Motion-correction strategies for enhancing whole-body PET imaging.

Positron Emission Tomography (PET) is a powerful medical imaging technique widely used for detection and monitoring of disease. However, PET imaging can be adversely affected by patient motion, leading to degraded image quality and diagnostic capability. Hence, motion gating schemes have been developed to monitor various motion sources including head motion, respiratory motion, and cardiac motion. The approaches for these techniques have commonly come in the form of hardware-driven gating and data-driven gating, where the distinguishing aspect is the use of external hardware to make motion measurements vs. deriving these measures from the data itself. The implementation of these techniques helps correct for motion artifacts and improves tracer uptake measurements. With the great impact that these methods have on the diagnostic and quantitative quality of PET images, much research has been performed in this area, and this paper outlines the various approaches that have been developed as applied to whole-body PET imaging.

RobMedNAS: searching robust neural network architectures for medical image synthesis.

Investigating U-Net model robustness in medical image synthesis against adversarial perturbations, this study introduces RobMedNAS, a neural architecture search strategy for identifying resilient U-Net configurations. Through retrospective analysis of synthesized CT from MRI data, employing Dice coefficient and mean absolute error metrics across critical anatomical areas, the study evaluates traditional U-Net models and RobMedNAS-optimized models under adversarial attacks. Findings demonstrate RobMedNAS's efficacy in enhancing U-Net resilience without compromising on accuracy, proposing a novel pathway for robust medical image processing.

Biparametric Quantitative MRI for Prostate Cancer Detection.

OBJECTIVES: This study sought to prospectively investigate a novel quantitative biparametric prostate magnetic resonance imaging (MRI) protocol to detect prostate cancer (PCa) in biopsy-naïve men. Secondarily, this study reports the accuracy of fractional order calculus (FROC) diffusion and quantitative T2 compared with the Prostate Imaging Reporting & Data System (PI-RADS). METHODS: This prospective pilot study (NCT04175730) enrolled 50 prostate biopsy-naïve men who met eligibility criteria. All men received 3T MRI with T2 and diffusion-weighted imaging (DWI) (b-values: 50-4,000 s/mm2). Men with PI-RADS lesions ≥3 underwent targeted and systematic prostate biopsy, omitting systematic biopsy cores in peripheral zone lesions. DWI series images were fit to signal decay to calculate ADC (mm2/s) and the FROC model for coefficient DF (mm2/s). The primary end point was detection of Gleason grade group ≥2 (GG≥2) PCa. Receiver operating characteristic regression and area under the curve (AUC) were reported. RESULTS: Forty-eight men underwent MRI and biopsy. Mean age was 61.5 years (56-68), 29% were White, 52% were African American, mean PSA was 6.0 ng/mL (4.9-8.0), and mean PSA density was 0.14 ng/mL2. In total, 61 PI-RADS ≥3 lesions were targeted for biopsy. GG≥2 PC was found in 7% (1/14) of PI-RADS 3 lesions, 28% (10/36) of PI-RADS 4 lesions, and 36% (4/11) of PI-RADS 5 lesions. The AUC for detection of GG≥2 PC was 0.63 (0.5-0.76) for PI-RADS, 0.82 (0.68-0.96) for ADC, and 0.87 (0.77-0.97) for the FROC model. CONCLUSION: This small prospective pilot study demonstrates the feasibility of a novel quantitative biparametic MRI protocol to detect prostate cancer in biopsy-naïve men.

Diagnostic performance of tomoelastography of the liver and spleen for staging hepatic fibrosis.

OBJECTIVES: To determine the diagnostic performance, cut-off values, and optimal drive frequency range for staging hepatic fibrosis using tomoelastography by multifrequency MR elastography of the liver and spleen. METHODS: This prospective study consecutively enrolled a total of 61 subjects between June 2014 and April 2017: 45 patients with chronic liver disease and proven stage of fibrosis and 16 healthy volunteers. Tomoelastography was performed at 1.5 T using six drive frequencies from 35 to 60 Hz. Cut-off values and AUC were calculated. Shear wave speed (in m/s) of the liver and spleen was assessed separately and in combination as a surrogate of stiffness. RESULTS: For compound multifrequency processing of the liver, cut-off and AUC values by fibrosis stage were as follows: F1, 1.52 m/s and 0.89; F2, 1.55 m/s and 0.94; F3, 1.67 m/s and 0.98; and F4, 1.72 m/s and 0.98. Diagnostic performance of the best single drive frequencies (45 Hz, 55 Hz, 60 Hz) was similar (mean AUC = 0.95, respectively). Combined analysis of the liver and spleen slightly improved performance at 60 Hz in F4 patients (mean AUC = 0.97 vs. 0.95, p = 0.03). Full-field-of-view elastograms displayed not only the liver and spleen but also small anatomical structures including the pancreas and major vessels. CONCLUSION: Tomoelastography provides full-field-of-view elastograms with unprecedented detail resolution and excellent diagnostic accuracy for staging hepatic fibrosis. Our analysis of single-frequency tomoelastography suggests that scan time can be further reduced in future studies, making tomoelastography easier to implement in clinical routine. KEY POINTS: • Tomoelastography provides full-field-of-view elastograms of the abdomen with unprecedented detail resolution and excellent diagnostic accuracy for staging hepatic fibrosis. • Diagnostic performance of single-frequency tomoelastography at higher frequencies (45 Hz, 55 Hz, 60 Hz) and compound multifrequency processing are equivalent for staging hepatic fibrosis. • Combined assessment of hepatic and splenic stiffness slightly improves diagnostic performance for staging hepatic fibrosis.