Three-Dimensional Customized Imaging Reconstruction for Urological Surgery: Diffusion and Role in Real-Life Practice from an International Survey.

Despite the arising interest in three-dimensional (3D) reconstruction models from 2D imaging, their diffusion and perception among urologists have been scarcely explored. The aim of the study is to report the results of an international survey investigating the use of such tools among urologists of different backgrounds and origins. Beyond demographics, the survey explored the degree to which 3D models are perceived to improve surgical outcomes, the procedures mostly making use of them, the settings in which those tools are mostly applied, the surgical steps benefiting from 3D reconstructions and future perspectives of improvement. One hundred responders fully completed the survey. All levels of expertise were allowed; more than half (53%) were first surgeons, and 59% had already completed their training. Their main application was partial nephrectomy (85%), followed by radical nephrectomy and radical prostatectomy. Three-dimensional models are mostly used for preoperative planning (75%), intraoperative consultation and tailoring. More than half recognized that 3D models may highly improve surgical outcomes. Despite their recognized usefulness, 77% of responders use 3D models in less than 25% of their major operations due to costs or the extra time taken to perform the reconstruction. Technical improvements and a higher availability of the 3D models will further increase their role in surgical and clinical daily practice.

3D print model for surgical planning in a case of recurrent osteoblastic osteosarcoma of the left maxilla. A case report.

Osteosarcoma (OS) of the head and neck is a rare and aggressive disease characterized by the formation of osteoid by malignant osteoblasts. The mandible or maxilla are the most common sites of presentation. Radiologically, these tumors show considerable, destructive growth with periosteal reaction, which can suggest the diagnosis of OS. 3D printing, as an emerging technology, can play a role in orthopedic oncology by providing patient-specific 3D printed models to improve surgical planning and facilitate patient understanding. We present the case of a male in his early 30s with a final histological diagnosis of recurrent osteosarcoma of the left maxilla, where a 3D printed model was helpful for the diagnostic workup, surgical planning, and the procedure.

Deep learning imaging reconstruction of reduced-dose 40 keV virtual monoenergetic imaging for early detection of colorectal cancer liver metastases.

OBJECTIVE: To explore whether reduced-dose (RD) gemstone spectral imaging (GSI) and deep learning image reconstruction (DLIR) of 40 keV virtual monoenergetic image (VMI) enhanced the early detection and diagnosis of colorectal cancer liver metastases (CRLM). METHODS: Thirty-five participants with pathologically confirmed colorectal cancer were prospectively enrolled from March to August 2022 after routine care abdominal computed tomography (CT). GSI mode was used for contrast-enhanced CT, and two portal venous phase CT images were obtained [standard-dose (SD) CT dose index (CTDIvol) = 15.51 mGy, RD CTDIvol = 7.95 mGy]. The 40 keV-VMI were reconstructed via filtered back projection (FBP) and iterative reconstruction (ASIR-V 60 %, AV60) of both SD and RD images. RD medium-strength deep learning image reconstruction (DLIR-M) and RD high-strength deep learning image reconstruction (DLIR-H) were used to reconstruct the 40 keV-VMI. The contrast-to-noise ratio (CNR) and signal-to-noise ratio (SNR) of the liver and the lesions were objectively evaluated. The overall image quality, lesion conspicuity, and diagnostic confidence were subjectively evaluated, to compare the differences in evaluation results among the different images. RESULTS: All 35 participants (mean age: 59.51 ± 11.01 years; 14 females) underwent SD and RD GSI portal venous-phase CT scans. The dose-length product of the RD GSI scan was reduced by 49-53 % lower than that of the SD GSI scan (420.22 ± 31.95) vs (817.58 ± 60.56). A total of 219 lesions were identified, including 55 benign lesions and 164 metastases, with an average size of 7.37 ± 4.14 mm. SD-FBP detected 207 lesions, SD-AV60 detected 201 lesions, and DLIR-M and DLIR-H detected 199 and 190 lesions, respectively. For lesions ≤ 5 mm, there was no statistical difference between SD-FBP vs DLIR-M (χ2McNemar = 1.00, P = 0.32) and SD-AV60 vs DLIR-M (χ2McNemar = 0.33, P = 0.56) in the detection rate. The CNR, SNR, and noise of DLIR-M and DLIR-H 40 keV-VMI images were better than those of SD-FBP images (P < 0.01) but did not differ significantly from those of SD-AV60 images (P > 0.05). When the lesions ≤ 5 mm, there were statistical differences in the overall diagnostic sensitivity of lesions compared with SD-FBP, SD-AV60, DLIR-M and DLIR-H (P＜0.01). There were no statistical differences in the sensitivity of lesions diagnosis between SD-FBP, SD-AV60 and DLIR-M (both P＞0.05). However, the DLIR-M subjective image quality and lesion diagnostic confidence were higher for SD-FBP (both P < 0.01). CONCLUSION: Reduced dose DLIR-M of 40 keV-VMI can be used for routine follow-up care of colorectal cancer patients, to optimize evaluations and ensure CT image quality. Meanwhile, the detection rate and diagnostic sensitivity and specificity of small lesions, early liver metastases is not obviously reduced.

Compressed Imaging Reconstruction Based on Block Compressed Sensing with Conjugate Gradient Smoothed l0 Norm.

Compressed imaging reconstruction technology can reconstruct high-resolution images with a small number of observations by applying the theory of block compressed sensing to traditional optical imaging systems, and the reconstruction algorithm mainly determines its reconstruction accuracy. In this work, we design a reconstruction algorithm based on block compressed sensing with a conjugate gradient smoothed l0 norm termed BCS-CGSL0. The algorithm is divided into two parts. The first part, CGSL0, optimizes the SL0 algorithm by constructing a new inverse triangular fraction function to approximate the l0 norm and uses the modified conjugate gradient method to solve the optimization problem. The second part combines the BCS-SPL method under the framework of block compressed sensing to remove the block effect. Research shows that the algorithm can reduce the block effect while improving the accuracy and efficiency of reconstruction. Simulation results also verify that the BCS-CGSL0 algorithm has significant advantages in reconstruction accuracy and efficiency.

Computational Integral Imaging Reconstruction via Elemental Image Blending without Normalization.

This paper presents a novel computational integral imaging reconstruction (CIIR) method using elemental image blending to eliminate the normalization process in CIIR. Normalization is commonly used in CIIR to address uneven overlapping artifacts. By incorporating elemental image blending, we remove the normalization step in CIIR, leading to decreased memory consumption and computational time compared to those of existing techniques. We conducted a theoretical analysis of the impact of elemental image blending on a CIIR method using windowing techniques, and the results showed that the proposed method is superior to the standard CIIR method in terms of image quality. We also performed computer simulations and optical experiments to evaluate the proposed method. The experimental results showed that the proposed method enhances the image quality over that of the standard CIIR method, while also reducing memory usage and processing time.

Numerical and Clinical Evaluation of the Robustness of Open-source Networks for Parallel MR Imaging Reconstruction.

PURPOSE: Deep neural networks (DNNs) for MRI reconstruction often require large datasets for training. Still, in clinical settings, the domains of datasets are diverse, and how robust DNNs are to domain differences between training and testing datasets has been an open question. Here, we numerically and clinically evaluate the generalization of the reconstruction networks across various domains under clinically practical conditions and provide practical guidance on what points to consider when selecting models for clinical application. METHODS: We compare the reconstruction performance between four network models: U-Net, the deep cascade of convolutional neural networks (DC-CNNs), Hybrid Cascade, and variational network (VarNet). We used the public multicoil dataset fastMRI for training and testing and performed a single-domain test, where the domains of the dataset used for training and testing were the same, and cross-domain tests, where the source and target domains were different. We conducted a single-domain test (Experiment 1) and cross-domain tests (Experiments 2-4), focusing on six factors (the number of images, sampling pattern, acceleration factor, noise level, contrast, and anatomical structure) both numerically and clinically. RESULTS: U-Net had lower performance than the three model-based networks and was less robust to domain shifts between training and testing datasets. VarNet had the highest performance and robustness among the three model-based networks, followed by Hybrid Cascade and DC-CNN. Especially, VarNet showed high performance even with a limited number of training images (200 images/10 cases). U-Net was more robust to domain shifts concerning noise level than the other model-based networks. Hybrid Cascade showed slightly better performance and robustness than DC-CNN, except for robustness to noise-level domain shifts. The results of the clinical evaluations generally agreed with the results of the quantitative metrics. CONCLUSION: In this study, we numerically and clinically evaluated the robustness of the publicly available networks using the multicoil data. Therefore, this study provided practical guidance for clinical applications.

Linear fine-tuning: a linear transformation based transfer strategy for deep MRI reconstruction.

Introduction: Fine-tuning (FT) is a generally adopted transfer learning method for deep learning-based magnetic resonance imaging (MRI) reconstruction. In this approach, the reconstruction model is initialized with pre-trained weights derived from a source domain with ample data and subsequently updated with limited data from the target domain. However, the direct full-weight update strategy can pose the risk of "catastrophic forgetting" and overfitting, hindering its effectiveness. The goal of this study is to develop a zero-weight update transfer strategy to preserve pre-trained generic knowledge and reduce overfitting. Methods: Based on the commonality between the source and target domains, we assume a linear transformation relationship of the optimal model weights from the source domain to the target domain. Accordingly, we propose a novel transfer strategy, linear fine-tuning (LFT), which introduces scaling and shifting (SS) factors into the pre-trained model. In contrast to FT, LFT only updates SS factors in the transfer phase, while the pre-trained weights remain fixed. Results: To evaluate the proposed LFT, we designed three different transfer scenarios and conducted a comparative analysis of FT, LFT, and other methods at various sampling rates and data volumes. In the transfer scenario between different contrasts, LFT outperforms typical transfer strategies at various sampling rates and considerably reduces artifacts on reconstructed images. In transfer scenarios between different slice directions or anatomical structures, LFT surpasses the FT method, particularly when the target domain contains a decreasing number of training images, with a maximum improvement of up to 2.06 dB (5.89%) in peak signal-to-noise ratio. Discussion: The LFT strategy shows great potential to address the issues of "catastrophic forgetting" and overfitting in transfer scenarios for MRI reconstruction, while reducing the reliance on the amount of data in the target domain. Linear fine-tuning is expected to shorten the development cycle of reconstruction models for adapting complicated clinical scenarios, thereby enhancing the clinical applicability of deep MRI reconstruction.

Low-rank tensor assisted K-space generative model for parallel imaging reconstruction.

Although recent deep learning methods, especially generative models, have shown good performance in magnetic resonance imaging, there is still much room for improvement. Considering that the sample number and internal dimension in score-based generative model have key influence on estimating the gradients of data distribution, we present a new idea for parallel imaging reconstruction, named low-rank tensor assisted k-space generative model (LR-KGM). It means that we transform low-rank information into high-dimensional prior information for learning. More specifically, the multi-channel data is constructed into a large Hankel matrix to reduce the number of training samples, which is subsequently collapsed into a tensor for the stage of prior learning. In the testing phase, the low-rank rotation strategy is utilized to impose low-rank constraints on the output tensors of the generative network. Furthermore, we alternate the reconstruction between traditional generative iterations and low-rank high-dimensional tensor iterations. Experimental comparisons with the state-of-the-arts demonstrated that the proposed LR-KGM method achieved better performance.

Ultrasonic imaging through reverberation media.

Thin layered media like thermal barrier and corrosion resistant coating layers, are important components to protect and strengthen the base materials. Nevertheless, the non-destructive testing (NDT) of base materials under thin layer media are still strongly demanded. However, surface and reverberation waves propagating in the top thin layer deteriorate the ultrasonic imaging results of base materials. Particularly, they overwhelm the reflection waves of defects, making ultrasonic NDT of base materials a challenge. These waves are determined by the structural of testing objects and called structural noises. Here, a pre-process of ultrasonic total focusing method is proposed to remove the structural noises. The pre-process utilizes the different similarity characteristics of structural noises and defect signals in diagonal matrices to suppress the noises by principal component analysis. The experimental results show that it can effectively improve the SNR about 5-8 dB and reduce array performance indicators about 30-40%.

Multi-weight respecification of scan-specific learning for parallel imaging.

Parallel imaging is widely used in magnetic resonance imaging as an acceleration technology. Traditional linear reconstruction methods in parallel imaging often suffer from noise amplification. Recently, a non-linear robust artificial-neural-network for k-space interpolation (RAKI) exhibits superior noise resilience over other linear methods. However, RAKI performs poorly at high acceleration rates and needs a large number of autocalibration signals as the training samples. In order to tackle these issues, we propose a multi-weight method that implements multiple weighting matrices on the under-sampled data, named MW-RAKI. Enforcing multiple weighted matrices on the measurements can effectively reduce the influence of noise and increase the data constraints. Furthermore, we incorporate the strategy of multiple weighting matrixes into a residual version of RAKI, and form MW-rRAKI. Experimental comparisons with the alternative methods demonstrated noticeably better reconstruction performances, particularly at high acceleration rates. With only 12.5% of the k-space data is available, the PSNR of MW-RAKI and MW-rRAKI is improved by about 3 dB and 4 dB compared to RAKI and rRAKI, respectively.

A deep neural network for parametric image reconstruction on a large axial field-of-view PET.

PURPOSE: The PET scanners with long axial field of view (AFOV) having ~ 20 times higher sensitivity than conventional scanners provide new opportunities for enhanced parametric imaging but suffer from the dramatically increased volume and complexity of dynamic data. This study reconstructed a high-quality direct Patlak Ki image from five-frame sinograms without input function by a deep learning framework based on DeepPET to explore the potential of artificial intelligence reducing the acquisition time and the dependence of input function in parametric imaging. METHODS: This study was implemented on a large AFOV PET/CT scanner (Biograph Vision Quadra) and twenty patients were recruited with 18F-fluorodeoxyglucose (18F-FDG) dynamic scans. During training and testing of the proposed deep learning framework, the last five-frame (25 min, 40-65 min post-injection) sinograms were set as input and the reconstructed Patlak Ki images by a nested EM algorithm on the vendor were set as ground truth. To evaluate the image quality of predicted Ki images, mean square error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) were calculated. Meanwhile, a linear regression process was applied between predicted and true Ki means on avid malignant lesions and tumor volume of interests (VOIs). RESULTS: In the testing phase, the proposed method achieved excellent MSE of less than 0.03%, high SSIM, and PSNR of ~ 0.98 and ~ 38 dB, respectively. Moreover, there was a high correlation (DeepPET: [Formula: see text]= 0.73, self-attention DeepPET: [Formula: see text]=0.82) between predicted Ki and traditionally reconstructed Patlak Ki means over eleven lesions. CONCLUSIONS: The results show that the deep learning-based method produced high-quality parametric images from small frames of projection data without input function. It has much potential to address the dilemma of the long scan time and dependency on input function that still hamper the clinical translation of dynamic PET.

Self-supervised learning enables 3D digital subtraction angiography reconstruction from ultra-sparse 2D projection views: A multicenter study.

3D digital subtraction angiography (DSA) reconstruction from rotational 2D projection X-ray angiography is an important basis for diagnosis and treatment of intracranial aneurysms (IAs). The gold standard requires approximately 133 different projection views for 3D reconstruction. A method to significantly reduce the radiation dosage while ensuring the reconstruction quality is yet to be developed. We propose a self-supervised learning method to realize 3D-DSA reconstruction using ultra-sparse 2D projections. 202 cases (100 from one hospital for training and testing, 102 from two other hospitals for external validation) suspected to be suffering from IAs were conducted to analyze the reconstructed images. Two radiologists scored the reconstructed images from internal and external datasets using eight projections and identified all 82 lesions with high diagnostic confidence. The radiation dosages are approximately 1/16.7 compared with the gold standard method. Our proposed method can help develop a revolutionary 3D-DSA reconstruction method for use in clinic.

Iterative self-consistent parallel magnetic resonance imaging reconstruction based on nonlocal low-rank regularization.

Iterative self-consistent parallel imaging reconstruction (SPIRiT) is an effective self-calibrated reconstruction model for parallel magnetic resonance imaging (PMRI). The joint L1 norm of wavelet or tight frame coefficients and joint total variation (TV) regularization terms are incorporated into the SPIRiT model to improve the reconstruction performance. The simultaneous two-directional low-rankness (STDLR) in k-space data is incorporated into SPIRiT to realize improved reconstruction. Recent methods have exploited the nonlocal self-similarity (NSS) of images by imposing nonlocal low-rankness of similar patches to achieve a superior performance. To fully utilize both the NSS in Magnetic resonance (MR) images and calibration consistency in the k-space domain, we propose a nonlocal low-rank (NLR)-SPIRiT model by incorporating NLR regularization into the SPIRiT model. We apply the weighted nuclear norm (WNN) as a surrogate of the rank and employ the Nash equilibrium (NE) formulation and alternating direction method of multipliers (ADMM) to efficiently solve the NLR-SPIRiT model. The experimental results demonstrate the superior performance of NLR-SPIRiT over the state-of-the-art methods via three objective metrics and visual comparison.

Sparse reconstruction of magnetic resonance image combined with two-step iteration and adaptive shrinkage factor.

As an advanced technique, compressed sensing has been used for rapid magnetic resonance imaging in recent years, Two-step Iterative Shrinkage Thresholding Algorithm (TwIST) is a popular algorithm based on Iterative Thresholding Shrinkage Algorithm (ISTA) for fast MR image reconstruction. However TwIST algorithms cannot dynamically adjust shrinkage factor according to the degree of convergence. So it is difficult to balance speed and efficiency. In this paper, we proposed an algorithm which can dynamically adjust the shrinkage factor to rebalance the fidelity item and regular item during TwIST iterative process. The shrinkage factor adjusting is judged by the previous reconstructed results throughout the iteration cycle. It can greatly accelerate the iterative convergence while ensuring convergence accuracy. We used MR images with 2 body parts and different sampling rates to simulate, the results proved that the proposed algorithm have a faster convergence rate and better reconstruction performance. We also used 60 MR images of different body parts for further simulation, and the results proved the universal superiority of the proposed algorithm.

Application of Monte Carlo Algorithms to Cardiac Imaging Reconstruction.

Monte Carlo algorithms have a growing impact on nuclear medicine reconstruction processes. One of the main limitations of myocardial perfusion imaging (MPI) is the effective mitigation of the scattering component, which is particularly challenging in Single Photon Emission Computed Tomography (SPECT). In SPECT, no timing information can be retrieved to locate the primary source photons. Monte Carlo methods allow an event-by-event simulation of the scattering kinematics, which can be incorporated into a model of the imaging system response. This approach was adopted in the late Nineties by several authors, and recently took advantage of the increased computational power made available by high-performance CPUs and GPUs. These recent developments enable a fast image reconstruction with improved image quality, compared to deterministic approaches. Deterministic approaches are based on energy-windowing of the detector response, and on the cumulative estimate and subtraction of the scattering component. In this paper, we review the main strategies and algorithms to correct the scattering effect in SPECT and focus on Monte Carlo developments, which nowadays allow the threedimensional reconstruction of SPECT cardiac images in a few seconds.

Review and Prospect: Artificial Intelligence in Advanced Medical Imaging.

Artificial intelligence (AI) as an emerging technology is gaining momentum in medical imaging. Recently, deep learning-based AI techniques have been actively investigated in medical imaging, and its potential applications range from data acquisition and image reconstruction to image analysis and understanding. In this review, we focus on the use of deep learning in image reconstruction for advanced medical imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET). Particularly, recent deep learning-based methods for image reconstruction will be emphasized, in accordance with their methodology designs and performances in handling volumetric imaging data. It is expected that this review can help relevant researchers understand how to adapt AI for medical imaging and which advantages can be achieved with the assistance of AI.

Image Reconstruction with the Fourier Coefficients for Magnetic Induction Tomography.

BACKGROUND: Image reconstruction of magnetic induction tomography (MIT) is a typical ill-posed inverse problem, which means that the measurements are always far from enough. Thus, MIT image reconstruction results using conventional algorithms such as linear back projection and Landweber often suffer from limitations such as low resolution and blurred edges. METHODS: In this paper, based on the recent finite rate of innovation (FRI) framework, a novel image reconstruction method with MIT system is presented. RESULTS: This is achieved through modeling and sampling the MIT signals in FRI framework, resulting in a few new measurements, namely, fourier coefficients. Because each new measurement contains all the pixel position and conductivity information of the dense phase medium, the illposed inverse problem can be improved, by rebuilding the MIT measurement equation with the measurement voltage and the new measurements. Finally, a sparsity-based signal reconstruction algorithm is presented to reconstruct the original MIT image signal, by solving this new measurement equation. CONCLUSION: Experiments show that the proposed method has better indicators such as image error and correlation coefficient. Therefore, it is a kind of MIT image reconstruction method with high accuracy.

An Automated Preprocessing Method for Diffuse Optical Tomography to Improve Breast Cancer Diagnosis.

The ultrasound-guided diffuse optical tomography is a noninvasive imaging technique for breast cancer diagnosis and treatment monitoring. The technique uses a handheld probe capable of providing measurements of multiple wavelengths in a few seconds. These measurements are used to estimate optical absorptions of lesions and calculate the total hemoglobin concentration. Any measurement errors caused by low signal to noise ratio data and/or movements during data acquisition would reduce the accuracy of reconstructed total hemoglobin concentration. In this article, we introduce an automated preprocessing method that combines data collected from multiple sets of lesion measurements of 4 optical wavelengths to detect and correct outliers in the perturbation. Two new measures of correlation between each pair of wavelength measurements and a wavelength consistency index of all reconstructed absorption maps are introduced. For phantom and patients' data without evidence of measurement errors, the correlation coefficient between each pair of wavelength measurements was above 0.6. However, for patients with measurement errors, the correlation coefficient was much lower. After applying the correction method to 18 patients' data with measurement errors, the correlation has improved and the wavelength consistency index is in the same range as the cases without wavelength-dependent measurement errors. The results show an improvement in classification of malignant and benign lesions.

Compact ultrasound-guided diffuse optical tomography system for breast cancer imaging.

Near-infrared diffuse optical tomography (DOT) has demonstrated a great potential as an adjunct modality for differentiation of malignant and benign breast lesions and for monitoring treatment response in patients with locally advanced breast cancers. The path toward commercialization of DOT techniques depends upon the improvement of robustness and user-friendliness of this technique in hardware and software. In this study, we introduce our recently developed ultrasound-guided DOT system, which has been improved in system compactness, robustness, and user-friendliness by custom-designed electronics, automated data preprocessing, and implementation of a new two-step reconstruction algorithm. The system performance has been tested with several sets of solid and blood phantoms and the results show accuracy in reconstructed absorption coefficients as well as blood oxygen saturation. A clinical example of a breast cancer patient, who was undergoing neoadjuvant chemotherapy, is given to demonstrate the system performance.

Step adaptive fast iterative shrinkage thresholding algorithm for compressively sampled MR imaging reconstruction.

In order to accelerate magnetic resonance imaging (MRI) scanning, fast MRI technique based on compressed sensing (CS) was proposed. The shrinkage thresholding algorithm (STA) is an efficient method in related algorithms to decrease the incoherent artifacts produced by the undersampling in k-space directly. The traditional STA uses the fixed iteration step size during the reconstruction progress, and it is not conducive to accelerate the convergence speed. In order to improve global iteration efficiency, in this paper, step adaptive fast iterative shrinkage thresholding algorithm (SAFISTA) was proposed for MRI reconstruction based on STA. It used a feedback to dynamically adjust the iteration step size. The feedback parameter was calculated from the total variations (TV) of two previous iterations. It can effectively improve the efficiency of iteration. Experiments over three kinds of MR images (human head, blood vessels and knee) under different sample ratios indicated that the proposed algorithm SAFISTA showed better reconstruction performance than iterative shrinkage thresholding algorithm (ISTA), fast iterative shrinkage thresholding algorithm (FISTA) and generalized thresholding iterative algorithm (GTIA) in terms of mean square error (MSE), peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM).