Preoperative Differentiation of HER2-Zero and HER2-Low from HER2-Positive Invasive Ductal Breast Cancers Using BI-RADS MRI Features and Machine Learning Modeling.

BACKGROUND: Accurate determination of human epidermal growth factor receptor 2 (HER2) is important for choosing optimal HER2 targeting treatment strategies. HER2-low is currently considered HER2-negative, but patients may be eligible to receive new anti-HER2 drug conjugates. PURPOSE: To use breast MRI BI-RADS features for classifying three HER2 levels, first to distinguish HER2-zero from HER2-low/positive (Task-1), and then to distinguish HER2-low from HER2-positive (Task-2). STUDY TYPE: Retrospective. POPULATION: 621 invasive ductal cancer, 245 HER2-zero, 191 HER2-low, and 185 HER2-positive. For Task-1, 488 cases for training and 133 for testing. For Task-2, 294 cases for training and 82 for testing. FIELD STRENGTH/SEQUENCE: 3.0 T; 3D T1-weighted DCE, short time inversion recovery T2, and single-shot EPI DWI. ASSESSMENT: Pathological information and BI-RADS features were compared. Random Forest was used to select MRI features, and then four machine learning (ML) algorithms: decision tree (DT), support vector machine (SVM), k-nearest neighbors (k-NN), and artificial neural nets (ANN), were applied to build models. STATISTICAL TESTS: Chi-square test, one-way analysis of variance, and Kruskal-Wallis test were performed. The P values <0.05 were considered statistically significant. For ML models, the generated probability was used to construct the ROC curves. RESULTS: Peritumoral edema, the presence of multiple lesions and non-mass enhancement (NME) showed significant differences. For distinguishing HER2-zero from non-zero (low + positive), multiple lesions, edema, margin, and tumor size were selected, and the k-NN model achieved the highest AUC of 0.86 in the training set and 0.79 in the testing set. For differentiating HER2-low from HER2-positive, multiple lesions, edema, and margin were selected, and the DT model achieved the highest AUC of 0.79 in the training set and 0.69 in the testing set. DATA CONCLUSION: BI-RADS features read by radiologists from preoperative MRI can be analyzed using more sophisticated feature selection and ML algorithms to build models for the classification of HER2 status and identify HER2-low. TECHNICAL EFFICACY: Stage 2.

Breast lesions on MRI in mass and non-mass enhancement: Kaiser score and modified Kaiser score + for readers of variable experience.

OBJECTIVES: To compare the diagnostic performance of three readers using BI-RADS and Kaiser score (KS) based on mass and non-mass enhancement (NME) lesions. METHODS: A total of 630 lesions, 393 malignant and 237 benign, 458 mass and 172 NME, were analyzed. Three radiologists with 3 years, 6 years, and 13 years of experience made diagnoses. 596 cases had diffusion-weighted imaging, and the apparent diffusion coefficient (ADC) was measured. For lesions with ADC > 1.4 × 10-3 mm2/s, the KS was reduced by 4 as the modified KS +, and the benefit was assessed. RESULTS: When using BI-RADS, AUC was 0.878, 0.915, and 0.941 for mass, and 0.771, 0.838, 0.902 for NME for Reader-1, 2, and 3, respectively, better for mass than for NME. The diagnostic accuracy of KS was improved compared to BI-RADS for less experienced readers. For Reader-1, AUC was increased from 0.878 to 0.916 for mass (p = 0.005) and from 0.771 to 0.822 for NME (p = 0.124). Based on the cut-off value of BI-RADS ≥ 4B and KS ≥ 5 as malignant, the sensitivity of KS by Readers-1 and -2 was significantly higher for both Mass and NME. When ADC was considered to change to modified KS +, the AUC and the accuracy for all three readers were improved, showing higher specificity with slightly degraded sensitivity. CONCLUSION: The benefit of KS compared to BI-RADS was most noticeable for the less experienced readers in improving sensitivity. Compared to KS, KS + can improve specificity for all three readers. For NME, the KS and KS + criteria need to be further improved. CLINICAL RELEVANCE STATEMENT: KS provides an intuitive method for diagnosing lesions on breast MRI. BI-RADS and KS face greater difficulties in evaluating NME compared to mass lesions. Adding ADC to the KS can improve specificity with slightly degraded sensitivity. KEY POINTS: KS provides an intuitive method for interpreting breast lesions on MRI, most helpful for novice readers. KS, compared to BI-RADS, improved sensitivity in both mass and NME groups for less experienced readers. NME lesions were considered during the development of the KS flowchart, but may need to be better defined.

Radiomics analysis for the prediction of locoregional recurrence of locally advanced oropharyngeal cancer and hypopharyngeal cancer.

PURPOSE: By radiomic analysis of the postcontrast CT images, this study aimed to predict locoregional recurrence (LR) of locally advanced oropharyngeal cancer (OPC) and hypopharyngeal cancer (HPC). METHODS: A total of 192 patients with stage III-IV OPC or HPC from two independent cohort were randomly split into a training cohort with 153 cases and a testing cohort with 39 cases. Only primary tumor mass was manually segmented. Radiomic features were extracted using PyRadiomics, and then the support vector machine was used to build the radiomic model with fivefold cross-validation process in the training data set. For each case, a radiomics score was generated to indicate the probability of LR. RESULTS: There were 94 patients with LR assigned in the progression group and 98 patients without LR assigned in the stable group. There was no significant difference of TNM staging, treatment strategies and common risk factors between these two groups. For the training data set, the radiomics model to predict LR showed 83.7% accuracy and 0.832 (95% CI 0.72, 0.87) area under the ROC curve (AUC). For the test data set, the accuracy and AUC slightly declined to 79.5% and 0.770 (95% CI 0.64, 0.80), respectively. The sensitivity/specificity of training and test data set for LR prediction were 77.6%/89.6%, and 66.7%/90.5%, respectively. CONCLUSIONS: The image-based radiomic approach could provide a reliable LR prediction model in locally advanced OPC and HPC. Early identification of those prone to post-treatment recurrence would be helpful for appropriate adjustments to treatment strategies and post-treatment surveillance.

Prediction of poor outcome in stroke patients using radiomics analysis of intraparenchymal and intraventricular hemorrhage and clinical factors.

PURPOSE: To build three prognostic models using radiomics analysis of the hemorrhagic lesions, clinical variables, and their combination, to predict the outcome of stroke patients with spontaneous intracerebral hemorrhage (sICH). MATERIALS AND METHODS: Eighty-three sICH patients were included. Among them, 40 patients (48.2%) had poor prognosis with modified Rankin scale (mRS) of 5 and 6 at discharge, and the prognostic model was built to differentiate mRS ≤ 4 vs. 5 + 6. The region of interest (ROI) of intraparenchymal hemorrhage (IPH) and intraventricular hemorrhage (IVH) were separately segmented. Features were extracted using PyRadiomics, and the support vector machine was applied to select features and build radiomics models based on IPH and IPH + IVH. The clinical models were built using multivariate logistic regression, and then the radiomics scores were combined with clinical variables to build the combined model. RESULTS: When using IPH, the AUC for radiomics, clinical, and combined model was 0.78, 0.82, and 0.87, respectively. When using IPH + IVH, the AUC was increased to 0.80, 0.84, and 0.90, respectively. The combined model had a significantly improved AUC compared to the radiomics by DeLong test. A clinical prognostic model based on the ICH score of 0-1 only achieved AUC of 0.71. CONCLUSIONS: The combined model using the radiomics score derived from IPH + IVH and the clinical factors could achieve a high accuracy in prediction of sICH patients with poor outcome, which may be used to assist in making the decision about the optimal care.

Body Map of Droplet Distributions During Oropharyngeal Suction to Protect Health Care Workers From Airborne Diseases.

PURPOSE: Health care workers (HCWs), and in particular anesthesia providers, often must perform aerosol-generating medical procedures (AGMPs). However, no studies have analyzed droplet distributions on the bodies of HCWs during AGMPs. Therefore, the purpose of this study was to assess and analyze droplet distributions on the bodies of HCWs during suction of oral cavities with and without oral airways and during extubations. DESIGN: Using a quasi-experiemental design, we assumed the HCWs perform suction and extubation on intubated patients, and we prepared an intubated mannequin mimicking a patient. This study performed the oral suction and extubation on the intubated mannequin (with or without oral airways in place) and analyzed the droplet distributions. METHODS: We prepared a mannequin intubated with an 8.0 mm endotracheal tube, assuming the situation of general anesthesia. We designed the body mapping gown, and divided it into 10 areas including the head, neck, chest, abdomen, upper arms, forearms, and hands. We classified experiments into group O when suctions were performed on the mannequin with an oral airway, and into group X when the suctions were performed on the mannequin without an oral airway. An experienced board-certified anesthesiologist performed 10 oral suctions on each mannequin, and 10 extubations. We counted the droplets on the anesthesiologist's gown according to the divided areas after each procedure. FINDINGS: The mean droplet count after suction was 6.20 ± 2.201 in group O and 13.6 ± 4.300 in group X, with a significant difference between the two groups (P < .001). The right and left hands were the most contaminated areas in group O (2.8 ± 1.033 droplets and 2.0 ± 0.943 droplets, respectively). The abdomen, right hand, left forearm, and left hand showed many droplets in group X. (1.3 ± 1.337 droplets, 3.1 ± 1.792 droplets, 3.2 ± 3.910 droplets, and 4.3 ± 2.214 droplets, respectively). The chest, abdomen, and left hand presented significantly more droplets in group X than in group O. The trunk area (chest and abdomen) was exposed to more droplets during extubations than during suctions. CONCLUSIONS: During suctions, more droplets are splattered from mannequins without oral airways than from those with oral airways. The right and left hands were the most contaminated areas in group O. Moreover, the abdomen, right hand, left forearm, and left hand presented a lot of droplets in group X. In addition, extubations contaminate wider areas (the head, neck, chest and abdomen) of an HCW than suctions.

Assessment of breast lesions by the Kaiser score for differential diagnosis on MRI: the added value of ADC and machine learning modeling.

OBJECTIVES: To evaluate the diagnostic performance of Kaiser score (KS) adjusted with the apparent diffusion coefficient (ADC) (KS+) and machine learning (ML) modeling. METHODS: A dataset of 402 malignant and 257 benign lesions was identified. Two radiologists assigned the KS. If a lesion with KS > 4 had ADC > 1.4 × 10-3 mm2/s, the KS was reduced by 4 to become KS+. In order to consider the full spectrum of ADC as a continuous variable, the KS and ADC values were used to train diagnostic models using 5 ML algorithms. The performance was evaluated using the ROC analysis, compared by the DeLong test. The sensitivity, specificity, and accuracy achieved using the threshold of KS > 4, KS+ > 4, and ADC ≤ 1.4 × 10-3 mm2/s were obtained and compared by the McNemar test. RESULTS: The ROC curves of KS, KS+, and all ML models had comparable AUC in the range of 0.883-0.921, significantly higher than that of ADC (0.837, p < 0.0001). The KS had sensitivity = 97.3% and specificity = 59.1%; and the KS+ had sensitivity = 95.5% with significantly improved specificity to 68.5% (p < 0.0001). However, when setting at the same sensitivity of 97.3%, KS+ could not improve specificity. In ML analysis, the logistic regression model had the best performance. At sensitivity = 97.3% and specificity = 65.3%, i.e., compared to KS, 16 false-positives may be avoided without affecting true cancer diagnosis (p = 0.0015). CONCLUSION: Using dichotomized ADC to modify KS to KS+ can improve specificity, but at the price of lowered sensitivity. Machine learning algorithms may be applied to consider the ADC as a continuous variable to build more accurate diagnostic models. KEY POINTS: • When using ADC to modify the Kaiser score to KS+, the diagnostic specificity according to the results of two independent readers was improved by 9.4-9.7%, at the price of slightly degraded sensitivity by 1.5-1.8%, and overall had improved accuracy by 2.6-2.9%. • When the KS and the continuous ADC values were combined to train models by machine learning algorithms, the diagnostic specificity achieved by the logistic regression model could be significantly improved from 59.1 to 65.3% (p = 0.0015), while maintaining at the high sensitivity of KS = 97.3%, and thus, the results demonstrated the potential of ML modeling to further evaluate the contribution of ADC. • When setting the sensitivity at the same levels, the modified KS+ and the original KS have comparable specificity; therefore, KS+ with consideration of ADC may not offer much practical help, and the original KS without ADC remains as an excellent robust diagnostic method.

A deep learning-based method for the diagnosis of vertebral fractures on spine MRI: retrospective training and validation of ResNet.

PURPOSE: To improve the performance of less experienced clinicians in the diagnosis of benign and malignant spinal fracture on MRI, we applied the ResNet50 algorithm to develop a decision support system. METHODS: A total of 190 patients, 50 with malignant and 140 with benign fractures, were studied. The visual diagnosis was made by one senior MSK radiologist, one fourth-year resident, and one first-year resident. The MSK radiologist also gave the binary score for 15 qualitative imaging features. Deep learning was implemented using ResNet50, using one abnormal spinal segment selected from each patient as input. The T1W and T2W images of the lesion slice and its two neighboring slices were considered. The diagnostic performance was evaluated using tenfold cross-validation. RESULTS: The overall reading accuracy was 98, 96, and 66% for the senior MSK radiologist, fourth-year resident, and first-year resident, respectively. Of the 15 imaging features, 10 showed a significant difference between benign and malignant groups with p < = 0.001. The accuracy achieved by using the ResNet50 deep learning model for the identified abnormal vertebral segment was 92%. Compared to the first-year resident's reading, the model improved the sensitivity from 78 to 94% (p < 0.001) and the specificity from 61 to 91% (p < 0.001). CONCLUSION: Our deep learning-based model may provide information to assist less experienced clinicians in the diagnosis of spinal fractures on MRI. Other findings away from the vertebral body need to be considered to improve the model, and further investigation is required to generalize our findings to real-world settings.

Differential diagnosis of benign and malignant vertebral fracture on CT using deep learning.

OBJECTIVES: To evaluate the performance of deep learning using ResNet50 in differentiation of benign and malignant vertebral fracture on CT. METHODS: A dataset of 433 patients confirmed with 296 malignant and 137 benign fractures was retrospectively selected from our spinal CT image database. A senior radiologist performed visual reading to evaluate six imaging features, and three junior radiologists gave diagnostic prediction. A ROI was placed on the most abnormal vertebrae, and the smallest square bounding box was generated. The input channel into ResNet50 network was 3, including the slice with its two neighboring slices. The diagnostic performance was evaluated using 10-fold cross-validation. After obtaining the malignancy probability from all slices in a patient, the highest probability was assigned to that patient to give the final diagnosis, using the threshold of 0.5. RESULTS: Visual features such as soft tissue mass and bone destruction were highly suggestive of malignancy; the presence of a transverse fracture line was highly suggestive of a benign fracture. The reading by three radiologists with 5, 3, and 1 year of experience achieved an accuracy of 99%, 95.2%, and 92.8%, respectively. In ResNet50 analysis, the per-slice diagnostic sensitivity, specificity, and accuracy were 0.90, 0.79, and 85%. When the slices were combined to ve per-patient diagnosis, the sensitivity, specificity, and accuracy were 0.95, 0.80, and 88%. CONCLUSION: Deep learning has become an important tool for the detection of fractures on CT. In this study, ResNet50 achieved good accuracy, which can be further improved with more cases and optimized methods for future clinical implementation. KEY POINTS: • Deep learning using ResNet50 can yield a high accuracy for differential diagnosis of benign and malignant vertebral fracture on CT. • The per-slice diagnostic sensitivity, specificity, and accuracy were 0.90, 0.79, and 85% in deep learning using ResNet50 analysis. • The slices combined with per-patient diagnostic sensitivity, specificity, and accuracy were 0.95, 0.80, and 88% in deep learning using ResNet50 analysis.

Prediction of breast cancer molecular subtypes on DCE-MRI using convolutional neural network with transfer learning between two centers.

OBJECTIVES: To apply deep learning algorithms using a conventional convolutional neural network (CNN) and a recurrent CNN to differentiate three breast cancer molecular subtypes on MRI. METHODS: A total of 244 patients were analyzed, 99 in training dataset scanned at 1.5 T and 83 in testing-1 and 62 in testing-2 scanned at 3 T. Patients were classified into 3 subtypes based on hormonal receptor (HR) and HER2 receptor: (HR+/HER2-), HER2+, and triple negative (TN). Only images acquired in the DCE sequence were used in the analysis. The smallest bounding box covering tumor ROI was used as the input for deep learning to develop the model in the training dataset, by using a conventional CNN and the convolutional long short-term memory (CLSTM). Then, transfer learning was applied to re-tune the model using testing-1(2) and evaluated in testing-2(1). RESULTS: In the training dataset, the mean accuracy evaluated using tenfold cross-validation was higher by using CLSTM (0.91) than by using CNN (0.79). When the developed model was applied to the independent testing datasets, the accuracy was 0.4-0.5. With transfer learning by re-tuning parameters in testing-1, the mean accuracy reached 0.91 by CNN and 0.83 by CLSTM, and improved accuracy in testing-2 from 0.47 to 0.78 by CNN and from 0.39 to 0.74 by CLSTM. Overall, transfer learning could improve the classification accuracy by greater than 30%. CONCLUSIONS: The recurrent network using CLSTM could track changes in signal intensity during DCE acquisition, and achieved a higher accuracy compared with conventional CNN during training. For datasets acquired using different settings, transfer learning can be applied to re-tune the model and improve accuracy. KEY POINTS: • Deep learning can be applied to differentiate breast cancer molecular subtypes. • The recurrent neural network using CLSTM could track the change of signal intensity in DCE images, and achieved a higher accuracy compared with conventional CNN during training. • For datasets acquired using different scanners with different imaging protocols, transfer learning provided an efficient method to re-tune the classification model and improve accuracy.

Development of U-Net Breast Density Segmentation Method for Fat-Sat MR Images Using Transfer Learning Based on Non-Fat-Sat Model.

To develop a U-net deep learning method for breast tissue segmentation on fat-sat T1-weighted (T1W) MRI using transfer learning (TL) from a model developed for non-fat-sat images. The training dataset (N = 126) was imaged on a 1.5 T MR scanner, and the independent testing dataset (N = 40) was imaged on a 3 T scanner, both using fat-sat T1W pulse sequence. Pre-contrast images acquired in the dynamic-contrast-enhanced (DCE) MRI sequence were used for analysis. All patients had unilateral cancer, and the segmentation was performed using the contralateral normal breast. The ground truth of breast and fibroglandular tissue (FGT) segmentation was generated using a template-based segmentation method with a clustering algorithm. The deep learning segmentation was performed using U-net models trained with and without TL, by using initial values of trainable parameters taken from the previous model for non-fat-sat images. The ground truth of each case was used to evaluate the segmentation performance of the U-net models by calculating the dice similarity coefficient (DSC) and the overall accuracy based on all pixels. Pearson's correlation was used to evaluate the correlation of breast volume and FGT volume between the U-net prediction output and the ground truth. In the training dataset, the evaluation was performed using tenfold cross-validation, and the mean DSC with and without TL was 0.97 vs. 0.95 for breast and 0.86 vs. 0.80 for FGT. When the final model developed with and without TL from the training dataset was applied to the testing dataset, the mean DSC was 0.89 vs. 0.83 for breast and 0.81 vs. 0.81 for FGT, respectively. Application of TL not only improved the DSC, but also decreased the required training case number. Lastly, there was a high correlation (R2 > 0.90) for both the training and testing datasets between the U-net prediction output and ground truth for breast volume and FGT volume. U-net can be applied to perform breast tissue segmentation on fat-sat images, and TL is an efficient strategy to develop a specific model for each different dataset.

Diagnosis of Benign and Malignant Breast Lesions on DCE-MRI by Using Radiomics and Deep Learning With Consideration of Peritumor Tissue.

BACKGROUND: Computer-aided methods have been widely applied to diagnose lesions detected on breast MRI, but fully-automatic diagnosis using deep learning is rarely reported. PURPOSE: To evaluate the diagnostic accuracy of mass lesions using region of interest (ROI)-based, radiomics and deep-learning methods, by taking peritumor tissues into consideration. STUDY TYPE: Retrospective. POPULATION: In all, 133 patients with histologically confirmed 91 malignant and 62 benign mass lesions for training (74 patients with 48 malignant and 26 benign lesions for testing). FIELD STRENGTH/SEQUENCE: 3T, using the volume imaging for breast assessment (VIBRANT) dynamic contrast-enhanced (DCE) sequence. ASSESSMENT: 3D tumor segmentation was done automatically by using fuzzy-C-means algorithm with connected-component labeling. A total of 99 texture and histogram parameters were calculated for each case, and 15 were selected using random forest to build a radiomics model. Deep learning was implemented using ResNet50, evaluated with 10-fold crossvalidation. The tumor alone, smallest bounding box, and 1.2, 1.5, 2.0 times enlarged boxes were used as inputs. STATISTICAL TESTS: The malignancy probability was calculated using each model, and the threshold of 0.5 was used to make a diagnosis. RESULTS: In the training dataset, the diagnostic accuracy was 76% using three ROI-based parameters, 84% using the radiomics model, and 86% using ROI + radiomics model. In deep learning using the per-slice basis, the area under the receiver operating characteristic (ROC) was comparable for tumor alone, smallest and 1.2 times box (AUC = 0.97-0.99), which were significantly higher than 1.5 and 2.0 times box (AUC = 0.86 and 0.71, respectively). For per-lesion diagnosis, the highest accuracy of 91% was achieved when using the smallest bounding box, and that decreased to 84% for tumor alone and 1.2 times box, and further to 73% for 1.5 times box and 69% for 2.0 times box. In the independent testing dataset, the per-lesion diagnostic accuracy was also the highest when using the smallest bounding box, 89%. DATA CONCLUSION: Deep learning using ResNet50 achieved a high diagnostic accuracy. Using the smallest bounding box containing proximal peritumor tissue as input had higher accuracy compared to using tumor alone or larger boxes. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 2.

Diagnosis of spinal lesions using perfusion parameters measured by DCE-MRI and metabolism parameters measured by PET/CT.

PURPOSE: To investigate the correlation of parameters measured by dynamic-contrast-enhanced MRI (DCE-MRI) and 18F-FDG PET/CT in spinal tumors, and their role in differential diagnosis. METHODS: A total of 49 patients with pathologically confirmed spinal tumors, including 38 malignant, six benign and five borderline tumors, were analyzed. The MRI and PET/CT were done within 3 days, before biopsy. On MRI, the ROI was manually placed on area showing the strongest enhancement to measure pharmacokinetic parameters Ktrans and kep. On PET, the maximum standardized uptake value SUVmax was measured. The parameters in different histological groups were compared. ROC was performed to differentiate between the two largest subtypes, metastases and plasmacytomas. Spearman rank correlation was performed to compare DCE-MRI and PET/CT parameters. RESULTS: The Ktrans, kep and SUVmax were not statistically different among malignant, benign and borderline groups (P = 0.95, 0.50, 0.11). There was no significant correlation between Ktrans and SUVmax (r = - 0.20, P = 0.18), or between kep and SUVmax (r = - 0.16, P = 0.28). The kep was significantly higher in plasmacytoma than in metastasis (0.78 ± 0.17 vs. 0.61 ± 0.18, P = 0.02); in contrast, the SUVmax was significantly lower in plasmacytoma than in metastasis (5.58 ± 2.16 vs. 9.37 ± 4.26, P = 0.03). In differential diagnosis, the AUC of kep and SUVmax was 0.79 and 0.78, respectively. CONCLUSIONS: The vascular parameters measured by DCE-MRI and glucose metabolism measured by PET/CT from the most aggressive tumor area did not show a significant correlation. The results suggest they provide complementary information reflecting different aspects of the tumor, which may aid in diagnosis of spinal lesions. These slides can be retrieved under Electronic Supplementary Material.

Feasibility and Diagnostic Performance of Voxelwise Computed Diffusion-Weighted Imaging in Breast Cancer.

BACKGROUND: Conventional diffusion-weighted imaging (DWI) with high b-values may improve lesion conspicuity, but with a low signal intensity and thus a low signal-to-noise ratio (SNR). The voxelwise computed DWI (vcDWI) may generate high-quality images with a strong lesion signal and low background. PURPOSE: To evaluate the feasibility and diagnostic performance of vcDWI. STUDY TYPE: Retrospective. POPULATION: In all, 67 patients with 72 lesions, 33 malignant and 39 benign. FIELD STRENGTH/SEQUENCE: 3T, including T2 /T1 , DWI with two b-values, and dynamic contrast-enhanced MRI (DCE-MRI). ASSESSMENT: Computed DWI (cDWI) with high b-values of 1500, 2000, 2500 s/mm2 (cDWI1500 , cDWI2000 , cDWI2500 ) and vcDWI were generated from measured DWI (mDWI). The mDWI, cDWIs and vcDWI were evaluated by three readers independently to determine lesion conspicuity, background signal suppression, overall image quality using 1-5 rating scales, as well as to give BI-RADS scores. The mean apparent diffusion coefficient (ADC) value for each lesion was measured. STATISTICAL TESTS: Agreement among the three readers was evaluated by the intraclass correlation coefficient. Receiver operating characteristic (ROC) analysis was performed to compare the diagnostic performance based on reading of mDWI, cDWIs, vcDWI, and the measured ADC values. RESULTS: vcDWI provided the best lesion conspicuity compared with mDWI and cDWIs (P < 0.005). For overall image quality, vcDWI was significantly better than cDWI (P < 0.005), but not significantly better compared with mDWI for two readers (P = 0.037 and P = 0.013) and significantly worse for the third reader (P < 0.005). Background signal suppression was the best on cDWI2500 , and better on vcDWI than on mDWI, cDWI1500 , and cDWI2000 . The AUC value for differential diagnosis was 0.868 for mDWI, 0.862 for cDWI1500 , 0.781 for cDWI2000 , 0.704 for cDWI2500 , 0.946 for vcDWI, 0.704 for ADC value, and 0.961 for DCE-MRI. DATA CONCLUSION: vcDWI was implemented without increasing scanning time, and it provided excellent lesion conspicuity for detection of breast lesions and assisted in differentiating malignant from benign breast lesions. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018.

Radiomics approach for prediction of recurrence in skull base meningiomas.

PURPOSE: A subset of skull base meningiomas (SBM) may show early progression/recurrence (P/R) as a result of incomplete resection. The purpose of this study is the implementation of MR radiomics to predict P/R in SBM. METHODS: From October 2006 to December 2017, 60 patients diagnosed with pathologically confirmed SBM (WHO grade I, 56; grade II, 3; grade III, 1) were included in this study. Preoperative MRI including T2WI, diffusion-weighted imaging (DWI), and contrast-enhanced T1WI were analyzed. On each imaging modality, 13 histogram parameters and 20 textural gray level co-occurrence matrix (GLCM) features were extracted. Random forest algorithms were utilized to evaluate the importance of these parameters, and the most significant three parameters were selected to build a decision tree for prediction of P/R in SBM. Furthermore, ADC values obtained from manually placed ROI in tumor were also used to predict P/R in SBM for comparison. RESULTS: Gross-total resection (Simpson Grades I-III) was performed in 33 (33/60, 55%) patients, and 27 patients received subtotal resection. Twenty-one patients had P/R (21/60, 35%) after a postoperative follow-up period of at least 12 months. The three most significant parameters included in the final radiomics model were T1 max probability, T1 cluster shade, and ADC correlation. In the radiomics model, the accuracy for prediction of P/R was 90%; by comparison, the accuracy was 83% using ADC values measured from manually placed tumor ROI. CONCLUSIONS: The results show that the radiomics approach in preoperative MRI offer objective and valuable clinical information for treatment planning in SBM.

Role of dynamic contrast-enhanced MRI in evaluating the association between contralateral parenchymal enhancement and survival outcome in ER-positive, HER2-negative, node-negative invasive breast cancer.

BACKGROUND: Background parenchymal enhancement (BPE) on dynamic contrast-enhanced (DCE)-MRI has been associated with breast cancer risk, both based on qualitative and quantitative assessments. PURPOSE: To investigate whether BPE of the contralateral breast on preoperative DCE-MRI is associated with therapy outcome in ER-positive, HER2-negative, node-negative invasive breast cancer. STUDY TYPE: Retrospective. POPULATION: In all, 289 patients with unilateral ER-positive, HER2-negative, node-negative breast cancer larger than 5 mm. FIELD STRENGTH/SEQUENCE: 3T, T1 -weighted DCE sequence. ASSESSMENT: BPE of the contralateral breast was assessed qualitatively by two dedicated radiologists and quantitatively (using region-of-interest and automatic breast segmentation). STATISTICAL TESTS: Cox regression analysis was used to determine associations with recurrence-free survival (RFS) and distant metastasis-free survival (DFS). Interobserver variability for parenchymal enhancement was assessed using kappa statistics and intraclass correlation coefficient (ICC). RESULTS: The median follow-up time was 75.8 months. Multivariate analysis showed receipt of total mastectomy (hazard ratio [HR]: 5.497) and high Ki-67 expression level (HR: 5.956) were independent factors associated with worse RFS (P < 0.05). Only a high Ki-67 expression level was associated with worse DFS (HR: 3.571, P = 0.045). BPE assessments were not associated with outcome (RFS [qualitative BPE: P = 0.75, 0.92 for readers 1 and 2; quantitative BPE: P = 0.38-0.99], DFS, [qualitative BPE: P = 0.41, 0.16 for readers 1 and 2; quantitative BPE: P = 0.68-0.99]). For interobserver variability, there was good agreement between qualitative (κ = 0.700) and good to perfect agreement for most quantitative parameters of BPE. DATA CONCLUSION: Contralateral BPE showed no association with survival outcome in patients with ER-positive, HER2-negative, node-negative invasive breast cancer. A high Ki-67 expression level was associated with both worse recurrence-free and distant metastasis-free survival. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 4 J. Magn. Reson. Imaging 2018;48:1678-1689.

Evaluation of the association between quantitative mammographic density and breast cancer occurred in different quadrants.

BACKGROUND: To investigate the relationship between mammographic density measured in four quadrants of a breast with the location of the occurred cancer. METHODS: One hundred and ten women diagnosed with unilateral breast cancer that could be determined in one specific breast quadrant were retrospectively studied. Women with previous cancer/breast surgery were excluded. The craniocaudal (CC) and mediolateral oblique (MLO) mammography of the contralateral normal breast were used to separate a breast into 4 quadrants: Upper-Outer (UO), Upper-Inner (UI), Lower-Outer (LO), and Lower-Inner (LI). The breast area (BA), dense area (DA), and percent density (PD) in each quadrant were measured by using the fuzzy-C-means segmentation. The BA, DA, and PD were compared between patients who had cancer occurring in different quadrants. RESULTS: The upper-outer quadrant had the highest BA (37 ± 15 cm2) and DA (7.1 ± 2.9 cm2), with PD = 20.0 ± 5.8%. The order of BA and DA in the 4 separated quadrants were: UO > UI > LO > LI, and almost all pair-wise comparisons showed significant differences. For tumor location, 67 women (60.9%) had tumor in UO, 16 (14.5%) in UI, 7 (6.4%) in LO, and 20 (18.2%) in LI quadrant, respectively. The estimated odds and the 95% confidence limits of tumor development in the UO, UI, LO and LI quadrants were 1.56 (1.06, 2.29), 0.17 (0.10, 0.29), 0.07 (0.03, 0.15), and 0.22 (0.14, 0.36), respectively. In these 4 groups of women, the order of quadrant BA and DA were all the same (UO > UI > LO > LI), and there was no significant difference in BA, DA or PD among them (all p > 0.05). CONCLUSIONS: Breast cancer was most likely to occur in the UO quadrant, which was also the quadrant with highest BA and DA; but for women with tumors in other quadrants, the density in that quadrant was not the highest. Therefore, there was no direct association between quadrant density and tumor occurrence.

Morphological and dynamic contrast enhanced MR imaging features for the differentiation of chordoma and giant cell tumors in the Axial Skeleton.

PURPOSE: To characterize the morphological and dynamic-contrast-enhanced (DCE) MRI features of chordoma and giant cell tumor (GCT) of bone occurring in the axial skeleton. MATERIALS AND METHODS: A total of 13 patients with chordoma and 26 patients with GCT who received conventional T1, T2, and DCE-MRI on 3 Tesla MR scanners were retrospectively identified and analyzed. Two radiologists evaluated morphological features independently, including the lesion location, expansile bone changes, vertebral compression, presence of paraspinal soft tissue mass, fibrous septa, and the signal intensity on T1WI and T2WI. The inter-observer agreement was evaluated by kappa test. The DCE kinetics was measured to obtain the initial area under curve (IAUC) and the wash-out slope; also the two-compartmental pharmacokinetic model was applied to obtain Ktrans and kep . The diagnostic accuracy was evaluated by CHAID decision tree and ROC analysis. RESULTS: Chordomas were more likely to show soft tissue mass than GCTs (13/13 = 100% versus 15/26 = 58%; P = 0.007), as well as fibrous septa (9/13 = 69% versus 0; P < 0.001). In decision tree analysis, presence of fibrous septa and lesion location yield 31/39 = 79% accuracy. The DCE-MRI pharmacokinetic parameters Ktrans and kep of GCTs were significantly higher than those of chordomas, 0.13 ± 0.65 versus 0.06 ± 0.04 (1/min) for Ktrans , 0.62 ± 0.22 versus 0.17 ± 0.12 (1/min) for kep , P < 0.001 for both. If using kep = 0.43/min as the cut-off value, it achieved 100% sensitivity and 92% specificity to differentiate chordoma from GCT, with an overall accuracy of 37/39 = 95%. The IAUC was highly correlated with Ktrans (r = 0.94), and the slope was highly correlated with kep (r = 0.95). CONCLUSION: Several morphological features were significantly different between chordoma and GCT, but their diagnostic performance was inferior to that of DCE-MRI. LEVEL OF EVIDENCE: 4 J. Magn. Reson. Imaging 2017;45:1068-1075.

Sample size and power determination when limited preliminary information is available.

BACKGROUND: We describe a novel strategy for power and sample size determination developed for studies utilizing investigational technologies with limited available preliminary data, specifically of imaging biomarkers. We evaluated diffuse optical spectroscopic imaging (DOSI), an experimental noninvasive imaging technique that may be capable of assessing changes in mammographic density. Because there is significant evidence that tamoxifen treatment is more effective at reducing breast cancer risk when accompanied by a reduction of breast density, we designed a study to assess the changes from baseline in DOSI imaging biomarkers that may reflect fluctuations in breast density in premenopausal women receiving tamoxifen. METHOD: While preliminary data demonstrate that DOSI is sensitive to mammographic density in women about to receive neoadjuvant chemotherapy for breast cancer, there is no information on DOSI in tamoxifen treatment. Since the relationship between magnetic resonance imaging (MRI) and DOSI has been established in previous studies, we developed a statistical simulation approach utilizing information from an investigation of MRI assessment of breast density in 16 women before and after treatment with tamoxifen to estimate the changes in DOSI biomarkers due to tamoxifen. RESULTS: Three sets of 10,000 pairs of MRI breast density data with correlation coefficients of 0.5, 0.8 and 0.9 were simulated and generated and were used to simulate and generate a corresponding 5,000,000 pairs of DOSI values representing water, ctHHB, and lipid. Minimum sample sizes needed per group for specified clinically-relevant effect sizes were obtained. CONCLUSION: The simulation techniques we describe can be applied in studies of other experimental technologies to obtain the important preliminary data to inform the power and sample size calculations.

Breast density quantification using structured-light-based diffuse optical tomography simulations.

We present the feasibility of structured-light-based diffuse optical tomography (DOT) to quantify the breast density with an extensive simulation study. This study is performed on multiple numerical breast phantoms built from magnetic resonance imaging (MRI) images. These phantoms represent realistic tissue morphologies and are given typical breast optical properties. First, synthetic data are simulated at five wavelengths using our structured-light-based DOT forward problem. Afterwards, the inverse problem is solved to obtain the absorption images and subsequently the chromophore concentration maps. Parameters, such as segmented volumes and mean concentrations, are extracted from these maps and used in a regression model to estimate the percent breast densities. These estimations are correlated with the true values from MRI, r=0.97, showing that our new technique is promising in measuring breast density.