Image Domain Research Articles

Patch-based dual-domain photon-counting CT data correction with residual-based WGAN-ViT.

X-ray photon-counting detectors (PCDs) have recently gained popularity due to their capabilities in energy discrimination power, noise suppression, and resolution refinement. The latest extremity photon-counting computed tomography (PCCT) scanner leverages these advantages for tissue characterization, material decomposition, beam hardening correction, and metal artifact reduction. However, technical challenges such as charge splitting and pulse pileup can distort the energy spectrum and compromise image quality. Also, there is a clinical need to balance radiation dose and imaging speed for contrast-enhancement and other studies. This paper aims to address these challenges by developing a dual-domain correction approach to enhance PCCT reconstruction quality quantitatively and qualitatively. We propose a novel correction method that operates in both projection and image domains. In the projection domain, we employ a residual-based Wasserstein generative adversarial network (R-WGAN) to capture local and global features, suppressing pulse pileup, charge splitting, and data noise. This is facilitated with traditional filtering methods in the image domain to enhance signal-to-noise ratio while preserving texture across each energy channel. To address GPU memory constraints, our approach utilizes a patch-based volumetric refinement network. Our dual-domain correction approach demonstrates significant fidelity improvements across both projection and image domains. Experiments on simulated and real datasets reveal that the proposed model effectively suppresses noise and preserves intricate details, outperforming the state-of-the-art methods. This approach highlights the potential of dual-domain PCCT data correction to enhance image quality for clinical applications, showing promise for advancing PCCT image fidelity and applicability in preclinical/clinical environments.

Expert consensus statement for quantitative measurement and morphologic assessment of optical coherence tomography: update 2025.

In this updated expert consensus document, the methods for the quantitative measurement and morphologic assessment of optical coherence tomography (OCT) / optical frequency domain imaging images (OFDI) are briefly summarized. The focus is on the clinical application and the clinical evidence of OCT / OFDI to guide percutaneous coronary interventions.

A Survey: Deep Fake Detection

This research addresses the pressing need for effective deep fake detection in both image domains, employing advanced deep learning methodologies. Deep fakes, which encompass the manipulation and fabrication of digital content, pose significant challenges to the authenticity and trustworthiness of media. In this study, we explore the evolving landscape of deep fake creation and the persistent challenges it presents. By leveraging state-of-the-art neural networks, natural language processing techniques, we aim to develop detection systems capable of distinguishing genuine from manipulated content. Our investigation also delves into the dynamic nature of deep fake detection, where creators continuously adapt their techniques. Staying one step ahead in this ongoing arms race is crucial for maintaining the integrity of digital content. In conclusion, this research contributes to the ongoing efforts to combat deep fake-related challenges, preserving public trust in the veracity of digital media. The development of reliable deep fake detection systems for both images is essential in an era where the line between reality and manipulation is increasingly blurred. [2].

Toward low-noise on-chip plasmonic three-dimensional biological cell imaging

Enhancing accessibility to affordable and efficient cell imaging tools has been a longstanding worldwide objective for rapid disease detection and diagnosis. We present an innovative approach to this goal, introducing a compact, portable, and user-friendly three-dimensional (3D) cell imaging platform leveraging silicon photonics and the surface plasmon coupled emission (SPCE) phenomenon. Central to our method is a specially designed slide that incorporates a fundamental SPCE structure seamlessly integrated with a silicon nitride (SiN) waveguide. We introduce a grooved array on the slide to couple light into the waveguide, interfacing with a broadband light source. This source is employed to excite fluorescently labeled cells. The excitation is achieved using edge coupling through the SiN waveguide, directing the excitation light to the specimen placed on the SPCE platform. This integrated architecture eliminates the necessity for an additional filter to extract the required light for fluorophore excitation while enabling precise excitation of labeled cells. Following the fluorophore excitation, the emitted SPCE signals are captured and subjected to analysis. We have developed an imaging algorithm based on the emitted light patterns, which we comprehensively detail through theoretical demonstration. This algorithm has the remarkable capability of achieving 3D cell imaging. This fusion of optics and computational techniques can significantly impact the domain of cell imaging by enabling the development of easily accessible and portable point-of-care (POC) imaging tools.

Artificial intelligence in four-dimensional imaging for motion management in radiation therapy

Four-dimensional imaging (4D-imaging) plays a critical role in achieving precise motion management in radiation therapy. However, challenges remain in 4D-imaging such as a long imaging time, suboptimal image quality, and inaccurate motion estimation. With the tremendous success of artificial intelligence (AI) in the image domain, particularly deep learning, there is great potential in overcoming these challenges and improving the accuracy and efficiency of 4D-imaging without the need for hardware modifications. In this review, we provide a comprehensive overview of how these AI-based methods could drive the evolution of 4D-imaging for motion management. We discuss the inherent issues associated with multiple 4D modalities and explore the current research progress of AI in 4D-imaging. Furthermore, we delve into the unresolved challenges and limitations in 4D-imaging and provide insights into the future direction of this field.

Speckle-illumination spatial frequency domain imaging with a stereo laparoscope for profile-corrected optical property mapping.

Laparoscopic surgery presents challenges in localizing oncological margins due to poor contrast between healthy and malignant tissues. Optical properties can uniquely identify various tissue types and disease states with high sensitivity and specificity, making it a promising tool for surgical guidance. Although spatial frequency domain imaging (SFDI) effectively measures quantitative optical properties, its deployment in laparoscopy is challenging due to the constrained imaging environment. Thus, there is a need for compact structured illumination techniques to enable accurate, quantitative endogenous contrast in minimally invasive surgery. We introduce a compact, two-camera laparoscope that incorporates both active stereo depth estimation and speckle-illumination SFDI (si-SFDI) to map profile-corrected, pixel-level absorption ( ), and reduced scattering ( ) optical properties in images of tissues with complex geometries. We used a multimode fiber-coupled 639-nm laser illumination to generate high-contrast speckle patterns on the object. These patterns were imaged through a modified commercial stereo laparoscope for optical property estimation via si-SFDI. Compared with the original si-SFDI work, which required images of randomized speckle patterns for accurate optical property estimations, our approach approximates the DC response using a laser speckle reducer (LSR) and consequently requires only two images. In addition, we demonstrate 3D profilometry using active stereo from low-coherence RGB laser flood illumination. Sample topography was then used to correct for measured intensity variations caused by object height and surface angle differences with respect to a calibration phantom. The low-contrast RGB speckle pattern was blurred using an LSR to approximate incoherent white light illumination. We validated profile-corrected si-SFDI against conventional SFDI in phantoms with simple and complex geometries, as well as in a human finger in vivo time-series constriction study. Laparoscopic si-SFDI optical property measurements agreed with conventional SFDI measurements when measuring flat tissue phantoms, exhibiting an error of 6.4% for absorption and 5.8% for reduced scattering. Profile-correction improved the accuracy for measurements of phantoms with complex geometries, particularly for absorption, where it reduced the error by 23.7%. An in vivo finger constriction study further validated laparoscopic si-SFDI, demonstrating an error of 8.2% for absorption and 5.8% for reduced scattering compared with conventional SFDI. Moreover, the observed trends in optical properties due to physiological changes were consistent with previous studies. Our stereo-laparoscopic implementation of si-SFDI provides a simple method to obtain accurate optical property maps through a laparoscope for flat and complex geometries. This has the potential to provide quantitative endogenous contrast for minimally invasive surgical guidance.

Deep Learning-Based Multi-View Projection Synthesis Approach for Improving the Quality of Sparse-View CBCT in Image-Guided Radiotherapy.

While radiation hazards induced by cone-beam computed tomography (CBCT) in image-guided radiotherapy (IGRT) can be reduced by sparse-view sampling, the image quality is inevitably degraded. We propose a deep learning-based multi-view projection synthesis (DLMPS) approach to improve the quality of sparse-view low-dose CBCT images. In the proposed DLMPS approach, linear interpolation was first applied to sparse-view projections and the projections were rearranged into sinograms; these sinograms were processed with a sinogram restoration model and then rearranged back into projections. The sinogram restoration model was modified from the 2D U-Net by incorporating dynamic convolutional layers and residual learning techniques. The DLMPS approach was trained, validated, and tested on CBCT data from 163, 30, and 30 real patients respectively. Sparse-view projection datasets with 1/4 and 1/8 of the original sampling rate were simulated, and the corresponding full-view projection datasets were restored via the DLMPS approach. Tomographic images were reconstructed using the Feldkamp-Davis-Kress algorithm. Quantitative metrics including root-mean-square error (RMSE), peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and feature similarity (FSIM) were calculated in both the projection and image domains to evaluate the performance of the DLMPS approach. The DLMPS approach was compared with 11 state-of-the-art (SOTA) models, including CNN and Transformer architectures. For 1/4 sparse-view reconstruction task, the proposed DLMPS approach achieved averaged RMSE, PSNR, SSIM, and FSIM values of 0.0271, 45.93 dB, 0.9817, and 0.9587 in the projection domain, and 0.000885, 37.63 dB, 0.9074, and 0.9885 in the image domain, respectively. For 1/8 sparse-view reconstruction task, the DLMPS approach achieved averaged RMSE, PSNR, SSIM, and FSIM values of 0.0304, 44.85 dB, 0.9785, and 0.9524 in the projection domain, and 0.001057, 36.05 dB, 0.8786, and 0.9774 in the image domain, respectively. The DLMPS approach outperformed all the 11 SOTA models in both the projection and image domains for 1/4 and 1/8 sparse-view reconstruction tasks. The proposed DLMPS approach effectively improves the quality of sparse-view CBCT images in IGRT by accurately synthesizing missing projections, exhibiting potential in substantially reducing imaging dose to patients with minimal loss of image quality.

Patial-frequency aware zero-centric residual unfolding network for MRI reconstruction.

Magnetic Resonance Imaging is a cornerstone of medical diagnostics, providing high-quality soft tissue contrast through non-invasive methods. However, MRI technology faces critical limitations in imaging speed and resolution. Prolonged scan times not only increase patient discomfort but also contribute to motion artifacts, further compromising image quality. Compressed Sensing (CS) theory has enabled the acquisition of partial k-space data, which can then be effectively reconstructed to recover the original image using advanced reconstruction algorithms. Recently, deep learning has been widely applied to MRI reconstruction, aiming to reduce the artifacts in the image domain caused by undersampling in k-space and enhance image quality. As deep learning continues to evolve, the undersampling factors in k-space have gradually increased in recent years. However, these layers are limited in compensating for reconstruction errors in the unsampled areas, impeding further performance improvements. To address this, we propose a learnable spatial-frequency difference-aware module that complements the learnable data consistency layer, mapping k-space domain differences to the spatial image domain for perceptual compensation. Additionally, inspired by wavelet decomposition, we introduce explicit priors by decomposing images into mean and residual components, enforcing a refined zero-mean constraint on the residuals while maintaining computational efficiency. Comparative experiments on the FastMRI and Calgary-Campinas datasets demonstrate that our method achieves superior reconstruction performance against seven state-of-the-art techniques. Ablation studies further confirm the efficacy of our model's architecture, establishing a new pathway for enhanced MRI reconstruction.

Syn2Real: synthesis of CT image ring artifacts for deep learning-based correction.

Objective.We strive to overcome the challenges posed by ring artifacts in X-ray computed tomography (CT) by developing a novel approach for generating training data for deep learning-based methods. Training such networks require large, high quality, datasets that are often generated in the data domain, time-consuming and expensive. Our objective is to develop a technique for synthesizing realistic ring artifacts directly in the image domain, enabling scalable production of training data without relying on specific imaging system physics.
Approach.We develop ''Syn2Real,'' a computationally efficient pipeline that generates realistic ring artifacts directly in the image domain. To demonstrate the effectiveness of our approach, we train two versions of UNet, vanilla and a high capacity version with self-attention layers that we call UNetpp, with ℓ2and perceptual losses, as well as a diffusion model, on energy-integrating CT images with and without these synthetic ring artifacts. 
Main Results.Despite being trained on conventional single-energy CT images, our models effectively correct ring artifacts across various monoenergetic images, at different energy levels and slice thicknesses, from a prototype photon-counting CT system. This generalizability validates the realism and versatility of our ring artifact generation process.
Significance.Ring artifacts in X-ray CT pose a unique challenge to image quality and clinical utility. By focusing on data generation, our work provides a foundation for developing more robust and adaptable ring artifact correction methods for pre-clinical, clinical and other CT applications.

Comparative image quality and dosimetric performance of two generations of dedicated breast CT systems.

Dedicated breast computed tomography (bCT) systems offer detailed imaging for breast cancer diagnosis and treatment. As new bCT generations are developed, it is important to evaluate their imaging performance and dose efficiency to understand differences over previous models. To characterize the imaging performance and dose efficiency of a second-generation (GEN2) bCT system and compare them to those of a first-generation (GEN1) system. The imaging performance was evaluated through key metrics: modulation transfer function (MTF), noise power spectrum (NPS), and detective quantum efficiency (DQE) in the projection domain. In the image domain, contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), and the visibility of calcifications were analyzed using a quality control (QC) phantom with masses and calcification clusters. Air kerma and tube output were measured and mean glandular dose (MGD) estimated for different phantom sizes for dosimetric characterization of the acquisition protocols set by the automatic exposure control (AEC). GEN2 outperformed GEN1 at higher spatial frequencies, with 57% of the MTF observed at 1cycles/mm compared to 43% for GEN1. For a 2mm diameter mass, GEN2 showed 60% higher CNR and 63% higher SNR. However, for larger masses, GEN1 outperformed GEN2, with CNR and SNR values higher by 12% to 44% and 14% to 43%, respectively. GEN2 also achieves higher DQE across the frequency spectrum, with 45% at 1 cycle/mm, compared to GEN1's 20%. Regarding calcifications in the QC phantom, the 320µm calcifications resulted in distinct full-width-at-half-maxima (FWHM±SD), with 897±58µm for GEN1 and 811±127µm for GEN2, with a p-value of 0.19. For 290µm calcifications, GEN1's FWHM was 866±129µm, while GEN2's was narrower at 665±57µm, with a p-valueof 0.01. The tube output was higher for GEN1 (45.2 mGy/mAs) compared to GEN2 (31.5 mGy/mAs). Additionally, GEN2 resulted in 8% lower MGD values compared to GEN1. While GEN1 offers better CNR and SNR for larger masses, GEN2 provides superior resolution for calcifications, better MTF, improved DQE, and lower MGD at AEC-determined settings.

Invariant discovery of features across multiple length scales: Applications in microscopy and autonomous materials characterization

Physical imaging is a foundational characterization method in areas from condensed matter physics and chemistry to astronomy and spans length scales from atomic to universe. Images encapsulate crucial data regarding atomic bonding, materials microstructures, and dynamic phenomena such as microstructural evolution and turbulence, among other phenomena. The challenge lies in effectively extracting and interpreting this information. Variational Autoencoders (VAEs) have emerged as powerful tools for identifying the underlying factors of variation in image data, providing a systematic approach to distilling meaningful patterns from complex data sets. However, a significant hurdle in their application is the definition and selection of appropriate descriptors reflecting local structures. Here, we introduce the scale-invariant VAE approach (SI-VAE) based on the progressive training of the VAE with the descriptors sampled at different length scales. The SI-VAE allows the discovery of the length scale-dependent factors of variation in the system. Here, we illustrate this approach using the ferroelectric domain images and generalize it to the movies of the electron-beam induced phenomena in graphene and topography evolution across combinatorial libraries. This approach can further be used to initialize the decision making in automated experiments including structure–property discovery and can be applied across a broad range of imaging methods. This approach is universal and can be applied to any spatially resolved data including both experimental imaging studies and simulations, and can be particularly useful for exploration of phenomena such as turbulence and scale-invariant transformation fronts.

C MAL: cascaded network-guided class-balanced multi-prototype auxiliary learning for source-free domain adaptive medical image segmentation.

Source-free domain adaptation (SFDA) has become crucial in medical image analysis, enabling the adaptation of source models across diverse datasets without labeled target domain images. Self-training, a popular SFDA approach, iteratively refines self-generated pseudo-labels using unlabeled target domain data to adapt a pre-trained model from the source domain. However, it often faces model instability due to incorrect pseudo-label accumulation and foreground-background class imbalance. This paper presents a pioneering SFDA framework, named cascaded network-guided class-balanced multi-prototype auxiliary learning (C MAL), to enhance model stability. Firstly, we introduce the cascaded translation-segmentation network (CTS-Net), which employs iterative learning between translation and segmentation networks to generate accurate pseudo-labels. The CTS-Net employs a translation network to synthesize target-like images from unreliable predictions of the initial target domain images. The synthesized results refine segmentation network training, ensuring semantic alignment and minimizing visual disparities. Subsequently, reliable pseudo-labels guide the class-balanced multi-prototype auxiliary learning network (CMAL-Net) for effective model adaptation. CMAL-Net incorporates a new multi-prototype auxiliary learning strategy with a memory network to complement source domain data. We propose a class-balanced calibration loss and multi-prototype-guided symmetry cross-entropy loss to tackle class imbalance issue and enhance model adaptability to the target domain. Extensive experiments on four benchmark fundus image datasets validate the superiority of C MAL over state-of-the-art methods, especially in scenarios with significant domain shifts. Our code is available at https://github.com/yxk-art/C2MAL .

Differences in technical and clinical perspectives on AI validation in cancer imaging: mind the gap!

Good practices in artificial intelligence (AI) model validation are key for achieving trustworthy AI. Within the cancer imaging domain, attracting the attention of clinical and technical AI enthusiasts, this work discusses current gaps in AI validation strategies, examining existing practices that are common or variable across technical groups (TGs) and clinical groups (CGs). The work is based on a set of structured questions encompassing several AI validation topics, addressed to professionals working in AI for medical imaging. A total of 49 responses were obtained and analysed to identify trends and patterns. While TGs valued transparency and traceability the most, CGs pointed out the importance of explainability. Among the topics where TGs may benefit from further exposure are stability and robustness checks, and mitigation of fairness issues. On the other hand, CGs seemed more reluctant towards synthetic data for validation and would benefit from exposure to cross-validation techniques, or segmentation metrics. Topics emerging from the open questions were utility, capability, adoption and trustworthiness. These findings on current trends in AI validation strategies may guide the creation of guidelines necessary for training the next generation of professionals working with AI in healthcare and contribute to bridging any technical-clinical gap in AI validation. RELEVANCE STATEMENT: This study recognised current gaps in understanding and applying AI validation strategies in cancer imaging and helped promote trust and adoption for interdisciplinary teams of technical and clinical researchers. KEY POINTS: Clinical and technical researchers emphasise interpretability, externalvalidation with diverse data, and biasawarenessin AI validation for cancer imaging. In cancer imaging AI research, clinical researchers prioritise explainability, whiletechnical researchers focus ontransparency and traceability, and see potential insynthetic datasets. Researchers advocate for greater homogenisation of AI validation practices in cancer imaging.

Electric Field-Induced Nonreciprocal Directional Dichroism in a Time-Reversal-Odd Antiferromagnet.

Antiferromagnets with broken time-reversal ( ) symmetry ( -odd antiferromagnets) have gained extensive attention, mainly due to their ferromagnet-like behavior despite the absence of net magnetization. However, certain types of -odd antiferromagnets remain inaccessible by the typical ferromagnet-like phenomena (e.g., anomalous Hall effect). One such system is characterized by a -odd scalar quantity, the magnetic toroidal monopole. To access the broken symmetry in such a system, a unique nonreciprocal optical phenomenon, electric field-induced nonreciprocal directional dichroism (E-induced NDD), is employed. Signals of E-induced NDD are successfully detected in a -odd antiferromagnet, Co₂SiO₄, whose magnetic structure is characterized by the magnetic toroidal monopole. Furthermore, by spatially resolving the E-induced NDD, spatial distributions of a pair of domain states related to one another by the operation are visualized. The domain imaging revealed the inversion of the domain pattern by applying a magnetic field, which is explained by trilinear coupling attributed to the piezomagnetic effect. The observation of E-induced NDD highlights unique functionalities of -odd antiferromagnets.

Unsupervised domain adaptation teacher–student network for retinal vessel segmentation via full-resolution refined model

Retinal blood vessels are the only blood vessels in the human body that can be observed non-invasively. Changes in vessel morphology are closely associated with hypertension, diabetes, cardiovascular disease and other systemic diseases, and computers can help doctors identify these changes by automatically segmenting blood vessels in fundus images. If we train a highly accurate segmentation model on one dataset (source domain) and apply it to another dataset (target domain) with a different data distribution, the segmentation accuracy will drop sharply, which is called the domain shift problem. This paper proposes a novel unsupervised domain adaptation method to address this problem. It uses a teacher–student framework to generate pseudo labels for the target domain image, and trains the student network with a combination of source domain loss and domain adaptation loss; finally, the weights of the teacher network are updated from the exponential moving average of the student network and used for the target domain segmentation. We reconstructed the encoder and decoder of the network into a full-resolution refined model by computing the training loss at multiple semantic levels and multiple label resolutions. We validated our method on two publicly available datasets DRIVE and STARE. From STARE to DRIVE, the accuracy, sensitivity, and specificity are 0.9633, 0.8616,and 0.9733, respectively. From DRIVE to STARE, the accuracy, sensitivity, and specificity are 0.9687, 0.8470, and 0.9785, respectively. Our method outperforms most state-of-the-art unsupervised methods. Compared with domain adaptation methods, our method also has the best F1 score (0.8053) from STARE to DRIVE and a competitive F1 score (0.8001) from DRIVE to STARE.

Hepatocellular Carcinoma: Imaging Advances in 2024 with a Focus on Magnetic Resonance Imaging.

The EASL diagnostic algorithm for hepatocellular carcinoma, currently in use, dates back to 2018. While awaiting its update, numerous advancements have emerged in the field of hepatocellular carcinoma imaging. These innovations impact every step of the diagnostic algorithm, from surveillance protocols to diagnostic processes, encompassing aspects preceding a patient's inclusion in surveillance programs as well as the potential applications of imaging after the hepatocellular carcinoma diagnosis. Notably, these diagnostic advancements are particularly evident in the domain of magnetic resonance imaging. For example, the sensitivity of ultrasound in diagnosing very early-stage and early-stage hepatocellular carcinoma during the surveillance phase is very low (less than 50%) and a potential improvement in this sensitivity value could be achieved by using abbreviated protocols in magnetic resonance imaging. The aim of this review is to explore the 2024 updates in magnetic resonance imaging for hepatocellular carcinoma, with a focus on its role in surveillance, nodular size assessment, post-diagnosis imaging applications, and its potential role before the initiation of surveillance.

Fluorescence Lifetime Endoscopy with a Nanosecond Time-Gated CAPS Camera with IRF-Free Deep Learning Method.

Fluorescence imaging has been widely used in fields like (pre)clinical imaging and other domains. With advancements in imaging technology and new fluorescent labels, fluorescence lifetime imaging is gradually gaining recognition. Our research department is developing the tauCAMTM, based on the Current-Assisted Photonic Sampler, to achieve real-time fluorescence lifetime imaging in the NIR (700-900 nm) region. Incorporating fluorescence lifetime into endoscopy could further improve the differentiation of malignant and benign cells based on their distinct lifetimes. In this work, the capabilities of an endoscopic lifetime imaging system are demonstrated using a rigid endoscope involving various phantoms and an IRF-free deep learning-based method with only 6-time points. The results show that this application's fluorescence lifetime image has better lifetime uniformity and precision with 6-time points than the conventional methods.

Iatrogenic aorto-coronary dissection triggered by contrast injection during coronary evaluation with optical frequency domain imaging.

Iatrogenic aorto-coronary dissection triggered by contrast injection during coronary evaluation with optical frequency domain imaging.

Deep learning-based image domain reconstruction enhances image quality and pulmonary nodule detection in ultralow-dose CT with adaptive statistical iterative reconstruction-V.

To evaluate the image quality and lung nodule detectability of ultralow-dose CT (ULDCT) with adaptive statistical iterative reconstruction-V (ASiR-V) post-processed using a deep learning image reconstruction (DLIR)-based image domain compared to low-dose CT (LDCT) and ULDCT without DLIR. A total of 210 patients undergoing lung cancer screening underwent LDCT (mean ± SD, 0.81 ± 0.28 mSv) and ULDCT (0.17 ± 0.03 mSv) scans. ULDCT images were reconstructed with ASiR-V (ULDCT-ASiR-V) and post-processed using DLIR (ULDCT-DLIR). The quality of the three CT images was analyzed. Three radiologists detected and measured pulmonary nodules on all CT images, with LDCT results serving as references. Nodule conspicuity was assessed using a five-point Likert scale, followed by further statistical analyses. A total of 463 nodules were detected using LDCT. The image noise of ULDCT-DLIR decreased by 60% compared to that of ULDCT-ASiR-V and was lower than that of LDCT (p < 0.001). The subjective image quality scores for ULDCT-DLIR (4.4 [4.1, 4.6]) were also higher than those for ULDCT-ASiR-V (3.6 [3.1, 3.9]) (p < 0.001). The overall nodule detection rates for ULDCT-ASiR-V and ULDCT-DLIR were 82.1% (380/463) and 87.0% (403/463), respectively (p < 0.001). The percentage difference between diameters > 1 mm was 2.9% (ULDCT-ASiR-V vs. LDCT) and 0.5% (ULDCT-DLIR vs. LDCT) (p = 0.009). Scores of nodule imaging sharpness on ULDCT-DLIR (4.0 ± 0.68) were significantly higher than those on ULDCT-ASiR-V (3.2 ± 0.50) (p < 0.001). DLIR-based image domain improves image quality, nodule detection rate, nodule imaging sharpness, and nodule measurement accuracy of ASiR-V on ULDCT. Question Deep learning post-processing is simple and cheap compared with raw data processing, but its performance is not clear on ultralow-dose CT. Findings Deep learning post-processing enhanced image quality and improved the nodule detection rate and accuracy of nodule measurement of ultralow-dose CT. Clinical relevance Deep learning post-processing improves the practicability of ultralow-dose CT and makes it possible for patients with less radiation exposure during lung cancer screening.

Unraveling the Invisible: Topological Data Analysis as the New Frontier in Radiology's Diagnostic Arsenal.

This commentary examines Topological Data Analysis (TDA) in radiology imaging, highlighting its revolutionary potential in medical image interpretation. TDA, which is grounded in mathematical topology, provides novel insights into complex, high-dimensional radiological data through persistent homology and topological features. We explore TDA's applications across medical imaging domains, including tumor characterization, cardiovascular imaging, and COVID-19 detection, where it demonstrates 15-20% improvements over traditional methods. The synergy between TDA and artificial intelligence presents promising opportunities for enhanced diagnostic accuracy. While implementation challenges exist, TDA's ability to uncover hidden patterns positions it as a transformative tool in modern radiology.