RESUMO
OBJECTIVES: To evaluate the early prevalence of anthracycline-induced cardiotoxicity (AIC) and anthracycline-induced liver injury (AILI) using T2 and T2* mapping and to explore their correlations. MATERIALS AND METHODS: The study included 17 cardiotoxic rabbits that received weekly injections of doxorubicin and magnetic resonance imaging (MRI) every 2 weeks for 10 weeks. Cardiac function and T2 and T2* values were measured on each period. Histopathological examinations for two to five rabbits were performed after each MRI scan. The earliest sensitive time and the threshold of MRI parameters for detecting AIC and AILI based on these MRI parameters were obtained. Moreover, the relationship between myocardial and liver damage was assessed. RESULTS: Early AIC could be detected by T2 mapping as early as the second week and focused on the 7th, 11th, and 12th segments of left ventricle. The cutoff value of 46.64 for the 7th segment had the best diagnostic value, with an area under the curve (of 0.767, sensitivity of 100%, and specificity of 52%. T2* mapping could detect the change in iron content for early AIC at the middle interventricular septum and AILI as early as the sixth week (p = 0.014, p = 0.027). The T2* values of the middle interventricular septum showed a significant positive association with the T2* values of the liver (r = 0.39, p = 0.002). CONCLUSION: T2 and T2* mapping showed value one-stop assessment of AIC and AILI and could obtain the earliest MRI diagnosis point and optimal parameter thresholds for these conditions. CLINICAL RELEVANCE STATEMENT: Anthracycline-induced cardiotoxicity could be detected by T2 mapping as earlier as the second week, mainly focusing on the 7th, 11th, and 12th segments of left ventricle. Combined with T2* mapping, hepatoxicity and supplementary cardiotoxicity were assessed by one-stop scan. KEY POINTS: ⢠MRI screening time of cardiotoxicity was as early as the second week with focusing on T2 values of the 7th, 11th, and 12th segments of left ventricle. ⢠T2* mapping could be used as a complement to T2 mapping to evaluate cardiotoxicity and as an effective index to detect iron change in the early stages of chemotherapy. ⢠The T2* values of the middle interventricular septum showed a significant positive association with the T2* values of the liver, indicating that iron content in the liver and heart increased with an increase in the chemotherapeutic drugs.
Assuntos
Antraciclinas , Antibióticos Antineoplásicos , Cardiotoxicidade , Doxorrubicina , Animais , Coelhos , Antraciclinas/efeitos adversos , Antibióticos Antineoplásicos/efeitos adversos , Cardiotoxicidade/diagnóstico por imagem , Cardiotoxicidade/tratamento farmacológico , Ferro , Fígado/diagnóstico por imagem , Doxorrubicina/uso terapêuticoRESUMO
BACKGROUND: Deep learning algorithms (DLAs) could enable automatic measurements of solid portions of mixed ground-glass nodules (mGGNs) in agreement with the invasive component sizes measured during pathologic examinations. However, the measurement of pure ground-glass nodules (pGGNs) based on DLAs has rarely been reported in the literature. PURPOSE: To evaluate the use of a commercially available DLA for the automatic measurement of pGGNs on computed tomography (CT). MATERIAL AND METHODS: In this retrospective study, we included 68 patients with 81 pGGNs. The maximum diameter of the nodules was manually measured by senior radiologists and automatically segmented and measured by the DLA. Agreement between the measurements by the radiologist and DLA was assessed using Bland-Altman plots, and correlations were analyzed using Pearson correlation. Finally, we evaluated the association between the radiologist and DLA measurements and the invasiveness of lung adenocarcinoma in patients with pGGNs on preoperative CT. RESULTS: The radiologist and DLA measurements exhibited good agreement with a Bland-Altman bias of 3.0%, which were clinically acceptable. The correlation between both sets of maximum diameters was also strong, with a Pearson correlation coefficient of 0.968 (P < 0.001). In addition, both sets of maximum diameters were larger in the invasive adenocarcinoma group than in the non-invasive adenocarcinoma group (P < 0.001). CONCLUSION: Automatic pGGNs measurements by the DLA were comparable with those measured manually and were closely associated with the invasiveness of lung adenocarcinoma.
Assuntos
Adenocarcinoma de Pulmão , Adenocarcinoma , Aprendizado Profundo , Neoplasias Pulmonares , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/patologia , Estudos Retrospectivos , Invasividade Neoplásica , Adenocarcinoma de Pulmão/patologia , Adenocarcinoma/patologia , Tomografia Computadorizada por Raios X/métodos , AlgoritmosRESUMO
PURPOSE: The objective of this study is to construct a computer aided diagnosis system for normal people and pneumoconiosis using X-raysand deep learning algorithms. MATERIALS AND METHODS: 1760 anonymous digital X-ray images of real patients between January 2017 and June 2020 were collected for this experiment. In order to concentrate the feature extraction ability of the model more on the lung region and restrain the influence of external background factors, a two-stage pipeline from coarse to fine was established. First, the U-Net model was used to extract the lung regions on each sides of the collection images. Second, the ResNet-34 model with transfer learning strategy was implemented to learn the image features extracted in the lung region to achieve accurate classification of pneumoconiosis patients and normal people. RESULTS: Among the 1760 cases collected, the accuracy and the area under curve of the classification model were 92.46% and 89% respectively. CONCLUSION: The successful application of deep learning in the diagnosis of pneumoconiosis further demonstrates the potential of medical artificial intelligence and proves the effectiveness of our proposed algorithm. However, when we further classified pneumoconiosis patients and normal subjects into four categories, we found that the overall accuracy decreased to 70.1%. We will use the CT modality in future studies to provide more details of lung regions.
Assuntos
Aprendizado Profundo , Diagnóstico por Computador , Pneumoconiose/diagnóstico por imagem , Adulto , Idoso , Idoso de 80 Anos ou mais , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Estudos Retrospectivos , Raios XRESUMO
Objective: In this study, we aimed to utilize computed tomography (CT)-derived radiomics and various machine learning approaches to differentiate between invasive mucinous adenocarcinoma (IMA) and invasive non-mucinous adenocarcinoma (INMA) preoperatively in solitary pulmonary nodules (SPN) ≤3 cm. Methods: A total of 538 patients with SPNs measuring ≤3 cm were enrolled, categorized into either the IMA group (n = 50) or INMA group (n = 488) based on postoperative pathology. Radiomic features were extracted from non-contrast-enhanced CT scans and identified using the least absolute shrinkage and selection operator (LASSO) algorithm. In constructing radiomics-based models, logistic regression, support vector machines, classification and regression trees, and k-nearest neighbors were employed. Additionally, a clinical model was developed, focusing on CT radiological features. Subsequently, this clinical model was integrated with the most effective radiomic model to create a combined model. Performance assessments of these models were conducted, utilizing metrics such as the area under the receiver operating characteristic curve (AUC), DeLong's test, net reclassification index (NRI), and integrated discrimination improvement (IDI). Results: The support vector machine approach showed superior predictive efficiency, with AUCs of 0.829 and 0.846 in the training and test cohorts, respectively. The clinical model had AUCs of 0.760 and 0.777 in the corresponding cohorts. The combined model had AUCs of 0.847 and 0.857 in the corresponding cohorts. Furthermore, compared to the radiomic model, the combined model significantly improved performance in both the training (DeLong test P = 0.045, NRI 0.206, IDI 0.024) and test cohorts (P = 0.029, NRI 0.125, IDI 0.032), as well as compared to the clinical model in both the training (P = 0.01, NRI 0.310, IDI 0.09) and test cohorts (P = 0.047, NRI 0.382, IDI 0.085). Conclusion: the combined model exhibited excellent performance in distinguishing between IMA and INMA in SPNs ≤3 cm.
RESUMO
Background: The identification of anthracycline-induced cardiotoxicity holds significant importance in guiding subsequent treatment strategies, and recent research has demonstrated the efficacy of cardiac magnetic resonance (CMR) global strain analysis for its diagnosis. On the other hand, it is noteworthy that abnormal global myocardial strain may exhibit a temporal delay due to different cardiac movement in each segment of the left ventricle. To address this concern, this study aims to assess the diagnostic utility of CMR segmental strain analysis as an early detection method for cardiotoxicity. Methods: A serials of CMR scans were performed in 18 adult males New Zealand rabbits at baseline time (n=15), followed by scans at week 2 (n=15), week 4 (n=9), week 6 (n=6), and week 8 (n=5) after each week's anthracycline injection. Additionally, following each CMR scan, two to three rabbits were euthanized for pathological comparison. Cardiac functional parameters, global peak strain parameters, segmental peak strain parameters of the left ventricle, and the presence of myocardial cells damage were obtained. A mixed linear model was employed to obtain the earliest CMR diagnostic time. Receiver operating characteristic (ROC) analysis was performed to get the parameter threshold indicative of cardiotoxicity. Results: The left ventricular ejection fraction decreased at week 8 (P=0.002). There were no statistical differences in global strain throughout the experiment period (P>0.05). Regarding segmental strain analysis, the peak segmental radial strain of the apical lateral wall exhibited a decrease starting from week 2 and reached its lowest point at this week (P=0.011). Conversely, peak segmental circumferential strain of the apical anterior wall showed an increase at week 2 and reached its peak at week 6 (P=0.026). The cutoff strain value by ROC analysis for these two walls were 46.285 and -16.920, with the respective areas under the curve (AUC) 0.593 [specificity =0.267, sensitivity =1.000, 95% confidence interval (CI): 0.471-0.777] and 0.764 (specificity =0.733, sensitivity =0.784, 95% CI: 0.511-0.816). Peak segmental longitudinal strain of the apical anterior and apical lateral wall showed relatively delayed changes, occurring in the 4th week (P=0.030 and P=0.048), the cutoff values for these strains were -12.415 and -15.960, with corresponding AUCs of 0.645 (specificity =0.333, sensitivity =0.955, 95% CI: 0.495-0.795) and 0.717 (specificity =0.433, sensitivity =0.955, 95% CI: 0.566-0.902), respectively. Notably, the myocardial injury was also observed at the corresponding periods. Conclusions: Based on experimental evidence, the peak segmental strain of the apical lateral and anterior wall, as determined by CMR, demonstrated an earlier detection of anthracycline-induced cardiotoxicity compared to peak global strain and cardiac function.
RESUMO
Objective: Spread through air space (STAS) is an invasive characterization of lung adenocarcinoma and is regarded as a risk factor for poor prognosis. The aim of this study is to develop a random forest model for preoperative prediction of spread through air spaces (STAS) in stage IA lung adenocarcinoma. Methods: 92 patients with stage IA lung adenocarcinoma, who underwent computed tomography (CT) scan and surgical resection, were retrospectively reviewed. Each pulmonary nodule was automatically segmented by artificial intelligence (AI) software, and its CT-based radiomics were extracted. All patients were pathologically classified into STAS-negative and STAS-positive cohorts; then, clinical pathological and CT-based radiomics were compared between the two cohorts. Finally, a prediction model for evaluating STAS status in stage IA lung adenocarcinoma was established by a random forest model. Results: Among 92 patients with stage IA lung adenocarcinoma, STAS positive was identified in 19 patients. The random forest classification model identified predictive features, including CT maximum value, consolidation to tumor ratio (CTR), 3D diameter, CT mean value, entropy, and CT minimum value. The misclassification rate of the random forest model is only 7.69%. Conclusion: The risk factors of STAS in stage IA lung adenocarcinoma can be effectively identified based on the random forest model, and the hierarchical management of characteristic risk can be effectively realized. A random forest model for predicting STAS in IA lung adenocarcinoma is simple and practical.