Search

Objective: Establish a workflow that utilizes convolutional neural nets (CNN) to classify solid, lipid-poor, contrast enhancing renal masses using multiphase contrast enhanced CT (CECT) images and to assess the performance of the resulting network., Methods: In this institutional review board approved study of 143 patients with predominantly solid, lipid-poor, contrast enhancing renal lesions (46 benign and 97 malignant), patients with a pre-operative multiphase CECT of the abdomen and pelvis obtained between June 2009 and June 2015 were retrospectively queried. Benign renal masses included oncocytoma and lipid-poor angiomyolipoma and the malignant group included clear cell, papillary, and chromophobe carcinomas.Region of interests of whole tumor volumes were manually segmented, and CT phase images with the largest cross-section of the segmented tumor in the axial plane were used for assessment. Post-surgical pathological evaluation was used to establish diagnosis.The segmented images of renal masses were used as input to a CNN. The data were augmented and split into training (83.9%) and validation sets (16.1%) to determine the hyperparameters of the CNN. Thereafter. the performance of the resulting CNN was quantified using eightfold cross-validation., Results: The CNN-based classifier demonstrated an overall accuracy of 78% (95% confidence interval: 76-80%), sensitivity of 70% (95% confidence interval: 66-74%), specificity of 81% (79-83%) and an area under the curve of 0.82., Conclusion: A CNN-based classifier to diagnose solid enhancing malignant renal masses based on multiphase CECT images was developed., Advances in Knowledge: It was established that a CNN-based classifier could be trained to accurately distinguish malignant renal lesions.

A systematic search was conducted to categorize targeted ultrasound contrast agents (UCAs) used in cancer-related angiogenesis detection. We identified 15 unique contrast agents from 2008 to March 2018. Most primary research articles studied UCAs targeted to vascular endothelial growth factor receptor or α v β 3 -integrin. Breast cancer and colon cancer are the most common neoplastic processes in which these agents were studied. BR55 (Bracco Research SA, Geneva, Switzerland), a vascular endothelial growth factor receptor-targeting UCA, is the first targeted UCA that has completed phase 0 trials. Our review identifies a gap in the literature regarding the application of targeted UCAs in cancer models beyond breast and colon cancers and identifies other promising UCAs., (© 2019 by the American Institute of Ultrasound in Medicine.)

Objective: To study the feasibility of contrast-enhanced ultrasound (CEUS) for identification of SLN associated with cutaneous melanoma., Study Design: Single arm pilot study in a swine animal model., Methods: One milliliter of perflubutane (Sonazoid, GE Healthcare, Milwaukee, WI) was injected into the peritumoral dermis in five swine with cutaneous melanoma. Ultrasonography was used to follow enhancing lymphatic channels to lymph nodes (LN). Intradermal injection of vital blue (VB) dye was used as a positive control. LN identified by either method were excised and examined histologically., Results: There were five primary cutaneous melanomas with mean area of 4.36 ± 4.75 cm 2 and Breslow depth of 3.6 ± 1.5 mm. Six possible sentinel lymph node (SLN)s were identified with CEUS, and nine were identified with VB. SLN averaged 12.44 ± 6.15 cm from the primary tumor. Four of six (67%) SLNs identified by CEUS and four of nine (44%) candidate SLNs identified by VB contained histologically confirmed metastatic melanoma. All six CEUS-identified SLNs were also identified with VB. Two LNs not containing melanoma were identified by CEUS; three were identified with VB. In all SLN with metastases, metastatic cells were scattered throughout the LN and not clustered in a discrete mass., Conclusion: CEUS with perflubutane feasibly identifies SLN associated with cutaneous melanoma and may be a useful adjunct technology in facilitating precise SLN dissection. Our work supports a clinical trial investigating the use of CEUS for this application., Level of Evidence: NA Laryngoscope, 129:1117-1122, 2019., (© 2018 The American Laryngological, Rhinological and Otological Society, Inc.)

The optimal strategy for imaging after focal therapy for prostate cancer is evolving. This series is an initial report on the use of contrast-enhanced transrectal ultrasound (TRUS) in follow-up of patients after high-intensity focused ultrasound (HIFU) hemiablation for prostate cancer. In 7 patients who underwent HIFU hemiablation, contrast-enhanced TRUS findings were as follows: (1) contrast-enhanced TRUS clearly showed the HIFU ablation defect as a sharply marginated nonenhancing zone in all patients; (2) contrast-enhanced TRUS identified suspicious foci of recurrent enhancement within the ablation zone in 2 patients, facilitating image-guided prostate biopsy, which showed prostate cancer; and (3) contrast-enhanced TRUS findings correlated with multiparametric magnetic resonance imaging and biopsy histologic findings., (© 2018 by the American Institute of Ultrasound in Medicine.)

Liposarcoma is the most common paratesticular scrotal malignancy. Ultrasound is the conventional imaging modality for evaluating scrotal masses. Contrast-enhanced ultrasound (CEUS) can provide complementary information by identifying distinct enhancement patterns. We present CEUS findings of 2 concurrent soft tissue masses in 1 patient: a spermatic cord well-differentiated liposarcoma and a retroperitoneal dedifferentiated liposarcoma. We review the Doppler ultrasound, computed tomography, and histopathologic appearances of low- versus high-grade liposarcomas in addition to the utility of CEUS with quantitative analysis in potentially grading liposarcomas.

The clinical use of noncardiac contrast-enhanced ultrasound scan (CEUS) has been steadily gaining momentum. CEUS is a reliable and safe technique with a diverse array of applications. This article reviews the current and potential future clinical applications of CEUS. Emphasis will be placed on evaluating focal lesions with the liver and kidney. Contrast agent composition and mechanism are also briefly reviewed., (Copyright © 2014 Elsevier Inc. All rights reserved.)

Purpose: To compare iodixanol-enhanced multidetector-row computed tomography angiography (MDCTA) with digital subtraction angiography (DSA), perioperative angiography, or surgical findings in the evaluation of the abdominal aorta and its main branches., Material and Methods: 173 patients with known or suspected aortic aneurysms or stenosis/occlusion of the abdominal aorta or its major branches were enrolled. The iso-osmolar contrast medium iodixanol (320 mg Iota/ml) was used, and data were acquired using four-, eight-, or 16-active-detector-row scanners. Reference diagnoses were provided by surgical findings, interventional findings, or DSA. Diagnostic accuracy was estimated with reference to surgery or interventional arteriography or DSA. Image quality was assessed as excellent, good, sufficient, or insufficient, and correlations were made with attenuation values in the aortic lumen. Tolerability of iodixanol was monitored during the injection for discomfort and other adverse events, and for 72 hours after contrast injection., Results: In 132 of 136 evaluable cases, MDCTA diagnosis matched the reference diagnosis, yielding an agreement rate of 97.1% (95% CI 92.6-99.2%). The quality of most MDCTA scans (147/173) was rated as excellent. Overall mean attenuation was 305.7 HU. MDCTA appeared more accurate than DSA for identification of lesion calcification, thrombus, irregularity, and ulceration. Tolerability of iodixanol was good, and no serious adverse events were reported., Conclusion: MDCTA using iodixanol is a promising, noninvasive alternative for evaluating patients with abdominal aortic disease.