Artifact Correction Research Articles

Multifunctional GAN-based optimization for X-ray tomography under different conditions

Based on the generative adversarial network (GAN), we present a multifunctional X-ray tomographic protocol for artifact correction, noise suppression, and super-resolution of reconstruction. The protocol mainly consists of a data preprocessing module and multifunctional GAN-based loss function simultaneously dealing with ring artifacts and super-resolution. The experimental protocol removes ring artifacts and improves the contrast-to-noise ratio (CNR) and spatial resolution (SR) of reconstructed images successfully, which shows the capability to adaptively rectify ring artifacts with varying intensities and types while achieving super-resolution. Compared with the main existing deep learning models or conventional tomographic correction methods, it also enables higher processing speed and minimal information loss, especially for images of smaller dimensions. This study provides a robust optimization tool for the equivalent realization of large fields of view and high-resolution X-ray tomography. The experimental datasets were collected from a series of X-ray cone-beam computed tomography scans of biological samples.

Identification of ocular artifact in EEG signals using VMD and Hurst exponent.

Electroencephalographic (EEG) readings are usually infected with unavoidable artifacts, especially physiological ones. One such physiological artifact is the ocular artifacts (OAs) that are generally related to eyes and are characterized by high magnitude and a specific spike pattern in the prefrontal region of the brain. During the long-duration EEG acquisition, the retrieval of important information becomes quite complicated in prefrontal regions as ocular artifacts dominate the EEG recorded, making it difficult to discern underlying brain activity. With the progress and development in signal processing techniques, artifact handling has become a progressive field of investigation. This paper presents a framework for the detection and correction of ocular artifacts. This study emphasizes improving the quality and reducing the time complexity by using higher-order statistics (HOS) for artifact identification and variational mode decomposition (VMD) for OA correction. An overall SNR of 14 dB, MAE of 0.09, and PSNR of 33.59 dB has been attained by the proposed framework. It was observed that the proposed HOS-VMD surpassed the state-of-the-art mode decomposition techniques.

Disentangling the impact of motion artifact correction algorithms on functional near-infrared spectroscopy-based brain network analysis.

Functional near-infrared spectroscopy (fNIRS) has been widely used to assess brain functional networks due to its superior ecological validity. Generally, fNIRS signals are sensitive to motion artifacts (MA), which can be removed by various MA correction algorithms. Yet, fNIRS signals may also undergo varying degrees of distortion due to MA correction, leading to notable alternation in functional connectivity (FC) analysis results. We aimed to investigate the effect of different MA correction algorithms on the performance of brain FC and topology analyses. We evaluated various MA correction algorithms on simulated and experimental datasets, including principal component analysis, spline interpolation, correlation-based signal improvement, Kalman filtering, wavelet filtering, and temporal derivative distribution repair (TDDR). The mean FC of each pre-defined network, receiver operating characteristic (ROC), and graph theory metrics were investigated to assess the performance of different algorithms. Although most algorithms did not differ significantly from each other, the TDDR and wavelet filtering turned out to be the most effective methods for FC and topological analysis, as evidenced by their superior denoising ability, the best ROC, and an enhanced ability to recover the original FC pattern. The findings of our study elucidate the varying impact of MA correction algorithms on brain FC analysis, which could serve as a reference for choosing the most appropriate method for future FC research. As guidance, we recommend using TDDR or wavelet filtering to minimize the impact of MA correction in brain network analysis.

Comments on the paper "Data-driven gating (DDG)-based motion match for improved CTAC registration. EJNMMI Physics. 2024;11(1):42."

Misregistration between CT and PET in PET/CT is mainly caused by respiratory motion or irregular respiration during the CT scan in PET/CT. Other than repeat CT, repeat PET/CT, or data-driven gated (DDG) CT, there is no practical approach to mitigate the misregistration artifacts and subsequent CT attenuation correction (CTAC) of the PET data. DDG PET derives a respiratory motion model based on the multiple phases of PET images without hardware gating and it allows for a potential correction of the misregistration artifacts based on the respiratory motion model. The purpose of this commentary was to compare the recent two publications on matching the random phase of helical CT with one of the PET phases derived from the motion model of DDG PET and warping the misregistered helical CT for CTAC of and registration with PET or DDG PET. The two publications were similar in methodology. However, the data sets used for the comparison were different and could potentially impact their conclusions.

Impact of applying different levels of threshold-based artifact correction on the processing of heart rate variability data in individuals with temporomandibular disorder.

Although heart rate variability (HRV) is a valid method to evaluate the behavior of the autonomic nervous system in individuals with temporomandibular disorder (TMD), the measurement can easily be biased by factors involving the analysis methodology, such as the removal of artifacts. Therefore, the objective of this investigation is to evaluate the impact of using different levels of threshold-based artifact correction to process HRV data in individuals with TMD. This cross-sectional observational study. Adults aged 18 to 55 years old with a diagnosis of myogenic TMD, score ≥ 50 on the Fonseca Anamnestic Index (FAI) and pain ≥ 3 on the Numerical Pain Scale (NPS) participated. The HRV was registered in the supine position (short-term) using a Polar S810i. Kubios software was used for HRV analysis using all filters. One-way ANOVA with Tukey-Kramer post-hoc was used to test the differences in HRV using the different Kubios Software artifact correction filters. The effect size was calculated based on the Cohen d. The very strong filter was statistically different (p < 0.05) compared to the no filter in all overview and time domain variables. In the frequency domain, the variables VLF, LF, HF and Total Power showed statistical differences (p < 0.05) when using the very strong filter. The same occurred with the variables SD1, SD2 and DFA α2 of the non-linear analysis (p < 0.05). The most restrictive filter of the Kubios software (very strong) significantly impacts the quantification of HRV parameters in individuals with TMD.

Optimizing EEG Signal Integrity: A Comprehensive Guide to Ocular Artifact Correction.

Ocular artifacts, including blinks and saccades, pose significant challenges in the analysis of electroencephalographic (EEG) data, often obscuring crucial neural signals. This tutorial provides a comprehensive guide to the most effective methods for correcting these artifacts, with a focus on algorithms designed for both laboratory and real-world settings. We review traditional approaches, such as regression-based techniques and Independent Component Analysis (ICA), alongside more advanced methods like Artifact Subspace Reconstruction (ASR) and deep learning-based algorithms. Through detailed step-by-step instructions and comparative analysis, this tutorial equips researchers with the tools necessary to maintain the integrity of EEG data, ensuring accurate and reliable results in neurophysiological studies. The strategies discussed are particularly relevant for wearable EEG systems and real-time applications, reflecting the growing demand for robust and adaptable solutions in applied neuroscience.

AIDM-CT: software for cone-beam X-ray tomography and deep-learning-based analysis

ABSTRACT Non-destructive testing (NDT) with high-resolution cone-beam X-ray computed tomography (XCT) plays a crucial role in revealing the 3D distribution and morphology of defects within an object. It’s necessary to generalise an intelligent and customised XCT-based NDT protocol, providing solutions for reconstruction quality improvement and complex defect quantitative analysis for users. We analysed the key techniques of XCT and developed the systematic software for data acquisition, reconstruction, intelligent super-resolution and segmentation in our advanced imaging and data mining laboratory (AIDM-CT). The experimental results demonstrated the software efficiently achieves the control of XCT scanning, artefact correction algorithms related to cone-beam geometrics, beam hardening, ring and radial artefacts, deep-learning based slice super-resolution and feature segmentation, and quantitative analysis. The software is programmed by Python language to provide the friendly multi-function graphical user interface (GUI), in which the programming of reconstruction and corrections combined with Computer Unified Device Architecture (CUDA) acceleration to guarantee the high efficiency of XCT task. Particularly, the multi-functional super resolution module (MF-GAN) is proposed to optimise the quality of CT image and the improved U-Net segmentation module (CBAM U-Net) is also developed to fulfill the high-precision quantitative non-destructive testing of homogeneous and variform microdefects in our AIDM-CT software.

Improved metal suppression using new generation low-field MRI: a biophantom feasibility study.

Novel 0.55 MRI scanners have the potential to reduce metal artifacts around orthopedic implants. The purpose of this study was to compare metal artifact size and depiction of anatomy between 0.55T and 3.0T MRI in a biophantom. Steel and titanium screws were implanted in 12 porcine knee specimens and imaging at 0.55T and 3T MRI was performed using the following sequences: turbo spin-echo (TSE), TSE with view angle tilting (VAT), and slice encoding for metal artifact correction (SEMAC) with proton-density (PD) and T2-weighted short-tau inversion-recovery (T2w-STIR) contrasts. Artifacts were measured, and visualization of anatomy (cartilage, bone, growth plates, cruciate ligaments) was assessed and compared between groups. Metal artifacts were significantly smaller at 0.55T. The smallest artifact sizes were achieved with SEMAC at 0.55T for both PD and T2w-STIR sequences; corresponding relative size reductions vs. 3.0T were 78.7% and 79.4% (stainless steel) and 45.3% and 1.4% (titanium). Depiction of anatomical structures was superior at 0.55T. Substantial reduction of artifact size resulting in superior depiction of anatomical structures is possible on novel 0.55T MRI systems. Further clinical studies are required to elucidate patient-relevant advantages.

Comparing different motion correction approaches for resting-state functional connectivity analysis with functional near-infrared spectroscopy data.

Motion artifacts are a notorious challenge in the functional near-infrared spectroscopy (fNIRS) field. However, little is known about how to deal with them in resting-state data. We assessed the impact of motion artifact correction approaches on assessing functional connectivity, using semi-simulated datasets with different percentages and types of motion artifact contamination. Thirty-five healthy adults underwent a 15-min resting-state acquisition. Semi-simulated datasets were generated by adding spike-like and/or baseline-shift motion artifacts to the real dataset. Fifteen pipelines, employing various correction approaches, were applied to each dataset, and the group correlation matrix was computed. Three metrics were used to test the performance of each approach. When motion artifact contamination was low, various correction approaches were effective. However, with increased contamination, only a few pipelines were reliable. For datasets mostly free of baseline-shift artifacts, discarding contaminated frames after pre-processing was optimal. Conversely, when both spike and baseline-shift artifacts were present, discarding contaminated frames before pre-processing yielded the best results. This study emphasizes the need for customized motion correction approaches as the effectiveness varies with the specific type and amount of motion artifacts present.

Satellite-derived bathymetry using Sentinel-2 in mesotidal coasts

Coastal zones are strategic environments of high socioeconomic, political, and ecological value, with over half of the world’s population residing within 200 km of the coast. This proximity highlights their vulnerability to extreme events, which are exacerbated by global changes, leading to significant coastal impacts such as erosion, flooding, and ecosystem services deterioration. Consequently, efficient and operational methodologies for continuous monitoring are urgently needed to face these challenges. Bathymetric data are essential for understanding coastal dynamics, yet traditional data collection methods are often constrained by logistical challenges and high costs. Spaceborne remote sensing techniques offer significant advantages over traditional ground-based methods, particularly in terms of cost-effectiveness and operational efficiency. Over the last half-century, different Satellite-derived bathymetry (SDB) methodologies have been developed; however, challenges still persist. In this research, we applied a robust SDB methodology to three different study sites: Cíes Islands, Baiona Bay, and Vao beach within the Ría de Vigo, Galicia (NW Spain). These areas offer diverse and complex mesotidal environments to test for the very first time the methodology's efficacy. SDB was retrieved with a median absolute error (MedAE) ranging from 0.35 m to 1.55 m for depths up to 14 m. Results with different data source were evaluated, obtaining MedAE for nautical charts ranging from 0.46 m to 1.55 m. The precision between the data sources were quite close. In addition, multi-image composite was generated using images coinciding with both low tide (LT) and high tide (HT) conditions across the three zones. The lowest MedAE values were consistently obtained in images classified as LT (0.46 m) corresponding to Vao area. The results highlight the potential of nautical charts as a reliable source of calibration data for SDB, confirm the effectiveness of multi-image and switching models to correct artifacts and turbidity, considering tidal effects, improving single image approaches, and leverage visible bands for precise depth retrieval under varying conditions.

O-CLEAN: a novel multi-stage algorithm for the ocular artifacts' correction from EEG data in out-of-the-lab applications.

In the context of electroencephalographic (EEG) signal processing, artifacts generated by ocular movements, such as blinks, are significant confounding factors. These artifacts overwhelm informative EEG features and may occur too frequently to simply remove affected epochs without losing valuable data. Correcting these artifacts remains a challenge, particularly in out-of-lab and online applications using wearable EEG systems (i.e. with low number of EEG channels, without any additional channels to track EOG).Objective.The main objective of the present work consisted in validating a novel ocular blinks artefacts correction method, named multi-stage OCuLar artEfActs deNoising algorithm (o-CLEAN), suitable for online processing with minimal EEG channels.Approach.The research was conducted considering one EEG dataset collected in highly controlled environment, and a second one collected in real environment. The analysis was performed by comparing the o-CLEAN method with previously validated state-of-art techniques, and by evaluating its performance along two dimensions: (a) the ocular artefacts correction performance (IN-Blink), and (b) the EEG signal preservation when the method was applied without any ocular artefacts occurrence (OUT-Blink).Main results.Results highlighted that (i) o-CLEAN algorithm resulted to be, at least, significantly reliable as the most validated approaches identified in scientific literature in terms of ocular blink artifacts correction, (ii) o-CLEAN showed the best performances in terms of EEG signal preservation especially with a low number of EEG channels.Significance.The testing and validation of the o-CLEAN addresses a relevant open issue in bioengineering EEG processing, especially within out-of-the-lab application. In fact, the method offers an effective solution for correcting ocular artifacts in EEG signals with a low number of available channels, for online processing, and without any specific template of the EOG. It was demonstrated to be particularly effective for EEG data gathered in real environments using wearable systems, a rapidly expanding area within applied neuroscience.

Optimization of reconstruction in quantitative brain PET images: Benefits from PSF modeling and correction of edge artifacts.

Modern PET reconstruction algorithms incorporate point-spread-function (PSF) correction to mitigate partial volume effect. However, PSF correction can introduce edge artifacts that lead to quantification errors. Consequently, current international guidelines advise against using PSF correction in brain PET reconstruction. We aimed to investigate PSF-induced quantification errors in recent digital PET systems and identify conditions that mitigate them. This study utilized brain PET imaging with alginate-based realistic phantoms, simulating lesion-to-background activity ratios of 10:1 and 2:1, with eleven reconstruction parameter sets. Phantoms were prepared using a commercial anthropomorphic head phantom and two homemade inserts. Each insert contained a homogeneous 18F-FDG alginate background with hot spheres of varying diameter (3, 4, 6, 8, 10, 12, and 15mm). PET imaging was conducted on a digital PET-CT system Biograph Vision 600 (Siemens), with a 10 min scan duration. Imaging was performed with and without PSF correction, with 2, 4, 6, 12, 18, or 24 iterations in reconstruction, and with or without additional Gaussian postfiltering. We assessed the recovery coefficient (RC), contrast recovery coefficient (CRC), variability, and CRC-to-variability ratios for each sphere size and reconstruction parameter set. PSF-corrected images of the 10:1 spheres exhibited a nonmonotonic CRC-to-sphere diameter relationship due to edge artifacts overshoot in the 10mm-diameter sphere. In contrast, PSF images of the 2:1 spheres showed a monotonically increasing relationship. Non-PSF images of both phantoms showed an expected monotonically increasing CRC-to-sphere diameter relationship but with lower CRC values compared to PSF images. The nonmonotonic relationship observed with 10:1 spheres was mitigated by applying a 3-mm FWHM Gaussian postfiltering. For both phantoms, reconstructions with 6 iterations, PSF correction, and additional 3-mm FWHM Gaussian postfiltering demonstrated the highest CRC-to-variability ratios. Our findings indicate that Gaussian postfiltering suppresses PSF artifacts. This parameter set corrected the nonmonotonic CRC-to-sphere diameter relationship and improved the CRC-to-variability ratio compared to non-PSF reconstructions. Therefore, to enhance lesion detectability without compromising quantification accuracy, PSF correction coupled with Gaussian postfiltering should be used in brain PET.

CNN-based approach for 3D artifact correction of intensity diffraction tomography images

CNN-based approach for 3D artifact correction of intensity diffraction tomography images

Prediction of H3K27M alteration in midline gliomas of brain using radiomics- A multi-institute study

Abstract Background Non-invasive prediction of H3K27M-altered Diffuse midline gliomas is important because of the involvement of deep locations and proximity to eloquent structures. We aim to predict H3K27M alteration in midline gliomas using radiomics features of T2W images. Methods Radiomics features extracted from 124 subjects (69 H3K27M-altered/55 H3K27M-wildtype). T2W-images were resampled to 1x1x1mm voxel-size, pre-processed, and normalized for artefact correction, intensity variations. Feature-set was normalized, subjected to reduction by variance thresholding, correlation coefficient thresholding, and sequential feature selector. Adaptive synthesis oversampling technique was used to over-sample the training data. Random forest classifier (RFC), Decision tree classifier (DTC) and K-nearest neighbors classifier (KNN) were trained over the training dataset and the performance was assessed over the internal test dataset and external test data set (52 subjects: 33 H3K27M-altered/19-H3K27M-wildtype). Results DTC achieved validation score of 77.33% (5-fold cross-validation) and accuracy of 80.64%, 75% on internal and external test dataset. RFC achieved validation score of 80.7% (5-fold cross-validation) and accuracy of 80.6%, 73% on internal and external test dataset. DTC achieved validation score of 78.67% (5-fold cross-validation) and accuracy of 80.64%, 61.53% on internal and external test dataset. Accuracy score of DTC, RFC, and KNN on internal test dataset was approximately 80% while on the external test dataset, DTC achieved 75% accuracy, RFC achieved 73% accuracy and KNN achieved 65.1% accuracy. Conclusion H3K27M alteration is a potential immunotherapeutic marker and is associated with poor prognosis and radiomics features extracted from conventional T2W-images can help in identifying H3K27M-altered cases non-invasively with high precision.

O20 CURRENT 24-HOUR AMBULATORY BLOOD PRESSURE TECHNOLOGIES SHOULD BE RECONSIDERED AS THE REFERENCE STANDARD FOR VALIDATION OF CUFFLESS BLOOD PRESSURE DEVICES

Background and Objective: Recommendations for the validation of cuffless blood pressure (BP) devices were recently released by the European Society of Hypertension (ESH). In this recommendation, 24-hour ambulatory BP monitoring (ABPM) is the reference standard for a newly proposed ‘awake-asleep’ accuracy test. However, this reference standard may be inappropriate because ABPM is subject to measurement insecurities, and it is unknown if it would pass the awake-asleep test. Therefore, the aim of this study was to determine if ABPM itself would pass the awake-asleep test recommended for validation of cuffless BP devices. Methods: Dual arm, simultaneous ABPM were recorded using two identical cuff-based devices (TM-2430, A&amp;D, Japan) among 46 healthy adults (22±2.3 years; 54% female). The awake-asleep test was defined as the difference between the left arm ABPM minus right arm ABPM for assessing the change in BP between awake-asleep time (ESH recommendations: mean difference ± SD ≤5±8 mmHg, correlation r&gt;0.7 for test and reference values; awake-asleep BP components calculated based on personalized sleeping times). Measurement artefacts were identified by analysis of the cuff deflation pressure curves and hydrostatic pressure differences (body position) between the cuffs. Results: ABPM did not pass the awake-asleep test due to higher than acceptable measurement variability for systolic BP, -0.1±8.6 mmHg, r=0.69 and partially met requirements for diastolic BP, -0.7±5.9 mmHg, r=0.63. After correction for measurement artefacts and hydrostatic pressure differences, ABPM passed the awake-asleep test for systolic BP (-1.7±5.0 mmHg, r=0.76) but still did not meet requirements for diastolic BP due to insufficient correlation (r=0.64). Conclusion: In this analysis, ABPM itself did not meet the awake-asleep test criteria recommended by the ESH. Using current ABPM technologies as a reference standard for cuffless BP validation protocols may need to be reconsidered and they need improvement before use for this purpose. Improving ABPM through better measurement artefact detection could be an initial solution which would also improve its value for clinical decision making.

The moving wave: Applications of the mobile EEG approach to study human attention.

Although historically confined to traditional research laboratories, electroencephalography (EEG) paradigms are now being applied to study a wide array of behaviors, from daily activities to specialized tasks in diverse fields such as sports science, neurorehabilitation, and education. This transition from traditional to real-world mobile research can provide new tools for understanding attentional processes as they occur naturally. Early mobile EEG research has made progress, despite the large size and wired connections. Recent developments in hardware and software have expanded the possibilities of mobile EEG, enabling a broader range of applications. Despite these advancements, limitations influencing mobile EEG remain that must be overcome to achieve adequate reliability and validity. In this review, we first assess the feasibility of mobile paradigms, including electrode selection, artifact correction techniques, and methodological considerations. This review underscores the importance of ecological, construct, and predictive validity in ensuring the trustworthiness and applicability of mobile EEG findings. Second, we explore studies on attention in naturalistic settings, focusing on replicating classic P3 component studies in mobile paradigms like stationary biking in our lab, and activities such as walking, cycling, and dual-tasking outside of the lab. We emphasize how the mobile approach complements traditional laboratory paradigms and the types of insights gained in naturalistic research settings. Third, we discuss promising applications of portable EEG in workplace safety and other areas including road safety, rehabilitation medicine, and brain-computer interfaces. In summary, this review explores the expanding possibilities of mobile EEG while recognizing the existing challenges in fully realizing its potential.

Motion Artifact Correction for OCT Microvascular Images Based on Image Feature Matching.

Optical coherence tomography angiography (OCTA), a functional extension of optical coherence tomography (OCT), is widely employed for high-resolution imaging of microvascular networks. However, due to the relatively low scan rate of OCT, the artifacts caused by the involuntary bulk motion of tissues severely impact the visualization of microvascular networks. This study proposes a fast motion correction method based on image feature matching for OCT microvascular images. First, the rigid motion-related mismatch between B-scans is compensated through the image feature matching based on the improved oriented FAST and rotated BRIEF algorithm. Then, the axial motion within A-scan lines in each B-scan image is corrected according to the displacement deviation between the detected boundaries achieved by the Scharr operator in a non-rigid transformation manner. Finally, an optimized intensity-based Doppler variance algorithm is developed to enhance the robustness of the OCTA imaging. The experimental results demonstrate the effectiveness of the method.

Advancements and Challenges in Algebraic Techniques for Medical Imaging: A Comprehensive Review of MRI and CT Scan Applications in Nigeria

Medical imaging plays a crucial role in modern healthcare by providing essential diagnostic and treatment information. This review examines the advancements and challenges of algebraic techniques in enhancing Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) scans in Nigeria. Algebraic methods, including Algebraic Reconstruction Techniques (ART), Compressed Sensing (CS), and Total Variation (TV) regularization, are integral in refining image reconstruction processes, reducing noise, and improving diagnostic accuracy. These techniques facilitate high-resolution imaging, artifact correction, and effective data fusion across different modalities. Despite the promising advancements, Nigeria faces several challenges, including high implementation costs, limited access to advanced imaging equipment, and a shortage of trained professionals. The economic barriers and disparities in technology access underscore the need for strategic investments, policy support, and collaborative initiatives to broaden the reach of these techniques. Successful case studies from institutions such as Lagos University Teaching Hospital and University College Hospital, Ibadan, highlight the tangible benefits of algebraic imaging techniques, including enhanced diagnostic clarity and reduced scan times. Training and education are essential for leveraging these advanced techniques, necessitating interdisciplinary programs and international collaborations. The integration of algebraic methods holds transformative potential for Nigeria's healthcare system, improving patient outcomes through early disease detection, precise treatment planning, and expanded access to advanced imaging services. Addressing the associated challenges through targeted efforts and continued innovation will further enhance diagnostic practices and healthcare delivery in Nigeria. Keywords: Algebraic Techniques, Medical Imaging, Magnetic Resonance Imaging (MRI), Computed Tomography (CT), Nigeria.

Learning Scatter Artifact Correction in Cone-Beam X-Ray CT Using Incomplete Projections with Beam Hole Array

X-ray cone-beam computed tomography (CBCT) is a powerful tool for nondestructive testing and evaluation, yet the CT image quality can be compromised by artifact due to X-ray scattering within dense materials such as metals. This problem leads to the need for hardware- and software-based scatter artifact correction to enhance the image quality. Recently, deep learning techniques have merged as a promising approach to obtain scatter-free images efficiently. However, these deep learning techniques rely heavily on training data, often gathered through simulation. Simulated CT images, unfortunately, do not accurately reproduce the real properties of objects, and physically accurate X-ray simulation still requires significant computation time, hindering the collection of a large number of CT images. To address these problems, we propose a deep learning framework for scatter artifact correction using projections obtained solely by real CT scanning. To this end, we utilize a beam-hole array (BHA) to block the X-rays deviating from the primary beam path, thereby capturing scatter-free X-ray intensity at certain detector pixels. As the BHA shadows a large portion of detector pixels, we incorporate several regularization losses to enhance the training process. Furthermore, we introduce radiographic data augmentation to mitigate the need for long scanning time, which is a concern as CT devices equipped with BHA require two series of CT scans. Experimental validation showed that the proposed framework outperforms a baseline method that learns simulated projections where the entire image is visible and does not contain scattering artifacts.

An Immunofluorescence-Guided Segmentation Model in Hematoxylin and Eosin Images Is Enabled by Tissue Artifact Correction Using a Cycle-Consistent Generative Adversarial Network

Despite recent advances, the adoption of computer vision methods into clinical and commercial applications has been hampered by the limited availability of accurate ground truth tissue annotations required to train robust supervised models. Generating such ground truth can be accelerated by annotating tissue molecularly using immunofluorescence (IF) staining and mapping these annotations to a post-IF hematoxylin and eosin (H&E) (terminal H&E) stain. Mapping the annotations between IF and terminal H&E increases both the scale and accuracy by which ground truth could be generated. However, discrepancies between terminal H&E and conventional H&E caused by IF tissue processing have limited this implementation. We sought to overcome this challenge and achieve compatibility between these parallel modalities using synthetic image generation, in which a cycle-consistent generative adversarial network was applied to transfer the appearance of conventional H&E such that it emulates terminal H&E. These synthetic emulations allowed us to train a deep learning model for the segmentation of epithelium in terminal H&E that could be validated against the IF staining of epithelial-based cytokeratins. The combination of this segmentation model with the cycle-consistent generative adversarial network stain transfer model enabled performative epithelium segmentation in conventional H&E images. The approach demonstrates that the training of accurate segmentation models for the breadth of conventional H&E data can be executed free of human expert annotations by leveraging molecular annotation strategies such as IF, so long as the tissue impacts of the molecular annotation protocol are captured by generative models that can be deployed prior to the segmentation process.