Routine Clinical Imaging Research Articles

Prognostic and diagnostic implications of impaired rest and exercise-stress left atrial compliance in heart failure with preserved ejection fraction: Insights from the HFpEF Stress Trial

Abstract Background With emerging therapies, early diagnosis of heart failure with preserved ejection fraction (HFpEF) comes to the fore. Whilst the reference standard of exercise-stress right heart catheterisation is well established, the clinical routine struggles between feasibility of exercise-stress and diagnostic accuracy of available tests. Methods The HFpEF Stress Trial (DZHK-17) prospectively enrolled 75 patients with exertional dyspnoea and echocardiographic signs of diastolic dysfunction (E/e’>8) who underwent simultaneous rest and exercise-stress echocardiography and RHC. HFpEF was defined according to pulmonary capillary wedge pressure (HFpEF: PCWP rest: ≥15mmHg stress: ≥25mmHg). Patients were classified as non-cardiac dyspnoea (NCD) in the absence of HFpEF and cardiovascular disease. LA compliance was defined as reservoir strain (Es)/(E/e’). Follow-up was conducted after 4 years to evaluate cardiovascular hospitalisation (CVH). Results The final study population included 68 patients (HFpEF n=34 and NCD n=34) of which 23 reached the clinical endpoint, 1 Patient was lost to follow-up. Patients with HFpEF according to the HFA-PEFF score (≥5 points) had significantly lower LA compliance at rest (p<0.001) compared to patients with a score ≤4. LA compliance at rest outperformed E/e’ (AUC 0.78 vs 0.87, p=0.024) and showed a statistical trend to outperform Es (AUC 0.79 vs 0.87, p=0.090) for the diagnosis of HFpEF. LA compliance at rest predicted CVH (HR 2.83, 95% CI 1.70-4.74, p<0.001) irrespective of concomitant atrial fibrillation. Conclusions LA compliance at rest can be obtained from clinical routine imaging and bears strong diagnostic and prognostic accuracy. Addition of LA compliance can improve the role of echocardiography as the primary test and gatekeeper.

Accurate low and high grade glioma classification using free water eliminated diffusion tensor metrics and ensemble machine learning

Glioma, a predominant type of brain tumor, can be fatal. This necessitates an early diagnosis and effective treatment strategies. Current diagnosis is based on biopsy, prompting the need for non invasive neuroimaging alternatives. Diffusion tensor imaging (DTI) is a promising method for studying the pathophysiological impact of tumors on white matter (WM) tissue. Single-shell DTI studies in brain glioma patients have not accounted for free water (FW) contamination due to tumors. This study aimed to (a) assess the efficacy of a two-compartment DTI model that accounts for FW contamination and (b) identify DTI-based biomarkers to classify low-grade glioma (LGG) and high-grade glioma (HGG) patients. DTI data from 86 patients (LGG n = 39, HGG n = 47) were obtained using a routine clinical imaging protocol. DTI metrics of tumorous regions and normal-appearing white matter (NAWM) were evaluated. Advanced stacked-based ensemble learning was employed to classify LGG and HGG patients using both single- and two-compartment DTI model measures. The DTI metrics of the two-compartment model outperformed those of the standard single-compartment DTI model in terms of sensitivity, specificity, and area under the curve of receiver operating characteristic (AUC-ROC) score in classifying LGG and HGG patients. Four features (out of 16 features), namely fractional anisotropy (FA) of the edema and core region and FA and mean diffusivity of the NAWM region, showed superior performance (sensitivity = 92%, specificity = 90%, and AUC-ROC = 90%) in classifying LGG and HGG. This demonstrates that both tumorous and NAWM regions may be differentially affected in LGG and HGG patients. Our results demonstrate the significance of using a two-compartment DTI model that accounts for FW contamination by improving diagnostic accuracy. This improvement may eventually aid in planning treatment strategies for glioma patients.

Non-invasive CT radiomic biomarkers predict microsatellite stability status in colorectal cancer: a multicenter validation study

BackgroundMicrosatellite instability (MSI) status is a strong predictor of response to immunotherapy of colorectal cancer. Radiogenomic approaches promise the ability to gain insight into the underlying tumor biology using non-invasive routine clinical images. This study investigates the association between tumor morphology and the status of MSI versus microsatellite stability (MSS), validating a novel radiomic signature on an external multicenter cohort.MethodsPreoperative computed tomography scans with matched MSI status were retrospectively collected for 243 colorectal cancer patients from three hospitals: Seoul National University Hospital (SNUH);Netherlands Cancer Institute (NKI); and Fondazione IRCCS Istituto Nazionale dei Tumori, Milan Italy (INT). Radiologists delineated primary tumors in each scan, from which radiomic features were extracted. Machine learning models trained on SNUH data to identify MSI tumors underwent external validation using NKI and INT images. Performances were compared in terms of area under the receiving operating curve (AUROC).ResultsWe identified a radiomic signature comprising seven radiomic features that were predictive of tumors with MSS or MSI (AUROC 0.69, 95% confidence interval [CI] 0.54−0.84, p = 0.018). Integrating radiomic and clinical data into an algorithm improved predictive performance to an AUROC of 0.78 (95% CI 0.60−0.91, p = 0.002) and enhanced the reliability of the predictions.ConclusionDifferences in the radiomic morphological phenotype between tumors MSS or MSI could be detected using radiogenomic approaches. Future research involving large-scale multicenter prospective studies that combine various diagnostic data is necessary to refine and validate more robust, potentially tumor-agnostic MSI radiogenomic models.Relevance statementNoninvasive radiomic signatures derived from computed tomography scans can predict MSI in colorectal cancer, potentially augmenting traditional biopsy-based methods and enhancing personalized treatment strategies.Key PointsNoninvasive CT-based radiomics predicted MSI in colorectal cancer, enhancing stratification.A seven-feature radiomic signature differentiated tumors with MSI from those with MSS in multicenter cohorts.Integrating radiomic and clinical data improved the algorithm’s predictive performance.Graphical

Morphological MRI features as prognostic indicators in brain metastases

BackgroundStereotactic radiotherapy is the preferred treatment for managing patients with fewer than five brain metastases (BMs). However, some lesions recur after irradiation. The purpose of this study was to identify patients who are at a higher risk of failure, which can help in adjusting treatments and preventing recurrence.MethodsIn this retrospective multicenter study, we analyzed the predictive significance of a set of interpretable morphological features derived from contrast-enhanced (CE) T1-weighted MR images as imaging biomarkers using Kaplan–Meier analysis. The feature sets studied included the total and necrotic volumes, the surface regularity and the CE rim width. Additionally, we evaluated other nonmorphological variables and performed multivariate Cox analysis.ResultsA total of 183 lesions in 128 patients were included (median age 61 [31–95], 64 men and 64 women) treated with stereotactic radiotherapy (57% single fraction, 43% fractionated radiotherapy). None of the studied variables measured at diagnosis were found to have prognostic value. However, the total and necrotic volumes and the CE rim width measured at the first follow-up after treatment and the change in volume due to irradiation can be used as imaging biomarkers for recurrence. The optimal classification was achieved by combining the changes in tumor volume before and after treatment with the presence or absence of necrosis (p < < 0.001).ConclusionThis study demonstrated the prognostic significance of interpretable morphological features extracted from routine clinical MR images following irradiation in brain metastases, offering valuable insights for personalized treatment strategies.

Quantitative metrics of bone quality determined at the distal radius using photon-counting CT.

To determine the accuracy of photon-counting-detector CT (PCD-CT) at deriving bone morphometric indices and demonstrate utility in vivo in the distal radius. Ten cadaver wrists were scanned using PCD-CT and high-resolution peripheral quantitative CT (HRpQCT). Correlation between PCD-CT and HRpQCT morphometric indices was determined. Agreement was assessed by Lin's concordance correlation coefficient (Lin's CCC). Wrist PCD-CTs of patients between 02/2022 and 08/2023 were also evaluated for clinical utility. Morphometric indices of the in vivo distal radii were extracted and compared between patients with or without osteoporosis. In cadavers, strong correlation between PCD-CT and HRpQCT was observed for cortical thickness (Spearman correlation, ρ, 0.85), trabecular spacing (ρ = 0.98), and trabecular bone volume fraction (ρ = 0.68). Moderate negative correlation (ρ = - 0.49) was observed for trabecular thickness. PCD-CT shows good agreement to HRpQCT for cortical thickness, trabecular spacing, and trabecular bone volume fraction (Lin's CCC = 0.80, 0.94, and 0.86, respectively) but poor agreement (Lin's CCC = - 0.1) for trabecular thickness. In forty participants (31 adults and 9 pediatric), bone morphometrics indices for cortical thickness, trabecular thickness, trabecular spacing, and trabecular bone volume fraction were 0.99mm (IQR, 0.89-1.06), 0.38mm (IQR, 0.25-0.40), 0.82mm (IQR, 0.72-1.05), and 0.28 (IQR, 0.25-0.33), respectively. Patients with osteoporosis had statistically significantly larger trabecular spacing (p = 0.025) and lower trabecular volumetric bone mineral density (p = 0.042). This study demonstrates the agreement of PCD-CT to HRpQCT in cadavers of most cortical and bone morphometrics examined and provide in vivo quantitative metrics of bone microarchitecture from routine clinical PCD-CT images of the distal radius.

The diagnostic value of [18F]FAPI-42 PET/CT for pulmonary artery masses: comparison with [18F]FDG PET/CT.

To investigate the potential utility of [18F]fibroblast activation protein inhibitor (FAPI) positron emission tomography/computed tomography (PET/CT) for evaluating pulmonary artery (PA) masses, and compare it with [18F]fluorodeoxyglucose (FDG) PET/CT. Participants with clinically suspected PA malignancy were prospectively enrolled and underwent dual-tracer PET/CT ([18F]FAPI-42 and [18F]FDG) imaging. Visual analysis and semi-quantitative parameters were compared between the two types of radiotracers. The tissue specimen underwent immunohistochemical staining to verify FAP expression in the tissue. Thirty-three patients (18 males/15 females; mean age 53.1 ± 15.4 years) were enrolled. All 21 patients with malignant PA masses were FDG-positive (100%), whereas 20 out of 21 patients were FAPI-positive (95.2%). All 12 patients with benign PA masses were both negative in FDG and FAPI PET. The mean maximum standardized uptake value (SUVmax) and target-to-background ratio (TBR) of FAPI and FDG in malignant PA masses were significantly higher than those of benign masses. Although there was no significant difference in SUVmax between FDG and FAPI in malignant PA masses (11.36 vs. 9.18, p = 0.175), the TBR (liver) and TBR (left ventricle) were more favorable for FAPI than for FDG (13.04 vs. 5.17, p < 0.001); (median: 7.75 vs. 2.75, p = 0.007). Immunohistochemical analysis (n = 16) validated that the level of FAP expression corresponded strongly to the uptake of FAPI in PET/CT scans (rs = 0.712, p = 0.002). For clinical management, FAPI PET found more metastatic lesions than FDG PET in 4 patients, with 2 patients upgrading and 1 patient changing treatment decisions. FAPI PET/CT is feasible in the diagnosis of PA masses. Although not superior to FDG PET/CT, FAPI PET/CT showed better target-to-background contrast. This study found that FAPI PET/CT is not superior to FDG PET/CT in diagnosing PA masses, but FAPI PET/CT displays better target-to-background contrast and more positive lesions, which may help improve disease management. Pulmonary malignancies lack specificity in clinical manifestations, laboratory tests, and routine imaging examinations. FAPI PET/CT is not diagnostically better than FDG PET/CT but displays better target-to-background contrast and more positive lesions. Dual-tracer PET/CT ([18F]FAPI-42 and [18F]FDG) imaging improves clinical management of pulmonary artery masses.

Predicting Language Function Post-Stroke: A Model-Based Structural Connectivity Approach

Background The prediction of post-stroke language function is essential for the development of individualized treatment plans based on the personal recovery potential of aphasic stroke patients. Objective To establish a framework for integrating information on connectivity disruption of the language network based on routinely collected clinical magnetic resonance (MR) images into Random Forest modeling to predict post-stroke language function. Methods Language function was assessed in 76 stroke patients from the Non-Invasive Repeated Therapeutic Stimulation for Aphasia Recovery trial, using the Token Test (TT), Boston Naming Test (BNT), and Semantic Verbal Fluency (sVF) Test as primary outcome measures. Individual infarct masks were superimposed onto a diffusion tensor imaging tractogram reference set to calculate Change in Connectivity scores of language-relevant gray matter regions as estimates of structural connectivity disruption. Multivariable Random Forest models were derived to predict language function. Results Random Forest models explained moderate to high amount of variance at baseline and follow-up for the TT (62.7% and 76.2%), BNT (47.0% and 84.3%), and sVF (52.2% and 61.1%). Initial language function and non-verbal cognitive ability were the most important variables to predict language function. Connectivity disruption explained additional variance, resulting in a prediction error increase of up to 12.8% with variable omission. Left middle temporal gyrus (12.8%) and supramarginal gyrus (9.8%) were identified as among the most important network nodes. Conclusion Connectivity disruption of the language network adds predictive value beyond lesion volume, initial language function, and non-verbal cognitive ability. Obtaining information on connectivity disruption based on routine clinical MR images constitutes a significant advancement toward practical clinical application.

Enhanced Myocardial Tissue Visualization: A Comparative Cardiovascular Magnetic Resonance Study of Gradient-Spin Echo-STIR and Conventional STIR Imaging.

This study is aimed at evaluating the efficacy of the gradient-spin echo- (GraSE-) based short tau inversion recovery (STIR) sequence (GraSE-STIR) in cardiovascular magnetic resonance (CMR) imaging compared to the conventional turbo spin echo- (TSE-) based STIR sequence, specifically focusing on image quality, specific absorption rate (SAR), and image acquisition time. In a prospective study, we examined forty-four normal volunteers and seventeen patients referred for CMR imaging using conventional STIR and GraSE-STIR techniques. Signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), image quality, T2 signal intensity (SI) ratio, SAR, and image acquisition time were compared between both sequences. GraSE-STIR showed significant improvements in image quality (4.15 ± 0.8 vs. 3.34 ± 0.9, p = 0.024) and cardiac motion artifact reduction (7 vs. 18 out of 53, p = 0.038) compared to conventional STIR. Furthermore, the acquisition time (27.17 ± 3.53 vs. 36.9 ± 4.08 seconds, p = 0.041) and the local torso SAR (<13% vs. <17%, p = 0.047) were significantly lower for GraSE-STIR compared to conventional STIR in short-axis plan. However, no significant differences were shown in T2 SI ratio (p = 0.141), SNR (p = 0.093), CNR (p = 0.068), and SAR (p = 0.071) between these two sequences. GraSE-STIR offers notable advantages over conventional STIR sequence, with improved image quality, reduced motion artifacts, and shorter acquisition times. These findings highlight the potential of GraSE-STIR as a valuable technique for routine clinical CMR imaging.

Oxygen-enhanced MRI assessment of tumour hypoxia in head and neck cancer is feasible and well tolerated in the clinical setting

BackgroundTumour hypoxia is a recognised cause of radiotherapy treatment resistance in head and neck squamous cell carcinoma (HNSCC). Current positron emission tomography-based hypoxia imaging techniques are not routinely available in many centres. We investigated if an alternative technique called oxygen-enhanced magnetic resonance imaging (OE-MRI) could be performed in HNSCC.MethodsA volumetric OE-MRI protocol for dynamic T1 relaxation time mapping was implemented on 1.5-T clinical scanners. Participants were scanned breathing room air and during high-flow oxygen administration. Oxygen-induced changes in T1 times (ΔT1) and R2* rates (ΔR2*) were measured in malignant tissue and healthy organs. Unequal variance t-test was used. Patients were surveyed on their experience of the OE-MRI protocol.ResultsFifteen patients with HNSCC (median age 59 years, range 38 to 76) and 10 non-HNSCC subjects (median age 46.5 years, range 32 to 62) were scanned; the OE-MRI acquisition took less than 10 min and was well tolerated. Fifteen histologically confirmed primary tumours and 41 malignant nodal masses were identified. Median (range) of ΔT1 times and hypoxic fraction estimates for primary tumours were -3.5% (-7.0 to -0.3%) and 30.7% (6.5 to 78.6%) respectively. Radiotherapy-responsive and radiotherapy-resistant primary tumours had mean estimated hypoxic fractions of 36.8% (95% confidence interval [CI] 17.4 to 56.2%) and 59.0% (95% CI 44.6 to 73.3%), respectively (p = 0.111).ConclusionsWe present a well-tolerated implementation of dynamic, volumetric OE-MRI of the head and neck region allowing discernment of differing oxygen responses within biopsy-confirmed HNSCC.Trial registrationClinicalTrials.gov, NCT04724096. Registered on 26 January 2021.Relevance statementMRI of tumour hypoxia in head and neck cancer using routine clinical equipment is feasible and well tolerated and allows estimates of tumour hypoxic fractions in less than ten minutes.Key points• Oxygen-enhanced MRI (OE-MRI) can estimate tumour hypoxic fractions in ten-minute scanning.• OE-MRI may be incorporable into routine clinical tumour imaging.• OE-MRI has the potential to predict outcomes after radiotherapy treatment.Graphical

RadioLabeling of the Mutant form of Anti-PlGF Nanobody by 99mTc-Tricarbonyl.

Molecular imaging is a highly effective method for diagnosing cancer and evaluating treatment. A molecular tracer often consists of two segments: A targeting segment, which can be antibodies, antibody fragments, or VHH (nanobody), and a detection segment, such as radioisotopes. The small size of VHH allows for excellent tissue penetration and fast clearance, resulting in minimal nonspecific background, which makes them appealing for use as imaging agents. 99m-technetium (99mTc), one of the well-known radioisotopes, is particularly useful in routine clinical imaging. This study aims to construct 99mTc-anti-placenta growth factor (PlGF) nanobody and assess its radiochemical purity (RCP). The mutant form of anti-PlGF nanobody was expressed in E. coli TG1 and purified using Ni-NTA column affinity chromatography. The purified nanobodies were confirmed by SDS-PAGE and western blotting. A 99mTc-tricarbonyl solution was added to phosphate-buffered saline (PBS) containing the mutant nanobody for labeling, and the mixture was purified using a PD-10 column. The RCP of 99mTc-tricarbonyl is > 98%. After the addition of radioisotopes to the mixture of nanobodies, purity reached 70% in 2 hours and remained constant during incubation. After purifying the labeled nanobody, activity was measured, and the highest amount of labeled nanobodies was collected in the second part. The stability of the labeled nanobody in PBS and in competition with histidine for 4 hours was checked by thin-layer chromatography (TLC). The findings of this study reveal that the RCP of the labeled nanobody was above 95% after 4 hours, indicating the labeled antibody's stability. These results are promising and could be utilized in future in vitro and in vivo studies.

Sensitive Positron Emission Tomography Imaging of PD-L1 Expression in Human Breast and Lung Carcinoma Xenografts Using the Radiometalated Peptide Ga-68-TRAP-WL12.

Noninvasive imaging of the immune checkpoint protein programmed death ligand 1 (PD-L1; synonyms: CD274, B7-H1) holds great promise to improve patient selection and, thus, response rates for immune checkpoint therapy (ICT) with monoclonal antibodies targeting the PD1/PD-L1 axis. The PD-L1 specific peptide WL12 (cyclo(AcY-(NMe)A-N-P-H-L-Hyp-W-S-W(Me)-(NMe)Nle-(NMe)Nle-O-C)-G-NH2) was functionalized with the Gallium-68 chelator TRAP by means of click chemistry (CuAAC). The resulting conjugate TRAP-WL12 was labeled with Gallium-68 within 16 min, with approximately 90% radiochemical yield and 99% radiochemical purity, affording Ga-68-TRAP-WL12 with molar activities typically exceeding 100 MBq/nmol. This radiotracer was characterized by positron emission tomography (PET) imaging and ex vivo biodistribution in murine xenografts of nontransfected PD-L1 expressing tumor cell lines, MDA-MB-231 (human breast carcinoma), and H2009 (human lung adenocarcinoma). It showed a favorable biodistribution profile with rapid renal clearance and low background (tumor-to-blood ratio = 26.6, 3 h p.i.). Conjugation of the Ga-68-TRAP moiety to WL12 successfully mitigated the nonspecific uptake of this peptide in organs, particularly the liver. This was demonstrated by comparing Ga-68-TRAP-WL12 with the archetypical Ga-68-DOTA-WL12, for which tumor-to-liver ratios of 1.4 and 0.5, respectively, were found. Although immunohistochemistry (IHC) revealed a low PD-L1 expression in MDA-MB-213 and H2009 xenografts that corresponds well to the clinical situation, PET showed high tumor uptakes (6.6 and 7.3% injected activity per gram of tissue (iA/g), respectively) for Ga-68-TRAP-WL12. Thus, this tracer has the potential for routine clinical PD-L1 PET imaging because it detects even very low PD-L1 expression densities with high sensitivity and may open an avenue to replace PD-L1 IHC of biopsies as the standard means to select potential responders for ICT.

Large-Scale Standardized Image Integration for Secondary Use Research Projects.

Imaging techniques are a cornerstone of today's medicine and can be crucial for a successful therapy. But in addition, the generated imaging series are an important resource for new informatics' methods, especially in the field of artificial intelligence. This paper describes the success of integrating clinical routine imaging data into a standardized format for research purposes. Thus, we designed an integration flow and successfully implemented it in the local data integration center of University Hospital Schleswig-Holstein. The flow integrates imaging series and radiological reports from the primary system into an openEHR repository with enrichment by semantic codes for better findability and retrieval using HL7 FHIR. As a result, 6.6 million radiological studies with 29 million image series are now available for further medical (informatics) research.

Intra-patient variability of iodine quantification across different dual-energy CT platforms: assessment of normalization techniques.

To investigate intra-patient variability of iodine concentration (IC) between three different dual-energy CT (DECT) platforms and to testdifferent normalization approaches. Forty-four patients who underwent portal venous phase abdominal DECT on a dual-source (dsDECT), a rapid kVp switching (rsDECT), and a dual-layer detector platform (dlDECT) during cancer follow-up were retrospectively included. IC in the liver, pancreas, and kidneys and different normalized ICs (NICPV:portal vein; NICAA:abdominal aorta; NICALL:overall iodine load) were compared between the three DECT scanners for each patient. A longitudinal mixed effects analysis was conducted to elucidate the effect of the scanner type, scan order, inter-scan time, and contrast media amount on normalized iodine concentration. Variability of IC was highest in the liver (dsDECT vs. dlDECT 28.96 (14.28-46.87) %, dsDECT vs. rsDECT 29.08 (16.59-62.55) %, rsDECT vs. dlDECT 22.85 (7.52-33.49) %), and lowest in the kidneys (dsDECT vs. dlDECT 15.76 (7.03-26.1) %, dsDECT vs. rsDECT 15.67 (8.86-25.56) %, rsDECT vs. dlDECT 10.92 (4.92-22.79) %). NICALL yielded the best reduction of IC variability throughout all tissues and inter-scanner comparisons, yet did not reduce the variability between dsDECT vs. dlDECT and rsDECT, respectively, in the liver. The scanner type remained a significant determinant for NICALL in the pancreas and the liver (F-values, 12.26 and 23.78; both, p < 0.0001). We found tissue-specific intra-patient variability of IC across different DECT scanner types. Normalization mitigated variability by reducing physiological fluctuations in iodine distribution.Afternormalization, the scanner type stillhad a significant effect on iodine variability in the pancreas and liver. Differences in iodine quantification between dual-energy CT scanners can partly be mitigated by normalization, yet remain relevant for specific tissues and inter-scanner comparisons, which should be taken into account at clinical routine imaging. • Iodine concentration showed the least variability between scanner types in the kidneys (range 10.92-15.76%) and highest variability in the liver (range 22.85-29.08%). • Normalizing tissue-specific iodine concentrations against the overall iodine load yielded the greatest reduction of variability between scanner types for 2/3 inter-scanner comparisons in the liver and for all (3/3) inter-scanner comparisons in the kidneys and pancreas, respectively. • However, even after normalization, the dual-energy CT scanner type was found to be the factor significantly influencing variability of iodine concentration in the liver and pancreas.

Optics and quantitative assessment of corneal transparency

While some optical properties of cornea like its stromal birefringence had been known since the early nineteenth century, theories explaining its transparency remained inconclusive until the publication of David Maurice' emblematic paper in 1957 Maurice made a model calculation of light scattering by a single collagen fibril as a “dielectric needle”. The volume density of the fibrils being known, Maurice could demonstrate that in the absence of any order among the fibrils the cornea would be opaque. Maurice postulated the hexagonal structure which since has been confirmed by electron microscopy. In modern terms, the order among the collagen fibrils within a stromal collagen lamella is described by a “structure factor” in the radiative transfer equation. This term corresponds to a description of the structure in reciprocal space and is thus equivalent to the representation of crystalline lattices in the first Brillouin zone used for structural modelling in crystallography.In a recent study we further analysed the collagen structure of healthy and oedematous corneas on a nanometric level observed by transmission electron microscopy (TEM). By automated image analysis we could retrieve the so‐called “pair correlation function” and calculate light attenuation within the corresponding cornea. Our findings show that the 1/e light penetration depth within healthy cornea could be calculated as 7300 ± 800 μm, which explains well the transparency of healthy cornea. However, the photon mean free path of oedematous cornea turned out to be from two to three times that value. In oedematous cornea, the “dilution” effect of the scatters is in fact stronger than the degradation of transparency by the perturbation of the structure. The actual loss of transparency in oedematous cornea may therefore be attributed to scattering processes at the micrometric level induced by the augmented optical contrast at the sites of the keratocytes between the collagen lamellae.Perturbations in corneal transparency do not only hamper vision, they also impact optical imaging methods on cornea. This, in turn, permits to study the transparency properties of the corneal tissue. One of the main research interests of our group is to analyse corneal images recorded by optical coherence tomography (OCT) and to extract quantitative parameters like photon mean path length and the fraction of coherently transmitted light.Our partners could show that in the light scattering regime, a term in the radiation transfer equation may be neglected and the attenuation of the full field OCT signal in the volume of the tissue reduces to a Lambert–Beer law. We developed a data analysis algorithm based on Bayesian inference to extract the attenuation coefficient and used it for the analysis of ex vivo corneal high‐resolution FF‐OCT images.In a second step, we developed an image processing algorithm for clinical OCT images removing typical artefacts and compensating for inhomogeneous illumination and corneal curvature. We presently are able to extract corneal transparency parameters from routine clinical OCT images and to provide post‐op follow‐up after keratoplasty or other surgical interventions.

Hemodynamic Failure Staging With Blood Oxygenation Level-Dependent Cerebrovascular Reactivity and Acetazolamide-Challenged (15O-)H2O-Positron Emission Tomography Across Individual Cerebrovascular Territories.

Staging of hemodynamic failure (HF) in symptomatic patients with cerebrovascular steno-occlusive disease is required to assess the risk of ischemic stroke. Since the gold standard positron emission tomography-based perfusion reserve is unsuitable as a routine clinical imaging tool, blood oxygenation level-dependent cerebrovascular reactivity (BOLD-CVR) with CO2 is a promising surrogate imaging approach. We investigated the accuracy of standardized BOLD-CVR to classify the extent of HF. Patients with symptomatic unilateral cerebrovascular steno-occlusive disease, who underwent both an acetazolamide challenge (15O-)H2O-positron emission tomography and BOLD-CVR examination, were included. HF staging of vascular territories was assessed using qualitative inspection of the positron emission tomography perfusion reserve images. The optimum BOLD-CVR cutoff points between HF stages 0-1-2 were determined by comparing the quantitative BOLD-CVR data to the qualitative (15O-)H2O-positron emission tomography classification using the 3-dimensional accuracy index to the randomly assigned training and test data sets with the following determination of a single cutoff for clinical application. In the 2-case scenario, classifying data points as HF 0 or 1-2 and HF 0-1 or 2, BOLD-CVR showed an accuracy of >0.7 for all vascular territories for HF 1 and HF 2 cutoff points. In particular, the middle cerebral artery territory had an accuracy of 0.79 for HF 1 and 0.83 for HF 2, whereas the anterior cerebral artery had an accuracy of 0.78 for HF 1 and 0.82 for HF 2. Standardized and clinically accessible BOLD-CVR examinations harbor sufficient data to provide specific cerebrovascular reactivity cutoff points for HF staging across individual vascular territories in symptomatic patients with unilateral cerebrovascular steno-occlusive disease.

PDFF-CNN: An attention-guided dynamic multi-orientation feature fusion method for gestational age prediction on imbalanced fetal brain MRI dataset.

Fetal brain magnetic resonance imaging (MRI)-based gestational age prediction has been widely used to characterize normal fetal brain development and diagnose congenital brainmalformations. The uncertainty of fetal position and external interference leads to variable localization and direction of the fetal brain. In addition, pregnant women typically concentrate on receiving MRI scans during the fetal anomaly scanning week, leading to an imbalanced distribution of fetal brain MRI data. The above-mentioned problems pose great challenges for deep learning-based fetal brain MRI gestational ageprediction. In this study, a pyramid squeeze attention (PSA)-guided dynamic feature fusion CNN (PDFF-CNN) is proposed to robustly predict gestational ages from fetal brain MRI images on an imbalanced dataset. PDFF-CNN contains four components: transformation module, feature extraction module, dynamic feature fusion module, and balanced mean square error (MSE) loss. The transformation and feature extraction modules are employed by using the PSA to learn multiscale and multi-orientation feature representations in a parallel weight-sharing Siamese network. The dynamic feature fusion module automatically learns the weights of feature vectors generated in the feature extraction module to dynamically fuse multiscale and multi-orientation brain sulci and gyri features. Considering the fact of the imbalanced dataset, the balanced MSE loss is used to mitigate the negative impact of imbalanced data distribution on gestational age predictionperformance. Evaluated on an imbalanced fetal brain MRI dataset of 1327 routine clinical T2-weighted MRI images from 157 subjects, PDFF-CNN achieved promising gestational age prediction performance with an overall mean absolute error of 0.848 weeks and an of 0.904. Furthermore, the attention activation maps of PDFF-CNN were derived, which revealed regional features that contributed to gestational age prediction at each gestationalstage. These results suggest that the proposed PDFF-CNN might have broad clinical applicability in guiding treatment interventions and delivery planning, which has the potential to be helpful with prenatal diagnosis.

Abstract 17610: A Novel Approach Using Deep Neural Networks on Clinical Cardiac MRIs Can Identify Patients With Clonal Hematopoiesis of Indeterminate Potential With High Accuracy

Background: Clonal hematopoiesis of indeterminate potential (CHIP) has been shown to be an independent risk factor for heart disease and heart failure. DNA sequencing is the gold standard to diagnose CHIP. It is unclear if deep learning techniques using routine clinical imaging can aid in identifying those who are likely to have CHIP and thus likely at increased risk for heart disease and heart failure. Hypothesis: We hypothesized that deep learning models trained on routine cardiac MRI (CMR) would be able to help predict who has CHIP Methods: We enrolled patients into an IRB approved study to evaluate for CHIP and associated imaging findings. Whole exome sequencing and our somatic variant pipeline was used to identify those who had CHIP. Various machine learning techniques were employed for training and testing, including SVM, random forest and convolutional neural networks (CNN) to predict who had CHIP from CMR imaging. Results: We enrolled 98 unique patients with CMR and found that 40 (41%) had CHIP. Majority were female 65 (66%) and there was no significant difference in median age between CHIP vs no CHIP (69, IQR 62-78 vs 65, IQR 54-72). There were no significant differences between CHIP vs no CHIP patients in co-morbidities such as CAD, DM, HTN, HF. Compared to SVM and random forest, the best performing model with high sensitivity, specificity and accuracy was derived from CNN (AUC 0.64 vs 0.71 vs 0.85 respectively). We found that multi-view MRI inputs were more accurate than single view MRI inputs for the CNN model. Using an unsupervised approach with CNN and multi-view input, we were able to predict CHIP with 82% accuracy. Conclusions: CNN is a promising deep learning technique that can accurately classify CHIP and thus those at higher cardiovascular disease risk. Ongoing analyses are underway to validate these findings using the UK Biobank and TOPMED datasets and predict who will develop cardiomyopathy with CHIP.

DTI-MR fingerprinting for rapid high-resolution whole-brain T1 , T2 , proton density, ADC, and fractional anisotropy mapping.

This study aims to develop a high-efficiency and high-resolution 3D imaging approach for simultaneous mapping of multiple key tissue parameters for routine brain imaging, including T1 , T2 , proton density (PD), ADC, and fractional anisotropy (FA). The proposed method is intended for pushing routine clinical brain imaging from weighted imaging to quantitative imaging and can also be particularly useful for diffusion-relaxometry studies, which typically suffer from lengthy acquisition time. To address challenges associated with diffusion weighting, such as shot-to-shot phase variation and low SNR, we integrated several innovative data acquisition and reconstruction techniques. Specifically, we used M1-compensated diffusion gradients, cardiac gating, and navigators to mitigate phase variations caused by cardiac motion. We also introduced a data-driven pre-pulse gradient to cancel out eddy currents induced by diffusion gradients. Additionally, to enhance image quality within a limited acquisition time, we proposed a data-sharing joint reconstruction approach coupled with a corresponding sequence design. The phantom and in vivo studies indicated that the T1 and T2 values measured by the proposed method are consistent with a conventional MR fingerprinting sequence and the diffusion results (including diffusivity, ADC, and FA) are consistent with the spin-echo EPI DWI sequence. The proposed method can achieve whole-brain T1 , T2 , diffusivity, ADC, and FA maps at 1-mm isotropic resolution within 10 min, providing a powerful tool for investigating the microstructural properties of brain tissue, with potential applications in clinical and research settings.

A deep learning framework for intracranial aneurysms automatic segmentation and detection on magnetic resonance T1 images.

To design a deep learning-based framework for automatic segmentation and detection of intracranial aneurysms (IAs) on magnetic resonance T1 images and test the robustness and performance of framework. A retrospective diagnostic study was conducted based on 159 IAs from 136 patients who underwent the T1 images. Among them, 127 cases were randomly selected for training and validation, and 32 cases were used to assess the accuracy and consistency of our algorithm. We developed and assembled three convolutional neural networks for the segmentation and detection of IAs. The segmentation and detection performance of the model were compared with the ground truth, and various metrics were calculated at the voxel level, IAs level, and patient level to show the performance of our framework. Our assembled model achieved overall Dice, voxel-level sensitivity, specificity, balanced accuracy, and F1 score of 0.802, 0.874, 0.9998, 0.937, and 0.802, respectively. A coincidence greater than 0.7 between the aneurysms predicted by the model and the ground truth was considered as a true positive. For IAs detection, the sensitivity reached 90.63% with 0.58 false positives per case. The volume of IAs segmented by our model showed a high agreement and consistency with the volume of IAs labeled by experts. The deep learning framework is achievable and robust for IAs segmentation and detection. Our model offers more clinical application opportunities compared to digital subtraction angiography (DSA)-based, CTA-based, and MRA-based methods. Our deep learning framework effectively detects and segments intracranial aneurysms using clinical routine T1 sequences, showing remarkable effectiveness and offering great potential for improving the detection of latent intracranial aneurysms and enabling early identification. •There is no segmentation method based on clinical routine T1 images. Our study shows that the proper deep learning framework can effectively localize the intracranial aneurysms. •The T1-based segmentation and detection method is more universal than other angiography-based detection methods, which can potentially reduce missed diagnoses caused by the absence of angiography images. •The deep learning framework is robust and has the potential to be applied in a clinical setting.

Adaptation of a channelized Hotelling observer model to accommodate anthropomorphic backgrounds and moving test objects in X-ray angiography.

Prior implementations of the channelized Hotelling observer (CHO) model have succeeded in assessing the performance of X-ray angiography systems under a variety of imaging conditions. However, often times these conditions do not resemble those present in routine clinical imaging scenarios, such as having complex anthropomorphic backgrounds in conjunction with moving test objects. This work builds up on prior established CHO methods and introduces a new approach to switch from the already established "multiple-sample" CHO implementation to a "single-sample" technique. The proposed implementation enables the inclusion of moving test objects upon nonuniform backgrounds by allowing only a single sample to represent the test object present condition that is to be used within the statistical test to estimate the detectability index. To assess the proposed method, two image data sets were acquired with a clinical X-ray angiography system. The first set consisted of a uniform background in combination with static test objects while the second consisted of an anthropomorphic chest phantom in conjunction with moving test objects. The first set was used to validate the proposed approach against the multiple-sample method while the second was used to assess the feasibility of the proposed method under a variety of imaging conditions, including seven object sizes and seven detector target dose (DTD)levels. For the uniform background data set, considering all detectability indices greater or equal than 1, the ratio between the detectability indices of the proposed single-sample approach versus the multiple-sample method was 0.997 ± 0.056 (range 0.884-1.159). The average single-direction width of the 95% confidence intervals (CIs) of the detectability index estimates for the multiple-sample method was 0.38 ± 0.43 (range 0.03-2.20). For the single-sample approach, the average width was 2.52 ± 0.63 (range 1.11-5.44). For the anthropomorphic background image set, the results were consistent with classical quantum-limited signal-to-noise ratio (SNR) theory. The magnitude of the detectability indices varied predictably with changes in both object size and DTD, with the highest value associated with the highest dose and the largest object size. Additionally, the proposed method was able to capture differences in the imaging performance for a given test object across the field of view, which was associated with the attenuation levels provided by different features of the anthropomorphicbackground. A new single-sample variant of the CHO model to assess the performance of X-ray angiography imaging systems is proposed. The new approach is consistent with quantum-limited image quality theory and with a standard implementation of the CHO model. The proposed method enables the assessment of moving test objects in combination with complex, nonuniform image backgrounds, thereby opening the possibility to assess imaging conditions which more closely resemble those used in clinicalcare.