Qualitative Image Analysis Research Articles

Application of a Deep Learning-Based Contrast-Boosting Algorithm to Low-Dose Computed Tomography Pulmonary Angiography With Reduced Iodine Load.

The aim of this study was to assess the effectiveness of a deep learning-based image contrast-boosting algorithm by enhancing the image quality of low-dose computed tomography pulmonary angiography at reduced iodine load. This study included 179 patients who underwent low-dose computed tomography pulmonary angiography with a reduced iodine load using 64 mL of a 1:1 mixture of contrast medium from January 1 to June 30, 2023. For single-energy computed tomography, the noise index was set at 15.4 to maintain a CTDIvol of <2 mGy at 80 kVp, and for dual-energy computed tomography, fast kV-switching between 80 and 140 kVp was employed with a fixed tube current of 145 mA. Images were reconstructed by 50% adaptive statistical iterative reconstruction (AR50) and a commercially available deep learning image reconstruction (TrueFidelity) package at a high strength level (TFH). In addition, AR50 images were further processed using a deep learning-based contrast-boosting algorithm (AR50-CB). Quantitative and qualitative image qualities and numbers of involved vessels with thrombus at each pulmonary artery level were compared in the 3 image types using the Friedman test and Wilcoxon signed rank test. Five hundred thirty-seven reconstructed image datasets of 179 patients were analyzed. Quantitative image analysis showed AR50-CB (30.8 ± 10.0 and 28.1 ± 9.6, respectively) had significantly higher signal-to-noise ratio and contrast-to-noise ratio values than AR50 (20.2 ± 6.2 and 17.8 ± 6.2, respectively) (P < 0.001) or TFH (28.3 ± 8.3 and 24.9 ± 8.1, respectively) (P < 0.001). Qualitative image analysis showed that contrast enhancement and noise scores of AR50-CB were significantly greater than those of AR50 (P < 0.001) and that AR50-CB enhancement scores were significantly higher than TFH enhancement scores (P < 0.001). The number of subsegmental pulmonary arteries affected by thrombus detected was significantly greater for AR50-CB (30 for AR50, 30 for TFH, and 55 for AR50-CB, P < 0.001). The use of a deep learning-based contrast-boosting algorithm improved image quality in terms of signal-to-noise ratio and contrast-to-noise ratio values and the detection of thrombi in subsegmental pulmonary arteries.

Characteristics and diagnostic performance of nonechoplanar diffusion-weighted imaging in detecting canine tympanokeratoma (cholesteatoma).

Tympanokeratomas (cholesteatomas) are destructive keratinic masses of the middle ear that are often treated surgically. In humans, nonechoplanar (non-EP) diffusion-weighted (DW) MRI is efficient in diagnosing tympanokeratomas and differentiating recurrent tympanokeratomas from granulation or fibrous tissue after surgery. The objectives of this study were to (1) determine the characteristics of non-EP DWI of histologically or cytologically confirmed canine tympanokeratomas, (2) determine the performance of non-EP DW images, apparent diffusion coefficient (ADC) map and ADC values in discriminating between tympanokeratomas and other causes of otitis media in dogs, and (3) find an optimal ADC cut-off value. Medical records of dogs diagnosed on MRI with otitis media in two veterinary hospitals were retrospectively reviewed. Sixty-two ears with a cytological or pathological diagnosis of either tympanokeratoma (36/62) or nontympanokeratoma otitis media (26/62) were selected. Diffusion-weighted images had an accuracy of 77.4%, a sensitivity of 94.4%, and a specificity of 53.8% for the detection of tympanokeratoma. The ADC value of middle ear content ranged from 517 to 1355.10-6mm2/s in tympanokeratoma and from 454 to 2447×10-6mm2/s in nontympanokeratoma otitis media. An ADC value below 916×10-6mm2/s interpreted as a tympanokeratoma yielded an accuracy of 78.7%, a sensitivity of 92.6%, and a specificity of 60%. In the study population, combined qualitative analysis of DW images and ADC maps was the most effective method for diagnosing tympanokeratomas with an accuracy of 80.9%, a sensitivity of 92.6%, and a specificity of 65%.

Crosslinked-hybrid nanoparticle embedded in thermogel for sustained co-delivery to inner ear

Treatment-induced ototoxicity and accompanying hearing loss are a great concern associated with chemotherapeutic or antibiotic drug regimens. Thus, prophylactic cure or early treatment is desirable by local delivery to the inner ear. In this study, we examined a novel way of intratympanically delivered sustained nanoformulation by using crosslinked hybrid nanoparticle (cHy-NPs) in a thermoresponsive hydrogel i.e. thermogel that can potentially provide a safe and effective treatment towards the treatment-induced or drug-induced ototoxicity. The prophylactic treatment of the ototoxicity can be achieved by using two therapeutic molecules, Flunarizine (FL: T-type calcium channel blocker) and Honokiol (HK: antioxidant) co-encapsulated in the same delivery system. Here we investigated, FL and HK as cytoprotective molecules against cisplatin-induced toxic effects in the House Ear Institute - Organ of Corti 1 (HEI-OC1) cells and in vivo assessments on the neuromast hair cell protection in the zebrafish lateral line. We observed that cytotoxic protective effect can be enhanced by using FL and HK in combination and developing a robust drug delivery formulation. Therefore, FL-and HK-loaded crosslinked hybrid nanoparticles (FL-cHy-NPs and HK-cHy-NPs) were synthesized using a quality-by-design approach (QbD) in which design of experiment-central composite design (DoE-CCD) following the standard least-square model was used for nanoformulation optimization. The physicochemical characterization of FL and HK loaded-NPs suggested the successful synthesis of spherical NPs with polydispersity index < 0.3, drugs encapsulation (> 75%), drugs loading (~ 10%), stability (> 2 months) in the neutral solution, and appropriate cryoprotectant selection. We assessed caspase 3/7 apopototic pathway in vitro that showed significantly reduced signals of caspase 3/7 activation after the FL-cHy-NPs and HK-cHy-NPs (alone or in combination) compared to the CisPt. The final formulation i.e. crosslinked-hybrid-nanoparticle-embedded-in-thermogel was developed by incorporating drug-loaded cHy-NPs in poloxamer-407, poloxamer-188, and carbomer-940-based hydrogel. A combination of artificial intelligence (AI)-based qualitative and quantitative image analysis determined the particle size and distribution throughout the visible segment. The developed formulation was able to release the FL and HK for at least a month. Overall, a highly stable nanoformulation was successfully developed for combating treatment-induced or drug-induced ototoxicity via local administration to the inner ear.Graphical

Deep Learning Reconstruction of Prospectively Accelerated MRI of the Pancreas: Clinical Evaluation of Shortened Breath-Hold Examinations With Dixon Fat Suppression.

Deep learning (DL)-enabled magnetic resonance imaging (MRI) reconstructions can enable shortening of breath-hold examinations and improve image quality by reducing motion artifacts. Prospective studies with DL reconstructions of accelerated MRI of the upper abdomen in the context of pancreatic pathologies are lacking. In a clinical setting, the purpose of this study is to investigate the performance of a novel DL-based reconstruction algorithm in T1-weighted volumetric interpolated breath-hold examinations with partial Fourier sampling and Dixon fat suppression (hereafter, VIBE-DixonDL). The objective is to analyze its impact on acquisition time, image sharpness and quality, diagnostic confidence, pancreatic lesion conspicuity, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). This prospective single-center study included participants with various pancreatic pathologies who gave written consent from January 2023 to September 2023. During the same session, each participant underwent 2 MRI acquisitions using a 1.5 T scanner: conventional precontrast and postcontrast T1-weighted VIBE acquisitions with Dixon fat suppression (VIBE-Dixon, reference standard) using 4-fold parallel imaging acceleration and 6-fold accelerated VIBE-Dixon acquisitions with partial Fourier sampling utilizing a novel DL reconstruction tailored to the acquisition. A qualitative image analysis was performed by 4 readers. Acquisition time, image sharpness, overall image quality, image noise and artifacts, diagnostic confidence, as well as pancreatic lesion conspicuity and size were compared. Furthermore, a quantitative analysis of SNR and CNR was performed. Thirty-two participants were evaluated (mean age ± SD, 62 ± 19 years; 20 men). The VIBE-DixonDL method enabled up to 52% reduction in average breath-hold time (7 seconds for VIBE-DixonDL vs 15 seconds for VIBE-Dixon, P < 0.001). A significant improvement of image sharpness, overall image quality, diagnostic confidence, and pancreatic lesion conspicuity was observed in the images recorded using VIBE-DixonDL (P < 0.001). Furthermore, a significant reduction of image noise and motion artifacts was noted in the images recorded using the VIBE-DixonDL technique (P < 0.001). In addition, for all readers, there was no evidence of a difference in lesion size measurement between VIBE-Dixon and VIBE-DixonDL. Interreader agreement between VIBE-Dixon and VIBE-DixonDL regarding lesion size was excellent (intraclass correlation coefficient, >90). Finally, a statistically significant increase of pancreatic SNR in VIBE-DIXONDL was observed in both the precontrast (P = 0.025) and postcontrast images (P < 0.001). Also, an increase of splenic SNR in VIBE-DIXONDL was observed in both the precontrast and postcontrast images, but only reaching statistical significance in the postcontrast images (P = 0.34 and P = 0.003, respectively). Similarly, an increase of pancreas CNR in VIBE-DIXONDL was observed in both the precontrast and postcontrast images, but only reaching statistical significance in the postcontrast images (P = 0.557 and P = 0.026, respectively). The prospectively accelerated, DL-enhanced VIBE with Dixon fat suppression was clinically feasible. It enabled a 52% reduction in breath-hold time and provided superior image quality, diagnostic confidence, and pancreatic lesion conspicuity. This technique might be especially useful for patients with limited breath-hold capacity.

Imaging and Quantification of the Hepatic Vasculature of Mice Using Ultrafast Doppler Ultrasound.

Non-invasive in vivo imaging of the vasculature is a powerful tool for studying disease mechanisms in rodents. To achieve high sensitivity imaging of the microvasculature using Doppler ultrasound methods, imaging modalities employing the concept of ultrafast imaging are preferred. By increasing the frame rate of the ultrasound scanner to thousands of frames per second, it becomes possible to improve the sensitivity of the blood flow down to 2 mm/s and to obtain functional information about the microcirculation in comparison to a sensitivity of around 1 cm/s in conventional Doppler modes. While Ultrafast Doppler ultrasound (UFUS) imaging has become adopted in neuroscience, where it can capture brain activity through neurovascular coupling, it presents greater challenges when imaging the vasculature of abdominal organs due to larger motions linked to breathing. The liver, positioned anatomically under the diaphragm, is particularly susceptible to out-of-plane movement and oscillating respiratory motion. These artifacts not only adversely affect Doppler imaging but also complicate the anatomical analysis of vascular structures and the computation of vascular parameters. Here, we present a qualitative and quantitative imaging analysis of the hepatic vasculature in mice by UFUS. We identify major anatomical vascular structures and provide graphical illustrations of the hepatic macroscopical anatomy, comparing it to an in-depth anatomical assessment of the hepatic vasculature based on Doppler readouts. Additionally, we have developed a quantification protocol for robust measurements of hepatic blood volume of the microvasculature over time. To contemplate further research, qualitative vascular analysis provides a comprehensive overview and suggests a standardized terminology for researchers working with mouse models of liver disease. Furthermore, it offers the opportunity to apply ultrasound as a non-invasive complementary method to inspect hepatic vascular defects in vivo and measure functional microvascular alterations deep within the organ before unraveling blood vessel anomalies at the micron scale levels using ex vivo staining on tissue sections.

Neural network model development for detecting atypical mitoses in histological slides

Background: Modern computer systems allow digitizing and examining images of histological preparations, which led the authors to the idea of using machine learning tools in digital pathohistology. The ability of neural networks to find sub-visual image features in digitized histological preparations provides the basis for better qualitative and quantitative image analysis. Existing machine learning methods provide good accuracy and speed in recognizing various images, which gives hope for their wide application, including in oncologic diagnostics. AIM: Use methods of mathematical modeling to identify pathological mitoses in histological preparations as the main sign of the difference between malignant and benign tumor growth. MATERIALS AND METHODS: Histological images of the N.N. Priorov National Medical Research Center of Traumatology and Orthopedics were used as a data set for the neural network model. The model was tested using 188 histologic slides from 67 patients treated at the institute. Histological preparations were scanned on a Leica Aperio CS2 microscope with a ×400 resolution and converted into JPEG format with further processing. Next, the test images were analyzed in streaming mode using the created neural network model in order to obtain the coordinates of the desired diagnostic object — pathological mitosis and the probability with which the model found the object of this category. The obtained images were analyzed by a pathologist to determine whether the detected object corresponded to pathological mitosis. RESULTS: The authors have chosen an architecture, developed a methodology for training a neural network, and created a model that can be used to detect pathologic mitoses in histologic preparations. The authors do not attempt to replace the physician, but show the possibility of an integrated approach to data analysis by a computer system and a pathologist. Conclusions: The developed mathematical model of neural network used as a part of technological solution for recognizing pathological mitoses in scanned histological preparations can be used as a tool to reduce the time of research and increase the accuracy of diagnosis by a pathologist.

Synchrotron tomography of magnetoprimed soybean plant root system architecture grown in arsenic-polluted soil.

The present study evaluated the repercussions of magnetopriming on the root system architecture of soybean plants subjected to arsenic toxicity using synchrotron radiation source based micro-computed tomography (SR-µCT). This will be used evey where as abbreviation for the technique for three-dimensional imaging. Seeds of soybean were exposed to the static magnetic field (SMF) of strength (200 mT) for 1h prior to sowing. Magnetoprimed and non-primed seeds were grown for 1 month in a soil-sand mixture containing four different levels of sodium arsenate (0, 5, 10, and 50 mg As kg-1 soil). The results showed that arsenic adversely affects the root growth in non-primed plants by reducing their root length, root biomass, root hair, size and number of root nodules, where the damaging effect of As was observed maximum at higher concentrations (10 and 50 mg As kg-1 soil). However, a significant improvement in root morphology was detected in magnetoprimed plants where SMF pretreatment enhanced the root length, root biomass, pore diameter of cortical cells, root hair formation, lateral roots branching, and size of root nodules and girth of primary roots. Qualitative analysis of x-ray micro-CT images showed that arsenic toxicity damaged the epidermal and cortical layers of the root as well as reduced the pore diameter of the cortical cells. However, the diameter of cortical cells pores in magnetoprimed plants was observed higher as compared to plants emerged from non-primed seeds at all level of As toxicity. Thus, the study suggested that magnetopriming has the potential to attenuate the toxic effect of As and could be employed as a pre-sowing treatment to reduce the phytotoxic effects of metal ions in plants by improving root architecture and root tolerance index. This study is the very first exploration of the potential benefits of magnetopriming in mitigating the toxicity of metals (As) in plant roots utilizing the micro-CT technique.

Super-resolution Deep Learning Reconstruction for 3D Brain MR Imaging: Improvement of Cranial Nerve Depiction and Interobserver Agreement in Evaluations of Neurovascular Conflict

Rationale and ObjectivesTo determine if super-resolution deep learning reconstruction (SR-DLR) improves the depiction of cranial nerves and interobserver agreement when assessing neurovascular conflict in 3D fast asymmetric spin echo (3D FASE) brain MR images, as compared to deep learning reconstruction (DLR). Materials and MethodsThis retrospective study involved reconstructing 3D FASE MR images of the brain for 37 patients using SR-DLR and DLR. Three blinded readers conducted qualitative image analyses, evaluating the degree of neurovascular conflict, structure depiction, sharpness, noise, and diagnostic acceptability. Quantitative analyses included measuring edge rise distance (ERD), edge rise slope (ERS), and full width at half maximum (FWHM) using the signal intensity profile along a linear region of interest across the center of the basilar artery. ResultsInterobserver agreement on the degree of neurovascular conflict of the facial nerve was generally higher with SR-DLR (0.429–0.923) compared to DLR (0.175–0.689). SR-DLR exhibited increased subjective image noise compared to DLR (p ≤ 0.008). However, all three readers found SR-DLR significantly superior in terms of sharpness (p < 0.001); cranial nerve depiction, particularly of facial and acoustic nerves, as well as the osseous spiral lamina (p < 0.001); and diagnostic acceptability (p ≤ 0.002). The FWHM (mm)/ERD (mm)/ERS (mm-1) for SR-DLR and DLR was 3.1–4.3/0.9–1.1/8,795.5–10,703.5 and 3.3–4.8/1.4–2.1/5,157.9–7,705.8, respectively, with SR-DLR's image sharpness being significantly superior (p ≤ 0.001). ConclusionsSR-DLR enhances image sharpness, leading to improved cranial nerve depiction and a tendency for greater interobserver agreement regarding facial nerve neurovascular conflict.

Influence of surface finishing on the outcome of a 3-point bending test in polymer-based dental composits assessed by qualitative and quantitative fractography

ObjectivesThe aim of the study was to evaluate the influence of surface finishing in three polymer-based composits (composits) on the result of a 3-point bending test using quantitative and qualitative fractography as well as microstructural characteristics. Materials and methods270 rectangular specimens (n = 30) of three composits were prepared, stored and tested according to NIST No. 4877. Prior testing, the samples were subjected to three surface treatments: 1) no treatment, to preserve the oxygen inhibition layer, 2) with FEPA P1200 (ANSI equivalent grit 600) SiC paper abraded surface, and 3) polished surface. A three-point bending testing was employed, followed by quantitative (assessment of reason for failure and fracture pattern) and qualitative (fracture mirror measurements) fractography, 3D and 2D surface imaging, surface roughness, reliability and Fe-SEM analysis. The mirror radius that runs in the direction of constant stress was used to calculate the mirror constant (A) using Orr's equation. Uni- and multifactorial ANOVA, Tukey's post hoc test, and Weibull analysis was performed for statistical analysis. ResultsSurface finishing has less influence on the fracture pattern, reliability and mechanical parameters and has no influence on the mirror constant. The amount of inorganic filler has a direct impact on flexural strength and modulus, while the ranking of materials was independent of surface treatment. Failures initiated by volume defects were the most common failure mode (77.0%) with surface defects accounting for 14.9% (edge) and 7.7% (corner). Polishing resulted in lower peak-to valley height compared to no treatment, both 3–4 times lower compared to the 600 grit treatment. The increase in roughness within the analyzed range did not lead to an increase in surface-related failures. ConclusionsThe clear dominance of volume defects in all examined materials as a cause of material fracture reduces the impact of roughness on the measured properties. This insight was only possible using qualitative and quantitative research fractography.

Comparison of the Pharmacokinetics of Gadolinium-Based and Iron Oxide-Based Contrast Agents inside the Lymphatic Structure using Magnetic Resonance Lymphangiography.

Gadolinium (Gd)-based contrast agents are primarily used for contrast-enhanced magnetic resonance lymphangiography (MRL). However, overcoming venous contamination issues remains challenging. This study aims to assess the MRL efficacy of the newly developed iron-based contrast agent (INV-001) that is specially designed to mitigate venous contamination issues. The study further explores the optimal dosage, including both injection volume and concentration, required to achieve successful visualization of the popliteal lymph nodes and surrounding lymphatic vessels. All animals utilized in this study were male Sprague-Dawley (SD) rats weighing between 250 and 300g. The contrast agents prepared were injected intradermally in the fourth phalanx of both hind limbs using a 30-gauge syringe in SD rats. MRL was performed every 16min on a coronal 3D time-of-flight sequence with saturation bands using a 9.4-T animal machine. Contrary to Gd-DOTA, which exhibited venous contamination in most animals irrespective of injection dosages and conditions, INV-001 showed no venous contamination. For Gd-DOTA, the popliteal lymph nodes and lymphatic vessels reached peak enhancement 16min after injection from the injection site and then rapidly washed out. However, with INV-001, they reached peak enhancement between 16 and 32min after injection, with prolonged visualization of the popliteal lymph node and lymphatic vessels. INV-001 at 0.45μmol (15mM, 30 μL) and 0.75μmol (15mM, 50 μL) achieved high scores for qualitative image analysis, providing good visualization of the popliteal lymph nodes and lymphatic vessels without issues of venous contamination, interstitial space enhancement, or lymph node enlargement. In MRL, INV-001, a novel T1 contrast agent based on iron, enables prolonged enhancement of popliteal lymph nodes and lymphatic vessels without venous contamination.

Use of Bone Scintigraphy in The Diagnosis of Cardiac Amyloidosis

Cardiac amyloidosis is a rare and progressive condition caused by the buildup of amyloid in the heart. There are two common forms of cardiac amyloidosis: light-chain amyloidosis (AL) and transthyretin amyloidosis (ATTR). The deposition of amyloid in the extracellular matrix of the myocardium leads to heart failure over time, and if left untreated, it can even be fatal. For this reason, early diagnosis is essential for both prognosis and improving patients' quality of life. Since cardiac amyloidosis is a potentially treatable condition, early diagnosis is key to improving patient survival and quality of life. There is now compelling evidence showing that nuclear imaging plays a fundamental role in the non-invasive diagnosis of transthyretin cardiac amyloidosis. Due to its high sensitivity and specificity, radiotracer compounds that target the bones are considered sufficient for establishing the diagnosis, avoiding the need for endomyocardial biopsy. In this study, we analyzed data obtained from examinations conducted on patients referred to the Cardiology Department of the "San Giovanni di Dio e Ruggi d'Aragona" University Hospital, who presented with suspected cardiac amyloidosis. These patients underwent scintigraphy with 99mTc-HMDP (hydroxymethylenediphosphonate), using a large-field computerized gamma camera with a parallel-hole collimator and SPECT. After performing early whole-body planar acquisitions at 5 minutes and late acquisitions at 3 hours after intravenous administration of approximately 700 MBq of Tc-99m HMDP, myocardial uptake was observed. Subsequently, targeted acquisitions and SPECT tomographic studies were performed on the myocardial uptake areas. All acquired images were subsequently subjected to quantitative and qualitative analysis, allowing us to extract a large number of parameters reflecting morphological and predictive characteristics using radiomics and more or less automated analysis algorithms. This analysis enabled us to obtain quantitative information that is not apparent in a qualitative image analysis. The ability to extract hidden information from digital medical images is of particular interest as it can enhance the predictive capabilities of existing automatic segmentation algorithms. Extracting new information that was previously hidden can be utilized for automatic image segmentation.

Deep learning reconstruction for high-resolution computed tomography images of the temporal bone: comparison with hybrid iterative reconstruction

PurposeWe investigated whether the quality of high-resolution computed tomography (CT) images of the temporal bone improves with deep learning reconstruction (DLR) compared with hybrid iterative reconstruction (HIR).MethodsThis retrospective study enrolled 36 patients (15 men, 21 women; age, 53.9 ± 19.5 years) who had undergone high-resolution CT of the temporal bone. Axial and coronal images were reconstructed using DLR, HIR, and filtered back projection (FBP). In qualitative image analyses, two radiologists independently compared the DLR and HIR images with FBP in terms of depiction of structures, image noise, and overall quality, using a 5-point scale (5 = better than FBP, 1 = poorer than FBP) to evaluate image quality. The other two radiologists placed regions of interest on the tympanic cavity and measured the standard deviation of CT attenuation (i.e., quantitative image noise). Scores from the qualitative and quantitative analyses of the DLR and HIR images were compared using, respectively, the Wilcoxon signed-rank test and the paired t-test.ResultsQualitative and quantitative image noise was significantly reduced in DLR images compared with HIR images (all comparisons, p ≤ 0.016). Depiction of the otic capsule, auditory ossicles, and tympanic membrane was significantly improved in DLR images compared with HIR images (both readers, p ≤ 0.003). Overall image quality was significantly superior in DLR images compared with HIR images (both readers, p < 0.001).ConclusionCompared with HIR, DLR provided significantly better-quality high-resolution CT images of the temporal bone.

Pancreatic cancer in photon-counting CT: Low keV virtual monoenergetic images improve tumor conspicuity

Purpose of the studyThe aim of the study was to identify differences in the tumor conspicuity of pancreatic adenocarcinomas in different monoenergetic or polyenergetic reconstructions and contrast phases in photon-counting CT (PCCT). Material and methods34 patients were retrospectively enrolled in this study. Quantitative image analysis was performed with region of interest (ROI) measurements in different monoenergetic levels ranging from 40 up to 70 keV (5-point steps) and polyenergetic series. Tumor-parenchyma attenuation differences and contrast-to-noise-ratio (CNR) were calculated. A qualitative image analysis was accomplished by 4 radiologists using a 5-point Likert scale (1 = “not recognizable” up to 5 = “easy recognizable”). Differences between groups were evaluated for statistical significance using the Friedman test and in case of significant differences pair-wise post-hoc testing with Bonferroni correction was applied. ResultsTumor-parenchyma attenuation difference was significantly different between the different image reconstructions for both arterial- and portal-venous-phase-images (p < 0.001). Tumor-parenchyma attenuation difference was significantly higher on arterial-phase-images at mono40keV compared to polyenergetic images (p < 0.001) and mono55keV images or higher (p < 0.001). For portal-venous-phase-images tumor-parenchyma attenuation difference was significantly higher on mono40keV images compared to polyenergetic images (p < 0.001) and mono50keV images (p = 0.03) or higher (p < 0.001). The same trend was seen for CNR. Tumor conspicuity was rated best on mono40keV images with 4.3 ± 0.9 for arterial-phase-images and 4.3 ± 1.1 for portal-venous-phase-images. In contrast, overall image quality was rated best on polyenergetic-images with 4.8 ± 0.5 for arterial-phase-images and 4.7 ± 0.6 for portal-venous-phase-images. ConclusionLow keV virtual monoenergetic images significantly improve the tumor conspicuity of pancreatic adenocarcinomas in PCCT based on quantitative and qualitative results. On the other hand, readers prefer polyenergetic images for overall image quality.

Deep-Learning Reconstruction of High-Resolution CT Improves Interobserver Agreement for the Evaluation of Pulmonary Fibrosis.

Objective: This study aimed to investigate whether deep-learning reconstruction (DLR) improves interobserver agreement in the evaluation of honeycombing for patients with interstitial lung disease (ILD) who underwent high-resolution computed tomography (CT) compared with hybrid iterative reconstruction (HIR). Methods: In this retrospective study, 35 consecutive patients suspected of ILD who underwent CT including the chest region were included. High-resolution CT images of the unilateral lung with DLR and HIR were reconstructed for the right and left lungs. A radiologist placed regions of interest on the lung and measured standard deviation of CT attenuation (i.e., quantitative image noise). In the qualitative image analyses, 5 blinded readers assessed the presence of honeycombing and reticulation, qualitative image noise, artifacts, and overall image quality using a 5-point scale (except for artifacts which was evaluated using a 3-point scale). Results: The quantitative and qualitative image noise in DLR was remarkably reduced compared to that in HIR (P < .001). Artifacts and overall DLR quality were significantly improved compared to those of HIR (P < .001 for 4 out of 5 readers). Interobserver agreement in the evaluations of honeycombing and reticulation for DLR (0.557 [0.450-0.693] and 0.525 [0.470-0.541], respectively) were higher than those for HIR (0.321 [0.211-0.520] and 0.470 [0.354-0.533], respectively). A statistically significant difference was found for honeycombing (P = .014). Conclusions: DLR improved interobserver agreement in the evaluation of honeycombing in patients with ILD on CT compared to HIR.

Noninvasive Assessment of Kidney Injury by Combining Structure and Function Using Artificial Intelligence-Based Manganese-Enhanced Magnetic Resonance Imaging.

Contrast-enhanced magnetic resonance imaging (MRI) is seriously limited in kidney injury detection due to the nephrotoxicity of clinically used gadolinium-based contrast agents. Herein, we propose a noninvasive method for the assessment of kidney injury by combining structure and function information based on manganese (Mn)-enhanced MRI for the first time. As a proof of concept, the Mn-melanin nanoprobe with good biocompatibility and excellent T1 relaxivity is applied in MRI of a unilateral ureteral obstruction mice model. The abundant renal structure and function information is obtained through qualitative and quantitative analysis of MR images, and a brand new comprehensive assessment framework is proposed to precisely identify the degree of kidney injury successfully. Our study demonstrates that Mn-enhanced MRI is a promising approach for the highly sensitive and biosafe assessment of kidney injury in vivo.

Magnetic Alignment of Collagen: Principles, Methods, Applications, and Fiber Alignment Analyses.

Anisotropically aligned collagen scaffolds mimic the microarchitectural properties of native tissue, possess superior mechanical properties, and provide the essential physicochemical cues to guide cell response. Biofabrication methodologies to align collagen fibers include mechanical, electrical, magnetic, and microfluidic approaches. Magnetic alignment of collagen was first published in 1983 but widespread use of this technique was hindered mainly due to the low diamagnetism of collagen molecules and the need for very strong tesla-order magnetic fields. Over the last decade, there is a renewed interest in the use of magnetic approaches that employ magnetic particles and low-level magnetic fields to align collagen fibers. In this review, the working principle, advantages, and limitations of different collagen alignment techniques with special emphasis on the magnetic alignment approach are detailed. Key findings from studies that employ high-strength magnetic fields and the magnetic particle-based approach to align collagen fibers are highlighted. In addition, the most common qualitative and quantitative image analyses methods to assess collagen alignment are discussed. Finally, current challenges and future directions are presented for further development and clinical translation of magnetically aligned collagen scaffolds.

Comparative Evaluation of Imaging Techniques for Paraspinal Muscle Fat Quantification

Introduction: Low back pain (LBP) is a prevalent health issue associated with morphological changes in paravertebral muscles. Magnetic resonance imaging (MRI) is effective in identifying muscle steatosis, with MR spectroscopy (MRS) considered the gold standard. However, MRS is limited by technical challenges, prompting interest in Dixon sequences for fat quantification. Materials and Methods: We conducted a study comparing Multi Echo VIBE Dixon with single-voxel MR spectroscopy in quantifying fat fractions in lumbar multifidus muscles of chronic LBP patients. Ninety-eight measurements from 49 patients were analysed. Qualitative and quantitative image analyses were performed, and statistical analysis was conducted using SPSS 27. Results: Significant positive correlation (correlation coefficient: 0.992, p &lt; 0.001) was found between Dixon and MRS fat fraction measurements. Intra-class correlation coefficient was 0.991 (p &lt; 0.001), indicating strong agreement. No proportion bias was observed. Factors such as age, sex, and spinal degeneration correlated positively with multifidus fat atrophy. Conclusion: T2*-corrected Dixon imaging aligns well with spectroscopic measurements, offering an accurate alternative for estimating paraspinal muscle fat content in chronic LBP patients. Further studies are needed to establish threshold values for Dixon imaging. Chronic LBP is associated with multifidus muscle atrophy and fat infiltration, highlighting the need for effective management strategies.

CRCS: An automatic image processing pipeline for hormone level analysis of Cushing’s disease

Due to the abnormal secretion of adreno-cortico-tropic-hormone (ACTH) by tumors, Cushing's disease leads to hypercortisonemia, a precursor to a series of metabolic disorders and serious complications. Cushing's disease has high recurrence rate, short recurrence time and undiscovered recurrence reason after surgical resection. Qualitative or quantitative automatic image analysis of histology images can potentially in providing insights into Cushing's disease, but still no software has been available to the best of our knowledge. In this study, we propose a quantitative image analysis-based pipeline CRCS, which aims to explore the relationship between the expression level of ACTH in normal cell tissues adjacent to tumor cells and the postoperative prognosis of patients. CRCS mainly consists of image-level clustering, cluster-level multi-modal image registration, patch-level image classification and pixel-level image segmentation on the whole slide imaging (WSI). On both image registration and classification tasks, our method CRCS achieves state-of-the-art performance compared to recently published methods on our collected benchmark dataset. In addition, CRCS achieves an accuracy of 0.83 for postoperative prognosis of 12 cases. CRCS demonstrates great potential for instrumenting automatic diagnosis and treatment for Cushing's disease.

Volumetric sonographic depiction of the fallopian tube lumen for the early detection of tubal abnormalities: A work in progress

ObjectivesThe fallopian tube (FT) has emerged as an important imaging target in the detection of early ovarian cancer, which has remained an evasive challenge in the field of medicine. Recent understanding of ovarian cancer has identified the distal FT as the site of early tumorigenesis. Evaluation of the FT poses challenges due to the small size and variable anatomic position. This study outlines image acquisition and analysis techniques for volumetric depiction of the FT lumen. MethodsWomen with BRCA+ ​mutations undergoing risk reduction salpingo-ophorectomy were imaged using contrast-enhanced 3D transvaginal ultrasound (n ​= ​7). Sono-salpingography was conducted with intraluminal contrast instilled through the cervix for improved imaging of the FT lumen. Three-dimensional volumetric data was collected for qualitative and quantitative image analysis. Pathologic correlation was conducted using the Sectioning and Extensively Examining the Fimbriated End Protocol (SEE-FIM). ResultsStudy subjects underwent 3D imaging with trans-cervical FT lumen contrast enhancement at the time of our interim reporting. None of the subjects in our initial study had serous tubal intraepithelial carcinoma (STIC) lesions, however one had acute inflammation of the FT. The 3D quantitative image analysis demonstrated areas of luminal irregularity corresponding to the regions of inflammation on pathology. ConclusionsOur study shows promise in the detailed evaluation of the FT lumen for the detection of luminal abnormalities. We continue to optimize image acquisition and analysis techniques for the detection of STIC lesions as we enroll additional patients.

Compressed-sensing navigator-triggered magnetic resonance cholangiopancreatography in clinical practice: qualitative image analysis and comparison with standard protocols

Compressed-sensing navigator-triggered magnetic resonance cholangiopancreatography in clinical practice: qualitative image analysis and comparison with standard protocols