Analysis of Deep Ultraviolet Fluorescence Images for Intraoperative Breast Tumor Margin Assessment.

Positive margin status after breast-conserving surgery (BCS) is a predictor of higher rates of local recurrence. Intraoperative margin assessment aims to achieve negative surgical margin status at the first operation, thus reducing the re-excision rates that are usually associated with potential surgical complications, increased medical costs, and mental pressure on patients. Microscopy with ultraviolet surface excitation (MUSE) can rapidly image tissue surfaces with subcellular resolution and sharp contrasts by utilizing the nature of the thin optical sectioning thickness of deep ultraviolet light. We have previously imaged 66 fresh human breast specimens that were topically stained with propidium iodide and eosin Y using a customized MUSE system. To achieve objective and automated assessment of MUSE images, a machine learning model is developed for binary (tumor vs. normal) classification of obtained MUSE images. Features extracted by texture analysis and pre-trained convolutional neural networks (CNN) have been investigated for sample descriptions. A sensitivity, specificity, and accuracy better than 90% have been achieved for detecting tumorous specimens. The result suggests the potential of MUSE with machine learning being utilized for intraoperative margin assessment during BCS.

Accurate Image Reconstruction in Dual-Energy CT with Limited-Angular-Range Data Using a Two-Step Method.

Dual-energy CT (DECT) with scans over limited-angular ranges (LARs) may allow reductions in scan time and radiation dose and avoidance of possible collision between the moving parts of a scanner and the imaged object. The beam-hardening (BH) and LAR effects are two sources of image artifacts in DECT with LAR data. In this work, we investigate a two-step method to correct for both BH and LAR artifacts in order to yield accurate image reconstruction in DECT with LAR data. From low- and high-kVp LAR data in DECT, we first use a data-domain decomposition (DDD) algorithm to obtain LAR basis data with the non-linear BH effect corrected for. We then develop and tailor a directional-total-variation (DTV) algorithm to reconstruct from the LAR basis data obtained basis images with the LAR effect compensated for. Finally, using the basis images reconstructed, we create virtual monochromatic images (VMIs), and estimate physical quantities such as iodine concentrations and effective atomic numbers within the object imaged. We conduct numerical studies using two digital phantoms of different complexity levels and types of structures. LAR data of low- and high-kVp are generated from the phantoms over both single-arc (SA) and two-orthogonal-arc (TOA) LARs ranging from 14∘ to 180∘. Visual inspection and quantitative assessment of VMIs obtained reveal that the two-step method proposed can yield VMIs in which both BH and LAR artifacts are reduced, and estimation accuracy of physical quantities is improved. In addition, concerning SA and TOA scans with the same total LAR, the latter is shown to yield more accurate images and physical quantity estimations than the former. We investigate a two-step method that combines the DDD and DTV algorithms to correct for both BH and LAR artifacts in image reconstruction, yielding accurate VMIs and estimations of physical quantities, from low- and high-kVp LAR data in DECT. The results and knowledge acquired in the work on accurate image reconstruction in LAR DECT may give rise to further understanding and insights into the practical design of LAR scan configurations and reconstruction procedures for DECT applications.

Spectral calibration of photon-counting detectors at high photon flux.

BACKGROUND: Calibration of photon-counting detectors (PCDs) is necessary for quantitatively accurate spectral computed tomography (CT), but the calibration process can be complicated by nonlinear flux-dependent physical factors such as pulse pile-up. PURPOSE: This work develops a method for spectral sensitivity calibration of a PCD-based spectral CT system that incorporates nonlinear flux dependence and can thus be employed at high photon flux. METHODS: A calibration model for the spectral response and polynomial flux dependence is proposed, which incorporates prior x-ray source spectrum and PCD models and that has a small set of parameters for adjusting to the spectral CT system of interest. The model parameters are determined by fitting transmission data from a known object of known composition: a step-wedge phantom composed of different thicknesses of aluminum, a bone equivalent, and polymethyl methacrylate (PMMA), a soft-tissue equivalent. This fitting employs Tikhonov regularization, and the regularization strength and the polynomial order for the intensity modeling are determined by bias and variance analysis. The spectral calibration and nonlinear intensity correction is validated on transmission measurements through a third material, Teflon, at different x-ray photon flux levels. RESULTS: The nonlinear intensity dependence is determined to be accurately accounted for with a third-order polynomial. The calibrated spectral CT model accurately predicts Teflon transmission to within 1% for flux levels up to 50% of the detector maximum. CONCLUSIONS: The proposed PCD calibration method enables accurate physical modeling necessary for quantitative imaging in spectral CT. Furthermore, the model applies to high flux settings so that acquisition times will not be limited by restricting the spectral CT system to low flux levels.

Technical note: Evaluation of a V-Net autosegmentation algorithm for pediatric CT scans: Performance, generalizability, and application to patient-specific CT dosimetry.

PURPOSE: This study developed and evaluated a fully convolutional network (FCN) for pediatric CT organ segmentation and investigated the generalizability of the FCN across image heterogeneities such as CT scanner model protocols and patient age. We also evaluated the autosegmentation models as part of a software tool for patient-specific CT dose estimation. METHODS: A collection of 359 pediatric CT datasets with expert organ contours were used for model development and evaluation. Autosegmentation models were trained for each organ using a modified FCN 3D V-Net. An independent test set of 60 patients was withheld for testing. To evaluate the impact of CT scanner model protocol and patient age heterogeneities, separate models were trained using a subset of scanner model protocols and pediatric age groups. Train and test sets were split to answer questions about the generalizability of pediatric FCN autosegmentation models to unseen age groups and scanner model protocols, as well as the merit of scanner model protocol or age-group-specific models. Finally, the organ contours resulting from the autosegmentation models were applied to patient-specific dose maps to evaluate the impact of segmentation errors on organ dose estimation. RESULTS: Results demonstrate that the autosegmentation models generalize to CT scanner acquisition and reconstruction methods which were not present in the training dataset. While models are not equally generalizable across age groups, age-group-specific models do not hold any advantage over combining heterogeneous age groups into a single training set. Dice similarity coefficient (DSC) and mean surface distance results are presented for 19 organ structures, for example, median DSC of 0.52 (duodenum), 0.74 (pancreas), 0.92 (stomach), and 0.96 (heart). The FCN models achieve a mean dose error within 5% of expert segmentations for all 19 organs except for the spinal canal, where the mean error was 6.31%. CONCLUSIONS: Overall, these results are promising for the adoption of FCN autosegmentation models for pediatric CT, including applications for patient-specific CT dose estimation.

Enhancing Reproductive Organ Segmentation in Pediatric CT via Adversarial Learning.

Accurately segmenting organs in abdominal computed tomography (CT) scans is crucial for clinical applications such as pre-operative planning and dose estimation. With the recent advent of deep learning algorithms, many robust frameworks have been proposed for organ segmentation in abdominal CT images. However, many of these frameworks require large amounts of training data in order to achieve high segmentation accuracy. Pediatric abdominal CT images containing reproductive organs are particularly hard to obtain since these organs are extremely sensitive to ionizing radiation. Hence, it is extremely challenging to train automatic segmentation algorithms on organs such as the uterus and the prostate. To address these issues, we propose a novel segmentation network with a built-in auxiliary classifier generative adversarial network (ACGAN) that conditionally generates additional features during training. The proposed CFG-SegNet (conditional feature generation segmentation network) is trained on a single loss function which combines adversarial loss, reconstruction loss, auxiliary classifier loss and segmentation loss. 2.5D segmentation experiments are performed on a custom data set containing 24 female CT volumes containing the uterus and 40 male CT volumes containing the prostate. CFG-SegNet achieves an average segmentation accuracy of 0.929 DSC (Dice Similarity Coefficient) on the prostate and 0.724 DSC on the uterus with 4-fold cross validation. The results show that our network is high-performing and has the potential to precisely segment difficult organs with few available training images.

Assessing the Influence of OCT-A Device and Scan Size on Retinal Vascular Metrics.

Purpose: The purpose of this study was to investigate the effect of device and scan size on quantitative optical coherence tomography angiography (OCT-A) metrics. Methods: The 3 × 3 mm scans from Optovue AngioVue and Zeiss AngioPlex systems were included for 18 eyes of 18 subjects without ocular pathology. The foveal avascular zone (FAZ) was segmented manually by two observers, from which estimates of FAZ area (using both the nominal image scale and the axial length corrected image scale) and acircularity were derived. Three scan sizes (3 mm, 6 mm HD, and 8 mm) from the AngioVue system were included for 15 eyes of 15 subjects without ocular pathology. For each subject, larger image sizes were resized to the same resolution as 3 × 3 mm scans, aligned, then cropped to a common area. FAZ area, FAZ acircularity, average and total parafoveal intercapillary area, vessel density, and vessel end points were computed. Results: Between the devices used here, there were no significant differences in FAZ acircularity (P = 0.88) or FAZ area using scaled (P = 0.11) or unscaled images (P = 0.069). Although there was no significant difference in FAZ area across scan sizes (P = 0.30), vessel morphometry metrics were all significantly influenced by scan size. Conclusions: The scan devices and sizes used here do not affect FAZ area measures derived from manual segmentations. In contrast, vessel morphometry metrics are affected by scan size. As individual differences in axial length induce differences in absolute scan size, extreme care should be taken when interpreting metrics of vessel morphometry, both between and within OCT-A devices. Translational Relevance: A better characterization of the confounds surrounding OCT-A retinal vasculature metrics can lead to improved application of these metrics as biomarkers for retinal and systemic diseases.

Technical Note: Enhancing soft tissue contrast and radiation-induced image changes with dual-energy CT for radiation therapy.

PURPOSE: The purpose of this work is to investigate the use of low-energy monoenergetic decompositions obtained from dual-energy CT (DECT) to enhance image contrast and the detection of radiation-induced changes of CT textures in pancreatic cancer. METHODS: The DECT data acquired for 10 consecutive pancreatic cancer patients during routine nongated CT-guided radiation therapy (RT) using an in-room CT (Definition AS Open, Siemens Healthcare, Malvern, PA) were analyzed. With a sequential DE protocol, the scanner rapidly performs two helical acquisitions, the first at a tube voltage of 80 kVp and the second at a tube voltage of 140 kVp. Virtual monoenergetic images across a range of energies from 40 to 140 keV were reconstructed using an image-based material decomposition. Intravenous (IV) bolus-free contrast enhancement in pancreas patient tumors was measured across a spectrum of monoenergies. For treatment response assessment, the changes in CT histogram features (including mean CT number (MCTN), entropy, kurtosis) in pancreas tumors were measured during treatment. The results from the monoenergetic decompositions were compared to those obtained from the standard 120 kVp CT protocol for the same subjects. RESULTS: Data of monoenergetic decompositions of the 10 patients confirmed the expected enhancement of soft tissue contrast as the energy is decreased. The changes in the selected CT histogram features in the pancreas during RT delivery were amplified with the low-energy monoenergetic decompositions, as compared to the changes measured from the 120 kVp CTs. For the patients studied, the average reduction in the MCTN in pancreas from the first to the last (the 28th) treatment fraction was 4.09 HU for the standard 120 kVp and 11.15 HU for the 40 keV monoenergetic decomposition. CONCLUSIONS: Low-energy monoenergetic decompositions from DECT substantially increase soft tissue contrast and increase the magnitude of radiation-induced changes in CT histogram textures during RT delivery for pancreatic cancer. Therefore, quantitative DECT may assist the detection of early RT response.

An algorithm for constrained one-step inversion of spectral CT data.

We develop a primal-dual algorithm that allows for one-step inversion of spectral CT transmission photon counts data to a basis map decomposition. The algorithm allows for image constraints to be enforced on the basis maps during the inversion. The derivation of the algorithm makes use of a local upper bounding quadratic approximation to generate descent steps for non-convex spectral CT data discrepancy terms, combined with a new convex-concave optimization algorithm. Convergence of the algorithm is demonstrated on simulated spectral CT data. Simulations with noise and anthropomorphic phantoms show examples of how to employ the constrained one-step algorithm for spectral CT data.

Quantifying the tibiofemoral joint space using x-ray tomosynthesis.

PURPOSE: Digital x-ray tomosynthesis (DTS) has the potential to provide 3D information about the knee joint in a load-bearing posture, which may improve diagnosis and monitoring of knee osteoarthritis compared with projection radiography, the current standard of care. Manually quantifying and visualizing the joint space width (JSW) from 3D tomosynthesis datasets may be challenging. This work developed a semiautomated algorithm for quantifying the 3D tibiofemoral JSW from reconstructed DTS images. The algorithm was validated through anthropomorphic phantom experiments and applied to three clinical datasets. METHODS: A user-selected volume of interest within the reconstructed DTS volume was enhanced with 1D multiscale gradient kernels. The edge-enhanced volumes were divided by polarity into tibial and femoral edge maps and combined across kernel scales. A 2D connected components algorithm was performed to determine candidate tibial and femoral edges. A 2D joint space width map (JSW) was constructed to represent the 3D tibiofemoral joint space. To quantify the algorithm accuracy, an adjustable knee phantom was constructed, and eleven posterior-anterior (PA) and lateral DTS scans were acquired with the medial minimum JSW of the phantom set to 0-5 mm in 0.5 mm increments (VolumeRad™, GE Healthcare, Chalfont St. Giles, United Kingdom). The accuracy of the algorithm was quantified by comparing the minimum JSW in a region of interest in the medial compartment of the JSW map to the measured phantom setting for each trial. In addition, the algorithm was applied to DTS scans of a static knee phantom and the JSW map compared to values estimated from a manually segmented computed tomography (CT) dataset. The algorithm was also applied to three clinical DTS datasets of osteoarthritic patients. RESULTS: The algorithm segmented the JSW and generated a JSW map for all phantom and clinical datasets. For the adjustable phantom, the estimated minimum JSW values were plotted against the measured values for all trials. A linear fit estimated a slope of 0.887 (R² = 0.962) and a mean error across all trials of 0.34 mm for the PA phantom data. The estimated minimum JSW values for the lateral adjustable phantom acquisitions were found to have low correlation to the measured values (R² = 0.377), with a mean error of 2.13 mm. The error in the lateral adjustable-phantom datasets appeared to be caused by artifacts due to unrealistic features in the phantom bones. JSW maps generated by DTS and CT varied by a mean of 0.6 mm and 0.8 mm across the knee joint, for PA and lateral scans. The tibial and femoral edges were successfully segmented and JSW maps determined for PA and lateral clinical DTS datasets. CONCLUSIONS: A semiautomated method is presented for quantifying the 3D joint space in a 2D JSW map using tomosynthesis images. The proposed algorithm quantified the JSW across the knee joint to sub-millimeter accuracy for PA tomosynthesis acquisitions. Overall, the results suggest that x-ray tomosynthesis may be beneficial for diagnosing and monitoring disease progression or treatment of osteoarthritis by providing quantitative images of JSW in the load-bearing knee.