Influence of deep learning image reconstruction algorithm for reducing radiation dose and image noise compared to iterative reconstruction and filtered back projection for head and chest computed tomography examinations: a systematic review.

Background: The most recent advances in Computed Tomography (CT) image reconstruction technology are Deep learning image reconstruction (DLIR) algorithms. Due to drawbacks in Iterative reconstruction (IR) techniques such as negative image texture and nonlinear spatial resolutions, DLIRs are gradually replacing them. However, the potential use of DLIR in Head and Chest CT has to be examined further. Hence, the purpose of the study is to review the influence of DLIR on Radiation dose (RD), Image noise (IN), and outcomes of the studies compared with IR and FBP in Head and Chest CT examinations. Methods: We performed a detailed search in PubMed, Scopus, Web of Science, Cochrane Library, and Embase to find the articles reported using DLIR for Head and Chest CT examinations between 2017 to 2023. Data were retrieved from the short-listed studies using Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) guidelines. Results: Out of 196 articles searched, 15 articles were included. A total of 1292 sample size was included. 14 articles were rated as high and 1 article as moderate quality. All studies compared DLIR to IR techniques. 5 studies compared DLIR with IR and FBP. The review showed that DLIR improved IQ, and reduced RD and IN for CT Head and Chest examinations. Conclusions: DLIR algorithm have demonstrated a noted enhancement in IQ with reduced IN for CT Head and Chest examinations at lower dose compared with IR and FBP. DLIR showed potential for enhancing patient care by reducing radiation risks and increasing diagnostic accuracy.

CNN application for automated determination of the patient's size to obtain the size-specific dose estimated in CT.

Introduction. The currently available dosimetry techniques in computed tomography can be inaccurate which overestimate the absorbed dose. Therefore, we aimed to provide an automated and fast methodology to more accurately calculate the SSDE usingDwobtained by using CNN from thorax and abdominal CT study images.Methods. The SSDE was determined from the 200 records files. For that purpose, patients' size was measured in two ways: (a) by developing an algorithm following the AAPM Report No. 204 methodology; and (b) using a CNN according to AAPM Report No. 220.Results. The patient's size measured by the in-house software in the region of thorax and abdomen was 27.63 ± 3.23 cm and 28.66 ± 3.37 cm, while CNN was 18.90 ± 2.6 cm and 21.77 ± 2.45 cm. The SSDE in thorax according to 204 and 220 reports were 17.26 ± 2.81 mGy and 23.70 ± 2.96 mGy for women and 17.08 ± 2.09 mGy and 23.47 ± 2.34 mGy for men. In abdomen was 18.54 ± 2.25 mGy and 23.40 ± 1.88 mGy in women and 18.37 ± 2.31 mGy and 23.84 ± 2.36 mGy in men.Conclusions. Implementing CNN-based automated methodologies can contribute to fast and accurate dose calculations, thereby improving patient-specific radiation safety in clinical practice.

Optimized scoring of end-to-end dosimetry audits for passive motion management - A simulation study using the IROC thorax phantom.

Dosimetry audits for passive motion management require dynamically-acquired measurements in a moving phantom to be compared to statically calculated planned doses. This study aimed to characterise the relationship between planning and delivery errors, and the measured dose in the Imaging and Radiation Oncology Core (IROC) thorax phantom, to assess different audit scoring approaches. Treatment plans were created using a 4DCT scan of the IROC phantom, equipped with film and thermoluminescent dosimeters (TLDs). Plans were created on the average intensity projection from all bins. Three levels of aperture complexity were explored: dynamic conformal arcs (DCAT), low-, and high-complexity volumetric modulated arcs (VMATLo, VMATHi). Simulated-measured doses were generated by modelling motion using isocenter shifts. Various errors were introduced including incorrect setup position and target delineation. Simulated-measured film doses were scored using gamma analysis and compared within specific regions of interest (ROIs) as well as the entire film plane. Positional offsets were estimated based on isodoses on the film planes, and point doses within TLD contours were compared. Motion-induced differences between planned and simulated-measured doses were evident even without introduced errors Gamma passing rates within target-centred ROIs correlated well with error-induced dose differences, while whole film passing rates did not. Isodose-based setup position measurements demonstrated high sensitivity to errors. Simulated point doses at TLD locations yielded erratic responses to introduced errors. ROI gamma analysis demonstrated enhanced sensitivity to simulated errors compared to whole film analysis. Gamma results may be further contextualized by other metrics such as setup position or maximum gamma.

BM-BronchoLC - A rich bronchoscopy dataset for anatomical landmarks and lung cancer lesion recognition.

Flexible bronchoscopy has revolutionized respiratory disease diagnosis. It offers direct visualization and detection of airway abnormalities, including lung cancer lesions. Accurate identification of airway lesions during flexible bronchoscopy plays an important role in the lung cancer diagnosis. The application of artificial intelligence (AI) aims to support physicians in recognizing anatomical landmarks and lung cancer lesions within bronchoscopic imagery. This work described the development of BM-BronchoLC, a rich bronchoscopy dataset encompassing 106 lung cancer and 102 non-lung cancer patients. The dataset incorporates detailed localization and categorical annotations for both anatomical landmarks and lesions, meticulously conducted by senior doctors at Bach Mai Hospital, Vietnam. To assess the dataset's quality, we evaluate two prevalent AI backbone models, namely UNet++ and ESFPNet, on the image segmentation and classification tasks with single-task and multi-task learning paradigms. We present BM-BronchoLC as a reference dataset in developing AI models to assist diagnostic accuracy for anatomical landmarks and lung cancer lesions in bronchoscopy data.

Generalizable disease detection using model ensemble on chest X-ray images.

In the realm of healthcare, the demand for swift and precise diagnostic tools has been steadily increasing. This study delves into a comprehensive performance analysis of three pre-trained convolutional neural network (CNN) architectures: ResNet50, DenseNet121, and Inception-ResNet-v2. To ensure the broad applicability of our approach, we curated a large-scale dataset comprising a diverse collection of chest X-ray images, that included both positive and negative cases of COVID-19. The models' performance was evaluated using separate datasets for internal validation (from the same source as the training images) and external validation (from different sources). Our examination uncovered a significant drop in network efficacy, registering a 10.66% reduction for ResNet50, a 36.33% decline for DenseNet121, and a 19.55% decrease for Inception-ResNet-v2 in terms of accuracy. Best results were obtained with DenseNet121 achieving the highest accuracy at 96.71% in internal validation and Inception-ResNet-v2 attaining 76.70% accuracy in external validation. Furthermore, we introduced a model ensemble approach aimed at improving network performance when making inferences on images from diverse sources beyond their training data. The proposed method uses uncertainty-based weighting by calculating the entropy in order to assign appropriate weights to the outputs of each network. Our results showcase the effectiveness of the ensemble method in enhancing accuracy up to 97.38% for internal validation and 81.18% for external validation, while maintaining a balanced ability to detect both positive and negative cases.

Hierarchical medical image report adversarial generation with hybrid discriminator.

BACKGROUND AND OBJECTIVES: Generating coherent reports from medical images is an important task for reducing doctors' workload. Unlike traditional image captioning tasks, the task of medical image report generation faces more challenges. Current models for generating reports from medical images often fail to characterize some abnormal findings, and some models generate reports with low quality. In this study, we propose a model to generate high-quality reports from medical images. METHODS: In this paper, we propose a model called Hybrid Discriminator Generative Adversarial Network (HDGAN), which combines Generative Adversarial Network (GAN) with Reinforcement Learning (RL). The HDGAN model consists of a generator, a one-sentence discriminator, and a one-word discriminator. Specifically, the RL reward signals are judged on the one-sentence discriminator and one-word discriminator separately. The one-sentence discriminator can better learn sentence-level structural information, while the one-word discriminator can learn word diversity information effectively. RESULTS: Our approach performs better on the IU-X-ray and COV-CTR datasets than the baseline models. For the ROUGE metric, our method outperforms the state-of-the-art model by 0.36 on the IU-X-ray, 0.06 on the MIMIC-CXR and 0.156 on the COV-CTR. CONCLUSIONS: The compositional framework we proposed can generate more accurate medical image reports at different levels.

Segmentation of Thoracic Organs through Distributed Extraction of Visual Feature Patterns Utilizing Resio-Inception U-Net and Deep Cluster Recognition Techniques.

BACKGROUND: Segmentation of medical images plays a key role in the correct identification and management of different diseases. In this study, we present a new segmentation method that meets the difficulties posed by sophisticated organ shapes in computed tomography (CT) images, particularly targeting lung, breast, and gastric cancers. METHODS: Our suggested methods, Resio-Inception U-Net and Deep Cluster Recognition (RIUDCR), use a Residual Inception Architecture, which combines the power of residual connections and inception blocks to achieve cutting-edge segmentation performance while reducing the risk of overfitting. RESULTS: We present mathematical equations and functions that describe the design, including the encoding and decoding steps within the UC-Net system. Furthermore, we provide strong testing results that show the effectiveness of our method. Through thorough testing on varied datasets, our method regularly beats current techniques, achieving amazing precision and stability in organ task segmentation. These results show the promise of our residual inception architecture in better medical picture analysis. CONCLUSION: In summary, our research not only shows a state-of-the-art segment methodology but also reinforces its usefulness through thorough testing. The inclusion of residual inception architecture in medical picture segmentation offers good possibilities for improving the identification and management of disease planning.

Portable Dynamic Chest Radiography: Literature Review and Potential Bedside Applications.

Dynamic digital radiography (DDR) is a high-resolution radiographic imaging technique using pulsed X-ray emission to acquire a multiframe cine-loop of the target anatomical area. The first DDR technology was orthostatic chest acquisitions, but new portable equipment that can be positioned at the patient's bedside was recently released, significantly expanding its potential applications, particularly in chest examination. It provides anatomical and functional information on the motion of different anatomical structures, such as the lungs, pleura, rib cage, and trachea. Native images can be further analyzed with dedicated post-processing software to extract quantitative parameters, including diaphragm motility, automatically projected lung area and area changing rate, a colorimetric map of the signal value change related to respiration and motility, and lung perfusion. The dynamic diagnostic information along with the significant advantages of this technique in terms of portability, versatility, and cost-effectiveness represents a potential game changer for radiological diagnosis and monitoring at the patient's bedside. DDR has several applications in daily clinical practice, and in this narrative review, we will focus on chest imaging, which is the main application explored to date in the literature. However, studies are still needed to understand deeply the clinical impact of this method.

CT-FEM of the human thorax: Frequency response function and 3D harmonic analysis at resonance.

BACKGROUND AND OBJECTIVE: High-frequency chest wall compression (HFCC) therapy by airway clearance devices (ACDs) acts on the rheological properties of bronchial mucus to assist in clearing pulmonary secretions. Investigating low-frequency vibrations on the human thorax through numerical simulations is critical to ensure consistency and repeatability of studies by reducing extreme variability in body measurements across individuals. This study aims to present the numerical investigation of the harmonic acoustic excitation of ACDs on the human chest as a gentle and effective HFCC therapy. METHODS: Four software programs were sequentially used to visualize medical images, decrease the number of surfaces, generate and repair meshes, and conduct numerical analysis, respectively. The developed methodology supplied the validation of the effect of HFCC through computed tomography-based finite element analysis (CT-FEM) of a human thorax. To illustrate the vibroacoustic characteristics of the HFCC therapy device, a 146-decibel sound pressure level (dBSPL) was applied on the back-chest surface of the model. Frequency response function (FRF) across 5-100 Hz was analyzed to characterize the behaviour of the human thorax with the state-space model. RESULTS: We discovered that FRF pertaining to accelerance equals 0.138 m/s2N at the peak frequency of 28 Hz, which is consistent with two independent experimental airway clearance studies reported in the literature. The state-space model assessed two apparent resonance frequencies at 28 Hz and 41 Hz for the human thorax. The total displacement, kinetic energy density, and elastic strain energy density were furthermore quantified at 1 µm, 5.2 µJ/m3, and 140.7 µJ/m3, respectively, at the resonance frequency. In order to deepen our understanding of the impact on internal organs, the model underwent simulations in both the time domain and frequency domain for a comprehensive analysis. CONCLUSION: Overall, the present study enabled determining and validating FRF of the human thorax to roll out the inconsistencies, contributing to the health of individuals with investigating gentle but effective HFCC therapy conditions with ACDs. This innovative finding furthermore provides greater clarity and a tangible understanding of the subject by simulating the responses of CT-FEM of the human thorax and internal organs at resonance.

Image quality in CT thorax: effect of altering reconstruction algorithm and tube load.

Non-linear properties of iterative reconstruction (IR) algorithms can alter image texture. We evaluated the effect of a model-based IR algorithm (advanced modelled iterative reconstruction; ADMIRE) and dose on computed tomography thorax image quality. Dual-source scanner data were acquired at 20, 45 and 65 reference mAs in 20 patients. Images reconstructed with filtered back projection (FBP) and ADMIRE Strengths 3-5 were assessed independently by six radiologists and analysed using an ordinal logistic regression model. For all image criteria studied, the effects of tube load 20 mAs and all ADMIRE strengths were significant (p < 0.001) when compared to reference categories 65 mAs and FBP. Increase in tube load from 45 to 65 mAs showed image quality improvement in three of six criteria. Replacing FBP with ADMIRE significantly improves perceived image quality for all criteria studied, potentially permitting a dose reduction of almost 70% without loss in image quality.

Lung-DT: An AI-Powered Digital Twin Framework for Thoracic Health Monitoring and Diagnosis.

The integration of artificial intelligence (AI) with Digital Twins (DTs) has emerged as a promising approach to revolutionize healthcare, particularly in terms of diagnosis and management of thoracic disorders. This study proposes a comprehensive framework, named Lung-DT, which leverages IoT sensors and AI algorithms to establish the digital representation of a patient's respiratory health. Using the YOLOv8 neural network, the Lung-DT system accurately classifies chest X-rays into five distinct categories of lung diseases, including "normal", "covid", "lung_opacity", "pneumonia", and "tuberculosis". The performance of the system was evaluated employing a chest X-ray dataset available in the literature, demonstrating average accuracy of 96.8%, precision of 92%, recall of 97%, and F1-score of 94%. The proposed Lung-DT framework offers several advantages over conventional diagnostic methods. Firstly, it enables real-time monitoring of lung health through continuous data acquisition from IoT sensors, facilitating early diagnosis and intervention. Secondly, the AI-powered classification module provides automated and objective assessments of chest X-rays, reducing dependence on subjective human interpretation. Thirdly, the twin digital representation of the patient's respiratory health allows for comprehensive analysis and correlation of multiple data streams, providing valuable insights as to personalized treatment plans. The integration of IoT sensors, AI algorithms, and DT technology within the Lung-DT system demonstrates a significant step towards improving thoracic healthcare. By enabling continuous monitoring, automated diagnosis, and comprehensive data analysis, the Lung-DT framework has enormous potential to enhance patient outcomes, reduce healthcare costs, and optimize resource allocation.

Domain adaptation via Wasserstein distance and discrepancy metric for chest X-ray image classification.

Deep learning technology can effectively assist physicians in diagnosing chest radiographs. Conventional domain adaptation methods suffer from inaccurate lesion region localization, large errors in feature extraction, and a large number of model parameters. To address these problems, we propose a novel domain-adaptive method WDDM to achieve abnormal identification of chest radiographic images by combining Wasserstein distance and difference measures. Specifically, our method uses BiFormer as a multi-scale feature extractor to extract deep feature representations of data samples, which focuses more on discriminant features than convolutional neural networks and Swin Transformer. In addition, based on the loss minimization of Wasserstein distance and contrast domain differences, the source domain samples closest to the target domain are selected to achieve similarity and dissimilarity across domains. Experimental results show that compared with the non-transfer method that directly uses the network trained in the source domain to classify the target domain, our method has an average AUC increase of 14.8% and above. In short, our method achieves higher classification accuracy and better generalization performance.

Estimation of heart inclination angle using posteroanterior chest radiograph and comparison with cardiac axis obtained from synthesized vectorcardiogram

ABSTRACT In medical practice, it is common to perform electrocardiography exams and by mathematical transformations to obtain the vectorcardiogram. The vectorcardiogram provides important information for medical diagnosis, such as the angle of inclination of the heart. This article aims to present a methodology for estimating the QRS vector-related angle of the heart using a posteroanterior chest radiograph image. We used an open source image processing software (Icy software version 2.3.0.0, Institut Pasteur, France, 2021) to perform a manual measurement of the target angle by analyzing relevant morphological structures from the x-ray images and using some functions to help the user to measure it. 18 radiographic images were selected to measure the angle of the heart by two independent individuals. The measured angles were compared using the mean absolute error (MAE). We then computed the QRS peak elevation angles of the vectorcardiogram (VCG) of the 57 patients collected at Dante Pazzanese Institute of Cardiology. In addition, an individual was randomly selected to measure a set of 57 radiographic images of these same patients. We performed the statistical treatments and the results suggested that the proposed manual method may be an alternative, viable and fast approach to estimating the anatomical heart axis for the purpose of aiding in medical diagnosis. However, further comparisons with more data and information are needed to determine its validity and possible method improvements.

HRCTCov19-a high-resolution chest CT scan image dataset for COVID-19 diagnosis and differentiation.

INTRODUCTION: Computed tomography (CT) was a widely used diagnostic technique for COVID-19 during the pandemic. High-Resolution Computed Tomography (HRCT), is a type of computed tomography that enhances image resolution through the utilization of advanced methods. Due to privacy concerns, publicly available COVID-19 CT image datasets are incredibly tough to come by, leading to it being challenging to research and create AI-powered COVID-19 diagnostic algorithms based on CT images. DATA DESCRIPTION: To address this issue, we created HRCTCov19, a new COVID-19 high-resolution chest CT scan image collection that includes not only COVID-19 cases of Ground Glass Opacity (GGO), Crazy Paving, and Air Space Consolidation but also CT images of cases with negative COVID-19. The HRCTCov19 dataset, which includes slice-level and patient-level labeling, has the potential to assist in COVID-19 research, in particular for diagnosis and a distinction using AI algorithms, machine learning, and deep learning methods. This dataset, which can be accessed through the web at http://databiox.com , includes 181,106 chest HRCT images from 395 patients labeled as GGO, Crazy Paving, Air Space Consolidation, and Negative.

Label correlation guided discriminative label feature learning for multi-label chest image classification.

BACKGROUND AND OBJECTIVE: Multi-label Chest X-ray (CXR) images often contain rich label relationship information, which is beneficial to improve classification performance. However, because of the intricate relationships among labels, most existing works fail to effectively learn and make full use of the label correlations, resulting in limited classification performance. In this study, we propose a multi-label learning framework that learns and leverages the label correlations to improve multi-label CXR image classification. METHODS: In this paper, we capture the global label correlations through the self-attention mechanism. Meanwhile, to better utilize label correlations for guiding feature learning, we decompose the image-level features into label-level features. Furthermore, we enhance label-level feature learning in an end-to-end manner by a consistency constraint between global and local label correlations, and a label correlation guided multi-label supervised contrastive loss. RESULTS: To demonstrate the superior performance of our proposed approach, we conduct three times 5-fold cross-validation experiments on the CheXpert dataset. Our approach obtains an average F1 score of 44.6% and an AUC of 76.5%, achieving a 7.7% and 1.3% improvement compared to the state-of-the-art results. CONCLUSION: More accurate label correlations and full utilization of the learned label correlations help learn more discriminative label-level features. Experimental results demonstrate that our approach achieves exceptionally competitive performance compared to the state-of-the-art algorithms.

Framework for dual-energy-like chest radiography image synthesis from single-energy computed tomography based on cycle-consistent generative adversarial network.

BACKGROUND: Dual-energy (DE) chest radiography (CXR) enables the selective imaging of two relevant materials, namely, soft tissue and bone structures, to better characterize various chest pathologies (i.e., lung nodule, bony lesions, etc.) and potentially improve CXR-based diagnosis. Recently, deep-learning-based image synthesis techniques have attracted considerable attention as alternatives to existing DE methods (i.e., dual-exposure-based and sandwich-detector-based methods) because software-based bone-only and bone-suppression images in CXR could be useful. PURPOSE: The objective of this study was to develop a new framework for DE-like CXR image synthesis from single-energy computed tomography (CT) based on a cycle-consistent generative adversarial network. METHODS: The core techniques of the proposed framework are divided into three categories: (1) data configuration from the generation of pseudo CXR from single energy CT, (2) learning of the developed network architecture using pseudo CXR and pseudo-DE imaging using a single-energy CT, and (3) inference of the trained network on real single-energy CXR. We performed a visual inspection and comparative evaluation using various metrics and introduced a figure of image quality (FIQ) to consider the effects of our framework on the spatial resolution and noise in terms of a single index through various test cases. RESULTS: Our results indicate that the proposed framework is effective and exhibits potential synthetic imaging ability for two relevant materials: soft tissue and bone structures. Its effectiveness was validated, and its ability to overcome the limitations associated with DE imaging techniques (e.g., increase in exposure dose owing to the requirement of two acquisitions, and emphasis on noise characteristics) via an artificial intelligence technique was presented. CONCLUSIONS: The developed framework addresses X-ray dose issues in the field of radiation imaging and enables pseudo-DE imaging with single exposure.

Interpretable CNN-Multilevel Attention Transformer for Rapid Recognition of Pneumonia From Chest X-Ray Images.

Chest imaging plays an essential role in diagnosing and predicting patients with COVID-19 with evidence of worsening respiratory status. Many deep learning-based approaches for pneumonia recognition have been developed to enable computer-aided diagnosis. However, the long training and inference time makes them inflexible, and the lack of interpretability reduces their credibility in clinical medical practice. This paper aims to develop a pneumonia recognition framework with interpretability, which can understand the complex relationship between lung features and related diseases in chest X-ray (CXR) images to provide high-speed analytics support for medical practice. To reduce the computational complexity to accelerate the recognition process, a novel multi-level self-attention mechanism within Transformer has been proposed to accelerate convergence and emphasize the task-related feature regions. Moreover, a practical CXR image data augmentation has been adopted to address the scarcity of medical image data problems to boost the model's performance. The effectiveness of the proposed method has been demonstrated on the classic COVID-19 recognition task using the widespread pneumonia CXR image dataset. In addition, abundant ablation experiments validate the effectiveness and necessity of all of the components of the proposed method.

Insights on Using Time-of-Flight Camera for Recovering Cardiac Pulse From Chest Motion in Depth Videos.

In this article, we introduce a novel use of depth camera to extract cardiac pulse signal from human chest area, in which the depth information is obtained from a near infrared sensor using time-of-flight technology. We successfully isolate weak chest motion due to heartbeat by processing a sequence of depth images without raising privacy concern. We discuss motion sensitivity in depth video with examples from actuator simulation and human chest motion. Compared to other imaging modalities, the depth image intensity can be directly used for micromotion reconstruction. To deal with the challenges of recovering heartbeat from the chest area, we develop a set of coherent processing techniques to suppress the unwanted motion interference from breathing motion and involuntary body motion and eventually obtain clean cardiac pulse signal. We, thus, derive inter-beat-interval, showing high consistency to the contact photoplethysmography. Additionally, we develop a graphical interpretation of the most and the less pulsatile principal components in eigen space. For validation, we test our method on ten healthy human subjects with different resting heart rates. More importantly, we conduct a set of experiments to study the robustness and weakness of our methods, including extended range, multi-subject, thickness of clothes and generation to other measurement site.

Thoracic cavity of the Shirazi cats: New insights using computed tomography and magnetic resonance imaging.

Our study provided a comprehensive characterization of the thorax of Shirazi cats by comparing the relevant soft and bone windows of computed tomography (CT) and magnetic resonance imaging (MRI) with cross, sagittal and coronal sectional anatomy. We outlined the mediastinum and its anatomic relationships with the trachea, oesophagus, lungs, heart, cranial and caudal vena cavae, and other thoracic structures using the data series gathered from adult normal Shirazi cats. The cranial mediastinum extended from the thoracic inlet to the 4th intercostal space, the middle mediastinum extended from the 5th and 7th intercostal spaces and was occupied by the heart and large blood vessels and the caudal mediastinum extended as a short and narrow portion from the 8th intercostal space to the diaphragm. The contents of the mediastinum and its relationship with the lungs and diaphragm were clearly presented in coronal-sectional anatomy and CT slices. The diaphragm was clearly observed in the lung windows of the ventral thorax. Sagittal-sectional anatomy and CT clarified the thorax's architecture and its contents, with higher density in the soft windows. The distribution of thoracic vessels on cross- and coronal-contrast CT scans was clearly visible. In addition, MRI scans provided an excellent anatomic reference of the thorax with the help of cross, coronal and sagittal scans, especially in the heart and blood vessels. Our study provides a valuable atlas for the diagnosis of malformations of the thoracic structures and offers better assessments for helping veterinary radiologists and clinicians in diagnostic processes.