Hyperspectral dark-field microscopy of human breast lumpectomy samples for tumor margin detection in breast-conserving surgery.

Significance: Hyperspectral dark-field microscopy (HSDFM) and data cube analysis algorithms demonstrate successful detection and classification of various tissue types, including carcinoma regions in human post-lumpectomy breast tissues excised during breast-conserving surgeries. Aim: We expand the application of HSDFM to the classification of tissue types and tumor subtypes in pre-histopathology human breast lumpectomy samples. Approach: Breast tissues excised during breast-conserving surgeries were imaged by the HSDFM and analyzed. The performance of the HSDFM is evaluated by comparing the backscattering intensity spectra of polystyrene microbead solutions with the Monte Carlo simulation of the experimental data. For classification algorithms, two analysis approaches, a supervised technique based on the spectral angle mapper (SAM) algorithm and an unsupervised technique based on the K-means algorithm are applied to classify various tissue types including carcinoma subtypes. In the supervised technique, the SAM algorithm with manually extracted endmembers guided by H&E annotations is used as reference spectra, allowing for segmentation maps with classified tissue types including carcinoma subtypes. Results: The manually extracted endmembers of known tissue types and their corresponding threshold spectral correlation angles for classification make a good reference library that validates endmembers computed by the unsupervised K-means algorithm. The unsupervised K-means algorithm, with no a priori information, produces abundance maps with dominant endmembers of various tissue types, including carcinoma subtypes of invasive ductal carcinoma and invasive mucinous carcinoma. The two carcinomas' unique endmembers produced by the two methods agree with each other within <2% residual error margin. Conclusions: Our report demonstrates a robust procedure for the validation of an unsupervised algorithm with the essential set of parameters based on the ground truth, histopathological information. We have demonstrated that a trained library of the histopathology-guided endmembers and associated threshold spectral correlation angles computed against well-defined reference data cubes serve such parameters. Two classification algorithms, supervised and unsupervised algorithms, are employed to identify regions with carcinoma subtypes of invasive ductal carcinoma and invasive mucinous carcinoma present in the tissues. The two carcinomas' unique endmembers used by the two methods agree to <2% residual error margin. This library of high quality and collected under an environment with no ambient background may be instrumental to develop or validate more advanced unsupervised data cube analysis algorithms, such as effective neural networks for efficient subtype classification.

CT Cadaveric dataset for Radiomics features stability assessment in lumbar vertebrae.

Radiomics features (RFs) studies have showed limitations in the reproducibility of RFs in different acquisition settings. To date, reproducibility studies using CT images mainly rely on phantoms, due to the harness of patient exposure to X-rays. The provided CadAIver dataset has the aims of evaluating how CT scanner parameters effect radiomics features on cadaveric donor. The dataset comprises 112 unique CT acquisitions of a cadaveric truck acquired on 3 different CT scanners varying KV, mA, field-of-view, and reconstruction kernel settings. Technical validation of the CadAIver dataset comprises a comprehensive univariate and multivariate GLM approach to assess stability of each RFs extracted from lumbar vertebrae. The complete dataset is publicly available to be applied for future research in the RFs field, and could foster the creation of a collaborative open CT image database to increase the sample size, the range of available scanners, and the available body districts.

A genetic optimisation and iterative reconstruction framework for sparse multi-dimensional diffusion-relaxation correlation MRI.

Multi-dimensional diffusion-relaxation correlation (DRC) magnetic resonance imaging (MRI) techniques have recently been developed to investigate tissue microstructures. Sub-voxel tissue heterogeneity is resolved from the local correlation distributions of relaxation time and molecular diffusivity. However, the implementation of these techniques considerably increases the total acquisition time, and simply reducing the scan time may be at the expense of detailed structural resolution. To overcome these limitations, an optimised framework was proposed for acquiring microstructural maps of the human brain on a clinically feasible timescale. First, the acquisition parameters of the multi-dimensional DRC MRI method were sparsely optimised using a genetic algorithm with a fitness function according to the spectral resolution of the correlation map, hardware requirements, and total scan time. Next, the acquired DRC MRI data were processed using a proposed numerical algorithm based on the dynamic inverse Laplace transform (ILT). Prior knowledge from one-dimensional data was then utilised in the iterative procedure to improve the spectral resolution. Finally, the proposed framework was validated using Monte Carlo simulations and experimental data acquired from healthy participants on an MRI scanner. The results demonstrated that the suggested approach is feasible for offering high-resolution DRC maps that correspond to distinct microstructures with a limited amount of optimised acquisition data from two-dimensional DRC sampling space. By significantly reducing scan time while retaining structural resolution, this approach may enable multi-dimensional DRC MRI to be more widely used for quantitative evaluation in biological and medical settings.

ReconU-Net: a direct PET image reconstruction using U-Net architecture with back projection-induced skip connection.

Objective.This study aims to introduce a novel back projection-induced U-Net-shaped architecture, called ReconU-Net, based on the original U-Net architecture for deep learning-based direct positron emission tomography (PET) image reconstruction. Additionally, our objective is to visualize the behavior of direct PET image reconstruction by comparing the proposed ReconU-Net architecture with the original U-Net architecture and existing DeepPET encoder-decoder architecture without skip connections.Approach. The proposed ReconU-Net architecture uniquely integrates the physical model of the back projection operation into the skip connection. This distinctive feature facilitates the effective transfer of intrinsic spatial information from the input sinogram to the reconstructed image via an embedded physical model. The proposed ReconU-Net was trained using Monte Carlo simulation data from the Brainweb phantom and tested on both simulated and real Hoffman brain phantom data.Main results. The proposed ReconU-Net method provided better reconstructed image in terms of the peak signal-to-noise ratio and contrast recovery coefficient than the original U-Net and DeepPET methods. Further analysis shows that the proposed ReconU-Net architecture has the ability to transfer features of multiple resolutions, especially non-abstract high-resolution information, through skip connections. Unlike the U-Net and DeepPET methods, the proposed ReconU-Net successfully reconstructed the real Hoffman brain phantom, despite limited training on simulated data.Significance. The proposed ReconU-Net can improve the fidelity of direct PET image reconstruction, even with small training datasets, by leveraging the synergistic relationship between data-driven modeling and the physics model of the imaging process.

Optimization of CT pulmonary angiography for pulmonary embolism using task-based image quality assessment and diagnostic reference levels: A multicentric study.

PURPOSE: To establish size-specific diagnostic reference levels (DRLs) for pulmonary embolism (PE) based on patient CT examinations performed on 74 CT devices. To assess task-based image quality (IQ) for each device and to investigate the variability of dose and IQ across different CTs. To propose a dose/IQ optimization. METHODS: 1051 CT pulmonary angiography dose data were collected. DRLs were calculated as the 75th percentile of CT dose index (CTDI) for two patient categories based on the thoracic perimeters. IQ was assessed with two thoracic phantom sizes using local acquisition parameters and three other dose levels. The area under the ROC curve (AUC) of a 2 mm low perfused vessel was assessed with a non-prewhitening with eye-filter model observer. The optimal IQ-dose point was mathematically assessed from the relationship between IQ and dose. RESULTS: The DRLs of CTDIvol were 6.4 mGy and 10 mGy for the two patient categories. 75th percentiles of phantom CTDIvol were 6.3 mGy and 10 mGy for the two phantom sizes with inter-quartile AUC values of 0.047 and 0.066, respectively. After the optimization, 75th percentiles of phantom CTDIvol decreased to 5.9 mGy and 7.55 mGy and the interquartile AUC values were reduced to 0.025 and 0.057 for the two phantom sizes. CONCLUSION: DRLs for PE were proposed as a function of patient thoracic perimeters. This study highlights the variability in terms of dose and IQ. An optimization process can be started individually and lead to a harmonization of practice throughout multiple CT sites.

Hepatic steatosis modeling and MRI signal simulations for comparison of single- and dual-R2* models and estimation of fat fraction at 1.5T and 3T.

BACKGROUND AND OBJECTIVE: Magnetic resonance imaging (MRI) has emerged as a noninvasive clinical tool for assessment of hepatic steatosis. Multi-spectral fat-water MRI models, incorporating single or dual transverse relaxation decay rate(s) (R2*) have been proposed for accurate fat fraction (FF) estimation. However, it is still unclear whether single- or dual-R2* model accurately mimics in vivo signal decay for precise FF estimation and the impact of signal-to-noise ratio (SNR) on each model performance. Hence, this study aims to construct virtual steatosis models and synthesize MRI signals with different SNRs to systematically evaluate the accuracy of single- and dual-R2* models for FF and R2* estimations at 1.5T and 3.0T. METHODS: Realistic hepatic steatosis models encompassing clinical FF range (0-60 %) were created using morphological features of fat droplets (FDs) extracted from human liver biopsy samples. MRI signals were synthesized using Monte Carlo simulations for noise-free (SNRideal) and varying SNR conditions (5-100). Fat-water phantoms were scanned with different SNRs to validate simulation results. Fat water toolbox was used to calculate R2* and FF for both single- and dual-R2* models. The model accuracies in R2* and FF estimates were analyzed using linear regression, bias plot and heatmap analysis. RESULTS: The virtual steatosis model closely mimicked in vivo fat morphology and Monte Carlo simulation produced realistic MRI signals. For SNRideal and moderate-high SNRs, water R2* (R2*W) by dual-R2* and common R2* (R2*com) by single-R2* model showed an excellent agreement with slope close to unity (0.95-1.01) and R2 > 0.98 at both 1.5T and 3.0T. In simulations, the R2*com-FF and R2*W-FF relationships exhibited slopes similar to in vivo calibrations, confirming the accuracy of our virtual models. For SNRideal, fat R2* (R2*F) was similar to R2*W and dual-R2* model showed slightly higher accuracy in FF estimation. However, in the presence of noise, dual-R2* produced higher FF bias with decreasing SNR, while leading to only marginal improvement for high SNRs and in regions dominated by fat and water. In contrast, single-R2* model was robust and produced accurate FF estimations in simulations and phantom scans with clinical SNRs. CONCLUSION: Our study demonstrates the feasibility of creating virtual steatosis models and generating MRI signals that mimic in vivo morphology and signal behavior. The single-R2* model consistently produced lower FF bias for clinical SNRs across entire FF range compared to dual-R2* model, hence signifying that single-R2* model is optimal for assessing hepatic steatosis.

Quantum-enhanced hybrid feature engineering in thoracic CT image analysis for state-of-the-art nodule classification: an advanced lung cancer assessment.

The intricate nature of lung cancer treatment poses considerable challenges upon diagnosis. Early detection plays a pivotal role in mitigating its escalating global mortality rates. Consequently, there are pressing demands for robust and dependable early detection and diagnostic systems. However, the technological limitations and complexity of the disease make it challenging to implement an efficient lung cancer screening system. AI-based CT image analysis techniques are showing significant contributions to the development of computer-assisted detection (CAD) systems for lung cancer screening. Various existing research groups are working on implementing CT image analysis systems for assessing and classifying lung cancer. However, the complexity of different structures inside the CT image is high and comprehension of significant information inherited by them is more complex even after applying advanced feature extraction and feature selection techniques. Traditional and classical feature selection techniques may struggle to capture complex interdependencies between features. They may get stuck in local optima and sometimes require additional exploration strategies. Traditional techniques may also struggle with combinatorial optimization problems when applied to a prominent feature space. This paper proposed a methodology to overcome the existing challenges by applying feature extraction using Vision Transformer (FexViT) and Feature selection using the Quantum Computing based Quadratic unconstrained binary optimization (QC-FSelQUBO) technique. This algorithm shows better performance when compared with other existing techniques. The proposed methodology showed better performance as compared to other existing techniques when evaluated by applying necessary output measures, such as accuracy, Area under roc (receiver operating characteristics) curve, precision, sensitivity, and specificity, obtained as 94.28%, 99.10%, 96.17%, 90.16% and 97.46%. The further advancement of CAD systems is essential to meet the demand for more reliable detection and diagnosis of cancer, which can be addressed by leading the proposed quantum computation and growing AI-based technology ahead.

3D printed phantom with 12 000 submillimeter lesions to improve efficiency in CT detectability assessment.

BACKGROUND: The detectability performance of a CT scanner is difficult to precisely quantify when nonlinearities are present in reconstruction. An efficient detectability assessment method that is sensitive to small effects of dose and scanner settings is desirable. We previously proposed a method using a search challenge instrument: a phantom is embedded with hundreds of lesions at random locations, and a model observer is used to detect lesions. Preliminary tests in simulation and a prototype showed promising results. PURPOSE: In this work, we fabricated a full-size search challenge phantom with design updates, including changes to lesion size, contrast, and number, and studied our implementation by comparing the lesion detectability from a nonprewhitening (NPW) model observer between different reconstructions at different exposure levels, and by estimating the instrument sensitivity to detect changes in dose. METHODS: Designed to fit into QRM anthropomorphic phantoms, our search challenge phantom is a cylindrical insert 10 cm wide and 4 cm thick, embedded with 12 000 lesions (nominal width of 0.6 mm, height of 0.8 mm, and contrast of -350 HU), and was fabricated using PixelPrint, a 3D printing technique. The insert was scanned alone at a high dose to assess printing accuracy. To evaluate lesion detectability, the insert was placed in a QRM thorax phantom and scanned from 50 to 625 mAs with increments of 25 mAs, once per exposure level, and the average of all exposure levels was used as high-dose reference. Scans were reconstructed with three different settings: filtered-backprojection (FBP) with Br40 and Br59, and Sinogram Affirmed Iterative Reconstruction (SAFIRE) with strength level 5 and Br59 kernel. An NPW model observer was used to search for lesions, and detection performance of different settings were compared using area under the exponential transform of free response ROC curve (AUC). Using propagation of uncertainty, the sensitivity to changes in dose was estimated by the percent change in exposure due to one standard deviation of AUC, measured from 5 repeat scans at 100, 200, 300, and 400 mAs. RESULTS: The printed insert lesions had an average position error of 0.20 mm compared to printing reference. As the exposure level increases from 50 mAs to 625 mAs, the lesion detectability AUCs increase from 0.38 to 0.92, 0.42 to 0.98, and 0.41 to 0.97 for FBP Br40, FBP Br59, and SAFIRE Br59, respectively, with a lower rate of increase at higher exposure level. FBP Br59 performed best with AUC 0.01 higher than SAFIRE Br59 on average and 0.07 higher than FBP Br40 (all P < 0.001). The standard deviation of AUC was less than 0.006, and the sensitivity to detect changes in mAs was within 2% for FBP Br59. CONCLUSIONS: Our 3D-printed search challenge phantom with 12 000 submillimeter lesions, together with an NPW model observer, provide an efficient CT detectability assessment method that is sensitive to subtle effects in reconstruction and is sensitive to small changes in dose.

A target containing phantom for accuracy assessment of cone-beam CT-guided histotripsy.

PURPOSE: Histotripsy is a nonionizing, noninvasive, and nonthermal focal tumor therapy. Cone-beam computed tomography (CBCT) guidance was developed for targeting tumors not visible on ultrasound. This approach assumes cavitation is formed at the geometrical focal point of the therapy transducer. In practice, the exact location might vary slightly between transducers. In this study, we present a phantom with an embedded target to evaluate CBCT-guided histotripsy accuracy and assess the completeness of treatments. METHODS: Spherical (2.8 cm) targets with alternating layers of agar and radiopaque barium were embedded in larger phantoms with similar layers. The layer geometry was designed so that targets were visible on pre-treatment CBCT scans. The actual histotripsy treatment zone was visualized via the mixing of adjacent barium and agar layers in post-treatment CBCT images. CBCT-guided histotripsy treatments of the targets were performed in six phantoms. Offsets between planned and actual treatment zones were measured and used for calibration refinement. To measure targeting accuracy after calibration refinement, six additional phantoms were treated. In a separate investigation, two groups (N = 3) of phantoms were treated to assess visualization of incomplete treatments ("undertreatment" group: 2 cm treatment within 2.8 cm tumor, "mistarget" group: 2.8 cm treatment intentionally shifted laterally). Treatment zones were segmented (3D Slicer 5.0.3), and the centroid distance between the prescribed target and actual treatment zones was quantified. RESULTS: In the calibration refinement group, a 2 mm offset in the direction of ultrasound propagation (Z) was measured. After calibration refinement, the centroid-to-centroid distance between prescribed and actual treatment volumes was 0.5 ± 0.2 mm. Average difference between the prescribed and measured treatment sizes in the incomplete treatment groups was 0.5 ± 0.7 mm. In the mistarget group, the distance between prescribed and measured shifts was 0.2 ± 0.1 mm. CONCLUSION: The proposed prototype phantom allowed for accurate measurement of treatment size and location, and the CBCT visible target provided a simple way to detect misalignments for preliminary quality assurance of CBCT-guided histotripsy.

Immunohistochemical assessment of HER2 low breast cancer: interobserver reproducibility and correlation with digital image analysis.

PURPOSE: The recent findings from the DESTINY-Breast04 trial highlighted the clinical importance of distinguishing between HER2 immunohistochemistry (IHC) scores 0 and 1 + in metastatic breast cancer (BC). However, pathologist interpretation of HER2 IHC scoring is subjective, and standardized methodology is needed. We evaluated the consistency of HER2 IHC scoring among pathologists and the accuracy of digital image analysis (DIA) in interpreting HER2 IHC staining in cases of HER2-low BC. METHODS: Fifty whole-slide biopsies of BC with HER2 IHC staining were evaluated, comprising 25 cases originally reported as IHC score 0 and 25 as 1 +. These slides were digitally scanned. Six pathologists with breast expertise independently reviewed and scored the scanned images, and DIA was applied. Agreement among pathologists and concordance between pathologist scores and DIA results were statistically analyzed using Kendall coefficient of concordance (W) tests. RESULTS: Substantial agreement among at least five of the six pathologists was found for 18 of the score 0 cases (72%) and 15 of the score 1 + cases (60%), indicating excellent interobserver agreement (W = 0.828). DIA scores were highly concordant with pathologist scores in 96% of cases (47/49), indicating excellent concordance (W = 0.959). CONCLUSION: Although breast subspecialty pathologists were relatively consistent in evaluating BC with HER2 IHC scores of 0 and 1 +, DIA may be a reliable supplementary tool to enhance the standardization and quantification of HER2 IHC assessment, especially in challenging cases where results may be ambiguous (i.e., scores 0-1 +). These findings hold promise for improving the accuracy and consistency of HER2 testing.

A joint brain extraction and image quality assessment framework for fetal brain MRI slices.

Brain extraction and image quality assessment are two fundamental steps in fetal brain magnetic resonance imaging (MRI) 3D reconstruction and quantification. However, the randomness of fetal position and orientation, the variability of fetal brain morphology, maternal organs around the fetus, and the scarcity of data samples, all add excessive noise and impose a great challenge to automated brain extraction and quality assessment of fetal MRI slices. Conventionally, brain extraction and quality assessment are typically performed independently. However, both of them focus on the brain image representation, so they can be jointly optimized to ensure the network learns more effective features and avoid overfitting. To this end, we propose a novel two-stage dual-task deep learning framework with a brain localization stage and a dual-task stage for joint brain extraction and quality assessment of fetal MRI slices. Specifically, the dual-task module compactly contains a feature extraction module, a quality assessment head and a segmentation head with feature fusion for simultaneous brain extraction and quality assessment. Besides, a transformer architecture is introduced into the feature extraction module and the segmentation head. We utilize a multi-step training strategy to guarantee a stable and successful training of all modules. Finally, we validate our method by a 5-fold cross-validation and ablation study on a dataset with fetal brain MRI slices in different qualities, and perform a cross-dataset validation in addition. Experiments show that the proposed framework achieves very promising performance.

Real-time breast lesion classification combining diffuse optical tomography frequency domain data and BI-RADS assessment.

Ultrasound (US)-guided diffuse optical tomography (DOT) has demonstrated potential for breast cancer diagnosis, in which real-time or near real-time diagnosis with high accuracy is desired. However, DOT's relatively slow data processing and image reconstruction speeds have hindered real-time diagnosis. Here, we propose a real-time classification scheme that combines US breast imaging reporting and data system (BI-RADS) readings and DOT frequency domain measurements. A convolutional neural network is trained to generate malignancy probability scores from DOT measurements. Subsequently, these scores are integrated with BI-RADS assessments using a support vector machine classifier, which then provides the final diagnostic output. An area under the receiver operating characteristic curve of 0.978 is achieved in distinguishing between benign and malignant breast lesions in patient data without image reconstruction.

Multimodal active subspace analysis for computing assessment oriented subspaces from neuroimaging data.

BACKGROUND: For successful biomarker discovery, it is essential to develop computational frameworks that summarize high-dimensional neuroimaging data in terms of involved sub-systems of the brain, while also revealing underlying heterogeneous functional and structural changes covarying with specific cognitive and biological traits. However, unsupervised decompositions do not inculcate clinical assessment information, while supervised approaches extract only individual feature importance, thereby impeding qualitative interpretation at the level of subspaces. NEW METHOD: We present a novel framework to extract robust multimodal brain subspaces associated with changes in a given cognitive or biological trait. Our approach involves active subspace learning on the gradients of a trained machine learning model followed by clustering to extract and summarize the most salient and consistent subspaces associated with the target variable. RESULTS: Through a rigorous cross-validation procedure on an Alzheimer's disease (AD) dataset, our framework successfully extracts multimodal subspaces specific to a given clinical assessment (e.g., memory and other cognitive skills), and also retains predictive performance in standard machine learning algorithms. We also show that the salient active subspace directions occur consistently across randomly sub-sampled repetitions of the analysis. COMPARISON WITH EXISTING METHOD(S): Compared to existing unsupervised decompositions based on principle component analysis, the subspace components in our framework retain higher predictive information. CONCLUSIONS: As an important step towards biomarker discovery, our framework not only uncovers AD-related brain regions in the associated brain subspaces, but also enables automated identification of multiple underlying structural and functional sub-systems of the brain that collectively characterize changes in memory and proficiency in cognitive skills related to brain disorders like AD.

A color-based tumor segmentation method for clinical ex vivo breast tissue assessment utilizing a multi-contrast brightfield imaging strategy.

We demonstrate an automated two-step tumor segmentation method leveraging color information from brightfield images of fresh core needle biopsies of breast tissue. Three different color spaces (HSV, CIELAB, YCbCr) were explored for the segmentation task. By leveraging white-light and green-light images, we identified two different types of color transformations that could separate adipose from benign and tumor or cancerous tissue. We leveraged these two distinct color transformation methods in a two-step process where adipose tissue segmentation was followed by benign tissue segmentation thereby isolating the malignant region of the biopsy. Our tumor segmentation algorithm and imaging probe could highlight suspicious regions on unprocessed biopsy tissue to guide selection of areas most similar to malignant tissues for tissue pathology whether it be formalin fixed or frozen sections, expedite tissue selection for molecular testing, detect positive tumor margins, or serve an alternative to tissue pathology, in countries where these services are lacking.

Motion-compensated image reconstruction for improved kidney function assessment using dynamic contrast-enhanced MRI.

Accurately measuring renal function is crucial for pediatric patients with kidney conditions. Traditional methods have limitations, but dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) provides a safe and efficient approach for detailed anatomical evaluation and renal function assessment. However, motion artifacts during DCE-MRI can degrade image quality and introduce misalignments, leading to unreliable results. This study introduces a motion-compensated reconstruction technique for DCE-MRI data acquired using golden-angle radial sampling. Our proposed method achieves three key objectives: (1) identifying and removing corrupted data (outliers) using a Gaussian process model fitting with a k -space center navigator, (2) efficiently clustering the data into motion phases and performing interphase registration, and (3) utilizing a novel formulation of motion-compensated radial reconstruction. We applied the proposed motion correction (MoCo) method to DCE-MRI data affected by varying degrees of motion, including both respiratory and bulk motion. We compared the outcomes with those obtained from the conventional radial reconstruction. Our evaluation encompassed assessing the quality of images, concentration curves, and tracer kinetic model fitting, and estimating renal function. The proposed MoCo reconstruction improved the temporal signal-to-noise ratio for all subjects, with a 21.8% increase on average, while total variation values of the aorta, right, and left kidney concentration were improved for each subject, with 32.5%, 41.3%, and 42.9% increases on average, respectively. Furthermore, evaluation of tracer kinetic model fitting indicated that the median standard deviation of the estimated filtration rate ( σ F T ), mean normalized root-mean-squared error (nRMSE), and chi-square goodness-of-fit of tracer kinetic model fit were decreased from 0.10 to 0.04, 0.27 to 0.24, and, 0.43 to 0.27, respectively. The proposed MoCo technique enabled more reliable renal function assessment and improved image quality for detailed anatomical evaluation in the case of bulk and respiratory motion during the acquisition of DCE-MRI.

Precise individual muscle segmentation in whole thigh CT scans for sarcopenia assessment using U-net transformer.

The study aims to develop a deep learning based automatic segmentation approach using the UNETR(U-net Transformer) architecture to quantify the volume of individual thigh muscles(27 muscles in 5 groups) for Sarcopenia assessment. By automating the segmentation process, this approach improves the efficiency and accuracy of muscle volume calculation, facilitating a comprehensive understanding of muscle composition and its relationship to Sarcopenia. The study utilized a dataset of 72 whole thigh CT scans from hip fracture patients, annotated by two radiologists. The UNETR model was trained to perform precise voxel-level segmentation and various metrics such as dice score, average symmetric surface distance, volume correlation, relative absolute volume difference and Hausdorff distance were employed to evaluate the model's performance. Additionally, the correlation between Sarcopenia and individual thigh muscle volumes was examined. The proposed model demonstrated superior segmentation performance compared to the baseline model, achieving higher dice scores (DC = 0.84) and lower average symmetric surface distances (ASSD = 1.4191 ± 0.91). The volume correlation between Sarcopenia and individual thigh muscles in the male group. Furthermore, the correlation analysis of grouped thigh muscles also showed negative associations with Sarcopenia in the male participants. This thesis presents a deep learning based automatic segmentation approach for quantifying individual thigh muscle volume in sarcopenia assessment. The results highlights the associations between Sarcopenia and specific individual muscles as well as grouped thigh muscle regions, particularly in males. The proposed method improves the efficiency and accuracy of muscle volume calculation, contributing to a comprehensive evaluation of Sarcopenia. This research enhances our understanding of muscle composition and performance, providing valuable insights for effective interventions in Sarcopenia management.

MCMC algorithm based on Markov random field in image segmentation.

In the realm of digital image applications, image processing technology occupies a pivotal position, with image segmentation serving as a foundational component. As the digital image application domain expands across industries, the conventional segmentation techniques increasingly challenge to cater to modern demands. To address this gap, this paper introduces an MCMC-based image segmentation algorithm based on the Markov Random Field (MRF) model, marking a significant stride in the field. The novelty of this research lies in its method that capitalizes on domain information in pixel space, amplifying the local segmentation precision of image segmentation algorithms. Further innovation is manifested in the development of an adaptive segmentation image denoising algorithm based on MCMC sampling. This algorithm not only elevates image segmentation outcomes, but also proficiently denoises the image. In the experimental results, MRF-MCMC achieves better segmentation performance, with an average segmentation accuracy of 94.26% in Lena images, significantly superior to other common image segmentation algorithms. In addition, the study proposes that the denoising model outperforms other algorithms in peak signal-to-noise ratio and structural similarity in environments with noise standard deviations of 15, 25, and 50. In essence, these experimental findings affirm the efficacy of this study, opening avenues for refining digital image segmentation methodologies.

Machine learning approach for proton range verification using real-time prompt gamma imaging with Compton cameras: addressing the total deposited energy information gap.

Objective.Compton camera imaging shows promise as a range verification technique in proton therapy. This work aims to assess the performance of a machine learning model in Compton camera imaging for proton beam range verification improvement.Approach.The presented approach was used to recognize Compton events and estimate more accurately the prompt gamma (PG) energy in the Compton camera to reconstruct the PGs emission profile during proton therapy. This work reports the results obtained from the Geant4 simulation for a proton beam impinging on a polymethyl methacrylate (PMMA) target. To validate the versatility of such an approach, the produced PG emissions interact with a scintillating fiber-based Compton camera.Main results.A trained multilayer perceptron (MLP) neural network shows that it was possible to achieve a notable three-fold increase in the signal-to-total ratio. Furthermore, after event selection by the trained MLP, the loss of full-energy PGs was compensated by means of fitting an MLP energy regression model to the available data from true Compton (signal) events, predicting more precisely the total deposited energy for Compton events with incomplete energy deposition.Significance.A considerable improvement in the Compton camera's performance was demonstrated in determining the distal falloff and identifying a few millimeters of target displacements. This approach has shown great potential for enhancing online proton range monitoring with Compton cameras in future clinical applications.

UBES: Unified scatter correction using ultrafast Boltzmann equation solver for conebeam CT.

A semi-analytical solution to the unified Boltzmann equation is constructed to exactly describe the scatter distribution on a flat-panel detector for high-quality conebeam CT (CBCT) imaging. The solver consists of three parts, including the phase space distribution estimator, the effective source constructor and the detector signal extractor. Instead of the tedious Monte Carlo solution, the derived Boltzmann equation solver achieves ultrafast computational capability for scatter signal estimation by combining direct analytical derivation and time-efficient one-dimensional numerical integration over the trajectory along each momentum of the photon phase space distribution. The execution of scatter estimation using the proposed ultrafast Boltzmann equation solver (UBES) for a single projection is finalized in around 0.4 seconds. We compare the performance of the proposed method with the state-of-the-art schemes, including a time-expensive Monte Carlo (MC) method and a conventional kernel-based algorithm using the same dataset, which is acquired from the CBCT scans of a head phantom and an abdominal patient. The evaluation results demonstrate that the proposed UBES method achieves comparable correction accuracy compared with the MC method, while exhibits significant improvements in image quality over learning and kernel-based methods. With the advantages of MC equivalent quality and superfast computational efficiency, the UBES method has the potential to become a standard solution to scatter correction in high-quality CBCT reconstruction.

Triplet-constrained deep hashing for chest X-ray image retrieval in COVID-19 assessment.

Radiology images of the chest, such as computer tomography scans and X-rays, have been prominently used in computer-aided COVID-19 analysis. Learning-based radiology image retrieval has attracted increasing attention recently, which generally involves image feature extraction and finding matches in extensive image databases based on query images. Many deep hashing methods have been developed for chest radiology image search due to the high efficiency of retrieval using hash codes. However, they often overlook the complex triple associations between images; that is, images belonging to the same category tend to share similar characteristics and vice versa. To this end, we develop a triplet-constrained deep hashing (TCDH) framework for chest radiology image retrieval to facilitate automated analysis of COVID-19. The TCDH consists of two phases, including (a) feature extraction and (b) image retrieval. For feature extraction, we have introduced a triplet constraint and an image reconstruction task to enhance discriminative ability of learned features, and these features are then converted into binary hash codes to capture semantic information. Specifically, the triplet constraint is designed to pull closer samples within the same category and push apart samples from different categories. Additionally, an auxiliary image reconstruction task is employed during feature extraction to help effectively capture anatomical structures of images. For image retrieval, we utilize learned hash codes to conduct searches for medical images. Extensive experiments on 30,386 chest X-ray images demonstrate the superiority of the proposed method over several state-of-the-art approaches in automated image search. The code is now available online.