Leng, Shuai

AbstractObjectiveTo measure the accuracy of material decomposition using a dual‐source photon‐counting‐detector (DS‐PCD) CT operated in the high‐pitch helical scanning mode and compare the results against dual‐source energy‐integrating‐detector (DS‐EID) CT, which requires use of a low‐pitch value in dual‐energy mode.MethodsA DS‐PCD CT and a DS‐EID CT were used to scan a cardiac motion phantom consisting of a 3‐mm diameter iodine cylinder. Iodine maps were reconstructed using DS‐PCD in high‐pitch mode and DS‐EID in low‐pitch mode. Image‐based circularity, diameter, and iodine concentration of the iodine cylinder were calculated and compared between the two scanners. With institutional review board approval, in vivo exams were performed with the DS‐PCD CT in high‐pitch mode. Images were qualitatively compared against patients with similar heart rates that were scanned with DS‐EID CT in low‐pitch dual‐energy mode.ResultsOn iodine maps, the mean circularity was 0.97 ± 0.02 with DS‐PCD in high‐pitch mode and 0.95 ± 0.06 with DS‐EID in low‐pitch mode. The mean diameter was 2.9 ± 0.2 mm with DS‐PCD and 3.1 ± 0.2 mm with DS‐EID, both of which are close to the 3 mm ground truth. For DS‐PCD, the mean iodine concentration was 9.6 ± 0.8 mg/ml and this was consistent with the 9.4 ± 0.6 mg/ml value obtained with the cardiac motion disabled. For DS‐EID, the concentration was 12.7 ± 1.2 mg/ml with motion enabled and 11.7 ± 0.5 mg/ml disabled. The background noise in the iodine maps was 15.1 HU with DS‐PCD and 14.4 HU with DS‐EID, whereas the volume CT dose index (CTDIvol) was 3 mGy with DS‐PCD and 11 mGy with DS‐EID. On comparison of six patients (three on PCD, three on EID) with similar heart rates, DS‐PCD provided iodine maps with well‐defined coronaries even at a high heart rate of 86 beats per minute. Meanwhile, there were substantial motion artifacts in iodine maps obtained with DS‐EID for patients with similar heart rates.ConclusionIn a cardiac motion phantom, DS‐PCD CT can perform accurate material decomposition in high‐pitch mode, providing iodine maps with excellent geometric accuracy and robustness to motion at approximately 38% of the dose for similar noise as DS‐EID CT.

AbstractBackgroundDeep artificial neural networks such as convolutional neural networks (CNNs) have been shown to be effective models for reducing noise in CT images while preserving anatomic details. A practical bottleneck for developing CNN‐based denoising models is the procurement of training data consisting of paired examples of high‐noise and low‐noise CT images. Obtaining these paired data are not practical in a clinical setting where the raw projection data is not available. This work outlines a technique to optimize CNN denoising models using methods that are available in a routine clinical setting.PurposeTo demonstrate a phantom‐based training framework for CNN noise reduction that can be efficiently implemented on any CT scanner.MethodsThe phantom‐based training framework uses supervised learning in which training data are synthesized using an image‐based noise insertion technique. Ten patient image series were used for training and validation (9:1) and noise‐only images obtained from anthropomorphic phantom scans. Phantom noise‐only images were superimposed on patient images to imitate low‐dose CT images for use in training. A modified U‐Net architecture was used with mean‐squared‐error and feature reconstruction loss. The training framework was tested for clinically indicated whole‐body‐low‐dose CT images, as well as routine abdomen‐pelvis exams for which projection data was unavailable. Performance was assessed based on root‐mean‐square error, structural similarity, line profiles, and visual assessment.ResultsWhen the CNN was tested on five reserved quarter‐dose whole‐body‐low‐dose CT images, noise was reduced by 75%, root‐mean‐square‐error reduced by 34%, and structural similarity increased by 60%. Visual analysis and line profiles indicated that the method significantly reduced noise while maintaining spatial resolution of anatomic features.ConclusionThe proposed phantom‐based training framework demonstrated strong noise reduction while preserving spatial detail. Because this method is based within the image domain, it can be easily implemented without access to projection data.

AbstractPurposeMetallic implants have been correlated to local control failure for spinal sarcoma and chordoma patients due to the uncertainty of implant delineation from computed tomography (CT). Such uncertainty can compromise the proton Monte Carlo dose calculation (MCDC) accuracy. A component method is proposed to determine the dimension and volume of the implants from CT images.MethodsThe proposed component method leverages the knowledge of surgical implants from medical supply vendors to predefine accurate contours for each implant component, including tulips, screw bodies, lockers, and rods. A retrospective patient study was conducted to demonstrate the feasibility of the method. The reference implant materials and samples were collected from patient medical records and vendors, Medtronic and NuVasive. Additional CT images with extensive features, such as extended Hounsfield units and various reconstruction diameters, were used to quantify the uncertainty of implant contours.ResultsFor in vivo patient implant estimation, the reference and the component method differences were 0.35, 0.17, and 0.04 cm3for tulips, screw bodies, and rods, respectively. The discrepancies by a conventional threshold method were 5.46, 0.76, and 0.05 cm3, respectively. The mischaracterization of implant materials and dimensions can underdose the clinical target volume coverage by 20 cm3for a patient with eight lumbar implants. The tulip dominates the dosimetry uncertainty as it can be made from titanium or cobalt–chromium alloys by different vendors.ConclusionsA component method was developed and demonstrated using phantom and patient studies with implants. The proposed method provides more accurate implant characterization for proton MCDC and can potentially enhance the treatment quality for proton therapy. The current proof‐of‐concept study is limited to the implant characterization for lumbar spine. Future investigations could be extended to cervical spine and dental implants for head‐and‐neck patients where tight margins are required to spare organs at risk.

AbstractBackgroundDual‐energy CT with virtual noncalcium (VNCa) images allows the evaluation of focal intramedullary bone marrow involvement in patients with multiple myeloma. However, current commercial VNCa techniques suffer from excessive image noise and artifacts due to material decomposition used in synthesizing VNCa images.ObjectivesIn this work, we aim to improve VNCa image quality for the assessment of focal multiple myeloma, using an Artificial intelligence based Generalizable Algorithm for mulTi‐Energy CT (AGATE) method.Materials and methodsAGATE method used a custom dual‐task convolutional neural network (CNN) that concurrently carries out material classification and quantification. The material classification task provided an auxiliary regularization to the material quantification task. CNN parameters were optimized using custom loss functions that involved cross‐entropy, physics‐informed constraints, structural redundancy in spectral and material images, and texture information in spectral images. For training data, CT phantoms (diameters 30 to 45 cm) with tissue‐mimicking inserts were scanned on a third generation dual‐source CT system. Scans were performed at routine dose and half of the routine dose. Small image patches (i.e., 40 × 40 pixels) of tissue‐mimicking inserts with known basis material densities were extracted for training samples. Numerically simulated insert materials with various shapes increased diversity of training samples. Generalizability of AGATE was evaluated using CT images from phantoms and patients. In phantoms, material decomposition accuracy was estimated using mean‐absolute‐percent‐error (MAPE), using physical inserts that were not used during the training. Noise power spectrum (NPS) and modulation transfer function (MTF) were compared across phantom sizes and radiation dose levels. Five patients with multiple myeloma underwent dual‐energy CT, with VNCa images generated using a commercial method and AGATE. Two fellowship‐trained musculoskeletal radiologists reviewed the VNCa images (commercial and AGATE) side‐by‐side using a dual‐monitor display, blinded to VNCa type, rating the image quality for focal multiple myeloma lesion visualization using a 5‐level Likert comparison scale (−2 = worse visualization and diagnostic confidence, −1 = worse visualization but equivalent diagnostic confidence, 0 = equivalent visualization and diagnostic confidence, 1 = improved visualization but equivalent diagnostic confidence, 2 = improved visualization and diagnostic confidence). A post hoc assignment of comparison ratings was performed to rank AGATE images in comparison to commercial ones.ResultsAGATE demonstrated consistent material quantification accuracy across phantom sizes and radiation dose levels, with MAPE ranging from 0.7% to 4.4% across all testing materials. Compared to commercial VNCa images, the AGATE‐synthesized VNCa images yielded considerably lower image noise (50–77% noise reduction) without compromising noise texture or spatial resolution across different phantom sizes and two radiation doses. AGATE VNCa images had markedly reduced area under NPS curves and maintained NPS peak frequency (0.7 lp/cm to 1.0 lp/cm), with similar MTF curves (50% MTF at 3.0 lp/cm). In patients, AGATE demonstrated reduced image noise and artifacts with improved delineation of focal multiple myeloma lesions (all readers comparison scores indicating improved overall diagnostic image quality [scores 1 or 2]).ConclusionsAGATE demonstrated reduced noise and artifacts in VNCa images and ability to improve visualization of bone marrow lesions for assessing multiple myeloma.