Photon-counting Detector CT with Deep Learning Noise Reduction to Detect Multiple Myeloma.

Background Photon-counting detector (PCD) CT and deep learning noise reduction may improve spatial resolution at lower radiation doses compared with energy-integrating detector (EID) CT. Purpose To demonstrate the diagnostic impact of improved spatial resolution in whole-body low-dose CT scans for viewing multiple myeloma by using PCD CT with deep learning denoising compared with conventional EID CT. Materials and Methods Between April and July 2021, adult participants who underwent a whole-body EID CT scan were prospectively enrolled and scanned with a PCD CT system in ultra-high-resolution mode at matched radiation dose (8 mSv for an average adult) at an academic medical center. EID CT and PCD CT images were reconstructed with Br44 and Br64 kernels at 2-mm section thickness. PCD CT images were also reconstructed with Br44 and Br76 kernels at 0.6-mm section thickness. The thinner PCD CT images were denoised by using a convolutional neural network. Image quality was objectively quantified in two phantoms and a randomly selected subset of participants (10 participants; median age, 63.5 years; five men). Two radiologists scored PCD CT images relative to EID CT by using a five-point Likert scale to detect findings reflecting multiple myeloma. The scoring for the matched reconstruction series was blinded to scanner type. Reader-averaged scores were tested with the null hypothesis of equivalent visualization between EID and PCD. Results Twenty-seven participants (median age, 68 years; IQR, 61-72 years; 16 men) were included. The blinded assessment of 2-mm images demonstrated improvement in viewing lytic lesions, intramedullary lesions, fatty metamorphosis, and pathologic fractures for PCD CT versus EID CT (P < .05 for all comparisons). The 0.6-mm PCD CT images with convolutional neural network denoising also demonstrated improvement in viewing all four pathologic abnormalities and detected one or more lytic lesions in 21 of 27 participants compared with the 2-mm EID CT images (P < .001). Conclusion Ultra-high-resolution photon-counting detector CT improved the visibility of multiple myeloma lesions relative to energy-integrating detector CT. © RSNA, 2022 Online supplemental material is available for this article.

Prognostic significance of acquired 1q22 gain in multiple myeloma.

Gain of 1q22 at diagnosis portends poorer outcomes in multiple myeloma (MM), but the prognostic significance of acquired 1q22 gain is unknown. We identified 63 MM patients seen at Mayo Clinic from 1/2004 to 12/2019 without 1q22 gain at diagnosis who acquired it during follow up and compared them to 63 control patients who did not acquire 1q22 gain with similar follow up. We also compared outcomes in the acquired 1q22 gain group with outcomes in 126 patients with 1q22 gain present at diagnosis. The incidence of acquired 1q22 gain was 6.1% (median follow-up 6.8 years); median time to acquisition was 5.0 years (range: 0.7-11.5 years). Abnormalities on baseline fluorescence in situ hybridization (FISH) included trisomies (54%) and monosomy 13 (39%); 16 (25%) had high-risk (HR) translocations or del(17p). Median progression-free survival with front line therapy was 29.5 months in patients with acquired 1q22 gain, versus 31.4 months in control patients (p = .34) and 31.2 months in patients with de novo 1q22 gain (p = .04). Median overall survival (OS) from diagnosis was 10.9 years in patients with acquired 1q22 gain, versus 13.0 years in control patients (p = .03) and 6.3 years in patients with de novo 1q22 gain (p = .01). Presence of HR FISH at baseline increased risk of 1q22 gain acquisition. We demonstrate that acquisition of 1q22 gain is a significant molecular event in MM, associated with reduced OS. Among HR patients for whom this clonal evolution is determined, a risk-adapted approach and/or clinical trial should be considered.

Simplified Risk Stratification Model for Patients With Waldenström Macroglobulinemia.

PURPOSE: Patients with Waldenström macroglobulinemia (WM) have disparate outcomes. Newer therapies have emerged since the development of International Prognostic Scoring System, and MYD88L265P mutation is now frequently assessed at diagnosis, warranting reexamination of the prognostic parameters. PATIENTS AND METHODS: We reviewed records of 889 treatment-naïve patients with active WM, consecutively seen between January 01, 1996, and December 31, 2017, to identify clinical predictors of overall survival (OS) in univariate analyses. Patients with complete data for the parameters significant on the univariate analyses (n = 341) were included in a multivariable analysis to derive a prognostic model, subsequently validated in a multi-institutional cohort. RESULTS: In the derivation cohort (n = 341), age (hazard ratio [HR], 1.9 [95% CI, 1.2 to 2.1]; P = .0009), serum lactate dehydrogenase (LDH) above upper limit of normal (HR, 2.3 [95% CI, 1.3 to 4.5]; P = .007), and serum albumin <3.5 g/dL (HR, 1.5 [95% CI, 0.99 to 2.3]; P = .056) were independently prognostic. By assigning a score of 1 point each to albumin <3.5 g/dL (HR, 1.5) and age 66-75 years (HR 1.4) and 2 points for age >75 years (HR, 2.6) or elevated LDH (HR, 2.3), four groups with distinct outcomes were observed on the basis of the composite scores. Five-year OS was 93% for the low-risk (score 0), 82% for low-intermediate risk (score 1), 69% for intermediate-risk (score 2), and 55% for the high-risk (score ≥3; P < .0001) groups. In the validation cohort (N = 335), the model maintained its prognostic value, with a 5-year OS of 93%, 90%, 75%, and 57% for the four groups, respectively (P < .0001). CONCLUSION: Modified Staging System for WM (MSS-WM), utilizing age, albumin, and LDH is a simple, clinically useful, and externally validated prognostic model that reliably risk-stratifies patients with symptomatic WM into four groups with distinct prognosis.

Deep learning-based virtual noncalcium imaging in multiple myeloma using dual-energy CT.

BACKGROUND: Dual-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. OBJECTIVES: In 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 METHODS: AGATE 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. RESULTS: AGATE 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]). CONCLUSIONS: AGATE demonstrated reduced noise and artifacts in VNCa images and ability to improve visualization of bone marrow lesions for assessing multiple myeloma.

Evaluating Unconscious Bias: Speaker Introductions at an International Oncology Conference.

PURPOSE: In a professional setting, the introduction of female speakers without their professional title may have an impact on the public's perception of the female speaker. We examined how professional titles were used during speakers' introductions at the ASCO Annual Meeting. METHODS: We conducted a retrospective, observational study of video-archived speaker introductions at the 2017 and 2018 ASCO Annual Meetings. A "professional address" was defined as the professional title followed by the speaker's full name or last name. Multivariable logistic regressions were used to identify factors associated with the form of address. RESULTS: Of 2,511 videos reviewed, 781 met inclusion criteria. Female speakers were addressed less often by their professional title compared with male speakers (62% v 81%; P < .001). Males were less likely to use a professional address when introducing female speakers compared with females when introducing male speakers (53% v 80%; P < .01). When women performed speaker introductions, no gender differences in professional address were observed (75% v 82%; P = .13). Female speakers were more likely to be introduced by first name only (17% v 3%; P < .001). Male introducers were more likely to address female speakers by first name only compared with female introducers (24% v 7%; P < .01). In a multivariable regression including gender, degree, academic rank, and geographic location of the speaker's institution, male speakers were more likely to receive a professional address compared with female speakers (odds ratio, 2.43; 95% CI, 1.71 to 3.47; P < .01). CONCLUSION: When introduced by men, female speakers were less likely to receive a professional address and more likely to be introduced by first name only compared with their male peers.