Search

Cancer care increasingly relies on imaging for patient management. The two most common cross-sectional imaging modalities in oncology are computed tomography (CT) and magnetic resonance imaging (MRI), which provide high-resolution anatomic and physiological imaging. Herewith is a summary of recent applications of rapidly advancing artificial intelligence (AI) in CT and MRI oncological imaging that addresses the benefits and challenges of the resultant opportunities with examples. Major challenges remain, such as how best to integrate AI developments into clinical radiology practice, the vigorous assessment of quantitative CT and MR imaging data accuracy, and reliability for clinical utility and research integrity in oncology. Such challenges necessitate an evaluation of the robustness of imaging biomarkers to be included in AI developments, a culture of data sharing, and the cooperation of knowledgeable academics with vendor scientists and companies operating in radiology and oncology fields. Herein, we will illustrate a few challenges and solutions of these efforts using novel methods for synthesizing different contrast modality images, auto-segmentation, and image reconstruction with examples from lung CT as well as abdome, pelvis, and head and neck MRI. The imaging community must embrace the need for quantitative CT and MRI metrics beyond lesion size measurement. AI methods for the extraction and longitudinal tracking of imaging metrics from registered lesions and understanding the tumor environment will be invaluable for interpreting disease status and treatment efficacy. This is an exciting time to work together to move the imaging field forward with narrow AI-specific tasks. New AI developments using CT and MRI datasets will be used to improve the personalized management of cancer patients.

We aimed to assess longitudinal changes in quantitative imaging metric values obtained from diffusion-weighted (DW-) and dynamic contrast-enhanced magnetic resonance imaging (DCE)-MRI at pre-treatment (TX[0]), immediately after the first fraction of stereotactic body radiotherapy (D1-TX[1]), and 6 weeks post-TX (Post-TX[2]) in patients with pancreatic ductal adenocarcinoma. Ten enrolled patients (n = 10) underwent DW- and DCE-MRI examinations on a 3.0 T scanner. The apparent diffusion coefficient, ADC (mm2/s), was derived from DW imaging data using a monoexponential model. The tissue relaxation rate, R1t, time-course data were fitted with a shutter-speed model, which provides estimates of the volume transfer constant, Ktrans (min−1), extravascular extracellular volume fraction, ve, and mean lifetime of intracellular water protons, τi (seconds). Wilcoxon rank-sum test compared the mean values, standard deviation, skewness, kurtosis, and relative percentage (r, %) changes (Δ) in ADC, Ktrans, ve, and τi values between the magnetic resonance examinations. rADCΔ2–0 values were significantly greater than rADCΔ1-0 values (P = .009). rKtransΔ2–0 values were significantly lower than rKtrans Δ1-0 values (P = .048). rveΔ2-1 and rveΔ2-0 values were significantly different (P = .016). rτiΔ2-1 values were significantly lower than rτiΔ2-0 values (P = .008). For group comparison, the pre-TX mean and kurtosis of ADC (P = .18 and P = .14), skewness and kurtosis of Ktrans values (P = .14 for both) showed a leaning toward significant difference between patients who experienced local control (n = 2) and failed early (n = 4). DW- and DCE-MRI-derived quantitative metrics could be useful biomarkers to evaluate longitudinal changes to stereotactic body radiotherapy in patients with pancreatic ductal adenocarcinoma.

We developed and tested the feasibility of computational fluid modeling (CFM) based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for quantitative estimation of interstitial fluid pressure (IFP) and velocity (IFV) in patients with head and neck (HN) cancer with locoregional lymph node metastases. Twenty-two patients with HN cancer, with 38 lymph nodes, underwent pretreatment standard MRI, including DCE-MRI, on a 3-Tesla scanner. CFM simulation was performed with the finite element method in COMSOL Multiphysics software. The model consisted of a partial differential equation (PDE) module to generate 3D parametric IFP and IFV maps, using the Darcy equation and Ktrans values (min−1, estimated from the extended Tofts model) to reflect fluid influx into tissue from the capillary microvasculature. The Spearman correlation (ρ) was calculated between total tumor volumes and CFM estimates of mean tumor IFP and IFV. CFM-estimated tumor IFP and IFV mean ± standard deviation for the neck nodal metastases were 1.73 ± 0.39 (kPa) and 1.82 ± 0.9 × (10−7 m/s), respectively. High IFP estimates corresponds to very low IFV throughout the tumor core, but IFV rises rapidly near the tumor boundary where the drop in IFP is precipitous. A significant correlation was found between pretreatment total tumor volume and CFM estimates of mean tumor IFP (ρ = 0.50, P = 0.004). Future studies can validate these initial findings in larger patients with HN cancer cohorts using CFM of the tumor in concert with DCE characterization, which holds promise in radiation oncology and drug-therapy clinical trials.

We aimed to compare the geometric distortion (GD) correction performance and apparent diffusion coefficient (ADC) measurements of single-shot diffusion-weighted echo-planar imaging (SS-DWEPI), multiplexed sensitivity encoding (MUSE)-DWEPI, and MUSE-DWEPI with reverse-polarity gradient (RPG) in phantoms and patients. We performed phantom studies at 3T magnetic resonance imaging (MRI) using the American College of Radiology phantom and Quantitative Imaging Biomarker Alliance DW-MRI ice-water phantom to assess GD and effect of distortion in the measurement of ADC, respectively. Institutional review board approved the prospective clinical component of this study. DW-MRI data were obtained from 11 patients with head and neck cancer using these three DW-MRI methods. Wilcoxon signed-rank (WSR) and Kruskal–Wallis (KW) tests were used to compare ADC values, and qualitative rating by radiologist between three DW-MRI methods. In the ACR phantom, GD of 0.17% was observed for the b = 0 s/mm2 image of the MUSE-DWEPI with RPG method compared with that of 1.53% and 2.1% of MUSE-DWEPI and SS-DWEPI, respectively, The corresponding methods root-mean-square errors were 0.58, 3.37, and 5.07 mm. WSR and KW tests showed no significant difference in the ADC measurement between these three DW-MRI methods for both healthy masseter muscles and neoplasms (P &gt, 05). We observed improvement in spatial accuracy for MUSE-DWEPI with RPG in the head and neck region with a higher correlation (R2 = 0.791) compared with that for SS-DWEPI (R2 = 0.707) and MUSE-DWEPI (R2 = 0.745). MUSE-DWEPI with RPG significantly reduces the distortion compared with MUSE-DWEPI or conventional SS-DWEPI techniques, and the ADC values were similar.

The present study aimed to investigate the correlation at pre-treatment (TX) between quantitative metrics derived from multimodality imaging (MMI), including 18F-FDG-PET/CT, 18F-FMISO-PET/CT, DW- and DCE-MRI, using a community detection algorithm (CDA) in head and neck squamous cell carcinoma (HNSCC) patients. Twenty-three HNSCC patients with 27 metastatic lymph nodes underwent a total of 69 MMI exams at pre-TX. Correlations among quantitative metrics derived from FDG-PET/CT (SUL), FMSIO-PET/CT (K1, k3, TBR, and DV), DW-MRI (ADC, IVIM [D, D*, and f]), and FXR DCE-MRI [Ktrans, ve, and τi]) were investigated using the CDA based on a “spin-glass model” coupled with the Spearman’s rank, ρ, analysis. Mean MRI T2 weighted tumor volumes and SULmean values were moderately positively correlated (ρ = 0.48, p = 0.01). ADC and D exhibited a moderate negative correlation with SULmean (ρ ≤ −0.42, p &lt, 0.03 for both). K1 and Ktrans were positively correlated (ρ = 0.48, p = 0.01). In contrast, Ktrans and k3max were negatively correlated (ρ = −0.41, p = 0.03). CDA revealed four communities for 16 metrics interconnected with 33 edges in the network. DV, Ktrans, and K1 had 8, 7, and 6 edges in the network, respectively. After validation in a larger population, the CDA approach may aid in identifying useful biomarkers for developing individual patient care in HNSCC.

Quantitative kurtosis phantoms are sought by multicenter clinical trials to establish accuracy and precision of quantitative imaging biomarkers on the basis of diffusion kurtosis imaging (DKI) parameters. We designed and evaluated precision, reproducibility, and long-term stability of a novel isotropic (i) DKI phantom fabricated using four families of chemicals based on vesicular and lamellar mesophases of liquid crystal materials. The constructed iDKI phantoms included negative control monoexponential diffusion materials to independently characterize noise and model-induced bias in quantitative kurtosis parameters. Ten test–retest DKI studies were performed on four scanners at three imaging centers over a six-month period. The tested prototype phantoms exhibited physiologically relevant apparent diffusion, Dapp, and kurtosis, Kapp, parameters ranging between 0.4 and 1.1 (×10−3 mm2/s) and 0.8 and 1.7 (unitless), respectively. Measured kurtosis phantom Kapp exceeded maximum fit model bias (0.1) detected for negative control (zero kurtosis) materials. The material-specific parameter precision [95% CI for Dapp: 0.013–0.022(×10−3 mm2/s) and for Kapp: 0.009–0.076] derived from the test–retest analysis was sufficient to characterize thermal and temporal stability of the prototype DKI phantom through correlation analysis of inter-scan variability. The present study confirms a promising chemical design for stable quantitative DKI phantom based on vesicular mesophase of liquid crystal materials. Improvements to phantom preparation and temperature monitoring procedures have potential to enhance precision and reproducibility for future multicenter iDKI phantom studies.

The aim of the present study was to identify whether the quantitative metrics from pre-treatment (TX) non-Gaussian intravoxel incoherent motion (NGIVIM) diffusion weighted (DW-) and fast exchange regime (FXR) dynamic contrast enhanced (DCE)-MRI can predict patients with locoregional failure (LRF) in nasopharyngeal carcinoma (NPC). Twenty-nine NPC patients underwent pre-TX DW- and DCE-MRI on a 3T MR scanner. DW imaging data from primary tumors were fitted to monoexponential (ADC) and NGIVIM (D, D*, f, and K) models. The metrics Ktrans, ve, and τi were estimated using the FXR model. Cumulative incidence (CI) analysis and Fine-Gray (FG) modeling were performed considering death as a competing risk. Mean ve values were significantly different between patients with and without LRF (p = 0.03). Mean f values showed a trend towards the difference between the groups (p = 0.08). Histograms exhibited inter primary tumor heterogeneity. The CI curves showed significant differences for the dichotomized cutoff value of ADC ≤ 0.68 × 10−3 (mm2/s), D ≤ 0.74 × 10−3 (mm2/s), and f ≤ 0.18 (p &lt, 0.05). τi ≤ 0.89 (s) cutoff value showed borderline significance (p = 0.098). FG’s modeling showed a significant difference for the K cutoff value of ≤0.86 (p = 0.034). Results suggest that the role of pre-TX NGIVIM DW- and FXR DCE-MRI-derived metrics for predicting LRF in NPC than alone.

Information about the factors associated with conservation participation by local communities is important to garner support and involvement within a natural protected area. This research examined how residents&rsquo, natural resource dependency and other social, economic, and access-related variables predict conservation participation. Data were collected based on a stratified random sampling of households from Gaurishankar Conservation Area Project (GCAP)&mdash, a newly designated mountainous protected area in Nepal. Analysis was conducted via an ordered logistic regression model. Higher levels of participation were observed among households that comprised of a larger family size, belonged to a higher caste/ethnicity, resided in higher elevations, and noted frequent visits and interactions with park management staff. However, natural resources dependency (i.e., income and fuelwood fodder) lacked a statistically significant relationship with conservation participation. Similarly, the economic dimension (i.e., land holdings and total livestock unit) was not a significant predictor of participation. Overall, key findings suggest that conservation participation at GCAP needs to be improved with multiple outreach activities, especially to resource-dependent households. More specifically, it is important to ensure equitable access so that locals can participate in programs that provide alternative resource use options, skills development, and trainings for income generation activities.