Development and Validation of a Diagnostic Model for Enhancing Lesions on Breast MRI: Based on Kaiser Score.

This study aims to develop and validate a new diagnostic model based on the Kaiser score for preoperative diagnosis of the malignancy probability of enhancing lesions on breast MRI. This study collected consecutive inpatient data (including imaging data, clinical data, and pathological data) from two different institutions. All patients underwent preoperative breast Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) examinations and were found to have enhancing lesions. These lesions were confirmed as benign or malignant by surgical resection or biopsy pathology (all carcinomas in situ were confirmed by pathology after surgical resection). Data from one institution were used as the training set(284 cases), and data from the other institution were used as the validation set(107 cases). The Kaiser score was directly incorporated into the diagnostic model as a single predictive variable. Other predictive variables were screened using Least Absolute Shrinkage and Selection Operator (LASSO) regression. Multivariate logistic regression was employed to integrate the Kaiser score and other selected predictive variables to construct a new diagnostic model, presented in the form of a nomogram. Receiver operating characteristic (ROC) curve, DeLong test, net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were adopted to evaluate and compare the discrimination of the diagnostic model for breast enhancing lesions based on Kaiser score (hereinafter referred to as the "breast lesion diagnostic model") and the Kaiser score alone. Calibration curves were used to assess the calibration of the breast lesion diagnostic model, and decision curve analysis (DCA) was used to evaluate the clinical efficacy of the diagnostic model and the Kaiser score. LASSO regression indicated that, besides the indicators already included in the Kaiser score system, "age", "MIP sign", "associated imaging features", and "clinical breast examination (CBE) results" were other valuable diagnostic parameters for breast enhancing lesions. In the training set, the AUCs of the breast lesion diagnostic model and the Kaiser score were 0.948 and 0.869, respectively, with a statistically significant difference (p < 0.05). In the validation set, the AUCs of the breast lesion diagnostic model and the Kaiser score were 0.956 and 0.879, respectively, with a statistically significant difference (p < 0.05). The DeLong test, NRI, and IDI showed that the breast lesion diagnostic model had a higher discrimination ability for breast enhancing lesions compared to the Kaiser score alone, with statistically significant differences (p < 0.05). The calibration curves indicated good calibration of the breast lesion diagnostic model. DCA demonstrated that the breast lesion diagnostic model had higher clinical application value, with greater net clinical benefit over a wide range of diagnostic thresholds compared to the Kaiser score. The Kaiser score-based breast lesion diagnostic model, which integrates "age," "MIP sign", "associated imaging features", and "CBE results", can be used for the preoperative diagnosis of the malignancy probability of breast enhancing lesions, and it outperforms the classic Kaiser score in terms of diagnostic performance for such lesions.

Yi X ，Wang G ，Yang Y ，Che Y ... -  《-》

Multiphases DCE-MRI Radiomics Nomogram for Preoperative Prediction of Lymphovascular Invasion in Invasive Breast Cancer.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics had been used to evaluate lymphovascular invasion (LVI) in patients with breast cancer. However, no studies had explored the associations between features from delayed phase as well as multiphases DCE-MRI and the LVI status. Thus, we aimed to develop an efficient nomogram based on multiphases DCE-MRI to predict the LVI status in invasive (IBC) breast cancer patients. A retrospective analysis was conducted on preoperative clinical, pathological, and DCE-MRI data of 173 breast cancer patients. All patients were randomly assigned into training set (n=121) and validation set (n=52) in 7:3 ratio. The clinical, pathologic, and conventional MRI characteristics were then subjected to univariate and multivariate logistic regression analysis, and the clinical risk factors with P < 0.05 in the multivariate logistic regression were used to build clinical models. Different single-phase models (early phase, peak phase, and terminal phase), as well as a multiphases model integrating radiomics features from multiple phases, were established. Furthermore, a preoperative radiomics nomogram model was constructed by combining the rad-score of the multiphases model with clinicopathologic independent risk factors. Finally, the performance of the multiphases model, clinical model, and rad-score was compared using receiver operating characteristic (ROC) curves, area under the curve (AUC) values, and decision curve analysis (DCA). The clinical utility of the rad-score was evaluated using calibration curves, and Delong test was used to compare the differences in AUC values among the different models. The axillary lymph nodes (ALN) status and Ki-67 had been identified as clinicopathologic independent predictors and a clinical model had been constructed. Image features that were extracted from the terminal phase of the DCE-MRI exhibited notably superior predictive performances compared to features from the other single phases. Particularly, in the multiphases model, terminal phase features were identified as potentially providing more predictive information. Among the nine features that were found to be associated with LVI in the multiphase model, one was derived from the early phase, two from the peak phase, and six from the terminal phase, indicating that terminal phase features contributed significantly more information towards predicting LVI. Evaluation of the nomogram performance revealed promising results in both the training set (AUCs: clinical model vs. multiphase model vs. nomogram=0.734 vs. 0.840 vs. 0.876) and the validation set (AUCs: clinical model vs. multiphase model vs. nomogram=0.765 vs. 0.753 vs. 0.832). The DCE-MRI-based radiomics model demonstrated utility in predicting LVI status, features of the terminal phase offered more valuable information particularly. The preoperative radiomics nomogram enhanced the diagnostic capability of identifying LVI status in IBC patients, and might aid clinicians in making personalized treatment decisions.

Ma Q ，Lu X ，Chen Q ，Gong H ，Lei J ... -  《-》

Comparison of Two Modern Survival Prediction Tools, SORG-MLA and METSSS, in Patients With Symptomatic Long-bone Metastases Who Underwent Local Treatment With Surgery Followed by Radiotherapy and With Radiotherapy Alone.

Survival estimation for patients with symptomatic skeletal metastases ideally should be made before a type of local treatment has already been determined. Currently available survival prediction tools, however, were generated using data from patients treated either operatively or with local radiation alone, raising concerns about whether they would generalize well to all patients presenting for assessment. The Skeletal Oncology Research Group machine-learning algorithm (SORG-MLA), trained with institution-based data of surgically treated patients, and the Metastases location, Elderly, Tumor primary, Sex, Sickness/comorbidity, and Site of radiotherapy model (METSSS), trained with registry-based data of patients treated with radiotherapy alone, are two of the most recently developed survival prediction models, but they have not been tested on patients whose local treatment strategy is not yet decided. (1) Which of these two survival prediction models performed better in a mixed cohort made up both of patients who received local treatment with surgery followed by radiotherapy and who had radiation alone for symptomatic bone metastases? (2) Which model performed better among patients whose local treatment consisted of only palliative radiotherapy? (3) Are laboratory values used by SORG-MLA, which are not included in METSSS, independently associated with survival after controlling for predictions made by METSSS? Between 2010 and 2018, we provided local treatment for 2113 adult patients with skeletal metastases in the extremities at an urban tertiary referral academic medical center using one of two strategies: (1) surgery followed by postoperative radiotherapy or (2) palliative radiotherapy alone. Every patient's survivorship status was ascertained either by their medical records or the national death registry from the Taiwanese National Health Insurance Administration. After applying a priori designated exclusion criteria, 91% (1920) were analyzed here. Among them, 48% (920) of the patients were female, and the median (IQR) age was 62 years (53 to 70 years). Lung was the most common primary tumor site (41% [782]), and 59% (1128) of patients had other skeletal metastases in addition to the treated lesion(s). In general, the indications for surgery were the presence of a complete pathologic fracture or an impending pathologic fracture, defined as having a Mirels score of ≥ 9, in patients with an American Society of Anesthesiologists (ASA) classification of less than or equal to IV and who were considered fit for surgery. The indications for radiotherapy were relief of pain, local tumor control, prevention of skeletal-related events, and any combination of the above. In all, 84% (1610) of the patients received palliative radiotherapy alone as local treatment for the target lesion(s), and 16% (310) underwent surgery followed by postoperative radiotherapy. Neither METSSS nor SORG-MLA was used at the point of care to aid clinical decision-making during the treatment period. Survival was retrospectively estimated by these two models to test their potential for providing survival probabilities. We first compared SORG to METSSS in the entire population. Then, we repeated the comparison in patients who received local treatment with palliative radiation alone. We assessed model performance by area under the receiver operating characteristic curve (AUROC), calibration analysis, Brier score, and decision curve analysis (DCA). The AUROC measures discrimination, which is the ability to distinguish patients with the event of interest (such as death at a particular time point) from those without. AUROC typically ranges from 0.5 to 1.0, with 0.5 indicating random guessing and 1.0 a perfect prediction, and in general, an AUROC of ≥ 0.7 indicates adequate discrimination for clinical use. Calibration refers to the agreement between the predicted outcomes (in this case, survival probabilities) and the actual outcomes, with a perfect calibration curve having an intercept of 0 and a slope of 1. A positive intercept indicates that the actual survival is generally underestimated by the prediction model, and a negative intercept suggests the opposite (overestimation). When comparing models, an intercept closer to 0 typically indicates better calibration. Calibration can also be summarized as log(O:E), the logarithm scale of the ratio of observed (O) to expected (E) survivors. A log(O:E) > 0 signals an underestimation (the observed survival is greater than the predicted survival); and a log(O:E) < 0 indicates the opposite (the observed survival is lower than the predicted survival). A model with a log(O:E) closer to 0 is generally considered better calibrated. The Brier score is the mean squared difference between the model predictions and the observed outcomes, and it ranges from 0 (best prediction) to 1 (worst prediction). The Brier score captures both discrimination and calibration, and it is considered a measure of overall model performance. In Brier score analysis, the "null model" assigns a predicted probability equal to the prevalence of the outcome and represents a model that adds no new information. A prediction model should achieve a Brier score at least lower than the null-model Brier score to be considered as useful. The DCA was developed as a method to determine whether using a model to inform treatment decisions would do more good than harm. It plots the net benefit of making decisions based on the model's predictions across all possible risk thresholds (or cost-to-benefit ratios) in relation to the two default strategies of treating all or no patients. The care provider can decide on an acceptable risk threshold for the proposed treatment in an individual and assess the corresponding net benefit to determine whether consulting with the model is superior to adopting the default strategies. Finally, we examined whether laboratory data, which were not included in the METSSS model, would have been independently associated with survival after controlling for the METSSS model's predictions by using the multivariable logistic and Cox proportional hazards regression analyses. Between the two models, only SORG-MLA achieved adequate discrimination (an AUROC of > 0.7) in the entire cohort (of patients treated operatively or with radiation alone) and in the subgroup of patients treated with palliative radiotherapy alone. SORG-MLA outperformed METSSS by a wide margin on discrimination, calibration, and Brier score analyses in not only the entire cohort but also the subgroup of patients whose local treatment consisted of radiotherapy alone. In both the entire cohort and the subgroup, DCA demonstrated that SORG-MLA provided more net benefit compared with the two default strategies (of treating all or no patients) and compared with METSSS when risk thresholds ranged from 0.2 to 0.9 at both 90 days and 1 year, indicating that using SORG-MLA as a decision-making aid was beneficial when a patient's individualized risk threshold for opting for treatment was 0.2 to 0.9. Higher albumin, lower alkaline phosphatase, lower calcium, higher hemoglobin, lower international normalized ratio, higher lymphocytes, lower neutrophils, lower neutrophil-to-lymphocyte ratio, lower platelet-to-lymphocyte ratio, higher sodium, and lower white blood cells were independently associated with better 1-year and overall survival after adjusting for the predictions made by METSSS. Based on these discoveries, clinicians might choose to consult SORG-MLA instead of METSSS for survival estimation in patients with long-bone metastases presenting for evaluation of local treatment. Basing a treatment decision on the predictions of SORG-MLA could be beneficial when a patient's individualized risk threshold for opting to undergo a particular treatment strategy ranged from 0.2 to 0.9. Future studies might investigate relevant laboratory items when constructing or refining a survival estimation model because these data demonstrated prognostic value independent of the predictions of the METSSS model, and future studies might also seek to keep these models up to date using data from diverse, contemporary patients undergoing both modern operative and nonoperative treatments. Level III, diagnostic study.

Lee CC ，Chen CW ，Yen HK ，Lin YP ，Lai CY ，Wang JL ，Groot OQ ，Janssen SJ ，Schwab JH ，Hsu FM ，Lin WH ... -  《-》

Diagnostic performance of the Kaiser score for contrast-enhanced mammography and magnetic resonance imaging in breast masses: A Comparative Study.

The Kaiser score (KS) is a simple and intuitive machine-learning derived decision rule for characterizing breast lesions in a clinical setting and screening for breast cancer. The present study aims to investigate the applicability of the KS for contrast-enhanced mammography (CEM) in breast masses, and to compare its diagnostic accuracy with magnetic resonance imaging (MRI). CEM may provide an alternative option for patients with breast masses, especially for those with MRI contraindications. Two hundred and seventy-five patients with breast enhanced masses were included in the study from May 2019 to September 2022. Patients were further divided into benign and malignant groups based on pathological diagnosis. The CEM and MRI imaging characteristics of these two groups were analyzed statistically. The paired chi-square and Cohen's kappa coefficient (κ) analysis were used to compare imaging characteristics between CEM and MRI. The Breast Imaging Reporting and Data System (BI-RADS) and KS for CEM and MRI were evaluated based on imaging characteristics. The diagnostic performance of BI-RADS and KS for CEM and MRI was assessed and compared using receiver operating characteristic (ROC) analysis and DeLong's test. The imaging characteristics of root sign, time-signal intensity curve (TIC/mTIC), margin, internal enhancement pattern (IEP), edema, apparent diffusion coefficient (ADC) values, and suspicious malignant microcalcifications showed significant differences between benign and malignant lesions (all p ≤ 0.011). The detection rate of root sign and margin showed substantial agreement between CEM and MRI (κ = 0.656, κ = 0.640), but IEP, TIC/mTIC, and edema showed poor agreement (κ = 0.380, κ = 0.320, κ = 0.324). For all lesion analyses, the area under the curves (AUCs) of the KS (0.897 ∼ 0.932) were higher than that of BI-RADS (0.691) in CEM (all p < 0.001). The AUC of KS (calcification)-CEM (0.932) was higher than those of both KS-CEM and KS (edema)-CEM (0.897 and 0.899) (all p < 0.001). For subgroup analyses, the AUCs of the KS (0.875 ∼ 0.876) were higher than that of BI-RADS (0.740) in MRI (all p < 0.001). The AUCs of KS-MRI (0.876) and KS (ADC)-MRI (0.875) were similar to those of KS-CEM (0.878) and KS (edema)-CEM (0.870) (all p > 0.100). The AUC of KS (calcification)-CEM (0.934) was slightly higher than those of both KS-MRI (0.876) and KS (ADC)-MRI (0.875), but no significant difference was observed (p = 0.051; p = 0.071). The KS for CEM provided high diagnostic accuracy in distinguishing breast masses, comparable to that of MRI. The application of KS (calcification)-CEM combined with suspicious malignant microcalcifications can improve diagnostic efficiency with an AUC of 0.932 ∼ 0.934. However, edema did not significantly improve performance when using the KS for CEM.

Hua B ，Yang G ，Wang Y ，Chen J ，Rong X ，Yuan T ，Quan G ... -  《-》

Defining the optimum strategy for identifying adults and children with coeliac disease: systematic review and economic modelling.

Elwenspoek MM ，Thom H ，Sheppard AL ，Keeney E ，O'Donnell R ，Jackson J ，Roadevin C ，Dawson S ，Lane D ，Stubbs J ，Everitt H ，Watson JC ，Hay AD ，Gillett P ，Robins G ，Jones HE ，Mallett S ，Whiting PF ... -  《-》