Machine Learning in Hypertrophic Cardiomyopathy: Nonlinear Model From Clinical and CMR Features Predicting Cardiovascular Events.

BACKGROUND: The cumulative burden of hypertrophic cardiomyopathy (HCM) is significant, with a noteworthy percentage (10%-15%) of patients with HCM per year experiencing major adverse cardiovascular events (MACEs). A current risk stratification scheme for HCM had only limited accuracy in predicting sudden cardiac death (SCD) and failed to account for a broader spectrum of adverse cardiovascular events and cardiac magnetic resonance (CMR) parameters. OBJECTIVES: This study sought to develop and evaluate a machine learning (ML) framework that integrates CMR imaging and clinical characteristics to predict MACEs in patients with HCM. METHODS: A total of 758 patients with HCM (67% male; aged 49 ± 14 years) who were admitted between 2010 and 2017 from 4 medical centers were included. The ML model was built on the internal discovery cohort (533 patients with HCM, admitted to Fuwai Hospital, Beijing, China) by using the light gradient-boosting machine and internally evaluated using cross-validation. The external test cohort consisted of 225 patients with HCM from 3 medical centers. A total of 14 CMR imaging features (strain and late gadolinium enhancement [LGE]) and 23 clinical variables were evaluated and used to inform the ML model. MACEs included a composite of arrhythmic events, SCD, heart failure, and atrial fibrillation-related stroke. RESULTS: MACEs occurred in 191 (25%) patients over a median follow-up period of 109.0 months (Q1-Q3: 73.0-118.8 months). Our ML model achieved areas under the curve (AUCs) of 0.830 and 0.812 (internally and externally, respectively). The model outperformed the classic HCM Risk-SCD model, with significant improvement (P < 0.001) of 22.7% in the AUC. Using the cubic spline analysis, the study showed that the extent of LGE and the impairment of global radial strain (GRS) and global circumferential strain (GCS) were nonlinearly correlated with MACEs: an elevated risk of adverse cardiovascular events was observed when these parameters reached the high enough second tertiles (11.6% for LGE, 25.8% for GRS, -17.3% for GCS). CONCLUSIONS: ML-empowered risk stratification using CMR and clinical features enabled accurate MACE prediction beyond the classic HCM Risk-SCD model. In addition, the nonlinear correlation between CMR features (LGE and left ventricular pressure gradient) and MACEs uncovered in this study provides valuable insights for the clinical assessment and management of HCM.

Acoustic-holography-patterned primary hepatocytes possess liver functions.

Acoustic holography (AH), a promising approach for cell patterning, emerges as a powerful tool for constructing novel invitro 3D models that mimic organs and cancers features. However, understanding changes in cell function post-AH remains limited. Furthermore, replicating complex physiological and pathological processes solely with cell lines proves challenging. Here, we employed acoustical holographic lattice to assemble primary hepatocytes directly isolated from mice into a cell cluster matrix to construct a liver-shaped tissue sample. For the first time, we evaluated the liver functions of AH-patterned primary hepatocytes. The patterned model exhibited large numbers of self-assembled spheroids and superior multifarious core hepatocyte functions compared to cells in 2D and traditional 3D culture models. AH offers a robust protocol for long-term in vitro culture of primary cells, underscoring its potential for future applications in disease pathogenesis research, drug testing, and organ replacement therapy.

Generalizable Reconstruction for Accelerating MR Imaging via Federated Learning with Neural Architecture Search.

Heterogeneous data captured by different scanning devices and imaging protocols can affect the generalization performance of the deep learning magnetic resonance (MR) reconstruction model. While a centralized training model is effective in mitigating this problem, it raises concerns about privacy protection. Federated learning is a distributed training paradigm that can utilize multi-institutional data for collaborative training without sharing data. However, existing federated learning MR image reconstruction methods rely on models designed manually by experts, which are complex and computationally expensive, suffering from performance degradation when facing heterogeneous data distributions. In addition, these methods give inadequate consideration to fairness issues, namely ensuring that the model's training does not introduce bias towards any specific dataset's distribution. To this end, this paper proposes a generalizable federated neural architecture search framework for accelerating MR imaging (GAutoMRI). Specifically, automatic neural architecture search is investigated for effective and efficient neural network representation learning of MR images from different centers. Furthermore, we design a fairness adjustment approach that can enable the model to learn features fairly from inconsistent distributions of different devices and centers, and thus facilitate the model to generalize well to the unseen center. Extensive experiments show that our proposed GAutoMRI has better performances and generalization ability compared with seven state-of-the-art federated learning methods. Moreover, the GAutoMRI model is significantly more lightweight, making it an efficient choice for MR image reconstruction tasks. The code will be made available at https://github.com/ternencewu123/GAutoMRI.

Accurate Whole-Brain Image Enhancement for Low-Dose Integrated PET/MR Imaging Through Spatial Brain Transformation.

Positron emission tomography/magnetic resonance imaging (PET/MRI) systems can provide precise anatomical and functional information with exceptional sensitivity and accuracy for neurological disorder detection. Nevertheless, the radiation exposure risks and economic costs of radiopharmaceuticals may pose significant burdens on patients. To mitigate image quality degradation during low-dose PET imaging, we proposed a novel 3D network equipped with a spatial brain transform (SBF) module for low-dose whole-brain PET and MR images to synthesize high-quality PET images. The FreeSurfer toolkit was applied to derive the spatial brain anatomical alignment information, which was then fused with low-dose PET and MR features through the SBF module. Moreover, several deep learning methods were employed as comparison measures to evaluate the model performance, with the peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and Pearson correlation coefficient (PCC) serving as quantitative metrics. Both the visual results and quantitative results illustrated the effectiveness of our approach. The obtained PSNR and SSIM were 41.96 ±4.91 dB (p<0.01) and 0.9654 ±0.0215 (p<0.01), which achieved a 19% and 20% improvement, respectively, compared to the original low-dose brain PET images. The volume of interest (VOI) analysis of brain regions such as the left thalamus (PCC = 0.959) also showed that the proposed method could achieve a more accurate standardized uptake value (SUV) distribution while preserving the details of brain structures. In future works, we hope to apply our method to other multimodal systems, such as PET/CT, to assist clinical brain disease diagnosis and treatment.

MMCA-NET: A Multimodal Cross Attention Transformer Network for Nasopharyngeal Carcinoma Tumor Segmentation Based on a Total-Body PET/CT System.

Nasopharyngeal carcinoma (NPC) is a malignant tumor primarily treated by radiotherapy. Accurate delineation of the target tumor is essential for improving the effectiveness of radiotherapy. However, the segmentation performance of current models is unsatisfactory due to poor boundaries, large-scale tumor volume variation, and the labor-intensive nature of manual delineation for radiotherapy. In this paper, MMCA-Net, a novel segmentation network for NPC using PET/CT images that incorporates an innovative multimodal cross attention transformer (MCA-Transformer) and a modified U-Net architecture, is introduced to enhance modal fusion by leveraging cross-attention mechanisms between CT and PET data. Our method, tested against ten algorithms via fivefold cross-validation on samples from Sun Yat-sen University Cancer Center and the public HECKTOR dataset, consistently topped all four evaluation metrics with average Dice similarity coefficients of 0.815 and 0.7944, respectively. Furthermore, ablation experiments were conducted to demonstrate the superiority of our method over multiple baseline and variant techniques. The proposed method has promising potential for application in other tasks.

Knowledge-driven deep learning for fast MR imaging: Undersampled MR image reconstruction from supervised to un-supervised learning.

Deep learning (DL) has emerged as a leading approach in accelerating MRI. It employs deep neural networks to extract knowledge from available datasets and then applies the trained networks to reconstruct accurate images from limited measurements. Unlike natural image restoration problems, MRI involves physics-based imaging processes, unique data properties, and diverse imaging tasks. This domain knowledge needs to be integrated with data-driven approaches. Our review will introduce the significant challenges faced by such knowledge-driven DL approaches in the context of fast MRI along with several notable solutions, which include learning neural networks and addressing different imaging application scenarios. The traits and trends of these techniques have also been given which have shifted from supervised learning to semi-supervised learning, and finally, to unsupervised learning methods. In addition, MR vendors' choices of DL reconstruction have been provided along with some discussions on open questions and future directions, which are critical for the reliable imaging systems.

B1 inhomogeneity corrected CEST MRI based on direct saturation removed omega plot model at 5T.

PURPOSE: CEST can image macromolecules/compounds via detecting chemical exchange between labile protons and bulk water. B1 field inhomogeneity impairs CEST quantification. Conventional B1 inhomogeneity correction methods depend on interpolation algorithms, B1 choices, acquisition number or calibration curves, making reliable correction challenging. This study proposed a novel B1 inhomogeneity correction method based on a direct saturation (DS) removed omega plot model. METHODS: Four healthy volunteers underwent B1 field mapping and CEST imaging under four nominal B1 levels of 0.75, 1.0, 1.5, and 2.0 µT at 5T. DS was resolved using a multi-pool Lorentzian model and removed from respective Z spectrum. Residual spectral signals were used to construct the omega plot as a linear function of 1/ B 1 2 $$ {B}_1^2 $$ , from which corrected signals at nominal B1 levels were calculated. Routine asymmetry analysis was conducted to quantify amide proton transfer (APT) effect. Its distribution across white matter was compared before and after B1 inhomogeneity correction and also with the conventional interpolation approach. RESULTS: B1 inhomogeneity yielded conspicuous artifact on APT images. Such artifact was mitigated by the proposed method. Homogeneous APT maps were shown with SD consistently smaller than that before B1 inhomogeneity correction and the interpolation method. Moreover, B1 inhomogeneity correction from two and four CEST acquisitions yielded similar results, superior over the interpolation method that derived inconsistent APT contrasts among different B1 choices. CONCLUSION: The proposed method enables reliable B1 inhomogeneity correction from at least two CEST acquisitions, providing an effective way to improve quantitative CEST MRI.

Acoustothermal transfection for cell therapy.

Transfected stem cells and T cells are promising in personalized cell therapy and immunotherapy against various diseases. However, existing transfection techniques face a fundamental trade-off between transfection efficiency and cell viability; achieving both simultaneously remains a substantial challenge. This study presents an acoustothermal transfection method that leverages acoustic and thermal effects on cells to enhance the permeability of both the cell membrane and nuclear envelope to achieve safe, efficient, and high-throughput transfection of primary T cells and stem cells. With this method, two types of plasmids were simultaneously delivered into the nuclei of mesenchymal stem cells (MSCs) with efficiencies of 89.6 ± 1.2%. CXCR4-transfected MSCs could efficiently target cerebral ischemia sites in vivo and reduce the infarct volume in mice. Our acoustothermal transfection method addresses a key bottleneck in balancing the transfection efficiency and cell viability, which can become a powerful tool in the future for cellular and gene therapies.

Nanoscale contrast agents: A promising tool for ultrasound imaging and therapy.

Nanoscale contrast agents have emerged as a versatile platform in the field of biomedical research, offering great potential for ultrasound imaging and therapy. Various kinds of nanoscale contrast agents have been extensively investigated in preclinical experiments to satisfy diverse biomedical applications. This paper provides a comprehensive review of the structure and composition of various nanoscale contrast agents, as well as their preparation and functionalization, encompassing both chemosynthetic and biosynthetic strategies. Subsequently, we delve into recent advances in the utilization of nanoscale contrast agents in various biomedical applications, including ultrasound molecular imaging, ultrasound-mediated drug delivery, and cell acoustic manipulation. Finally, the challenges and prospects of nanoscale contrast agents are also discussed to promote the development of this innovative nanoplatform in the field of biomedicine.

Non-Invasive Quantification of the Brain [¹8F]FDG-PET Using Inferred Blood Input Function Learned From Total-Body Data With Physical Constraint.

Full quantification of brain PET requires the blood input function (IF), which is traditionally achieved through an invasive and time-consuming arterial catheter procedure, making it unfeasible for clinical routine. This study presents a deep learning based method to estimate the input function (DLIF) for a dynamic brain FDG scan. A long short-term memory combined with a fully connected network was used. The dataset for training was generated from 85 total-body dynamic scans obtained on a uEXPLORER scanner. Time-activity curves from 8 brain regions and the carotid served as the input of the model, and labelled IF was generated from the ascending aorta defined on CT image. We emphasize the goodness-of-fitting of kinetic modeling as an additional physical loss to reduce the bias and the need for large training samples. DLIF was evaluated together with existing methods in terms of RMSE, area under the curve, regional and parametric image quantifications. The results revealed that the proposed model can generate IFs that closer to the reference ones in terms of shape and amplitude compared with the IFs generated using existing methods. All regional kinetic parameters calculated using DLIF agreed with reference values, with the correlation coefficient being 0.961 (0.913) and relative bias being 1.68±8.74% (0.37±4.93%) for [Formula: see text] ( [Formula: see text]. In terms of the visual appearance and quantification, parametric images were also highly identical to the reference images. In conclusion, our experiments indicate that a trained model can infer an image-derived IF from dynamic brain PET data, which enables subsequent reliable kinetic modeling.

Application of Spinal Subtraction and Bone Background Fusion CTA in the Accurate Diagnosis and Evaluation of Spinal Vascular Malformations.

BACKGROUND AND PURPOSE: Accurate pretreatment diagnosis and assessment of spinal vascular malformations using spinal CTA are crucial for patient prognosis, but the postprocessing reconstruction may not be able to fully depict the lesions due to the complexity inherent in spinal anatomy. Our purpose was to explore the application value of the spinal subtraction and bone background fusion CTA (SSBBF-CTA) technique in precisely depicting and localizing spinal vascular malformation lesions. MATERIALS AND METHODS: In this retrospective study, patients (between November 2017 and November 2022) with symptoms similar to those of spinal vascular malformations were divided into diseased (group A) and nondiseased (group B) groups. All patients underwent spinal CTA using Siemens dual-source CT. Multiplanar reconstruction; routine bone subtraction, and SSBBF-CTA images were obtained using the snygo.via and ADW4.6 postprocessing reconstruction workstations. Multiple observers researched the following 3 aspects: 1) preliminary screening capability using original images with multiplanar reconstruction CTA, 2) the accuracy and stability of the SSBBF-CTA postprocessing technique, and 3) diagnostic evaluation of spinal vascular malformations using the 3 types of postprocessing images. Diagnostic performance was analyzed using receiver operating characteristic analysis, while reader or image differences were analyzed using the Wilcoxon signed-rank test or the Kruskal-Wallis rank sum test. RESULTS: Forty-nine patients (groups A and B: 22 and 27 patients; mean ages, 44.0 [SD, 14.3] years and 44.6 [SD,15.2] years; 13 and 16 men) were evaluated. Junior physicians showed lower diagnostic accuracy and sensitivity using multiplanar reconstruction CTA (85.7% and 77.3%) than senior physicians (93.9% and 90.9%, 98% and 95.5%). Short-term trained juniors achieved SSBBF-CTA image accuracy similar to that of experienced physicians (P > .05). In terms of the visualization and localization of spinal vascular malformation lesions (nidus/fistula, feeding artery, and drainage vein), both multiplanar reconstruction and SSBBF-CTA outperformed routine bone subtraction CTA (P = .000). Compared with multiplanar reconstruction, SSBBF-CTA allowed less experienced physicians to achieve superior diagnostic capabilities (comparable with those of experienced radiologists) more rapidly (P < .05). CONCLUSIONS: The SSBBF-CTA technique exhibited excellent reproducibility and enabled accurate pretreatment diagnosis and assessment of spinal vascular malformations with high diagnostic efficiency, particularly for junior radiologists.

Learning CT-free attenuation-corrected total-body PET images through deep learning.

OBJECTIVES: Total-body PET/CT scanners with long axial fields of view have enabled unprecedented image quality and quantitative accuracy. However, the ionizing radiation from CT is a major issue in PET imaging, which is more evident with reduced radiopharmaceutical doses in total-body PET/CT. Therefore, we attempted to generate CT-free attenuation-corrected (CTF-AC) total-body PET images through deep learning. METHODS: Based on total-body PET data from 122 subjects (29 females and 93 males), a well-established cycle-consistent generative adversarial network (Cycle-GAN) was employed to generate CTF-AC total-body PET images directly while introducing site structures as prior information. Statistical analyses, including Pearson correlation coefficient (PCC) and t-tests, were utilized for the correlation measurements. RESULTS: The generated CTF-AC total-body PET images closely resembled real AC PET images, showing reduced noise and good contrast in different tissue structures. The obtained peak signal-to-noise ratio and structural similarity index measure values were 36.92 ± 5.49 dB (p < 0.01) and 0.980 ± 0.041 (p < 0.01), respectively. Furthermore, the standardized uptake value (SUV) distribution was consistent with that of real AC PET images. CONCLUSION: Our approach could directly generate CTF-AC total-body PET images, greatly reducing the radiation risk to patients from redundant anatomical examinations. Moreover, the model was validated based on a multidose-level NAC-AC PET dataset, demonstrating the potential of our method for low-dose PET attenuation correction. In future work, we will attempt to validate the proposed method with total-body PET/CT systems in more clinical practices. CLINICAL RELEVANCE STATEMENT: The ionizing radiation from CT is a major issue in PET imaging, which is more evident with reduced radiopharmaceutical doses in total-body PET/CT. Our CT-free PET attenuation correction method would be beneficial for a wide range of patient populations, especially for pediatric examinations and patients who need multiple scans or who require long-term follow-up. KEY POINTS: • CT is the main source of radiation in PET/CT imaging, especially for total-body PET/CT devices, and reduced radiopharmaceutical doses make the radiation burden from CT more obvious. • The CT-free PET attenuation correction method would be beneficial for patients who need multiple scans or long-term follow-up by reducing additional radiation from redundant anatomical examinations. • The proposed method could directly generate CT-free attenuation-corrected (CTF-AC) total-body PET images, which is beneficial for PET/MRI or PET-only devices lacking CT image poses.

Dynamic X-ray imaging with screen-printed perovskite CMOS array.

High performance X-ray detector with ultra-high spatial and temporal resolution are crucial for biomedical imaging. This study reports a dynamic direct-conversion CMOS X-ray detector assembled with screen-printed CsPbBr3, whose mobility-lifetime product is 5.2 × 10-4 cm2 V-1 and X-ray sensitivity is 1.6 × 104 µC Gyair-1 cm-2. Samples larger than 5 cm[Formula: see text]10 cm can be rapidly imaged by scanning this detector at a speed of 300 frames per second along the vertical and horizontal directions. In comparison to traditional indirect-conversion CMOS X-ray detector, this perovskite CMOS detector offers high spatial resolution (5.0 lp mm-1) X-ray radiographic imaging capability at low radiation dose (260 nGy). Moreover, 3D tomographic images of a biological specimen are also successfully reconstructed. These results highlight the perovskite CMOS detector's potential in high-resolution, large-area, low-dose dynamic biomedical X-ray and CT imaging, as well as in non-destructive X-ray testing and security scanning.

Ability of dynamic gadoxetic acid-enhanced magnetic resonance imaging combined with water-specific T1 mapping to reflect inflammation in a rat model of early-stage nonalcoholic steatohepatitis.

Background: Gadolinium ethoxybenzyl-diethylenetriaminepentaacetic acid (Gd-EOB-DTPA) has shown potential in reflecting the hepatic function alterations in nonalcoholic steatohepatitis (NASH). The purpose of this study was to evaluate whether Gd-EOB-DTPA combined with water-specific T1 (wT1) mapping can be used to detect liver inflammation in the early-stage of NASH in rats. Methods: In this study, 54 rats with methionine- and choline-deficient (MCD) diet-induced NASH and 10 normal control rats were examined. A multiecho variable flip angle gradient echo (VFA-GRE) sequence was performed and repeated 40 times after the injection of Gd-EOB-DTPA. The wT1 of the liver and the reduction rate of wT1 (rrT1) were calculated. All rats were histologically evaluated and grouped according to the NASH Clinical Research Network scoring system. Quantitative real-time polymerase chain reaction (qRT-PCR) was performed to detect the expression of Gd-EOB-DTPA transport genes. Analysis of variance and least significant difference tests were used for multiple comparisons of quantitative results between all groups. Multiple regression analysis was applied to identify variables associated with precontrast wT1 (wT1pre), and receiver operating characteristic (ROC) analysis was performed to assess the diagnostic performance. Results: The rats were grouped according to inflammatory stage (G0 =4, G1 =15, G2 =12, G3 =23) and fibrosis stage (F0 =26, F1 =19, F2 =9). After the infusion of Gd-EOB-DTPA, the rrT1 showed significant differences between the control and NASH groups (P<0.05) but no difference between the different inflammation and fibrosis groups at any time points. The areas under curve (AUCs) of rrT1 at 10, 20, and 30 minutes were only 0.53, 0.58, and 0.61, respectively, for differentiating between low inflammation grade (G0 + G1) and high inflammation grade (G2 + G3). The MRI findings were verified by qRT-PCR examination, in which the Gd-EOB-DTPA transporter expressions showed no significant differences between any inflammation groups. Conclusions: The wT1 mapping quantitative method combined with Gd-EOB-DTPA was not capable of discerning the inflammation grade in a rat model of early-stage NASH.

A novel automatic segmentation method directly based on magnetic resonance imaging K-space data for auxiliary diagnosis of glioma.

Background: The use of segmentation architectures in medical imaging, particularly for glioma diagnosis, marks a significant advancement in the field. Traditional methods often rely on post-processed images; however, key details can be lost during the fast Fourier transformation (FFT) process. Given the limitations of these techniques, there is a growing interest in exploring more direct approaches. The adaption of segmentation architectures originally designed for road extraction for medical imaging represents an innovative step in this direction. By employing K-space data as the modal input, this method completely eliminates the information loss inherent in FFT, thereby potentially enhancing the precision and effectiveness of glioma diagnosis. Methods: In the study, a novel architecture based on a deep-residual U-net was developed to accomplish the challenging task of automatically segmenting brain tumors from K-space data. Brain tumors from K-space data with different under-sampling rates were also segmented to verify the clinical application of our method. Results: Compared to the benchmarks set in the 2018 Brain Tumor Segmentation (BraTS) Challenge, our proposed architecture had superior performance, achieving Dice scores of 0.8573, 0.8789, and 0.7765 for the whole tumor (WT), tumor core (TC), and enhanced tumor (ET) regions, respectively. The corresponding Hausdorff distances were 2.5649, 1.6146, and 2.7187 for the WT, TC, and ET regions, respectively. Notably, compared to traditional image-based approaches, the architecture also exhibited an improvement of approximately 10% in segmentation accuracy on the K-space data at different under-sampling rates. Conclusions: These results show the superiority of our method compared to previous methods. The direct performance of lesion segmentation based on K-space data eliminates the time-consuming and tedious image reconstruction process, thus enabling the segmentation task to be accomplished more efficiently.

Skin-Conformable Flexible and Stretchable Ultrasound Transducer for Wearable Imaging.

Ultrasound imaging offers a noninvasive, radiation-free method for visualizing internal tissues and organs, with deep penetration capabilities. This has established it as a crucial tool for physicians in diagnosing internal tissue pathologies and monitoring human conditions. Nonetheless, conventional ultrasound probes are often characterized by their rigidity and bulkiness. Designing a transducer that can seamlessly adapt to the contours and dynamics of soft, curved human skin presents significant technical hurdles. We present a novel flexible and stretchable ultrasound transducer (FSUT) designed for adaptability to large-curvature surfaces while preserving superior imaging quality. Central to this breakthrough is the innovative use of screen-printed silver nanowires (AgNWs) coupled with a composite elastic substrate, together ensuring robust and stable electrical and mechanical connections. Standard tensile and fatigue tests verify its durability. The mechanical, electrical, and acoustic properties of FSUTs are characterized using standard methods, with large tensile strains (≥110%), high flexibility ( R ≥ 1.4 mm), and lightweight ( ≤ 1.58 g) to meet the needs of wearable devices. Center frequency and -6-dB bandwidth are approximately 5.3 MHz and 66.47%, respectively. Images of the commercial anechoic cyst phantom yielded an axial and lateral resolution (depths of 10-70 mm) of approximately 0.31 and 0.46, and 0.34 and 0.84 mm, respectively. The complex curved surface imaging capabilities of FSUT were tested on agar-gelatin-based breast cyst phantoms under different curvatures. Finally, ultrasound images of the thyroid, brachial, and carotid arteries were also obtained from volunteer wearing FSUT.

Evaluation of tumor microvasculature with 3D ultrasound localization microscopy based on 2D matrix array.

OBJECTIVE: Evaluation of tumor microvascular morphology is of great significance in tumor diagnosis, therapeutic effect prediction, and surgical planning. Recently, two-dimensional ultrasound localization microscopy (2DULM) has demonstrated its superiority in the field of microvascular imaging. However, it suffers from planar dependence and is unintuitive. We propose a novel three-dimensional ultrasound localization microscopy (3DULM) to avoid these limitations. METHODS: We investigated 3DULM based on a 2D array for tumor microvascular imaging. After intravenous injection of contrast agents, all elements of the 2D array transmit and receive signals to ensure a high and stable frame rate. Microbubble signal extraction, filtering, positioning, tracking, and other processing were used to obtain a 3D vascular map, flow velocity, and flow direction. To verify the effectiveness of 3DULM, it was validated on double helix tubes and rabbit VX2 tumors. Cisplatin was used to verify the ability of 3DULM to detect microvascular changes during tumor treatment. RESULTS: In vitro, the sizes measured by 3DULM at 3 mm and 13 mm were 178 µ m and 182 µ m , respectively. In the rabbit tumors, we acquired 9000 volumes to reveal vessels about 30 µ m in diameter, which surpasses the diffraction limit of ultrasound in traditional ultrasound imaging, and the results matched with micro-angiography. In addition, there were significant changes in vascular density and curvature between the treatment and control groups. CONCLUSIONS: The effectiveness of 3DULM was verified in vitro and in vivo. Hence, 3DULM may have potential applications in tumor diagnosis, tumor treatment evaluation, surgical protocol guidance, and cardiovascular disease. CLINICAL RELEVANCE STATEMENT: 3D ultrasound localization microscopy is highly sensitive to microvascular changes; thus, it has clinical potential for tumor diagnosis and treatment evaluation. KEY POINTS: • 3D ultrasound localization microscopy is demonstrated on double helix tubes and rabbit VX2 tumors. • 3D ultrasound localization microscopy can reveal vessels about 30 µ m in diameter-far smaller than traditional ultrasound. • This form of imaging has potential applications in tumor diagnosis, tumor treatment evaluation, surgical protocol guidance, and cardiovascular disease.

Transferring U-Net between low-dose CT denoising tasks: a validation study with varied spatial resolutions.

Background: Recently, deep learning techniques have been widely used in low-dose computed tomography (LDCT) imaging applications for quickly generating high quality computed tomography (CT) images at lower radiation dose levels. The purpose of this study is to validate the reproducibility of the denoising performance of a given network that has been trained in advance across varied LDCT image datasets that are acquired from different imaging systems with different spatial resolutions. Methods: Specifically, LDCT images with comparable noise levels but having different spatial resolutions were prepared to train the U-Net. The number of CT images used for the network training, validation and test was 2,400, 300 and 300, respectively. Afterwards, self- and cross-validations among six selected spatial resolutions (62.5, 125, 250, 375, 500, 625 µm) were studied and compared side by side. The residual variance, peak signal to noise ratio (PSNR), normalized root mean square error (NRMSE) and structural similarity (SSIM) were measured and compared. In addition, network retraining on a small number of image set was performed to fine tune the performance of transfer learning among LDCT tasks with varied spatial resolutions. Results: Results demonstrated that the U-Net trained upon LDCT images having a certain spatial resolution can effectively reduce the noise of the other LDCT images having different spatial resolutions. Regardless, results showed that image artifacts would be generated during the above cross validations. For instance, noticeable residual artifacts were presented at the margin and central areas of the object as the resolution inconsistency increased. The retraining results showed that the artifacts caused by the resolution mismatch can be greatly reduced by utilizing about only 20% of the original training data size. This quantitative improvement led to a reduction in the NRMSE from 0.1898 to 0.1263 and an increase in the SSIM from 0.7558 to 0.8036. Conclusions: In conclusion, artifacts would be generated when transferring the U-Net to a LDCT denoising task with different spatial resolution. To maintain the denoising performance, it is recommended to retrain the U-Net with a small amount of datasets having the same target spatial resolution.

Reducing pediatric total-body PET/CT imaging scan time with multimodal artificial intelligence technology.

OBJECTIVES: This study aims to decrease the scan time and enhance image quality in pediatric total-body PET imaging by utilizing multimodal artificial intelligence techniques. METHODS: A total of 270 pediatric patients who underwent total-body PET/CT scans with a uEXPLORER at the Sun Yat-sen University Cancer Center were retrospectively enrolled. 18F-fluorodeoxyglucose (18F-FDG) was administered at a dose of 3.7 MBq/kg with an acquisition time of 600 s. Short-term scan PET images (acquired within 6, 15, 30, 60 and 150 s) were obtained by truncating the list-mode data. A three-dimensional (3D) neural network was developed with a residual network as the basic structure, fusing low-dose CT images as prior information, which were fed to the network at different scales. The short-term PET images and low-dose CT images were processed by the multimodal 3D network to generate full-length, high-dose PET images. The nonlocal means method and the same 3D network without the fused CT information were used as reference methods. The performance of the network model was evaluated by quantitative and qualitative analyses. RESULTS: Multimodal artificial intelligence techniques can significantly improve PET image quality. When fused with prior CT information, the anatomical information of the images was enhanced, and 60 s of scan data produced images of quality comparable to that of the full-time data. CONCLUSION: Multimodal artificial intelligence techniques can effectively improve the quality of pediatric total-body PET/CT images acquired using ultrashort scan times. This has the potential to decrease the use of sedation, enhance guardian confidence, and reduce the probability of motion artifacts.

The role of dynamic, static, and delayed total-body PET imaging in the detection and differential diagnosis of oncological lesions.

OBJECTIVES: Commercialized total-body PET scanners can provide high-quality images due to its ultra-high sensitivity. We compared the dynamic, regular static, and delayed 18F-fluorodeoxyglucose (FDG) scans to detect lesions in oncologic patients on a total-body PET/CT scanner. MATERIALS & METHODS: In all, 45 patients were scanned continuously for the first 60 min, followed by a delayed acquisition. FDG metabolic rate was calculated from dynamic data using full compartmental modeling, whereas regular static and delayed SUV images were obtained approximately 60- and 145-min post-injection, respectively. The retention index was computed from static and delayed measures for all lesions. Pearson's correlation and Kruskal-Wallis tests were used to compare parameters. RESULTS: The number of lesions was largely identical between the three protocols, except MRFDG and delayed images on total-body PET only detected 4 and 2 more lesions, respectively (85 total). FDG metabolic rate (MRFDG) image-derived contrast-to-noise ratio and target-to-background ratio were significantly higher than those from static standardized uptake value (SUV) images (P < 0.01), but this is not the case for the delayed images (P > 0.05). Dynamic protocol did not significantly differentiate between benign and malignant lesions just like regular SUV, delayed SUV, and retention index. CONCLUSION: The potential quantitative advantages of dynamic imaging may not improve lesion detection and differential diagnosis significantly on a total-body PET/CT scanner. The same conclusion applied to delayed imaging. This suggested the added benefits of complex imaging protocols must be weighed against the complex implementation in the future. CLINICAL RELEVANCE: Total-body PET/CT was known to significantly improve the PET image quality due to its ultra-high sensitivity. However, whether the dynamic and delay imaging on total-body scanner could show additional clinical benefits is largely unknown. Head-to-head comparison between two protocols is relevant to oncological management.