i.e., age) impacts. The XGBoost model outperformed the radiologist, increasing the AUC by 44%. Conclusions: The radiomics-based XGBoost model predicted CCLNM in PTC patients. Visual interpretation using SHAP made the model an effective tool for preoperative guidance of clinical procedures, including positive and negative impacts.

Ultrasound-Guided Percutaneous Drainage of Iliopsoas Abscess With Septicemia in an Adolescent: A Case Report and Literature Review.

Introduction: Iliopsoas abscess with septicemia in the pediatric population is rare. Early diagnosis and effective management of this emergent disorder remain challenging for clinicians. Case Presentation: A 14-year-old girl presented with right lateral and posterior hip pain and fever for 7 days before admission. Blood culture was positive for Staphylococcus aureus. Enhanced magnetic resonance imaging revealed abscesses located in the right iliopsoas muscle and on the surface deep to the fascia of the right sacroiliac joint that were 6.8 cm × 6.2 cm × 5.7 cm and 3.7 cm × 3.5 cm × 2.1 cm, respectively. A diagnosis of right iliopsoas abscesses with septicemia was made. The patient received intravenous antibiotics, underwent ultrasound-guided percutaneous catheter drainage, and recovered uneventfully. Medical literature regarding this issue published in the English language during the last two decades was reviewed. Discussion: Primary synchronous psoas and iliacus muscle abscesses are rare and emergent disorders in the pediatric age group. The diagnosis is generally delayed owing to the deep anatomic location and nonspecific signs and symptoms. A comprehensive medical history, meticulous physical examination, and judicious use of imaging studies could establish a timely and accurate diagnosis. Surgeons should be aware of the occurrence of multiple abscesses. Prompt and adequate antibiotic therapy accompanied by a mini-invasive approach, such as ultrasound-guided, laparoscopic, or video-retroperitoneoscopic drainage of the infectious focus, if indicated and feasible, is important to achieve a good outcome in the management of iliopsoas abscess.

A Comparative Analysis of Six Machine Learning Models Based on Ultrasound to Distinguish the Possibility of Central Cervical Lymph Node Metastasis in Patients With Papillary Thyroid Carcinoma.

Current approaches to predict central cervical lymph node metastasis (CLNM) in patients with papillary thyroid carcinoma (PTC) have failed to identify patients who would benefit from preventive treatment. Machine learning has offered the opportunity to improve accuracy by comparing the different algorithms. We assessed which machine learning algorithm can best improve CLNM prediction. This retrospective study used routine ultrasound data of 1,364 PTC patients. Six machine learning algorithms were compared to predict the possibility of CLNM. Predictive accuracy was assessed by sensitivity, specificity, positive predictive value, negative predictive value, and the area under the curve (AUC). The patients were randomly split into the training (70%), validation (15%), and test (15%) data sets. Random forest (RF) led to the best diagnostic model in the test cohort (AUC 0.731 ± 0.036, 95% confidence interval: 0.664-0.791). The diagnostic performance of the RF algorithm was most dependent on the following five top-rank features: extrathyroidal extension (27.597), age (17.275), T stage (15.058), shape (13.474), and multifocality (12.929). In conclusion, this study demonstrated promise for integrating machine learning methods into clinical decision-making processes, though these would need to be tested prospectively.

Nomogram to Assess the Risk of Central Cervical Lymph Node Metastasis in Patients With Clinical N0 Papillary Thyroid Carcinoma.

OBJECTIVE: To develop and validate an individualized risk prediction model for the need for central cervical lymph node dissection in patients with clinical N0 papillary thyroid carcinoma (PTC) diagnosed using ultrasound. METHODS: Upon retrospective review, derivation and internal validation cohorts comprised 1585 consecutive patients with PTC treated from January 2017 to December 2019 at hospital A. The external validation cohort consisted of 406 consecutive patients treated at hospital B from January 2016 to June 2020. Independent risk factors for central cervical lymph node metastasis (CLNM) were determined through univariable and multivariable logistic regression analysis. An individualized risk prediction model was constructed and illustrated as a nomogram, which was internally and externally validated. RESULTS: The following risk factors of CLNM were established: a solitary primary thyroid nodule's diameter, shape, calcification, and capsular abutment-to-lesion perimeter ratio. The areas under the receiver operating characteristic curves of the risk prediction model for the internal and external validation cohorts were 0.921 and 0.923, respectively. The calibration curve showed good agreement between the nomogram-estimated probability of CLNM and the actual CLNM rates in the 3 cohorts. The decision curve analysis confirmed the clinical usefulness of the nomogram. CONCLUSION: This study developed and validated a model for predicting the risk of CLNM in individual patients with clinical N0 PTC, which should be an efficient tool for guiding clinical treatment.

Utility of lung ultrasound to identify interstitial lung disease: An observational study based on the STROBE guidelines.

ABSTRACT: Lung ultrasound (LUS) has recently been used to identify interstitial lung disease (ILD). However, data on the role of LUS in the detection of ILD remain limited. The aim of this study was to investigate the diagnostic value of LUS compared with high-resolution computed tomography (HRCT) in patients with ILD.The retrospective study was carried out by reviewing the medical records of patients with respiratory signs and symptoms discharged from the respiratory ward. Only patients with suspected ILD who underwent HRCT and LUS within a week were selected. ILD was identified with a semi-quantitative score of B-lines >5 and a Warrick score >0 points. The endpoints of LUS in diagnosing ILD (i.e., sensitivity, specificity, positive likelihood ratio [PLR], negative likelihood ratio [NLR], positive predictive value [PPV], and negative predictive value [NPV], and receiver operating characteristic [ROC] curve) was compared with that of HRCT. The reference standard used for the diagnosis of ILD was based on history, clinical findings and examination, and laboratory and instrumental tests, including pulmonary function tests, lung histopathology, and HRCT (without LUS findings).The final clinical diagnosis of ILD was 55 in 66 patients with suspected ILD. HRCT was positive in 55 patients, whereas LUS detected ILD in 51 patients. Four patients with negative LUS findings were positive on HRCT. The results showed 93% sensitivity, 73% specificity, 3.40 PLR, 0.10 NLR, 94% PPV, and 67% NPV for LUS, whereas 100% sensitivity, 82% specificity, 5.49 PLR, 0.01 NLR, 97% PPV, and 100% NPV for HRCT. Comparison of the 2 ROC curves revealed significant difference in the diagnostic value of the 2 methods for the diagnosis of ILD (P = .048).Our results indicated that LUS is a useful technique to identify ILD. Considering its non-radiation, portable and non-invasive advantages, LUS should be recommended as a valuable screening tool in patients with suspected ILD.

Correlation analysis between ultrasonography and mammography with other risk factors related to breast cancer.

Value and correlation analysis between ultrasound and mammography in the diagnosis and other risk factors related to breast cancer were explored. A total of 1,473 patients who underwent breast color ultrasonography and molybdenum target X-ray examination in Binzhou Medical University Hospital from March 2017 to August 2018 were collected, and the patient's ultrasound and mammography results were compared, also the pathological biopsy was used as the reference golden criteria to calculate the value of both test methods and the value of combined diagnosis in breast cancer. The risk factors associated with breast cancer were analyzed. Among the 1,473 patients, 387 breast cancer patients were detected by ultrasonography, 351 by mammography and 339 cases by combined diagnosis. A total of 314 cases were diagnosed as breast cancer after pathological biopsy. However, there were significant differences in tumor size, stages, and BI-RADS grades (P<0.05). There was no significant difference in the diagnostic efficacy between ultrasonography and mammography (P>0.05), however, the diagnostic efficacy of ultrasonography combined with mammography was significantly better than the two single tests (P<0.05). After logistic regression analysis, there was no significant correlation between residence address, height, blood type, ethnicity, or education with breast cancer (P>0.05). However, age, fertility status, and BMI were all risk factors related to breast cancer (OR>1; P<0.05). In conclusion, ultrasonography combined with mammography can effectively improve the early diagnosis rate of breast cancer, however, the patient's age, birth status, and BMI may affect the results of ultrasonography and mammography. In clinical practice, it is necessary to determine the imaging results in combination with the actual situation of the patients to improve the diagnosis rate of breast cancer.

Confirmed value of shear wave elastography for ultrasound characterization of breast masses using a conservative approach in Chinese women: a large-size prospective multicenter trial.

PURPOSE: This study aimed to investigate the value of shear wave elastography (SWE) for characterization of breast masses in a Chinese population. PATIENTS AND METHODS: Two thousand two hundred seventy-three women consented to be prospectively enrolled for the characterization of breast masses with ultrasound and SWE. Breast masses were known from symptoms, palpability, and/or previous imaging screening with mammography and/or ultrasound. Correlation of SWE qualitative and quantitative features with malignancy risk and impact on diagnostic performance of combining SWE features were assessed, and the Breast Imaging Reporting and Data System (BI-RADS) scoring was calculated using histopathology as reference. RESULTS: Data of 2,262 masses (median size: 13 mm; range: 1.3-50) from 2,262 patients (median age: 43 years; range: 18-91) were investigated, of which 752 (33.3%) were malignant. Sensitivity and specificity of BI-RADS diagnosis were 97.5% (733/752) and 54.8% (827/1,510), respectively. By logistic regression, the combination of maximum elasticity (E max) measurements with BI-RADS assessments increased the area under the receiver operating characteristic curve from 0.908 (95% CI: 0.896-0.920) to 0.954 (95% CI: 0.944-0.962). Using E max of 30 kPa or lower to selectively downgrade BI-RADS 4a masses to follow-up, and E max of 160 kPa or higher to selectively upgrade BI-RADS 3 lesions to biopsy, specificity significantly increased from 54.8% (827/1,510) to 66.1% (998/1,510) (P<0.001) while sensitivity decreased nonsignificantly from 97.5% (733/752) to 96.9% (729/752) (P=0.2891). Positive predictive value for biopsy recommendation increased from 51.7% (733/1,417) to 58.7% (729/1,241) (P<0.001). CONCLUSION: Adding SWE maximum stiffness to BI-RADS 3 and BI-RADS 4a breast masses in a Chinese population increased significantly the specificity of breast ultrasonography, without significant change in sensitivity.

Differential Diagnosis of Breast Category 3 and 4 Nodules Through BI-RADS Classification in Conjunction with Shear Wave Elastography.

Ultrasound (US) has become one of the important imaging methods for differentiating benign from malignant breast lesions. In 2013, the American College of Radiology published the fifth edition of the Breast Imaging-Reporting and Data System (BI-RADS). BI-RADS is a guide with recommendations for the standardization of breast imaging (US, mammography and magnetic resonance imaging) reports and for the auditing of centers employing such methods. Its objective is to standardize the nomenclature used in the reports. However, current US examinations are neither adequately sensitive nor sufficiently specific enough. The average Young's modulus was measured through shear wave elastography (SWE) to evaluate the diagnostic value of the BI-RADS classification in conjunction with SWE in differentiating BI-RADS 3 and 4 nodules. A total of 100 consecutive women with 126 breast lesions, including 65 benign and 61 malignant lesions, were included. The average Young's modulus of breast nodules and peri-nodule tissue (Emean1 and Emean2) was also determined through SWE. A receiver operating characteristic curve was drawn on the basis of pathologic results. The highest cut-off values were C1 and C2. At Emean1 > C1 or Emean2 > C2, BI-RADS 3 was increased to 4a and BI-RADS 4a was increased to 4b. At Emean1 ≤ C1 and Emean2 ≤ C2, BI-RADS 4b was decreased to 4a. Other BI-RADS classifications remained unchanged. BI-RADS 3 and 4a were considered benign. BI-RADS 4b and 4c were malignant. The area under the curve, sensitivity and specificity of the BI-RADS classification in conjunction with SWE were 0.952, 93.4% and 95.4%, respectively. The area under the curve, sensitivity and specificity of the original BI-RADS classification were 0.883, 82.0% and 87.7%, respectively. Differences were statistically significant (p = 0.028, Z-test). The diagnostic sensitivity and specificity were increased effectively. As a new method, BI-RADS classification in conjunction with SWE that combines the average Young's modulus yields a high value in terms of the differential diagnosis of breast nodules.

Assessment of Diffuse Thyroid Disease by Strain Ratio in Ultrasound Elastography.

The goal of this study was to explore the value of strain ratio from real-time elastography in the semi-quantitative assessment of diffuse thyroid disease. Fifty-one patients with primary hyperthyroidism, 70 with Hashimoto's thyroiditis, 8 with subacute thyroiditis and 43 with normal healthy thyroids were recruited to measure the strain ratio (SR) of thyroid tissue and sternocleidomastoid muscle (on the same side of the thyroid). SR values of all groups were subjected to statistical analysis. The SRs (mean ± standard deviation) of patients with hyperthyroidism, Hashimoto's thyroiditis and subacute thyroiditis were 2.30 ± 1.08, 7.04 ± 7.74 and 24.09 ± 13.56, respectively. The SR of the control group was 1.76 ± 0.54. SR values ranked in ascending order were control group < hyperthyroidism group < Hashimoto's thyroiditis group < subacute thyroiditis group. There were statistically significant (p < 0.05) differences in thyroid hardness between groups with different diffuse thyroid diseases. SR values of the hyperthyroidism and control groups did not statistically differ (p > 0.05). It is feasible to assess diffuse thyroid disease with strain ratios obtained with ultrasound elastography.

MicroRNA-486-5p targeting PIM-1 suppresses cell proliferation in breast cancer cells.

MicroRNAs (miRNAs) are emerging as critical regulators in carcinogenesis and tumor progression. Recently, miR-486-5p has been proved to play an important role in several cancers, but its functions in the context of breast cancer (BC) remain unknown. In this study, we found that miR-486-5p expression is significantly downregulated in BC tissues and cell lines. Overexpression of miR-486-5p dramatically suppressed BC cell proliferation in vitro and in vivo, induced G0/G1 arrest, and promoted apoptosis. We subsequently identified the oncogene PIM-1 as a direct target of miR-486-5p in BC. Overexpression of PIM-1 attenuated the function of miR-486-5p in BC cells. Together, we conclude that miR-486-5p exerts its antiproliferative function by directly downregulating PIM-1 expression. This novel miR-486-5p/PIM-1 axis provides insight into the pathogenesis of BC and might be therapeutic targets for prevention or treatment of BC.

Lack of efficacy of Tai Chi in improving quality of life in breast cancer survivors: a systematic review and meta-analysis.

BACKGROUND: It is controversial whether Tai Chi (TC) benefits breast cancer survivors (BCS) on quality of life (QoL). We therefore undertook a meta-analysis to assess this question. MATERIALS AND METHODS: A computerized search through electronic databases was performed to identify relevant randomized controlled trials (RCTs). The primary outcome was QoL, while secondary outcomes included body mass index (BMI), bone mineral density (BMD), and muscle strength. RESULTS: Five RCTs involving 407 patients were included in the meta-analysis. The pooled standardized mean differences were 0.10 (95% confidence interval (CI): -0.35-0.54) for physical well- being, 0.03 (95%CI: -0.18-0.25) for social/family well-being, 0.24 (95%CI: 0.02-0.45) for emotional well-being, 0.23 (95%CI: -0.03-0.49) for functional well-being, and 0.09 (95%CI: -0.19-0.36) for additional concerns. TC failed to improve BMI, BMD, and muscle strength. CONCLUSIONS: There is currently lack of sufficient evidence to support TC improving QoL and other important clinical endpoints.

Comparison of diffuse optical tomography, ultrasound elastography and mammography in the diagnosis of breast tumors.

Previous studies have reported the usefulness of diffuse optical tomography (DOT), ultrasound elastography (UE) and mammography in differentiating breast tumors. This study was aimed at evaluating and comparing DOT, UE and mammography with respect to their diagnostic performance in differentiating benign and malignant breast tumors. Of the 67 tumors, 45 were histopathologically benign, and 22 were malignant. UE was the most specific (93.33%) of the three diagnostics modalities. DOT and UE were both more accurate (80.60% and 89.55%, respectively) than mammography (63.08%). UE + mammography (93.33% and 91.04%) and DOT + mammography (77.78% and 82.09%) exhibited higher specificity and accuracy, respectively, than mammography alone (57.78% and 63.08%). Receiver operating characteristic (ROC) curves were constructed to assess the performance of the modalities. In conclusion, UE and DOT were superior to conventional mammography in terms of both specificity and accuracy. DOT and UE improve the specificity and accuracy of breast cancer diagnosis, and combining the two modalities improves the diagnostic value.

Evaluation of acoustic radiation force impulse imaging for the clinicopathological typing of renal fibrosis.

This study aimed to explore the assessment value of virtual touch quantization (VTQ) for the clinicopathological typing of renal fibrosis. The quantitative detection of 76 patients with nephropathy was performed using acoustic radiation force impulse imaging (ARFI). The extent of the renal fibrosis in each patient was confirmed using ultrasound-guided biopsy pathology. The VTQ values were compared with the degree of renal fibrosis in order to analyze the correlation between them. Patients were divided pathologically into four groups, as follows: non-fibrosis (n=14), mild fibrosis (n=40), moderate fibrosis (n=21) and severe fibrosis (n=1). Compared with the non-fibrosis group, the VTQ values of the mild and moderate fibrosis groups were significantly increased (P<0.01); however, there was no significant difference between the VTQ values of the mild and moderate fibrosis groups (P>0.05). According to the receiver operating characteristic (ROC) curve, a VTQ value of renal parenchyma of >1.67 m/sec was determined to be an indicator of renal fibrosis, with a sensitivity of 86.3% and a specificity of 83.3%. VTQ technology may be significant in the assessment of the extent of renal fibrosis.