and receiving personal fees and equity from Nava Health. No other disclosures were reported.

No abstract

No abstract

Contrast-enhanced digital mammography (CEDM) can provide improved breast cancer detection and characterization compared to conventional mammography by imaging the effects of tumour angiogenesis. Current small-molecule contrast agents used for CEDM are limited by a short plasma half-life and rapid extravasation into tissue interstitial space. To address these limitations, nanoscale agents that can remain intravascular except at sites of tumour angiogenesis can be used. For CEDM, this agent must be both biocompatible and strongly attenuate mammographic energy x-rays. Nanoscale perfluorooctylbromide (PFOB) droplets have good x-ray attenuation and have been used in patients for other applications. However, the macroscopic scale of x-ray imaging (50-100 µm) is inadequate for direct verification that PFOB droplets localize at sites of breast tumour angiogenesis. For efficient pre-clinical optimization for CEDM, we integrated an optical marker into PFOB droplets for microscopic assessment (≪50 µm). To develop PFOB droplets as a new nanoscale mammographic contrast agent, PFOB droplets were labelled with fluorescent quantum dots (QDs). The droplets had mean diameters of 160 nm, fluoresced at 635 nm and attenuated x-ray spectra at 30.5 keV mean energy with a relative attenuation of 5.6 ± 0.3 Hounsfield units (HU) mg(-1) mL(-1) QD-PFOB. With the agent loaded into tissue phantoms, good correlation between x-ray attenuation and optical fluorescence was found (R(2) = 0.96), confirming co-localization of the QDs with PFOB for quantitative assessment using x-ray or optical methods. Furthermore, the QDs can be removed from the PFOB agent without affecting its x-ray attenuation or structural properties for expedited translation of optimized PFOB droplet formulations into patients.

Purpose: Accurate segmentation of the hippocampus for hippocampal avoidance whole-brain radiotherapy currently requires high-resolution magnetic resonance imaging (MRI) in addition to neuroanatomic expertise for manual segmentation. Removing the need for MR images to identify the hippocampus would reduce planning complexity, the need for a treatment planning MR imaging session, potential uncertainties associated with MRI-computed tomography (CT) image registration, and cost. Three-dimensional (3D) deep convolutional network models have the potential to automate hippocampal segmentation. In this study, we investigate the accuracy and reliability of hippocampal segmentation by automated deep learning models from CT alone and compare the accuracy to experts using MRI fusion. Methods: Retrospectively, 390 Gamma Knife patients with high-resolution CT and MR images were collected. Following the RTOG 0933 guidelines, images were rigidly fused, and a neuroanatomic expert contoured the hippocampus on the MR, then transferred the contours to CT. Using a calculated cranial centroid, the image volumes were cropped to 200 9 200 9 35 voxels, which were used to train four models, including our proposed Attention-Gated 3D ResNet (AG-3D ResNet). These models were then compared with results from a nested tenfold validation. From the predicted test set volumes, we calculated the 100% Hausdorff distance (HD). Acceptability was assessed using the RTOG 0933 protocol criteria, and contours were considered passing with HD ≤ 7 mm. Results: The bilateral hippocampus passing rate across all 90 models trained in the nested cross-fold validation was 80.2% for AG-3D ResNet, which performs with a comparable pass rate (P = 0.3345) to physicians during centralized review for the RTOG 0933 Phase II clinical trial. Conclusions: Our proposed AG-3D ResNet's segmentation of the hippocampus from noncontrast CT images alone are comparable to those obtained by participating physicians from the RTOG 0933 Phase II clinical trial.