The use of deep learning towards dose optimization in low-dose computed tomography: A scoping review

Artificial intelligence in medical imaging education: Recommendations for undergraduate curriculum development

OBJECTIVES

Artificial intelligence (AI) is rapidly being integrated into medical imaging practice, prompting calls to enhance AI education in undergraduate radiography programs. Combining evidence from literature, practitioner insights, and industry perspectives, this paper provides recommendations for medical imaging undergraduate education, including curriculum revision and re-alignment.

KEY FINDINGS

A proposed modular framework is outlined to assist course providers in integrating AI into university programs. An example course design includes modules on data science fundamentals, machine learning, AI ethics and patient safety, governance and regulation, AI tool evaluation, and clinical applications. A proposal to embed these longitudinally in the curriculum combined with hands-on experience and work-integrated learning will help develop the necessary knowledge of AI and its real-world impacts. Authentic assessment examples reinforce learning, such as critically appraising published research and reflecting on current technologies. Maintenance of an up-to-date curriculum will require a collaborative, multidisciplinary approach involving educators, clinicians, and industry professionals.

CONCLUSION

Integrating AI education into undergraduate medical imaging programs equips future radiographers in an evolving technological landscape. A strategic approach to embedding AI modules throughout degree programs assures students a comprehensive understanding of AI principles, skills in utilising AI tools effectively, and the ability to critically evaluate their implications.

IMPLICATIONS FOR PRACTICE

The practical implementation of undergraduate AI education will prepare radiographers to incorporate these technologies while assuring patient care.

Machine learning-enhanced noninvasive prenatal testing of monogenic disorders

OBJECTIVE

Single-nucleotide variants (SNVs) are of great significance in prenatal diagnosis as they are the leading cause of inherited single-gene disorders (SGDs). Identifying SNVs in a non-invasive prenatal screening (NIPS) scenario is particularly challenging for maternally inherited SNVs. We present an improved method to predict inherited SNVs from maternal or paternal origin in a genome-wide manner.

METHODS

We performed SNV-NIPS based on the combination of fragments of cell free DNA (cfDNA) features, Bayesian inference and a machine-learning (ML) prediction refinement step using random forest (RF) classifiers trained on millions of non-pathogenic variants. We next evaluate the real-world performance of our refined method in a clinical setting by testing our models on 16 families with singleton pregnancies and varying fetal fraction (FF) levels, and validate the results over millions of inherited variants in each fetus.

RESULTS

The average area under the ROC curve (AUC) values are 0.996 over all families for paternally inherited variants, 0.81 for the challenging maternally inherited variants, 0.86 for homozygous biallelic variants and 0.95 for compound heterozygous variants. Discriminative AUCs were achieved even in families with a low FF. We further investigate the performance of our method in correctly predicting SNVs in coding regions of clinically relevant genes and demonstrate significantly improved AUCs in these regions. Finally, we focus on the pathogenic variants in our cohort and show that our method correctly predicts if the fetus is unaffected or affected in all (10/10, 100%) of the families containing a pathogenic SNV.

CONCLUSIONS

Overall, we demonstrate our ability to perform genome-wide NIPS for maternal and homozygous biallelic variants and showcase the utility of our method in a clinical setting.

A Review of deep learning methods for denoising of medical low-dose CT images

To prevent patients from being exposed to excess of radiation in CT imaging, the most common solution is to decrease the radiation dose by reducing the X-ray, and thus the quality of the resulting low-dose CT images (LDCT) is degraded, as evidenced by more noise and streaking artifacts. Therefore, it is important to maintain high quality CT image while effectively reducing radiation dose. In recent years, with the rapid development of deep learning technology, deep learning-based LDCT denoising methods have become quite popular because of their data-driven and high-performance features to achieve excellent denoising results. However, to our knowledge, no relevant article has so far comprehensively introduced and reviewed advanced deep learning denoising methods such as Transformer structures in LDCT denoising tasks. Therefore, based on the literatures related to LDCT image denoising published from year 2016-2023, and in particular from 2020 to 2023, this study presents a systematic survey of current situation, and challenges and future research directions in LDCT image denoising field. Four types of denoising networks are classified according to the network structure: CNN-based, Encoder-Decoder-based, GAN-based, and Transformer-based denoising networks, and each type of denoising network is described and summarized from the perspectives of structural features and denoising performances. Representative deep-learning denoising methods for LDCT are experimentally compared and analyzed. The study results show that CNN-based denoising methods capture image details efficiently through multi-level convolution operation, demonstrating superior denoising effects and adaptivity. Encoder-decoder networks with MSE loss, achieve outstanding results in objective metrics. GANs based methods, employing innovative generators and discriminators, obtain denoised images that exhibit perceptually a closeness to NDCT. Transformer-based methods have potential for improving denoising performances due to their powerful capability in capturing global information. Challenges and opportunities for deep learning based LDCT denoising are analyzed, and future directions are also presented.

Systematic Review on Learning-based Spectral CT

Spectral computed tomography (CT) has recently emerged as an advanced version of medical CT and significantly improves conventional (single-energy) CT. Spectral CT has two main forms: dual-energy computed tomography (DECT) and photon-counting computed tomography (PCCT), which offer image improvement, material decomposition, and feature quantification relative to conventional CT. However, the inherent challenges of spectral CT, evidenced by data and image artifacts, remain a bottleneck for clinical applications. To address these problems, machine learning techniques have been widely applied to spectral CT. In this review, we present the state-of-the-art data-driven techniques for spectral CT.

Synergizing photon-counting CT with deep learning: potential enhancements in medical imaging

This review article highlights the potential of integrating photon-counting computed tomography (CT) and deep learning algorithms in medical imaging to enhance diagnostic accuracy, improve image quality, and reduce radiation exposure. The use of photon-counting CT provides superior image quality, reduced radiation dose, and material decomposition capabilities, while deep learning algorithms excel in automating image analysis and improving diagnostic accuracy. The integration of these technologies can lead to enhanced material decomposition and classification, spectral image analysis, predictive modeling for individualized medicine, workflow optimization, and radiation dose management. However, data requirements, computational resources, and regulatory and ethical concerns remain challenges that need to be addressed to fully realize the potential of this technology. The fusion of photon-counting CT and deep learning algorithms is poised to revolutionize medical imaging and transform patient care.

CT image denoising methods for image quality improvement and radiation dose reduction

With the ever-increasing use of computed tomography (CT), concerns about its radiation dose have become a significant public issue. To address the need for radiation dose reduction, CT denoising methods have been widely investigated and applied in low-dose CT images. Numerous noise reduction algorithms have emerged, such as iterative reconstruction and most recently, deep learning (DL)-based approaches. Given the rapid advancements in Artificial Intelligence techniques, we recognize the need for a comprehensive review that emphasizes the most recently developed methods. Hence, we have performed a thorough analysis of existing literature to provide such a review. Beyond directly comparing the performance, we focus on pivotal aspects, including model training, validation, testing, generalizability, vulnerability, and evaluation methods. This review is expected to raise awareness of the various facets involved in CT image denoising and the specific challenges in developing DL-based models.

Ultra-low dose CT scanning for PET/CT

BACKGROUND

The use of computed tomography (CT) for attenuation correction (AC) in whole-body PET/CT can result in a significant contribution to radiation exposure. This can become a limiting factor for reducing considerably the overall radiation exposure of the patient when using the new long axial field of view (LAFOV) PET scanners. However, recent CT technology have introduced features such as the tin (Sn) filter, which can substantially reduce the CT radiation dose.

PURPOSE

The purpose of this study was to investigate the ultra-low dose CT for attenuation correction using the Sn filter together with other dose reduction options such as tube current (mAs) reduction. We explore the impact of dose reduction in the context of AC-CT and how it affects PET image quality.

METHODS

The study evaluated a range of ultra-low dose CT protocols using five physical phantoms that represented a broad collection of tissue electron densities. A long axial field of view (LAFOV) PET/CT scanner was used to scan all phantoms, applying various CT dose reduction parameters such as reducing tube current (mAs), increasing the pitch value, and applying the Sn filter. The effective dose resulting from the CT scans was determined using the CTDIVol reported by the scanner. Several voxel-based and volumes of interest (VOI)-based comparisons were performed to compare the ultra-low dose CT images, the generated attenuation maps, and corresponding PET images against those images acquired with the standard low dose CT protocol. Finally, two patient datasets were acquired using one of the suggested ultra-low dose CT settings.

RESULTS

By incorporating the Sn filter and adjusting mAs to the lowest available value, the radiation dose in CT images of PBU-60 phantom was significantly reduced; resulting in an effective dose of nearly 2% compared to the routine low dose CT protocols currently in clinical use. The assessment of PET images using VOI and voxel-based comparisons indicated relative differences (RD%) of under 6% for mean activity concentration (AC) in the torso phantom and patient dataset and under 8% for a source point in the CIRS phantom. The maximum RD% value of AC was 14% for the point source in the CIRS phantom. Increasing the tube current from 6 mAs to 30 mAs in patients with high BMI, or with arms down, can suppress the photon starvation artifact, whilst still preserving a dose reduction of 90%.

CONCLUSIONS

Introducing a Sn filter in CT imaging lowers radiation dose by more than 90%. This reduction has minimal effect on PET image quantification at least for patients without Body Mass Index (BMI) higher than 30. Notably, this study results need validation using a larger clinical PET/CT dataset in the future, including patients with higher BMI.

Photon-Counting Detector CT With Denoising for Imaging of the Osseous Pelvis at Low Radiation Doses: A Phantom Study

BACKGROUND. Photon-counting detector (PCD) CT may allow lower radiation doses than used for conventional energy-integrating detector (EID) CT, with preserved image quality. OBJECTIVE. The purpose of this study was to compare PCD CT and EID CT, reconstructed with and without a denoising tool, in terms of image quality of the osseous pelvis in a phantom, with attention to low radiation doses. METHODS. A pelvic phantom comprising human bones in acrylic material mimicking soft tissue underwent PCD CT and EID CT at various tube potentials and radiation doses ranging from 0.05 to 5.00 mGy. Additional denoised reconstructions were generated using a commercial tool. Noise was measured in the acrylic material. Two readers performed independent qualitative assessments that entailed determining the denoised EID CT reconstruction with the lowest acceptable dose and then comparing this reference reconstruction with PCD CT reconstructions without and with denoising, using subjective Likert scales. RESULTS. Noise was lower for PCD CT than for EID CT. For instance, at 0.05 mGy and 100 kV with tin filter, noise was 38.4 HU for PCD CT versus 48.8 HU for EID CT. Denoising further reduced noise; for example, for PCD CT at 100 kV with tin filter at 0.25 mGy, noise was 19.9 HU without denoising versus 9.7 HU with denoising. For both readers, lowest acceptable dose for EID CT was 0.10 mGy (total score, 11 of 15 for both readers). Both readers somewhat agreed that PCD CT without denoising at 0.10 mGy (reflecting reference reconstruction dose) was relatively better than the reference reconstruction in terms of osseous structures, artifacts, and image quality. Both readers also somewhat agreed that denoised PCD CT reconstructions at 0.10 mGy and 0.05 mGy (reflecting matched and lower doses, respectively, with respect to reference reconstruction dose) were relatively better than the reference reconstruction for the image quality measures. CONCLUSION. PCD CT showed better-quality images than EID CT when performed at the lowest acceptable radiation dose for EID CT. PCD CT with denoising yielded better-quality images at a dose lower than lowest acceptable dose for EID CT. CLINICAL IMPACT. PCD CT with denoising could facilitate lower radiation doses for pelvic imaging.

Self-supervised deep learning for joint 3D low-dose PET/CT image denoising

Deep learning (DL)-based denoising of low-dose positron emission tomography (LDPET) and low-dose computed tomography (LDCT) has been widely explored. However, previous methods have focused only on single modality denoising, neglecting the possibility of simultaneously denoising LDPET and LDCT using only one neural network, i.e., joint LDPET/LDCT denoising. Moreover, DL-based denoising methods generally require plenty of well-aligned LD-normal-dose (LD-ND) sample pairs, which can be difficult to obtain. To this end, we propose a self-supervised two-stage training framework named MAsk-then-Cycle (MAC), to achieve self-supervised joint LDPET/LDCT denoising. The first stage of MAC is masked autoencoder (MAE)-based pre-training and the second stage is self-supervised denoising training. Specifically, we propose a self-supervised denoising strategy named cycle self-recombination (CSR), which enables denoising without well-aligned sample pairs. Unlike other methods that treat noise as a homogeneous whole, CSR disentangles noise into signal-dependent and independent noises. This is more in line with the actual imaging process and allows for flexible recombination of noises and signals to generate new samples. These new samples contain implicit constraints that can improve the network's denoising ability. Based on these constraints, we design multiple loss functions to enable self-supervised training. Then we design a CSR-based denoising network to achieve joint 3D LDPET/LDCT denoising. Existing self-supervised methods generally lack pixel-level constraints on networks, which can easily lead to additional artifacts. Before denoising training, we perform MAE-based pre-training to indirectly impose pixel-level constraints on networks. Experiments on an LDPET/LDCT dataset demonstrate its superiority over existing methods. Our method is the first self-supervised joint LDPET/LDCT denoising method. It does not require any prior assumptions and is therefore more robust.

Dose reduction and image enhancement in micro-CT using deep learning

BACKGROUND

In preclinical settings, micro-computed tomography (CT) provides a powerful tool to acquire high resolution anatomical images of rodents and offers the advantage to in vivo non-invasively assess disease progression and therapy efficacy. Much higher resolutions are needed to achieve scale-equivalent discriminatory capabilities in rodents as those in humans. High resolution imaging however comes at the expense of increased scan times and higher doses. Specifically, with preclinical longitudinal imaging, there are concerns that dose accumulation may affect experimental outcomes of animal models.

PURPOSE

Dose reduction efforts under the ALARA (as low as reasonably achievable) principles are thus a key point of attention. However, low dose CT acquisitions inherently induce higher noise levels which deteriorate image quality and negatively impact diagnostic performance. Many denoising techniques already exist, and deep learning (DL) has become increasingly popular for image denoising, but research has mostly focused on clinical CT with limited studies conducted on preclinical CT imaging. We investigate the potential of convolutional neural networks (CNN) for restoring high quality micro-CT images from low dose (noisy) images. The novelty of the CNN denoising frameworks presented in this work consists of utilizing image pairs with realistic CT noise present in the input as well as the target image used for the model training; a noisier image acquired with a low dose protocol is matched to a less noisy image acquired with a higher dose scan of the same mouse.

METHODS

Low and high dose ex vivo micro-CT scans of 38 mice were acquired. Two CNN models, based on a 2D and 3D four-layer U-Net, were trained with mean absolute error (30 training, 4 validation and 4 test sets). To assess denoising performance, ex vivo mice and phantom data were used. Both CNN approaches were compared to existing methods, like spatial filtering (Gaussian, Median, Wiener) and iterative total variation image reconstruction algorithm. Image quality metrics were derived from the phantom images. A first observer study (n = 23) was set-up to rank overall quality of differently denoised images. A second observer study (n = 18) estimated the dose reduction factor of the investigated 2D CNN method.

RESULTS

Visual and quantitative results show that both CNN algorithms exhibit superior performance in terms of noise suppression, structural preservation and contrast enhancement over comparator methods. The quality scoring by 23 medical imaging experts also indicates that the investigated 2D CNN approach is consistently evaluated as the best performing denoising method. Results from the second observer study and quantitative measurements suggest that CNN-based denoising could offer a 2-4× dose reduction, with an estimated dose reduction factor of about 3.2 for the considered 2D network.

CONCLUSIONS

Our results demonstrate the potential of DL in micro-CT for higher quality imaging at low dose acquisition settings. In the context of preclinical research, this offers promising future prospects for managing the cumulative severity effects of radiation in longitudinal studies.

Investigating the Feasibility of Using DenseNet to Improve Coronary Calcification Detection in CT

OBJECTIVES

Interscan reproducibility of coronary artery calcium (CAC) scoring can be improved by using a smaller slice thickness but at the cost of higher image noise. This study aimed to investigate the feasibility of using densely connected convolutional network (DenseNet) to reduce the image noise in CAC scans reconstructed with slice thickness < 3 mm for improving coronary calcification detection in CT.

METHODS

Phantom data acquired with QRM and CIRS phantoms were used for model training and testing, where the DenseNet model adopted in this work was a convolutional neural network (CNN) designed for super resolution recovery. After phantom study, the proposed method was evaluated in terms of its ability to improve calcification detection using patient data. The CNN input images (IMGinput) were CAC scans reconstructed with 0.5-, 1.0- and 1.5-mm slice thickness, while CNN label images were CAC scans reconstructed with 3-mm slice thickness (IMG3mm). Region of interest (ROI) analysis was carried out on IMG3mm, IMGinput and CNN output images (IMGoutput). Two-sample t test was used to compare the difference in Hounsfield Unit (HU) values within ROI between IMG3mm and IMGoutput.

RESULTS

For the calcifications in QRM phantoms, no statistically significant difference was found when comparing the HU values of 400- and 800-HA calcifications identified on IMG3mm to those on IMGoutput with slice thickness of 0.5, 1.0 or 1.5 mm. On the other hand, statistically significant difference was found when comparing the HU values of 200-HA calcifications identified on IMG3mm to those on IMGoutput with a slice thickness of 0.5 and 1.0 mm. Meanwhile, no statistically significant difference was found when comparing the HU values of 200-HA calcifications identified on IMG3mm to those on IMGoutput with a slice thickness of 1.5 mm. As for the rod inserts in CIRS phantoms simulating 9 different tissue types in human body, there was no statistically significant difference between IMG3mm and IMGoutput with slice thickness of 1.5 mm, and all the p values were larger than 0.10. With regards to patient study, more calcification pixels were detected on IMGoutput with a slice thickness of 1.5 mm than on IMG3mm, so calcifications were more clear on the denoised images.

CONCLUSION

According to our results, the CNN-based denoising method could reduce statistical noise in IMGinput with a slice thickness of 1.5 mm without causing significant texture change or variation in HU values. The proposed method could improve cardiovascular risk prediction by detecting small and soft calcifications that are barely identified on 3-mm slice images used in conventional CAC scans.

Necrotizing Pneumonia in Children: Early Recognition and Management

Necrotizing pneumonia (NP) is an uncommon complicated pneumonia with an increasing incidence. Early recognition and timely management can bring excellent outcomes. The diagnosis of NP depends on chest computed tomography, which has radiation damage and may miss the optimal treatment time. The present review aimed to elaborate on the reported predictors for NP. The possible pathogenesis of Streptococcus pneumoniae, Staphylococcus aureus, Mycoplasma pneumoniae and coinfection, clinical manifestations and management were also discussed. Although there is still a long way for these predictors to be used in clinical, it is necessary to investigate early predictors for NP in children.

Transfer learning framework for low-dose CT reconstruction based on marginal distribution adaptation in multiscale

BACKGROUND

With the increasing use of computed tomography (CT) in clinical practice, limiting CT radiation exposure to reduce potential cancer risks has become one of the important directions of medical imaging research. As the dose decreases, the reconstructed CT image will be severely degraded by projection noise.

PURPOSE

As an important method of image processing, supervised deep learning has been widely used in the restoration of low-dose CT (LDCT) in recent years. However, the normal-dose CT (NDCT) corresponding to a specific LDCT (it is regarded as the label of the LDCT, which is necessary for supervised learning) is very difficult to obtain so that the application of supervised learning methods in LDCT reconstruction is limited. It is necessary to construct a unsupervised deep learning framework for LDCT reconstruction that does not depend on paired LDCT-NDCT datasets.

METHODS

We presented an unsupervised learning framework for the transferring from the identity mapping to the low-dose reconstruction task, called marginal distribution adaptation in multiscale (MDAM). For NDCTs as source domain data, MDAM is an identity map with two parts: firstly, it establishes a dimensionality reduction mapping, which can obtain the same feature distribution from NDCTs and LDCTs; and then NDCTs is retrieved by reconstructing the image overview and details from the low-dimensional features. For the purpose of the feature transfer between source domain and target domain (LDCTs), we introduce the multiscale feature extraction in the MDAM, and then eliminate differences in probability distributions of these multiscale features between NDCTs and LDCTs through wavelet decomposition and domain adaptation learning.

RESULTS

Image quality evaluation metrics and subjective quality scores show that, as an unsupervised method, the performance of the MDAM approaches or even surpasses some state-of-the-art supervised methods. Especially, MDAM has been favorably evaluated in terms of noise suppression, structural preservation, and lesion detection.

CONCLUSIONS

We demonstrated that, the MDAM framework can reconstruct corresponding NDCTs from LDCTs with high accuracy, and without relying on any labeles. Moreover, it is more suitable for clinical application compared with supervised learning methods.

Artificial Intelligence Advances in the World of Cardiovascular Imaging

The tremendous advances in digital information and communication technology have entered everything from our daily lives to the most intricate aspects of medical and surgical care. These advances are seen in electronic and mobile health and allow many new applications to further improve and make the diagnoses of patient diseases and conditions more precise. In the area of digital radiology with respect to diagnostics, the use of advanced imaging tools and techniques is now at the center of evaluation and treatment. Digital acquisition and analysis are central to diagnostic capabilities, especially in the field of cardiovascular imaging. Furthermore, the introduction of artificial intelligence (AI) into the world of digital cardiovascular imaging greatly broadens the capabilities of the field both with respect to advancement as well as with respect to complete and accurate diagnosis of cardiovascular conditions. The application of AI in recognition, diagnostics, protocol automation, and quality control for the analysis of cardiovascular imaging modalities such as echocardiography, nuclear cardiac imaging, cardiovascular computed tomography, cardiovascular magnetic resonance imaging, and other imaging, is a major advance that is improving rapidly and continuously. We document the innovations in the field of cardiovascular imaging that have been brought about by the acceptance and implementation of AI in relation to healthcare professionals and patients in the cardiovascular field.