RESUMO
OBJECTIVE: Utilizing ultrasound radiomics, we developed a machine learning (ML) model to construct a nomogram for the non-invasive evaluation of glomerular status in diabetic kidney disease (DKD). MATERIALS AND METHODS: Patients with DKD who underwent renal biopsy were retrospectively enrolled between February 2017 and February 2023. The patients were classified into mild or moderate-severe glomerular severity based on pathological findings. All patients were randomly divided into a training (n =79) or testing cohort (n = 35). Radiomic features were extracted from ultrasound images, and a logistic regression ML algorithm was applied to construct an ultrasound radiomic model after selecting the most significant features using univariate analysis and the least absolute shrinkage and selection operator algorithm (LASSO). A clinical model was created following univariate and multivariate logistic regression analyses of the patient's clinical characteristics. Then, the clinical-radiomic model was constructed by combining rad scores and independent clinical characteristics and plotting the nomogram. The receiver operating characteristic curve (ROC) and decision curve analysis (DCA), respectively, were used to evaluate the prediction abilities of the clinical model, ultrasound-radiomics model, and clinical-radiomics model. RESULTS: A total of 114 DKD patients were included in the study, including 43 with mild glomerulopathy and 71 with moderate-severe glomerulopathy. The area under the curve (AUC) for the clinical model based on clinical features and the radiomic model based on 2D ultrasound images in the testing cohort was 0.729 and 0.761, respectively. Further, the AUC for the clinical-radiomic nomogram was constructed by combining clinical features, and the rad score was 0.850 in the testing cohort. The outcomes were better than those of both the radiomic and clinical single-model approaches. CONCLUSION: The nomogram constructed by combining ultrasound radiomics and clinical features has good performance in assessing the glomerular status of patients with DKD and will help clinicians monitor the progression of DKD.
.RESUMO
OBJECTIVE: Through machine learning (ML) analysis of the radiomics features of ultrasound extracted from patients with lupus nephritis (LN), this attempt was made to non-invasively predict the chronicity index (CI)of LN. METHODS: A retrospective collection of 136 patients with LN who had renal biopsy was retrospectively collected, and the patients were randomly divided into training set and validation set according to 7:3. Radiomics features are extracted from ultrasound images, independent factors are obtained by using LASSO dimensionality reduction, and then seven ML models were used to establish predictive models. At the same time, a clinical model and an US model were established. The diagnostic efficacy of the model is evaluated by analysis of the receiver operating characteristics (ROC) curve, accuracy, specificity, and sensitivity. The performance of the seven machine learning models was compared with each other and with clinical and US models. RESULTS: A total of 1314 radiomics features are extracted from ultrasound images, and 5 features are finally screened out by LASSO for model construction, and the average ROC of the seven ML is 0.683, among which the Xgboost model performed the best, and the AUC in the test set is 0.826 (95% CI: 0.681-0.936). For the same test set, the AUC of clinical model constructed based on eGFR is 0.560 (95% CI: 0.357-0.761), and the AUC of US model constructed based on Ultrasound parameters is 0.679 (95% CI: 0.489-0.853). The Xgboost model is significantly more efficient than the clinical and US models. CONCLUSION: ML model based on ultrasound radiomics features can accurately predict the chronic degree of LN, which can provide a valuable reference for clinicians in the treatment strategy of LN patients.
Assuntos
Lúpus Eritematoso Sistêmico , Nefrite Lúpica , Humanos , Radiômica , Estudos Retrospectivos , UltrassonografiaRESUMO
RATIONALE AND OBJECTIVES: This study aimed to determine the feasibility of using the deep learning (DL) method to determine the degree (whether myometrial invasion [MI] >50%) of MI in patients with endometrial cancer (EC) based on ultrasound (US) images. MATERIALS AND METHODS: From September 2017 to April 2023, 1289 US images of 604 patients with EC who underwent surgical resection at center 1, center 2 or center 3 were obtained and divided into a training set and an internal validation set. Ninety-five patients from center 4 and center 5 were randomly selected as the external testing set according to the same criteria as those for the primary cohort. This study evaluated three DL models trained on the training set and tested them on the validation and testing sets. The models' performance was analyzed based on accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC), and the performance of the models was subsequently compared with that of 15 radiologists. RESULTS: In the final clinical diagnosis of MI in patients with EC, EfficientNet-B6 showed the best performance in the testing set in terms of area under the curve (AUC) [0.814, 95% CI (0.746-0.882]; accuracy [0.802, 95% CI (0.733-0.855]; sensitivity [0.623]; specificity [0.879]; positive likelihood ratio (PLR) [6.750]; and negative likelihood ratio (NLR) [0.389]. The diagnostic efficacy of EfficientNet-B6 was significantly better than that of the 15 radiologists, with an average diagnostic accuracy of 0.681, average AUC of 0.678, AUC of the best performance of 0.739, accuracy of 0.716, sensitivity of 0.806, specificity 0.672, PLR2.457, and NLR 0.289. CONCLUSION: Based on the preoperative US images of patients with EC, the DL model can accurately determine the degree of endometrial MI; the performance of this model is significantly better than that of radiologists, and it can effectively assist in clinical treatment decisions.
Assuntos
Aprendizado Profundo , Neoplasias do Endométrio , Miométrio , Invasividade Neoplásica , Ultrassonografia , Humanos , Feminino , Neoplasias do Endométrio/diagnóstico por imagem , Neoplasias do Endométrio/patologia , Pessoa de Meia-Idade , Invasividade Neoplásica/diagnóstico por imagem , Ultrassonografia/métodos , Idoso , Miométrio/diagnóstico por imagem , Miométrio/patologia , Sensibilidade e Especificidade , Radiologistas , Estudos de Viabilidade , Adulto , Vagina/diagnóstico por imagem , Vagina/patologia , Estudos Retrospectivos , Idoso de 80 Anos ou maisRESUMO
Background: Synaptic transmission between neurons and glioma cells can promote glioma progression. The soluble N-ethylmaleimide-sensitive fusion factor attachment protein receptors (SNARE) play a key role in synaptic functions. We aimed to construct and validate a novel model based on the SNARE proteins to predict the prognosis and immune microenvironment of glioma. Methods: Differential expression analysis and COX regression analysis were used to identify key SRGs in glioma datasets, and we constructed a prognostic risk model based on the key SRGs. The prognostic value and predictive performance of the model were assessed in The Cancer Genome Atlas (TCGA) and Chinese glioma Genome Atlas (CGGA) datasets. Functional enrichment analysis and immune-related evaluation were employed to reveal the association of risk scores with tumor progression and microenvironment. A prognostic nomogram containing the risk score was established and assessed by calibration curves and time-dependent receiver operating characteristic curves. We verified the changes of the key SRGs in glioma specimens and cells by real-time quantitative PCR and Western blot analyses. Results: Vesicle-associated membrane protein 2 (VAMP2) and vesicle-associated membrane protein 5 (VAMP5) were identified as two SRGs affecting the prognoses of glioma patients. High-risk patients characterized by higher VAMP5 and lower VAMP2 expression had a worse prognosis. Higher risk scores were associated with older age, higher tumor grades, IDH wild-type, and 1p19q non-codeletion. The SRGs risk model showed an excellent predictive performance in predicting the prognosis in TCGA and CGGA datasets. Differentially expressed genes between low- and high-risk groups were mainly enriched in the pathways related to immune infiltration, tumor metastasis, and neuronal activity. Immune score, stromal score, estimate score, tumor mutational burden, and expression of checkpoint genes were positively correlated with risk scores. The nomogram containing the risk score showed good performance in predicting the prognosis of glioma. Low VAMP2 and high VAMP5 were found in different grades of glioma specimens and cell lines. Conclusion: We constructed and validated a novel risk model based on the expression of VAMP2 and VAMP5 by bioinformatics analysis and experimental confirmation. This model might be helpful for clinically predicting the prognosis and response to immunotherapy of glioma patients.
RESUMO
BACKGROUND: The purpose of this study was to investigate the preoperative prediction of large-number central lymph node metastasis (CLNM) in single thyroid papillary carcinoma (PTC) with negative clinical lymph nodes. METHODS: A total of 634 patients with clinically lymph node-negative single PTC who underwent thyroidectomy and central lymph node dissection at the First Affiliated Hospital of Anhui Medical University and the Nanchong Central Hospital between September 2018 and September 2021 were analyzed retrospectively. According to the CLNM status, the patients were divided into two groups: small-number (≤5 metastatic lymph nodes) and large-number (>5 metastatic lymph nodes). Univariate and multivariate analyses were used to determine the independent predictors of large-number CLNM. Simultaneously, a nomogram based on risk factors was established to predict large-number CLNM. RESULTS: The incidence of large-number CLNM was 7.7%. Univariate and multivariate analyses showed that age, tumor size, and calcification were independent risk factors for predicting large-number CLNM. The combination of the three independent predictors achieved an AUC of 0.806. Based on the identified risk factors that can predict large-number CLNM, a nomogram was developed. The analysis of the calibration map showed that the nomogram had good performance and clinical application. CONCLUSION: In patients with single PTC with negative clinical lymph nodes large-number CLNM is related to age, size, and calcification in patients with a single PTC with negative clinical lymph nodes. Surgeons and radiologists should pay more attention to patients with these risk factors. A nomogram can help guide the surgical decision for PTC.
Assuntos
Carcinoma Papilar , Neoplasias da Glândula Tireoide , Humanos , Câncer Papilífero da Tireoide , Neoplasias da Glândula Tireoide/diagnóstico por imagem , Neoplasias da Glândula Tireoide/cirurgia , Neoplasias da Glândula Tireoide/patologia , Estudos Retrospectivos , Metástase Linfática/diagnóstico por imagem , Metástase Linfática/patologia , Ultrassom , Carcinoma Papilar/diagnóstico por imagem , Carcinoma Papilar/cirurgia , Carcinoma Papilar/patologia , Linfonodos/diagnóstico por imagem , Linfonodos/patologia , Linfonodos/cirurgia , Fatores de RiscoRESUMO
Introduction: To explore whether ultrasonic radiomics extracted by machine learning method can noninvasively evaluate lupus nephritis (LN) activity. Materials and Methods: This retrospective study included 149 patients with LN diagnosed by renal biopsy. They were divided into a training cohort (n=104) and a test cohort (n=45). Ultrasonic radiomics features were extracted from the ultrasound images, and the radiomics features were constructed. Furthermore, five machine learning algorithms were compared to evaluate LN activity. The performance of the binary classification model was evaluated by the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Results: The average AUC of the five machine learning models was 79.4, of which the MLP model was the best. The AUC of the training group was 89.1, with an accuracy of 81.7%, a sensitivity of 83%, a specificity of 80.7%, a negative predictive value of 85.2%, and a positive predictive value of 78%. The AUC of the test group was 82.2, the accuracy was 73.3%, the sensitivity was 78.9%, the specificity was 69.2%, the negative predictive value was 81.8%, and the positive predictive value was 65.2%. Conclusion: Machine learning classifier based on ultrasonic radiomics has high accuracy for LN activity. The model can be used to noninvasively detect the activity of LN and can be an effective tool to assist the clinical decision-making process.
RESUMO
Objective: Distinguishing the degree of differentiation, hepatocellular carcinoma (HCC) has important clinical significance in the therapeutic decision-making and patient prognosis evaluation. Methods: We developed a deep-learning radiomics (DLR) model based on contrast-enhanced ultrasound (CEUS) to evaluate the differentiation of HCC noninvasive. We retrospectively analyzed HCC patients who had undergone resection and CEUS one week preoperatively between November 2015 and August 2022. Enrolled patients were randomly divided into training (n=190) and testing (n=82) cohorts in a 7:3 ratio. The depth of learning and radiological characteristics reflecting the differentiation degree of HCC were extracted, and the least absolute shrinkage and selection operator(LASSO) was used for feature selection to obtain the most valuable features and then build a DLR model based on the useful features. Results: The deep-learning Radiomics model could accurately predict the degree of differentiation of HCC; the area under the curve of the DLR model in the training and testing cohorts was 0.969 and 0.932, respectively. The accuracy, sensitivity, and specificity of the CEUS-based DLR model for predicting the differentiation of HCC were 0.915, 0.938, and 0.900, respectively, in the testing cohort. The decision curve analysis confirmed that the combined model predicted good overall net income for differentiation. Conclusion: The CEUS-based DLR model provides an easy-to-use, visual, and personalized tool for predicting the differentiation of HCC and can help doctors formulate more favorable treatment plans for patients.
RESUMO
Objective: We used machine-learning (ML) models based on ultrasound radiomics to construct a nomogram for noninvasive evaluation of the crescent status in immunoglobulin A (IgA) nephropathy. Methods: Patients with IgA nephropathy diagnosed by renal biopsy (n=567) were divided into training (n=398) and test cohorts (n=169). Ultrasound radiomic features were extracted from ultrasound images. After selecting the most significant features using univariate analysis and the least absolute shrinkage and selection operator algorithm, three ML algorithms were assessed for final radiomic model establishment. Next, clinical, ultrasound radiomic, and combined clinical-radiomic models were compared for their ability to detect IgA crescents. The diagnostic performance of the three models was evaluated using receiver operating characteristic curve analysis. Results: The average area under the curve (AUC) of the three ML radiomic models was 0.762. The logistic regression model performed best, with AUC values in the training and test cohorts of 0.838 and 0.81, respectively. Among the final models, the combined model based on clinical characteristics and the Rad score showed good discrimination, with AUC values in the training and test cohorts of 0.883 and 0.862, respectively. The decision curve analysis verified the clinical practicability of the combined nomogram. Conclusion: ML classifier based on ultrasound radiomics has a potential value for noninvasive diagnosis of IgA nephropathy with or without crescents. The nomogram constructed by combining ultrasound radiomic and clinical features can provide clinicians with more comprehensive and personalized image information, which is of great significance for selecting treatment strategies.
Assuntos
Glomerulonefrite por IGA , Humanos , Glomerulonefrite por IGA/diagnóstico por imagem , Nomogramas , Algoritmos , Área Sob a Curva , Imunoglobulina ARESUMO
Pyrrolizidine alkaloids (PAs) present distinct toxicity potencies depending on their metabolites and in vivo toxicokinetics. To represent the potency differences of various PAs, the interim relative potency (REP) factors have been derived. However, little is known about the risk assessment for (herbal) teas when taking REP factors into account. In this study, a set of 68 individual 1,2-unsaturated PA in 21 types of (herbal) teas was analyzed using LC-MS/MS. The REP factors for these PAs were applied on the PA levels. The margin of exposure (MOE) approach was employed to assess the risks of the exposure to PAs due to consumption of (herbal) teas. The results show that the total PA levels ranged from 13.4 to 286,682.2 µg/kg d.m., which were decreased by REP correction in most of the teas. The MOE values for tephroseris, borage and lemon balm (melissa) tea based on REP-corrected PA levels were below 10,000, assuming daily consumption of one cup of tea during a lifetime, indicating that consuming these teas may raise a concern. Our study also indicates a priority for risk management for tephroseris tea, as having nephrosis tea for more than 11.2 weeks during a 75-year lifetime would result in an MOE of 10,000.