Search

Purpose: To establish and verify a predictive model involving multiparameter MRI and clinical manifestations for predicting synchronous lung metastases (SLM) in osteosarcoma. Materials and Methods: Seventy-eight consecutive patients with osteosarcoma (training dataset, n = 54; validation dataset, n = 24) were enrolled in our study. MRI features were extracted from the T1‐weighted image (T1WI), T2‐weighted image (T2WI), and contrast-enhanced T1-weighted image (CE-T1WI) of each patient. Least absolute shrinkage and selection operator (LASSO) regression and multifactor logistic regression were performed to select key features and build radiomics models in conjunction with logistic regression (LR) and support vector machine (SVM) classifiers. Eight individual models based on T1WI, T2WI, CE-T1WI, T1WI+T2WI, T1WI+CE-T1WI, T2WI+CE-T1WI, T1WI+T2WI+CE-T1WI, and clinical features, as well as two combined models, were built. The area under the receiver operating characteristic curve (AUC), sensitivity and specificity were employed to assess the different models. Results: Tumor size was the most significant univariate clinical indicator (1). The AUC values of the LR predictive model based on T1WI, T2WI, CE-T1WI, T1WI+T2WI, T1WI+CE-T1WI, T2WI+CE-T1WI, and T1WI+T2WI+CE-T1WI were 0.686, 0.85, 0.87, 0.879, 0.736, 0.85, and 0.914, respectively (2). The AUC values of the SVM predictive model based on T1WI, T2WI, CE-T1WI, T1WI+T2WI, T1WI +CE-T1WI, T2WI +CE-T1WI, and T1WI+T2WI+CE-T1WI were 0.629, 0.829, 0.771, 0.879, 0.643, 0.829, and 0.929, respectively (3). The AUC values of the clinical, combined 1 (clinical and LR-radiomics) and combined 2 (clinical and SVM-radiomics) predictive models were 0.779, 0.957, and 0.943, respectively. Conclusion: The combined model exhibited good performance in predicting osteosarcoma SLM and may be helpful in clinical decision-making. [ABSTRACT FROM AUTHOR]

Objectives: To investigate the effect of different breast lesions on exposure parameters in digital mammography and to determine whether the exposure parameters can additively improve diagnostic efficiency.Methods: Craniocaudal view and mediolateral view full-field digital mammography images from 982 women with unilateral lesions (341 with malignant lesions, 189 with benign lesions, and 452 healthy women) obtained at Nanfang Hospital were reviewed. Differences in exposure parameters (tube voltage and load, breast thickness (BT), and average glandular dose (AGD)) between breasts were calculated. The relationships between parameter differences and lesion size were explored. A logistic regression model was used based on the AGD and BT differences, and the area under the receiver operating characteristic curve (AUC) was used to assess the performance of these parameters in differentiating malignant from benign and healthy subjects. Independently, data from 129 women (82 with malignant and 47 with benign lesions) treated at Sun Yat-sen Memorial Hospital were collected to validate the model.Results: Differences in tube voltage and load, BT, and AGD between breasts were significantly greater in the malignant subjects than benign (p < 0.05) and healthy subjects (p < 0.05). The AUCs for the comparisons of malignant vs. healthy subjects, malignant vs. benign subjects, and benign vs. healthy subjects were 0.77 ± 0.02, 0.72 ± 0.02, and 0.57 ± 0.02, respectively. The model combining the exposure parameters with the BI-RADS category resulted in a higher AUC (0.910 ± 0.03) compared with physician diagnosis alone (0.820 ± 0.04) for differentiating between malignant and benign lesions.Conclusions: Exposure parameters additively improved diagnostic accuracy for breast cancer and yielded more reliable results.Key Points: • Differences in kVp, mAs, BT, and AGD between breasts were significantly greater in the malignant subjects than benign and healthy subjects. • The model combining exposure parameters with the BI-RADS category resulted in a higher AUC compared with the physician's diagnosis for differentiating between malignant and benign lesions. • Exposure parameters additively improved diagnostic accuracy for breast cancer. [ABSTRACT FROM AUTHOR]

This study established an interpretable machine learning model to predict the severity of coronavirus disease 2019 (COVID-19) and output the most crucial deterioration factors. Clinical information, laboratory tests, and chest computed tomography (CT) scans at admission were collected. Two experienced radiologists reviewed the scans for the patterns, distribution, and CT scores of lung abnormalities. Six machine learning models were established to predict the severity of COVID-19. After parameter tuning and performance comparison, the optimal model was explained using Shapley Additive explanations to output the crucial factors. This study enrolled and classified 198 patients into mild (n = 162 ; 46.93 ± 14.49 years old) and severe (n = 36 ; 60.97 ± 15.91 years old) groups. The severe group had a higher temperature (37.42 ± 0.99 °C vs. 36.75 ± 0.66 °C), CT score at admission, neutrophil count, and neutrophil-to-lymphocyte ratio than the mild group. The XGBoost model ranked first among all models, with an AUC, sensitivity, and specificity of 0.924, 90.91%, and 97.96%, respectively. The early stage of chest CT, total CT score of the percentage of lung involvement, and age were the top three contributors to the prediction of the deterioration of XGBoost. A higher total score on chest CT had a more significant impact on the prediction. In conclusion, the XGBoost model to predict the severity of COVID-19 achieved excellent performance and output the essential factors in the deterioration process, which may help with early clinical intervention, improve prognosis, and reduce mortality. [ABSTRACT FROM AUTHOR]

Background: The 21-gene recurrence score (RS) testing can predict the prognosis for luminal breast cancer patients. Meanwhile, patients > 50 years with RS > 25 have improved survival with adjuvant chemotherapy. The current study aimed to develop a nomogram with routine parameters to predict RS.Methods: We included patients diagnosed with hormone receptor (HR)-positive, human epidermal growth factor receptor-2 (HER2)-negative who underwent the 21-gene RS testing and aged > 50 years. The primary outcome was high-risk RS (> 25). Univariate and multivariate analyses were performed to identify significant predictors. A predictive nomogram based on logistic model was developed and evaluated with receiver operating characteristic (ROC) curves. The nomogram was internally validated for discrimination and calibration with bootstrapping method, and externally validated in another cohort. We then assessed the nomogram in different subgroups of patients and compared it with several published models.Results: A total of 1100 patients were included. Five clinicopathological parameters were used as predictors of a high-risk RS, including tumor grade, histologic subtype, ER expression, PR expression, and Ki-67 index. The area under the curve (AUC) was 0.798 (95% CI 0.772-0.825) and optimism adjusted AUC was 0.794 (95% CI 0.781-0.822). External validation demonstrated an AUC value of 0.746 (95% CI 0.685-0.807), which had no significant difference with the training cohort (P = 0.124). Calibration plots indicated that the nomogram-predicted results were well fitted to the actual outcomes in both internal and external validation. The nomogram had better discriminate ability in patients who had tumors > 2 cm (AUC = 0.847, 95% CI 0.804-0.890). When compared with four other existing models, similar AUC was observed between our nomogram and the model constructed by discriminate Lee et al. CONCLUSIONS: We developed a user-friendly nomogram to predict the high-risk RS in luminal breast cancer patients who were older than 50 years of age, which could guide treatment decision making for those who have no access to the 21-gene RS testing. [ABSTRACT FROM AUTHOR]

Objective. To develop and evaluate a multi-path synergic fusion (MSF) deep neural network model for breast mass classification using digital breast tomosynthesis (DBT). Methods. We retrospectively collected 441 patients who had undergone DBT in which the regions of interest (ROIs) covering the malignant/benign breast mass were extracted for model training and validation. In the proposed MSF framework, three multifaceted representations of the breast mass (gross mass, overview, and mass background) are extracted from the ROIs and independently processed by a multi-scale multi-level features enforced DenseNet (MMFED). The three MMFED sub-models are finally fused at the decision level to generate the final prediction. The advantages of the MMFED over the original DenseNet, as well as different fusion strategies embedded in MSF, were comprehensively compared. Results. The MMFED was observed to be superior to the original DenseNet, and multiple channel fusions in the MSF outperformed the single-channel MMFED and double-channel fusion with the best classification scores of area under the receiver operating characteristic (ROC) curve (87.03%), Accuracy (81.29%), Sensitivity (74.57%), and Specificity (84.53%) via the weighted fusion method embedded in MSF. The decision level fusion-based MSF was significantly better (in terms of the ROC curve) than the feature concatenation-based fusion (p< 0.05), the single MMFED using a fused three-channel image (p< 0.04), and the multiple MMFED end-to-end training (p< 0.004). Conclusions. Integrating multifaceted representations of the breast mass tends to increase benign/malignant mass classification performance and the proposed methodology was verified to be a promising tool to assist in clinical breast cancer screening. [ABSTRACT FROM AUTHOR]

Objectives. To compare the differences in normalized average glandular dose (NAGD) between the breasts of healthy subjects and those of cancer patients and to determine if the NAGD difference is associated with breast cancer risk and improves breast cancer classification. Materials and Methods. Craniocaudal view and mediolateral view full-field digital mammography (FFDM) images were obtained from 1682 healthy subjects whose breasts were categorized as Breast Imaging-Reporting and Data System (BI-RADS) I or II and from 811 biopsy-confirmed unilateral breast cancer patients whose breasts on the contralateral side were category I or II. Both populations were randomized into training and test sets. Multivariate logistic regression analysis was used to build the breast cancer risk assessment model, and the area under the receiver operating characteristic curve ( A z ) was used to evaluate the model. Twenty-two breast cancer patients who were originally categorized as BI-RADS I or II for both breasts, but were diagnosed with unilateral biopsy-confirmed breast cancer subsequently, were included to validate the model. Results. The NAGD differences in both FFDM images between tumor-bearing breasts and the healthy breasts of patients were significantly higher than those in healthy subjects (P < 0.001). The model with NAGD differences had a higher A z value than the model without NAGD differences. While there was no NAGD differences between originally healthy breasts of breast cancer patients, significant NAGD differences between now tumor-bearing breasts and the then previously healthy breasts were found in both FFDM images. Conclusions. NAGD differences between both breasts can be included in the breast cancer risk assessment model to evaluate breast cancer risk. [ABSTRACT FROM AUTHOR]

Computer-aided detection (CADe) and diagnosis (CADx) system of mammographic microcalcification clusters (MCCs) is built for helping human observers to find suspicious areas of MCC and providing risk predictions of malignancy as a reference, since it is challenging and time consuming for radiologists to manually identify some subtle microcalcifications (MCs) and perform precise interpretation in mammograms. However, the performance of traditional CADe and CADx systems is not good enough, thus it is difficult to combine them into a whole system that integrates detection and diagnosis together. The purpose of this study is to develop a fully automatic computer-aided MCC detection and diagnosis system based on deep learning method. In order to detect subtle MCs accurately, a MC candidate detection system is used to obtain a great number of potential MC candidates, then a deep convolution neural network (DCNN) is trained specially to discriminate true MCs from detected MC candidates. Different from previous literatures committing to finding and selecting effective features, the proposed method replaces manual feature extraction step by using DCNN. To accelerate the training procedure of the DCNN, a neutrosophic boosting (NB) strategy is applied in the training stage. Then a density-based regional clustering method is imposed on those true MCs to form MCCs. Finally, another DCNN is employed to differentiate benign from malignant MCC lesions. For cluster-based MCC detection evaluation, a sensitivity of 90% is achieved at 0.14 false positives (FPs) per image. For case-based MCC classification evaluation, the area under the receiver operating characteristic curves (AUCs) on validation and testing sets are 0.945, 0.933 for proposed system, respectively. Our obtained results demonstrated the effectiveness of the proposed method for automated detection and classification of MCCs. [ABSTRACT FROM AUTHOR]

• The malignant group had greater kVp, mAs, CBT, and MGD compared to benign group. • Breast thickness, density and lesion size were associated with the difference in MGD. • Breast lesion type clearly influenced exposure parameters when using AEC. • Our result can be helpful in distinguishing malignancies from benign lesions. To explore lesion-specific exposure parameters on digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM) and evaluate their efficiency for breast cancer diagnosis. We reviewed the DBT and FFDM images of 492 women with unilateral breast lesions and compared the findings with a healthy group comprising the contralateral breasts of all patients. The tube voltage (kVp), tube load (mAs), compressed breast thickness (CBT), and mean glandular dose (MGD) for each image were retrieved from the DICOM metadata, and the difference in MGD between DBT and FFDM images (△MGD) was calculated. Three models were developed to discriminate breast cancer: logistic model, comprising traditional risk factors alone; FFDM model, comprising exposure parameters from FFDM images alone, and a hybrid model, comprising traditional risk factors and exposure parameters from DBT and FFDM images. Model performance was assessed in an independent dataset of 189 women by determining the area under the receiver operating characteristic curve (AUC). The malignant group showed greater kVp, mAs, CBT, and MGD values than the benign and healthy groups on both FFDM and DBT. Breast thickness, density, and lesion size were independently associated with △MGD. The hybrid model showed a significantly higher AUC value (0.78 ± 0.04) than the logistic (0.68 ± 0.05) and FFDM models (0.56 ± 0.05). The breast lesion type has an influence on exposure parameters when using automatic exposure control. Our results provide evidence for lesion-specific exposure parameters, which can be helpful in distinguishing benign lesions from malignancies. [ABSTRACT FROM AUTHOR]

Background and Objective: In recent years, an increasing number of clinical prediction models have been developed to serve clinical care. Establishing a data-driven prediction model based on large-scale electronic health record (EHR) data can provide a more empirical basis for clinical decision making. However, research on model generalization and continuous improvement is insufficiently focused, which also hinders the application and evaluation of prediction models in real clinical environments. Therefore, this study proposes a multicenter collaborative prediction model construction framework to build a prediction model with greater generalizability and continuous improvement capabilities while preserving patient data security and privacy.Materials and Methods: Based on a multicenter collaborative research network, such as the Observational Health Data Sciences and Informatics (OHDSI), a multicenter collaborative prediction model construction framework is proposed. Based on the idea of multi-source transfer learning, in each source hospital, a base classifier was trained according to the model research setting. Then, in the target hospital with missing calibration data, a prediction model was established through weighted integration of base classifiers from source hospitals based on the smoothness assumption. Moreover, a passive-aggressive online learning algorithm was used for continuous improvement of the prediction model, which can help to maintain a high predictive performance to provide reliable clinical decision-making abilities. To evaluate the proposed prediction model construction framework, a prototype system for colorectal cancer prognosis prediction was developed. To evaluate the performance of models, 70,906 patients were screened, including 70,090 from 5 US hospital-specific datasets and 816 from a Chinese hospital-specific dataset. The area under the receiver operating characteristic curve (AUC) and the estimated calibration index (ECI) were used to evaluate the discrimination and calibration of models.Results: Regarding the colorectal cancer prognosis prediction in our prototype system, compared with the reference models, our model achieved a better performance in model calibration (ECI = 9.294 [9.146, 9.441]) and a similar ability in model discrimination (AUC = 0.783 [0.780, 0.786]). Furthermore, the online learning process provided in this study can continuously improve the performance of the prediction model when patient data with specified labels arrive (the AUC value increased from 0.709 to 0.715 and the ECI value decreased from 13.013 to 9.634 after 650 patient instances with specified labels from the Chinese hospital arrived), enabling the prediction model to maintain a good predictive performance during clinical application.Conclusions: This study proposes and evaluates a multicenter collaborative prediction model construction framework that can support the construction of prediction models with better generalizability and continuous improvement capabilities without the need to aggregate multicenter patient-level data. [ABSTRACT FROM AUTHOR]

Multifaceted features decoded from mammographic images may describe various perspectives of the breast mass heterogeneity, in this study, we aimed to explore a methodology to effectively integrate multifaceted mass representations extracted from the digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM) to enhance breast cancer discrimination. A novel multi-criterion decision making-based multi-channel fusion (MDMF) framework was proposed to fuse different breast mass representations processed in multi-channels built on the deep convolutional neural network (DCNN) and the multilayer perceptron (MLP) at the decision level. A hierarchical framework (HFMM) was also developed for multi-modality images and multi-channel fusion to integrate multimodality information from DBT and FFDM. We retrospectively collected 441 patients with both DBT and FFDM, and the regions of interest (ROIs) covering the malignant, benign, and normal tissues were extracted for validation. The MDMF achieved the area under the receiver operating characteristic curve (AUC) of 93.14%, 91.30%, 97.35% (FFDM) and 93.79%, 95.16%, 99.31% (DBT) respectively for the malignant, benign and normal mass. While the HFMM further boosted the performance to AUC of malignant 94.14%, benign 95.42% and normal mass 99.56% The matthews correlation coefficient (MCC) were 73.15% and 81.02% for FFDM and DBT accomplished by MDMF, and enhanced to 81.72% when integrating the multimodality information from DBT and FFDM via the proposed HFMM. The experimental results suggested that the proposed HFMM achieved superior discriminative performance when compared with the benchmark classification algorithms and fusion architectures, rendering it a practical tool for breast mass discrimination in breast cancer screening. • A decision making-based multi-channel fusion (MDMF) framework is proposed. • Proposed framework is based on deep convolutional network and multilayer perception. • Hierarchical fusion framework (HFMM) is designed to integrate multimodality DBT and FFDM images. • The proposed methods will aid in computer aided breast cancer screening. [ABSTRACT FROM AUTHOR]