Whole-tumor 3D volumetric MRI-based radiomics approach for distinguishing between benign and malignant soft tissue tumors.

OBJECTIVES: Our purpose was to differentiate between malignant from benign soft tissue neoplasms using a combination of MRI-based radiomics metrics and machine learning. METHODS: Our retrospective study identified 128 histologically diagnosed benign (n = 36) and malignant (n = 92) soft tissue lesions. 3D ROIs were manually drawn on 1 sequence of interest and co-registered to other sequences obtained during the same study. One thousand seven hundred eight radiomics features were extracted from each ROI. Univariate analyses with supportive ROC analyses were conducted to evaluate the discriminative power of predictive models constructed using Real Adaptive Boosting (Adaboost) and Random Forest (RF) machine learning approaches. RESULTS: Univariate analyses demonstrated that 36.89% of individual radiomics varied significantly between benign and malignant lesions at the p ≤ 0.05 level. Adaboost and RF performed similarly well, with AUCs of 0.77 (95% CI 0.68-0.85) and 0.72 (95% CI 0.63-0.81), respectively, after 10-fold cross-validation. Restricting the machine learning models to only sequences extracted from T2FS and STIR sequences maintained comparable performance, with AUCs of 0.73 (95% CI 0.64-0.82) and 0.75 (95% CI 0.65-0.84), respectively. CONCLUSION: Machine learning decision classifiers constructed from MRI-based radiomics features show promising ability to preoperatively discriminate between benign and malignant soft tissue masses. Our approach maintains applicability even when the dataset is restricted to T2FS and STIR fluid-sensitive sequences, which may bolster practicality in clinical application scenarios by eliminating the need for complex co-registrations for multisequence analysis. KEY POINTS: • Predictive models constructed from MRI-based radiomics data and machine learning-augmented approaches yielded good discriminative power to correctly classify benign and malignant lesions on preoperative scans, with AUCs of 0.77 (95% CI 0.68-0.85) and 0.72 (95% CI 0.63-0.81) for Real Adaptive Boosting (Adaboost) and Random Forest (RF), respectively. • Restricting the models to only use metrics extracted from T2 fat-saturated (T2FS) and Short-Tau Inversion Recovery (STIR) sequences yielded similar performance, with AUCs of 0.73 (95% CI 0.64-0.82) and 0.75 (95% CI 0.65-0.84) for Adaboost and RF, respectively. • Radiomics-based machine learning decision classifiers constructed from multicentric data more closely mimic the real-world practice environment and warrant additional validation ahead of prospective implementation into clinical workflows.

Shape and texture-based radiomics signature on CT effectively discriminates benign from malignant renal masses.

OBJECTIVES: Using a radiomics framework to quantitatively analyze tumor shape and texture features in three dimensions, we tested its ability to objectively and robustly distinguish between benign and malignant renal masses. We assessed the relative contributions of shape and texture metrics separately and together in the prediction model. MATERIALS AND METHODS: Computed tomography (CT) images of 735 patients with 539 malignant and 196 benign masses were segmented in this retrospective study. Thirty-three shape and 760 texture metrics were calculated per tumor. Tumor classification models using shape, texture, and both metrics were built using random forest and AdaBoost with tenfold cross-validation. Sensitivity analyses on five sub-cohorts with respect to the acquisition phase were conducted. Additional sensitivity analyses after multiple imputation were also conducted. Model performance was assessed using AUC. RESULTS: Random forest classifier showed shape metrics featuring within the top 10% performing metrics regardless of phase, attaining the highest variable importance in the corticomedullary phase. Convex hull perimeter ratio is a consistently high-performing shape feature. Shape metrics alone achieved an AUC ranging 0.64-0.68 across multiple classifiers, compared with 0.67-0.75 and 0.68-0.75 achieved by texture-only and combined models, respectively. CONCLUSION: Shape metrics alone attain high prediction performance and high variable importance in the combined model, while being independent of the acquisition phase (unlike texture). Shape analysis therefore should not be overlooked in its potential to distinguish benign from malignant tumors, and future radiomics platforms powered by machine learning should harness both shape and texture metrics. KEY POINTS: • Current radiomics research is heavily weighted towards texture analysis, but quantitative shape metrics should not be ignored in their potential to distinguish benign from malignant renal tumors. • Shape metrics alone can attain high prediction performance and demonstrate high variable importance in the combined shape and texture radiomics model. • Any future radiomics platform powered by machine learning should harness both shape and texture metrics, especially since tumor shape (unlike texture) is independent of the acquisition phase and more robust from the imaging variations.

Identification of robust and reproducible CT-texture metrics using a customized 3D-printed texture phantom.

OBJECTIVE: The objective of this study was to evaluate the robustness and reproducibility of computed tomography-based texture analysis (CTTA) metrics extracted from CT images of a customized texture phantom built for assessing the association of texture metrics to three-dimensional (3D) printed progressively increasing textural heterogeneity. MATERIALS AND METHODS: A custom-built 3D-printed texture phantom comprising of six texture patterns was used to evaluate the robustness and reproducibility of a radiomics panel under a variety of routine abdominal imaging protocols. The phantom was scanned on four CT scanners (Philips, Canon, GE, and Siemens) to assess reproducibility. The robustness assessment was conducted by imaging the texture phantom across different CT imaging parameters such as slice thickness, field of view (FOV), tube voltage, and tube current for each scanner. The texture panel comprised of 387 features belonging to 15 subgroups of texture extraction methods (e.g., Gray-level Co-occurrence Matrix: GLCM). Twelve unique image settings were tested on all the four scanners (e.g., FOV125). Interclass correlation two-way mixed with absolute agreement (ICC3) was used to assess the robustness and reproducibility of radiomic features. Linear regression was used to test the association between change in radiomic features and increased texture heterogeneity. Results were summarized in heat maps. RESULTS: A total of 5612 (23.2%) of 24 090 features showed excellent robustness and reproducibility (ICC ≥ 0.9). Intensity, GLCM 3D, and gray-level run length matrix (GLRLM) 3D features showed best performance. Among imaging variables, changes in slice thickness affected all metrics more intensely compared to other imaging variables in reducing the ICC3. From the analysis of linear trend effect of the CTTA metrics, the top three metrics with high linear correlations across all scanners and scanning settings were from the GLRLM 2D/3D and discrete cosine transform (DCT) texture family. CONCLUSION: The choice of scanner and imaging protocols affect texture metrics. Furthermore, not all CTTA metrics have a linear association with linearly varying texture patterns.

Benchmarking Various Radiomic Toolkit Features While Applying the Image Biomarker Standardization Initiative toward Clinical Translation of Radiomic Analysis.

The image biomarkers standardization initiative (IBSI) was formed to address the standardization of extraction of quantifiable imaging metrics. Despite its effort, there remains a lack of consensus or established guidelines regarding radiomic feature terminology, the underlying mathematics and their implementation across various software programs. This creates a scenario where features extracted using different toolboxes cannot be used to build or validate the same model leading to a non-generalization of radiomic results. In this study, IBSI-established phantom and benchmark values were used to compare the variation of the radiomic features while using 6 publicly available software programs and 1 in-house radiomics pipeline. All IBSI-standardized features (11 classes, 173 in total) were extracted. The relative differences between the extracted feature values from the different software programs and the IBSI benchmark values were calculated to measure the inter-software agreement. To better understand the variations, features are further grouped into 3 categories according to their properties: 1) morphology, 2) statistic/histogram and 3)texture features. While a good agreement was observed for a majority of radiomics features across the various tested programs, relatively poor agreement was observed for morphology features. Significant differences were also found in programs that use different gray-level discretization approaches. Since these software programs do not include all IBSI features, the level of quantitative assessment for each category was analyzed using Venn and UpSet diagrams and quantified using two ad hoc metrics. Morphology features earned lowest scores for both metrics, indicating that morphological features are not consistently evaluated among software programs. We conclude that radiomic features calculated using different software programs may not be interchangeable. Further studies are needed to standardize the workflow of radiomic feature extraction.

Responding to coronavirus disease 2019: LA County hospital experience.

The coronavirus disease 2019 (COVID-19) has rapidly spread across the world since first being identified in Wuhan, China, in late 2019. In order to prepare for the surge of patients and the corresponding increase in radiology exams, clear and detailed policies need to be implemented by hospitals and radiology departments. In this article, we highlight the experiences and policies at LAC+USC Medical Center, the largest single provider of healthcare in LA County. Our policies aim to reduce the risk of transmission, guide patient management and workflow, preserve and effectively allocate resources, and be responsive to changing dynamics. We hope this communication may help other institutions in dealing with this pandemic as well as future outbreaks.

Contrast-Enhanced Ultrasound Imaging of Breast Masses: Adjunct Tool to Decrease the Number of False-Positive Biopsy Results.

OBJECTIVES: This pilot study evaluated use of contrast-enhanced ultrasound (CEUS) to reduce the number of benign breast masses recommended for biopsy. METHODS: This prospective study included 131 consenting women, from October 2016 to June 2017, with American College of Radiology Breast Imaging Reporting and Data System category 4a, 4b, and 4c masses detected by mammography, conventional ultrasound (US), or both. Contrast-enhanced US examinations (using intravenous injection of perflutren lipid microspheres or sulfur hexafluoride lipid-type A microspheres) were performed before biopsy. Qualitative and quantitative CEUS parameters were compared with reference standard histopathologic results from biopsy of 131 masses. RESULTS: There were 109 benign, 6 high-risk, and 16 malignant masses, with a median size of 12 mm (range, 4 to 48 mm) on conventional US imaging. Of 131 masses, 93 (71%) enhanced on CEUS imaging, including 73 of 109 (67%) benign, 6 of 6 (100%) high-risk, and 14 of 16 (87.5%) malignant. Thirty-eight lesions did not enhance, including 36 of 109 (33%) benign and 2 of 16 (12.5%) malignant. Prediction models using recursive petitioning revealed that CEUS may reduce 31% (95% confidence interval, 23%, 40%) of benign biopsies for masses that are: nonenhancing with circumscribed margins or enhancing with an oval shape and homogeneous enhancement. Quantitative parameters indicated that benign masses had the longest time to peak (P = .078), highest time-to-peak ratio of mass to background (P = .036), lowest peak intensity (P = .021), and smallest difference in peak intensity between the mass and background (P = .079) compared to high-risk and malignant lesions. CONCLUSIONS: Contrast-enhanced US may be a valuable modality that can be used to predict benign pathologic results of breast masses, thereby reducing the number of biopsies.

Reliability of CT-based texture features: Phantom study.

OBJECTIVE: To determine the intra-, inter- and test-retest variability of CT-based texture analysis (CTTA) metrics. MATERIALS AND METHODS: In this study, we conducted a series of CT imaging experiments using a texture phantom to evaluate the performance of a CTTA panel on routine abdominal imaging protocols. The phantom comprises of three different regions with various textures found in tumors. The phantom was scanned on two CT scanners viz. the Philips Brilliance 64 CT and Toshiba Aquilion Prime 160 CT scanners. The intra-scanner variability of the CTTA metrics was evaluated across imaging parameters such as slice thickness, field of view, post-reconstruction filtering, tube voltage, and tube current. For each scanner and scanning parameter combination, we evaluated the performance of eight different types of texture quantification techniques on a predetermined region of interest (ROI) within the phantom image using 235 different texture metrics. We conducted the repeatability (test-retest) and robustness (intra-scanner) test on both the scanners and the reproducibility test was conducted by comparing the inter-scanner differences in the repeatability and robustness to identify reliable CTTA metrics. Reliable metrics are those metrics that are repeatable, reproducible and robust. RESULTS: As expected, the robustness, repeatability and reproducibility of CTTA metrics are variably sensitive to various scanner and scanning parameters. Entropy of Fast Fourier Transform-based texture metrics was overall most reliable across the two scanners and scanning conditions. Post-processing techniques that reduce image noise while preserving the underlying edges associated with true anatomy or pathology bring about significant differences in radiomic reliability compared to when they were not used. CONCLUSION: Following large-scale validation, identification of reliable CTTA metrics can aid in conducting large-scale multicenter CTTA analysis using sample sets acquired using different imaging protocols, scanners etc.

Preliminary Results of Lung Cancer Screening in a Socioeconomically Disadvantaged Population.

OBJECTIVE: The objective of our study was to describe the preliminary results of our clinical low-dose CT (LDCT) lung cancer screening program targeting a minority, socioeconomically disadvantaged, high-risk population different from that studied in the National Lung Screening Trial (NLST). MATERIALS AND METHODS: Community partner clinics in an underserved region of south Los Angeles County referred interested candidates to our program. All patients met National Comprehensive Cancer Network eligibility criteria for lung cancer screening. RESULTS: From July 21, 2015, through April 3, 2017, 889 individuals were referred to the program. Of the 329 eligible participants, 275 (mean age, 59 years; 52% men) underwent baseline screening LDCT: 84% of patients were black, and 66% had a high school education or less. The median pack-years was 40, and 81% of patients were current smokers. Thirty-one percent of participants reported occupational exposure to one or more known lung carcinogens. Lung CT Screening Reporting and Data System (Lung-RADS) categories were assigned using baseline LDCT examinations: Lung-RADS category 1 or 2 were assigned in 86% of patients, category 3 in 7%, category 4A in 4%, and category 4B or 4X in 3%. Lung cancer has been diagnosed in two of these patients (0.7%) to date: stage IIIB small cell lung carcinoma in one patient and stage IV lung cancer of unknown type in the other patient. Among the 275 patients, 29% had potentially clinically significant incidental findings. CONCLUSION: Lung cancer screening with LDCT in a minority, socioeconomically disadvantaged, high-risk population is feasible but may yield a different lung cancer profile than screening populations in more privileged communities. More follow-up time is required to determine whether the reduction in lung cancer mortality shown in the NLST applies to this underserved population.

Differentiation of Predominantly Solid Enhancing Lipid-Poor Renal Cell Masses by Use of Contrast-Enhanced CT: Evaluating the Role of Texture in Tumor Subtyping.

OBJECTIVE: The purpose of this study was to assess the accuracy of a panel of texture features extracted from clinical CT in differentiating benign from malignant solid enhancing lipid-poor renal masses. MATERIALS AND METHODS: In a retrospective case-control study of 174 patients with predominantly solid nonmacroscopic fat-containing enhancing renal masses, 129 cases of malignant renal cell carcinoma were found, including clear cell, papillary, and chromophobe subtypes. Benign renal masses-oncocytoma and lipid-poor angiomyolipoma-were found in 45 patients. Whole-lesion ROIs were manually segmented and coregistered from the standard-of-care multiphase contrast-enhanced CT (CECT) scans of these patients. Pathologic diagnosis of all tumors was obtained after surgical resection. CECT images of the renal masses were used as inputs to a CECT texture analysis panel comprising 31 texture metrics derived with six texture methods. Stepwise logistic regression analysis was used to select the best predictor among all candidate predictors from each of the texture methods, and their performance was quantified by AUC. RESULTS: Among the texture predictors aiding renal mass subtyping were entropy, entropy of fast-Fourier transform magnitude, mean, uniformity, information measure of correlation 2, and sum of averages. These metrics had AUC values ranging from good (0.80) to excellent (0.98) across the various subtype comparisons. The overall CECT-based tumor texture model had an AUC of 0.87 (p < 0.05) for differentiating benign from malignant renal masses. CONCLUSION: The CT texture statistical model studied was accurate for differentiating benign from malignant solid enhancing lipid-poor renal masses.

A Decision-Support Tool for Renal Mass Classification.

We investigate the viability of statistical relational machine learning algorithms for the task of identifying malignancy of renal masses using radiomics-based imaging features. Features characterizing the texture, signal intensity, and other relevant metrics of the renal mass were extracted from multiphase contrast-enhanced computed tomography images. The recently developed formalism of relational functional gradient boosting (RFGB) was used to learn human-interpretable models for classification. Experimental results demonstrate that RFGB outperforms many standard machine learning approaches as well as the current diagnostic gold standard of visual qualification by radiologists.

S1PR1 Tyr143 phosphorylation downregulates endothelial cell surface S1PR1 expression and responsiveness.

Activation of sphingosine-1-phosphate receptor 1 (S1PR1) plays a key role in repairing endothelial barrier function. We addressed the role of phosphorylation of the three intracellular tyrosine residues of S1PR1 in endothelial cells in regulating the receptor responsiveness and endothelial barrier function regulated by sphingosine 1-phosphate (S1P)-mediated activation of S1PR1. We demonstrated that phosphorylation of only Y143 site was required for S1PR1 internalization in response to S1P. Maximal S1PR1 internalization was seen in 20 min but S1PR1 returned to the cell surface within 1 h accompanied by Y143-dephosphorylation. Cell surface S1PR1 loss paralleled defective endothelial barrier enhancement induced by S1P. Expression of phospho-defective (Y143F) or phospho-mimicking (Y143D) mutants, respectively, failed to internalize or showed unusually high receptor internalization, consistent with the requirement of Y143 in regulating cell surface S1PR1 expression. Phosphorylation of the five S1PR1 C-terminal serine residues did not affect the role of Y143 phosphorylation in signaling S1PR1 internalization. Thus, rapid reduction of endothelial cell surface expression of S1PR1 subsequent to Y143 phosphorylation is a crucial mechanism of modulating S1PR1 signaling, and hence the endothelial barrier repair function of S1P.

Accuracy of Contrast-Enhanced Ultrasound Compared With Magnetic Resonance Imaging in Assessing the Tumor Response After Neoadjuvant Chemotherapy for Breast Cancer.

OBJECTIVES: This pilot study compared contrast enhanced ultrasound (US) with contrast-enhanced magnetic resonance imaging (MRI) in assessing the treatment response in patients with breast cancer receiving preoperative neoadjuvant chemotherapy (NAC). METHODS: This prospective Institutional Review Board-approved and Health Insurance Portability and Accountability Act-compliant study included 30 patients, from January 2014 to October 2015, with invasive breast cancer detected by mammography, conventional US imaging, or both and scheduled for NAC. Informed consent was obtained. Contrast-enhanced US (perflutren lipid microspheres, 10 µL/kg) and MRI (gadopentetate dimeglumine, 0.1 mmol/kg) scans were performed at baseline before starting NAC and after completing NAC before surgery. Results of the imaging techniques were compared with each other and with histopathologic findings obtained at surgery using the Spearman correlation. Tumor size and enhancement parameters were compared for 15 patients with contrast-enhanced US, MRI, and surgical pathologic findings. RESULTS: The median tumor size at baseline was 3.1 cm on both contrast-enhanced US and MRI scans. The Spearman correlation showed strong agreement in tumor size at baseline between contrast-enhanced US and MRI (r = 0.88; P < .001) but less agreement in tumor size after NAC (r = 0.66; P = .004). Trends suggested that contrast-enhanced US (r = 0.75; P < .001) had a better correlation than MRI (r = 0.42; P = .095) with tumor size at surgery. Contrast-enhanced US was as effective as MRI in predicting a complete pathologic response (4 patients; 75.0% accuracy for both) and a non-complete pathologic response (11 patients; 72.7% accuracy for both). CONCLUSIONS: Contrast enhanced US is a valuable imaging modality for assessing the treatment response in patients receiving NAC and had a comparable correlation as MRI with breast cancer size at surgery.

Active Surveillance of Small Renal Masses: A Review on the Role of Imaging With a Focus on Growth Rate.

OBJECTIVE: This study aimed to systematically summarize the current literature in the field of active surveillance for small renal masses, with the primary focus being the role of imaging in the primary decision-making and subsequent follow-up. MATERIALS: A systematic review of the electronic databases PubMed and Web of Knowledge was performed according to Preferred Reporting Items for Systematic Reviews and Meta-analysis statement guidelines. Variables were extracted from the data set and included the following: (1) patient demographics, (2) tumor characteristics, and (3) study design. RESULTS: Twenty-one articles studying imaging in active surveillance of small renal masses were selected. Seventy-two percent (15/21) of studies were retrospective; 19% (4/21) were prospective; and 9% (2/21) studies were bidirectional. Mean age of patients was 69 years (range, 57-81 years). A total of 1386 patients were in the study; 59% of patients were men. Mean follow-up was 39 months (range, 18.8-91.5 months). Sixty-seven percent of masses discussed in this review were followed up using more than one imaging modality; 19% consistently used computed tomography for follow-up whereas the remaining 14% did not specify what imaging modality was used. Imaging studies were reviewed by the investigators centrally in 86% (18/21). In 14% of the studies, only imaging report was reviewed. Biopsy was performed in 24% of masses. Mean growth rate for all tumors was 0.27 cm/y (range, 0.06-0.7 cm/y). For studies where growth rate of benign and malignant masses were differentiated, mean growth rate for benign masses was 0.3 cm/y and mean growth rate for malignant masses was 0.35 cm/y. CONCLUSIONS: Growth rate is often used as a discriminant in following up a small renal mass in patients undergoing active surveillance. However, there is great variability in growth rate and it alone is not an adequate marker for determining whether the tumor is malignant. Because very few studies specified radiological characteristics of small renal masses, future studies can be done to better characterize masses.

CT prediction of the Fuhrman grade of clear cell renal cell carcinoma (RCC): towards the development of computer-assisted diagnostic method.

PURPOSE: There are distinct quantifiable features characterizing renal cell carcinomas on contrast-enhanced CT examinations, such as peak tumor enhancement, tumor heterogeneity, and percent contrast washout. While qualitative visual impressions often suffice for diagnosis, quantitative metrics if developed and validated can add to the information available from standard of care diagnostic imaging. The purpose of this study is to assess the use of quantitative enhancement metrics in predicting the Fuhrman grade of clear cell RCC. MATERIALS AND METHODS: 65 multiphase CT examinations with clear cell RCCs were utilized, 44 tumors with Fuhrman grades 1 or 2 and 21 tumors with grades 3 or 4. After tumor segmentation, the following data were extracted: histogram analysis of voxel-based whole lesion attenuation in each phase, enhancement and washout using mean, median, skewness, kurtosis, standard deviation, and interquartile range. RESULTS: Statistically significant difference was observed in 4 measured parameters between grades 1-2 and grades 3-4: interquartile range of nephrographic attenuation values, standard deviation of absolute enhancement, as well as interquartile range and standard deviation of residual nephrographic enhancement. Interquartile range of nephrographic attenuation values was 292.86 HU for grades 1-2 and 241.19 HU for grades 3-4 (p value 0.02). Standard deviation of absolute enhancement was 41.26 HU for grades 1-2 and 34.66 HU for grades 3-4 (p value 0.03). Interquartile range was 297.12 HU for residual nephrographic enhancement for grades 1-2 and 235.57 HU for grades 3-4 (p value 0.02), and standard deviation of the same was 42.45 HU for grades 1-2 and 37.11 for grades 3-4 (p value 0.04). CONCLUSION: Our results indicate that absolute enhancement is more heterogeneous for lower grade tumors and that attenuation and residual enhancement in nephrographic phase is more heterogeneous for lower grade tumors. This represents an important step in devising a predictive non-invasive model to predict the nucleolar grade.

Contrast-Enhanced Sonography for Monitoring Neoadjuvant Chemotherapy in Soft Tissue Sarcomas.

Neoadjuvant chemotherapy is a mainstay in treating soft tissue sarcomas. Soft tissue sarcomas can show an increase in size and central necrosis, with a decrease in the viable tumor, as an initial response to neoadjuvant chemotherapy. Thus, the maximum tumor diameter may not reliably assess the response to this therapy. Contrast-enhanced sonography may address this limitation. We evaluated 4 patients with soft tissue sarcomas by contrast-enhanced sonography, performed concomitantly with conventional imaging (computed tomography, magnetic resonance imaging, or positron emission tomography). Quantitative analysis was also performed on 1 sarcoma. A viable, enhancing tumor versus tumor necrosis was nearly identical on contrast-enhanced sonography and conventional imaging. Preliminary results demonstrate potential for contrast-enhanced sonographic monitoring of soft tissue sarcomas during neoadjuvant chemotherapy.

Predicting Soft Tissue Sarcoma Response to Neoadjuvant Chemotherapy Using an MRI-Based Delta-Radiomics Approach.

OBJECTIVES: To evaluate the performance of machine learning-augmented MRI-based radiomics models for predicting response to neoadjuvant chemotherapy (NAC) in soft tissue sarcomas. METHODS: Forty-four subjects were identified retrospectively from patients who received NAC at our institution for pathologically proven soft tissue sarcomas. Only subjects who had both a baseline MRI prior to initiating chemotherapy and a post-treatment scan at least 2 months after initiating chemotherapy and prior to surgical resection were included. 3D ROIs were used to delineate whole-tumor volumes on pre- and post-treatment scans, from which 1708 radiomics features were extracted. Delta-radiomics features were calculated by subtraction of baseline from post-treatment values and used to distinguish treatment response through univariate analyses as well as machine learning-augmented radiomics analyses. RESULTS: Though only 4.74% of variables overall reached significance at p ≤ 0.05 in univariate analyses, Laws Texture Energy (LTE)-derived metrics represented 46.04% of all such features reaching statistical significance. ROC analyses similarly failed to predict NAC response, with AUCs of 0.40 (95% CI 0.22-0.58) and 0.44 (95% CI 0.26-0.62) for RF and AdaBoost, respectively. CONCLUSION: Overall, while our result was not able to separate NAC responders from non-responders, our analyses did identify a subset of LTE-derived metrics that show promise for further investigations. Future studies will likely benefit from larger sample size constructions so as to avoid the need for data filtering and feature selection techniques, which have the potential to significantly bias the machine learning procedures.

Plakoglobin regulates cell motility through Rho- and fibronectin-dependent Src signaling.

We previously showed that the cell-cell junction protein plakoglobin (PG) not only suppresses motility of keratinocytes in contact with each other, but also, unexpectedly, of single cells. Here we show that PG deficiency results in extracellular matrix (ECM)-dependent disruption of mature focal adhesions and cortical actin organization. Plating PG⁻/⁻ cells onto ECM deposited by PG+/⁻ cells partially restored normal cell morphology and inhibited PG⁻/⁻ cell motility. In over 70 adhesion molecules whose expression we previously showed to be altered in PG⁻/⁻ cells, a substantial decrease in fibronectin (FN) in PG⁻/⁻ cells stood out. Re-introduction of PG into PG⁻/⁻ cells restored FN expression, and keratinocyte motility was reversed by plating PG⁻/⁻ cells onto FN. Somewhat surprisingly, based on previously reported roles for PG in regulating gene transcription, PG-null cells exhibited an increase, not a decrease, in FN promoter activity. Instead, PG was required for maintenance of FN mRNA stability. PG⁻/⁻ cells exhibited an increase in activated Src, one of the kinases controlled by FN, a phenotype reversed by plating PG⁻/⁻ cells on ECM deposited by PG+/⁻ keratinocytes. PG⁻/⁻ cells also exhibited Src-independent activation of the small GTPases Rac1 and RhoA. Both Src and RhoA inhibition attenuated PG⁻/⁻ keratinocyte motility. We propose a novel role for PG in regulating cell motility through distinct ECM-Src and RhoGTPase-dependent pathways, influenced in part by PG-dependent regulation of FN mRNA stability.

Detection of differentially expressed basal cell proteins by mass spectrometry.

The ability of cells to modulate interactions with each other and the substrate is essential for epithelial tissue remodeling during processes such as wound healing and tumor progression. However, despite strides made in the field of proteomics, proteins involved in adhesion have been difficult to study. Here, we report a method for the enrichment and analysis of proteins associated with the basal surface of the cell and its underlying matrix. The enrichment involves deroofing the cells with 20 mM ammonium hydroxide and the removal of cytosolic and organellar proteins by stringent water wash. Proteomic profiling was achieved by LC-FTMS, which allowed comparison of differentially expressed or shared proteins under different cell states. First, we analyzed and compared the basal cell components of mouse keratinocytes lacking the cell-cell junction molecule plakoglobin with their control counterparts. Changes in the molecules involved in motility and invasion were detected in plakoglobin-deficient cells, including decreased detection of fibronectin, integrin beta(4), and FAT tumor suppressor. Second, we assessed the differences in basal cell components between two human oral squamous cell carcinoma lines originating from different sites in the oral cavity (CAL33 and UM-SCC-1). The data show differences between the two lines in the type and abundance of proteins specific to cell adhesion, migration, and angiogenesis. Therefore, the method described here has the potential to serve as a platform to assess proteomic changes in basal cell components including extracellular and adhesion-specific proteins involved in wound healing, cancer, and chronic and acquired adhesion-related disorders.

Imaging of Benign and Malignant Breast Lesions Using Contrast-Enhanced Ultrasound: A Pictorial Essay.

ABSTRACT: Contrast-enhanced ultrasound is a promising noninvasive imaging technique for evaluating benign and malignant breast lesions, as contrast provides information about perfusion and microvasculature. Contrast-enhanced ultrasound is currently off-label use in the breast in the United States, but its clinical and investigational use in breast imaging is gaining popularity. It is important for radiologists to be familiar with the imaging appearances of benign and malignant breast masses using contrast-enhanced ultrasound. This pictorial essay illustrates enhancement patterns of various breast masses from our own experience. Pathologies include subtypes of invasive breast cancer, fibroadenomas, papillary lesions, fibrocystic change, and inflammatory processes. Contrast-enhanced ultrasound pitfalls and limitations are discussed.

Characterizing breast masses using an integrative framework of machine learning and CEUS-based radiomics.

AIMS: We evaluated the performance of contrast-enhanced ultrasound (CEUS) based on radiomics analysis to distinguish benign from malignant breast masses. METHODS: 131 women with suspicious breast masses (BI-RADS 4a, 4b, or 4c) who underwent CEUS examinations (using intravenous injection of perflutren lipid microsphere or sulfur hexafluoride lipid-type A microspheres) prior to ultrasound-guided biopsies were retrospectively identified. Post biopsy pathology showed 115 benign and 16 malignant masses. From the cine clip of the CEUS exams obtained using the built-in GE scanner software, breast masses and adjacent normal tissue were then manually segmented using the ImageJ software. One frame representing each of the four phases: precontrast, early, peak, and delay enhancement were selected post segmentation from each CEUS clip. 112 radiomic metrics were extracted from each segmented tissue normalized breast mass using custom Matlab® code. Linear and nonlinear machine learning (ML) methods were used to build the prediction model to distinguish benign from malignant masses. tenfold cross-validation evaluated model performance. Area under the curve (AUC) was used to quantify prediction accuracy. RESULTS: Univariate analysis found 35 (38.5%) radiomic variables with p < 0.05 in differentiating between benign from malignant masses. No feature selection was performed. Predictive models based on AdaBoost reported an AUC = 0.72 95% CI (0.56, 0.89), followed by Random Forest with an AUC = 0.71 95% CI (0.56, 0.87). CONCLUSIONS: CEUS based texture metrics can distinguish between benign and malignant breast masses, which can, in turn, lead to reduced unnecessary breast biopsies.