Current and emerging artificial intelligence applications in chest imaging: a pediatric perspective

Advancements in imaging in ChILD

Interstitial and diffuse lung diseases in children constitute a range of congenital and acquired disorders. These disorders present with signs and symptoms of respiratory disease accompanied by diffuse radiographic changes. In many cases, radiographic findings are nonspecific, while in other disorders, chest computed tomography (CT) is diagnostic in the appropriate context. Regardless, chest imaging remains central in the evaluation of the patient with suspected childhood interstitial lung disease (chILD). Several newly described chILD entities, spanning both genetic and acquired etiologies, have imaging that aid in their diagnoses. Advances in CT scanning technology and CT analysis techniques continue to improve scan quality as well as expand use of chest CT as a research tool. Finally, ongoing research is expanding use of imaging modalities without ionizing radiation. Magnetic resonance imaging is being applied to investigate pulmonary structure and function, and ultrasound of the lung and pleura is a novel technique with an emerging role in chILD disorders. This review describes the current state of imaging in chILD including recently described diagnoses, advances in conventional imaging techniques and applications, and evolving new imaging modalities that expand the clinical and research roles for imaging in these disorders.

Update on the Role of Chest Imaging in Cystic Fibrosis

Cystic fibrosis is a genetic disease with multisystem involvement and associated morbidity and mortality that are most directly related to progressive lung disease. The hallmark findings of cystic fibrosis in the lungs are chronic inflammation and infection, leading to progressive loss of pulmonary function and often requiring lung transplant. Predominant lung findings include mucous plugging, bronchiectasis, and air trapping, often with associated atelectasis, consolidation, and emphysema; these findings form the basis of several clinical scoring systems that are used for imaging assessment. Recently, there have been major breakthroughs in the pharmacologic management of cystic fibrosis, including highly effective modulator therapies that directly target the underlying cystic fibrosis transmembrane conductance regulator molecular defect, often leading to remarkable improvements in lung function and quality of life with corresponding significant improvements in imaging markers. The authors review current guidelines regarding cystic fibrosis with respect to disease monitoring, identifying complications, and managing advanced lung disease. In addition, they discuss the evolving role of imaging, including current trends, emerging technologies, and proposed updates to imaging guidelines endorsed by international expert committees on cystic fibrosis, which favor increased use of cross-sectional imaging to enable earlier detection of structural changes in early disease and more sensitive detection of acute changes in advanced disease. It is important for radiologists to be familiar with these trends and updates so that they can most effectively assist clinicians in guiding the management of patients with cystic fibrosis in all stages of disease. ©RSNA, 2024.

How anatomical impairments found on CT affect perfusion percentage assessed by SPECT/CT scan?

AIM

CT images can identify structural and opacity alterations of the lungs while nuclear medicine's lung perfusion studies show the homogeneity (or lack of) of blood perfusion on the organ. Therefore, the use of SPECT/CT in lung perfusion scintigraphies can help physicians to assess anatomical and functional alterations of the lungs and to differentiate between acute and chronic disease.

OBJECTIVE

To develop a computer-aided methodology to quantify the total global perfusion of the lungs via SPECT/CT images and to compare these results with parenchymal alterations obtained in CT images.

METHODS

39 perfusion SPECT/CT images collected retrospectively from the Nuclear Medicine Facility of Botucatu Medical School's Clinics Hospital in São Paulo, Brazil, were analyzed. Anatomical lung impairments (emphysema, collapsed and infiltrated tissue) and the functional percentage of the lungs (blood perfusion) were quantified from CT and SPECT images, with the aid of the free, open-source software 3D Slicer. The results obtained with 3D Slicer (3D-TGP) were also compared to the total global perfusion of each patient's found on their medical report, obtained from visual inspection of planar images (2D-TGP).

RESULTS

This research developed a novel and practical methodology for obtaining lungs' total global perfusion from SPECT/CT images in a semiautomatic manner. 3D-TGP versus 2D-TGP showed a bias of 7% with a variation up to 67% between the two methods. Perfusion percentage showed a weak positive correlation with infiltration (p = 0.0070 and ρ = 0.43) and collapsed parenchyma (p = 0.040 and ρ = 0.33).

CONCLUSIONS

This research brings meaningful contributions to the scientific community because it used a free open-source software to quantify the lungs blood perfusion via SPECT/CT images and pointed that the relationship between parenchyma alterations and the organ's perfusion capability might not be so direct, given compensatory mechanisms.

Deep Learning Auto-Segmentation Network for Pediatric Computed Tomography Data Sets: Can We Extrapolate From Adults?

PURPOSE

Artificial intelligence (AI)-based auto-segmentation models hold promise for enhanced efficiency and consistency in organ contouring for adaptive radiation therapy and radiation therapy planning. However, their performance on pediatric computed tomography (CT) data and cross-scanner compatibility remain unclear. This study aimed to evaluate the performance of AI-based auto-segmentation models trained on adult CT data when applied to pediatric data sets and explore the improvement in performance gained by including pediatric training data. It also examined their ability to accurately segment CT data acquired from different scanners.

METHODS AND MATERIALS

Using the nnU-Net framework, segmentation models were trained on data sets of adult, pediatric, and combined CT scans for 7 pelvic/thoracic organs. Each model was trained on 290 to 300 cases per category and organ. Training data sets included a combination of clinical data and several open repositories. The study incorporated a database of 459 pediatric (0-16 years) CT scans and 950 adults (>18 years), ensuring all scans had human expert ground-truth contours of the selected organs. Performance was evaluated based on Dice similarity coefficients (DSC) of the model-generated contours.

RESULTS

AI models trained exclusively on adult data underperformed on pediatric data, especially for the 0 to 2 age group: mean DSC was below 0.5 for the bladder and spleen. The addition of pediatric training data demonstrated significant improvement for all age groups, achieving a mean DSC of above 0.85 for all organs in every age group. Larger organs like the liver and kidneys maintained consistent performance for all models across age groups. No significant difference emerged in the cross-scanner performance evaluation, suggesting robust cross-scanner generalization.

CONCLUSIONS

For optimal segmentation across age groups, it is important to include pediatric data in the training of segmentation models. The successful cross-scanner generalization also supports the real-world clinical applicability of these AI models. This study emphasizes the significance of data set diversity in training robust AI systems for medical image interpretation tasks.

XRAInet: AI-based decision support for pneumothorax and pleural effusion management

PURPOSE

This study aimed to develop and assess the performance of an artificial intelligence (AI)-driven decision support system, XRAInet, in accurately identifying pediatric patients with pleural effusion or pneumothorax and determining whether tube thoracostomy intervention is warranted.

METHODS

In this diagnostic accuracy study, we retrospectively analyzed a data set containing 510 X-ray images from 170 pediatric patients admitted between 2005 and 2022. Patients were categorized into two groups: Tube (requiring tube thoracostomy) and Conservative (managed conservatively). XRAInet, a deep learning-based algorithm, was trained using this data set. We evaluated its performance using various metrics, including mean Average Precision (mAP), recall, precision, and F1 score.

RESULTS

XRAInet, achieved a mAP score of 0.918. This result underscores its ability to accurately identify and localize regions necessitating tube thoracostomy for pediatric patients with pneumothorax and pleural effusion. In an independent testing data set, the model exhibited a sensitivity of 64.00% and specificity of 96.15%.

CONCLUSION

In conclusion, XRAInet presents a promising solution for improving the detection and decision-making process for cases of pneumothorax and pleural effusion in pediatric patients using X-ray images. These findings contribute to the expanding field of AI-driven medical imaging, with potential applications for enhancing patient outcomes. Future research endeavors should explore hybrid models, enhance interpretability, address data quality issues, and align with regulatory requirements to ensure the safe and effective deployment of XRAInet in healthcare settings.

The Role of AI in Hospitals and Clinics: Transforming Healthcare in the 21st Century

As healthcare systems around the world face challenges such as escalating costs, limited access, and growing demand for personalized care, artificial intelligence (AI) is emerging as a key force for transformation. This review is motivated by the urgent need to harness AI's potential to mitigate these issues and aims to critically assess AI's integration in different healthcare domains. We explore how AI empowers clinical decision-making, optimizes hospital operation and management, refines medical image analysis, and revolutionizes patient care and monitoring through AI-powered wearables. Through several case studies, we review how AI has transformed specific healthcare domains and discuss the remaining challenges and possible solutions. Additionally, we will discuss methodologies for assessing AI healthcare solutions, ethical challenges of AI deployment, and the importance of data privacy and bias mitigation for responsible technology use. By presenting a critical assessment of AI's transformative potential, this review equips researchers with a deeper understanding of AI's current and future impact on healthcare. It encourages an interdisciplinary dialogue between researchers, clinicians, and technologists to navigate the complexities of AI implementation, fostering the development of AI-driven solutions that prioritize ethical standards, equity, and a patient-centered approach.

Doctor's Orders-Why Radiologists Should Consider Adjusting Commercial Machine Learning Applications in Chest Radiography to Fit Their Specific Needs

This retrospective study evaluated a commercial deep learning (DL) software for chest radiographs and explored its performance in different scenarios. A total of 477 patients (284 male, 193 female, mean age 61.4 (44.7-78.1) years) were included. For the reference standard, two radiologists performed independent readings on seven diseases, thus reporting 226 findings in 167 patients. An autonomous DL reading was performed separately and evaluated against the gold standard regarding accuracy, sensitivity and specificity using ROC analysis. The overall average AUC was 0.84 (95%-CI 0.76-0.92) with an optimized DL sensitivity of 85% and specificity of 75.4%. The best results were seen in pleural effusion with an AUC of 0.92 (0.885-0.955) and sensitivity and specificity of each 86.4%. The data also showed a significant influence of sex, age, and comorbidity on the level of agreement between gold standard and DL reading. About 40% of cases could be ruled out correctly when screening for only one specific disease with a sensitivity above 95% in the exploratory analysis. For the combined reading of all abnormalities at once, only marginal workload reduction could be achieved due to insufficient specificity. DL applications like this one bear the prospect of autonomous comprehensive reporting on chest radiographs but for now require human supervision. Radiologists need to consider possible bias in certain patient groups, e.g., elderly and women. By adjusting their threshold values, commercial DL applications could already be deployed for a variety of tasks, e.g., ruling out certain conditions in screening scenarios and offering high potential for workload reduction.

Paediatric Thoracic Imaging in Cystic Fibrosis in the Era of Cystic Fibrosis Transmembrane Conductance Regulator Modulation

Cystic fibrosis (CF) is one of the most common progressive life-shortening genetic conditions worldwide. Ground-breaking translational research has generated therapies that target the primary cystic fibrosis transmembrane conductance regulator (CFTR) defect, known as CFTR modulators. A crucial aspect of paediatric CF disease is the development and progression of irreversible respiratory disease in the absence of clinical symptoms. Accurate thoracic diagnostics have an important role to play in this regard. Chest radiographs are non-specific and insensitive in the context of subtle changes in early CF disease, with computed tomography (CT) providing increased sensitivity. Recent advancements in imaging hardware and software have allowed thoracic CTs to be acquired in paediatric patients at radiation doses approaching that of a chest radiograph. CFTR modulators slow the progression of CF, reduce the frequency of exacerbations and extend life expectancy. In conjunction with advances in CT imaging techniques, low-dose thorax CT will establish a central position in the routine care of children with CF. International guidelines regarding the choice of modality and timing of thoracic imaging in children with CF are lagging behind these rapid technological advances. The continued progress of personalised medicine in the form of CFTR modulators will promote the emergence of personalised radiological diagnostics.

Performance Analysis in Children of Traditional and Deep Learning CT Lung Nodule Computer-Aided Detection Systems Trained on Adults

BACKGROUND. Although primary lung cancer is rare in children, chest CT is commonly performed to assess for lung metastases in children with cancer. Lung nodule computer-aided detection (CAD) systems have been designed and studied primarily using adult training data, and the efficacy of such systems when applied to pediatric patients is poorly understood. OBJECTIVE. The purpose of this study was to evaluate in children the diagnostic performance of traditional and deep learning CAD systems trained with adult data for the detection of lung nodules on chest CT scans and to compare the ability of such systems to generalize to children versus to other adults. METHODS. This retrospective study included pediatric and adult chest CT test sets. The pediatric test set comprised 59 CT scans in 59 patients (30 boys, 29 girls; mean age, 13.1 years; age range, 4-17 years), which were obtained from November 30, 2018, to August 31, 2020; lung nodules were annotated by fellowship-trained pediatric radiologists as the reference standard. The adult test set was the publicly available adult Lung Nodule Analysis (LUNA) 2016 subset 0, which contained 89 deidentified scans with previously annotated nodules. The test sets were processed through the traditional FlyerScan (github.com/rhardie1/FlyerScanCT) and deep learning Medical Open Network for Artificial Intelligence (MONAI; github.com/Project-MONAI/model-zoo/releases) lung nodule CAD systems, which had been trained on separate sets of CT scans in adults. Sensitivity and false-positive (FP) frequency were calculated for nodules measuring 3-30 mm; nonoverlapping 95% CIs indicated significant differences. RESULTS. Operating at two FPs per scan, on pediatric testing data FlyerScan and MONAI showed significantly lower detection sensitivities of 68.4% (197/288; 95% CI, 65.1-73.0%) and 53.1% (153/288; 95% CI, 46.7-58.4%), respectively, than on adult LUNA 2016 subset 0 testing data (83.9% [94/112; 95% CI, 79.1-88.0%] and 95.5% [107/112; 95% CI, 90.0-98.4%], respectively). Mean nodule size was smaller (p < .001) in the pediatric testing data (5.4 ± 3.1 [SD] mm) than in the adult LUNA 2016 subset 0 testing data (11.0 ± 6.2 mm). CONCLUSION. Adult-trained traditional and deep learning-based lung nodule CAD systems had significantly lower sensitivity for detection on pediatric data than on adult data at a matching FP frequency. The performance difference may relate to the smaller size of pediatric lung nodules. CLINICAL IMPACT. The results indicate a need for pediatric-specific lung nodule CAD systems trained on data specific to pediatric patients.

DraiNet: AI-driven decision support in pneumothorax and pleural effusion management

OBJECTIVE

This study presents DraiNet, a deep learning model developed to detect pneumothorax and pleural effusion in pediatric patients and aid in assessing the necessity for tube thoracostomy. The primary goal is to utilize DraiNet as a decision support tool to enhance clinical decision-making in the management of these conditions.

METHODS

DraiNet was trained on a diverse dataset of pediatric CT scans, carefully annotated by experienced surgeons. The model incorporated advanced object detection techniques and underwent evaluation using standard metrics, such as mean Average Precision (mAP), to assess its performance.

RESULTS

DraiNet achieved an impressive mAP score of 0.964, demonstrating high accuracy in detecting and precisely localizing abnormalities associated with pneumothorax and pleural effusion. The model's precision and recall further confirmed its ability to effectively predict positive cases.

CONCLUSION

The integration of DraiNet as an AI-driven decision support system marks a significant advancement in pediatric healthcare. By combining deep learning algorithms with clinical expertise, DraiNet provides a valuable tool for non-surgical teams and emergency room doctors, aiding them in making informed decisions about surgical interventions. With its remarkable mAP score of 0.964, DraiNet has the potential to enhance patient outcomes and optimize the management of critical conditions, including pneumothorax and pleural effusion.

Comparative survey among paediatricians, nurses and health information technicians on ethics implementation knowledge of and attitude towards social experiments based on medical artificial intelligence at children's hospitals in Shanghai: a cross-sectional study

OBJECTIVES

Implementing ethics is crucial to prevent harm and promote widespread benefits in social experiments based on medical artificial intelligence (MAI). However, insufficient information is available concerning this within the paediatric healthcare sector. We aimed to conduct a comparative survey among paediatricians, nurses and health information technicians regarding ethics implementation knowledge of and attitude towards MAI social experiments at children's hospitals in Shanghai.

DESIGN AND SETTING

A cross-sectional electronic questionnaire was administered from 1 July 2022 to 31 July 2022, at tertiary children's hospitals in Shanghai.

PARTICIPANTS

All the eligible individuals were recruited. The inclusion criteria were as follows: (1) should be a paediatrician, nurse and health information technician, (2) should have been engaged in or currently participating in social experiments based on MAI, and (3) voluntary participation in the survey.

PRIMARY OUTCOME

Ethics implementation knowledge of and attitude to MAI social experiments among paediatricians, nurses and health information technicians.

RESULTS

There were 137 paediatricians, 135 nurses and 60 health information technicians who responded to the questionnaire at tertiary children's hospitals. 2.4-9.6% of participants were familiar with ethics implementation knowledge of MAI social experiments. 31.9-86.1% of participants held an 'agree' ethics implementation attitude. Health information technicians accounted for the highest proportion of the participants who were familiar with the knowledge of implementing ethics, and paediatricians or nurses accounted for the highest proportion among those who held 'agree' attitudes.

CONCLUSIONS

There is a significant knowledge gap and variations in attitudes among paediatricians, nurses and health information technicians, which underscore the urgent need for individualised education and training programmes to enhance MAI ethics implementation in paediatric healthcare.

Prevalence and Clinical Characteristics of Children With Nonsevere Tuberculosis in Spain

BACKGROUND

To assess the prevalence and characteristics of nonsevere TB among children in Spain. It has been recently demonstrated that these children can be treated with a 4-month regimen instead of the classical 6-month treatment regimen, with the same effectivity and outcomes, decreasing toxicity and improving adherence.

METHODS

We conducted a retrospective cohort study in a cohort of children ≤16 years of age with TB. Nonsevere TB cases included smear-negative children with respiratory TB confined to 1 lobe, with no significant airway obstruction, no complex pleural effusion, no cavities and no signs of miliary disease, or with peripheral lymph-node disease. The remaining children were considered to have severe TB. We estimated the prevalence of nonsevere TB and compared the clinical characteristics and outcomes between children with nonsevere and severe TB.

RESULTS

A total of 780 patients were included [46.9% males, median age 5.5 years (IQR: 2.6-11.1)], 477 (61.1%) of whom had nonsevere TB. Nonsevere TB was less frequent in children <1 year (33% vs 67%; P < 0.001), and >14 years of age (35% vs 65%; P = 0.002), mostly diagnosed in contact tracing studies (60.4% vs 29.2%; P < 0.001) and more frequently asymptomatic (38.3% vs 17.7%; P < 0.001). TB confirmation in nonsevere disease was less frequent by culture (27.0% vs 57.1%; P < 0.001) and by molecular tests (18.2% vs 48.8%; P < 0.001). Sequelae were less frequent in children with nonsevere disease (1.7 vs 5.4%; P < 0.001). No child with nonsevere disease died.

CONCLUSIONS

Two-thirds of children had nonsevere TB, mostly with benign clinical presentation and negative microbiologic results. In low-burden countries, most children with TB might benefit from short-course regimens.

Generative Adversarial Network (Generative Artificial Intelligence) in Pediatric Radiology: A Systematic Review

Generative artificial intelligence, especially with regard to the generative adversarial network (GAN), is an important research area in radiology as evidenced by a number of literature reviews on the role of GAN in radiology published in the last few years. However, no review article about GAN in pediatric radiology has been published yet. The purpose of this paper is to systematically review applications of GAN in pediatric radiology, their performances, and methods for their performance evaluation. Electronic databases were used for a literature search on 6 April 2023. Thirty-seven papers met the selection criteria and were included. This review reveals that the GAN can be applied to magnetic resonance imaging, X-ray, computed tomography, ultrasound and positron emission tomography for image translation, segmentation, reconstruction, quality assessment, synthesis and data augmentation, and disease diagnosis. About 80% of the included studies compared their GAN model performances with those of other approaches and indicated that their GAN models outperformed the others by 0.1-158.6%. However, these study findings should be used with caution because of a number of methodological weaknesses. For future GAN studies, more robust methods will be essential for addressing these issues. Otherwise, this would affect the clinical adoption of the GAN-based applications in pediatric radiology and the potential advantages of GAN could not be realized widely.

Artificial Intelligence in Paediatric Tuberculosis

Tuberculosis (TB) continues to be a leading cause of death in children despite global efforts focused on early diagnosis and interventions to limit the spread of the disease. This challenge has been made more complex in the context of the coronavirus pandemic, which has disrupted the "End TB Strategy" and framework set out by the World Health Organization (WHO). Since the inception of artificial intelligence (AI) more than 60 years ago, the interest in AI has risen and more recently we have seen the emergence of multiple real-world applications, many of which relate to medical imaging. Nonetheless, real-world AI applications and clinical studies are limited in the niche area of paediatric imaging. This review article will focus on how AI, or more specifically deep learning, can be applied to TB diagnosis and management in children. We describe how deep learning can be utilised in chest imaging to provide computer-assisted diagnosis to augment workflow and screening efforts. We also review examples of recent AI applications for TB screening in resource constrained environments and we explore some of the challenges and the future directions of AI in paediatric TB.

European Society of Paediatric Radiology Artificial Intelligence taskforce: a new taskforce for the digital age

A new task force dedicated to artificial intelligence (AI) with respect to paediatric radiology was created in 2021 at the International Paediatric Radiology (IPR) meeting in Rome, Italy (a joint society meeting by the European Society of Pediatric Radiology [ESPR] and the Society for Pediatric Radiology [SPR]). The concept of a separate task force dedicated to AI was borne from an ESPR-led international survey of health care professionals' opinions, expectations and concerns regarding AI integration within children's imaging departments. In this survey, the majority (> 80%) of ESPR respondents supported the creation of a task force and helped define our key objectives. These include providing educational content about AI relevant for paediatric radiologists, brainstorming ideas for future projects and collaborating on AI-related studies with respect to collating data sets, de-identifying images and engaging in multi-case, multi-reader studies. This manuscript outlines the starting point of the ESPR AI task force and where we wish to go.

Chest radiography and computed tomography imaging in cystic fibrosis: current challenges and new perspectives

Imaging plays a pivotal role in the noninvasive assessment of cystic fibrosis (CF)-related lung damage, which remains the main cause of morbidity and mortality in children with CF. The development of new imaging techniques has significantly changed clinical practice, and advances in therapies have posed diagnostic and monitoring challenges. The authors summarise these challenges and offer new perspectives in the use of imaging for children with CF for both clinicians and radiologists. This article focuses on chest radiography and CT, which are the two main radiologic techniques used in most cystic fibrosis centres. Advantages and disadvantages of radiography and CT for imaging in CF are described, with attention to new developments in these techniques, such as the use of artificial intelligence (AI) image analysis strategies to improve the sensitivity of radiography and CT and the introduction of the photon-counting detector CT scanner to increase spatial resolution at no dose expense.

Automatic detection of punctate white matter lesions in infants using deep learning of composite images from two cases

Punctate white matter lesions (PWMLs) in infants may be related to neurodevelopmental outcomes based on the location or number of lesions. This study aimed to assess the automatic detectability of PWMLs in infants on deep learning using composite images created from several cases. To create the initial composite images, magnetic resonance (MR) images of two infants with the most PWMLs were used; their PWMLs were extracted and pasted onto MR images of infants without abnormality, creating many composite PWML images. Deep learning models based on a convolutional neural network, You Only Look Once v3 (YOLOv3), were constructed using the training set of 600, 1200, 2400, and 3600 composite images. As a result, a threshold of detection probability of 20% and 30% for all deep learning model sets yielded a relatively high sensitivity for automatic PWML detection (0.908-0.957). Although relatively high false-positive detections occurred with the lower threshold of detection probability, primarily, in the partial volume of the cerebral cortex (≥ 85.8%), those can be easily distinguished from the white matter lesions. Relatively highly sensitive automatic detection of PWMLs was achieved by creating composite images from two cases using deep learning.

Diagnostic Performance of Artificial Intelligence-Based Computer-Aided Detection and Diagnosis in Pediatric Radiology: A Systematic Review

Artificial intelligence (AI)-based computer-aided detection and diagnosis (CAD) is an important research area in radiology. However, only two narrative reviews about general uses of AI in pediatric radiology and AI-based CAD in pediatric chest imaging have been published yet. The purpose of this systematic review is to investigate the AI-based CAD applications in pediatric radiology, their diagnostic performances and methods for their performance evaluation. A literature search with the use of electronic databases was conducted on 11 January 2023. Twenty-three articles that met the selection criteria were included. This review shows that the AI-based CAD could be applied in pediatric brain, respiratory, musculoskeletal, urologic and cardiac imaging, and especially for pneumonia detection. Most of the studies (93.3%, 14/15; 77.8%, 14/18; 73.3%, 11/15; 80.0%, 8/10; 66.6%, 2/3; 84.2%, 16/19; 80.0%, 8/10) reported model performances of at least 0.83 (area under receiver operating characteristic curve), 0.84 (sensitivity), 0.80 (specificity), 0.89 (positive predictive value), 0.63 (negative predictive value), 0.87 (accuracy), and 0.82 (F1 score), respectively. However, a range of methodological weaknesses (especially a lack of model external validation) are found in the included studies. In the future, more AI-based CAD studies in pediatric radiology with robust methodology should be conducted for convincing clinical centers to adopt CAD and realizing its benefits in a wider context.

A deep convolutional neural network ensemble for composite identification of pulmonary nodules and incidental findings on routine PET/CT

AIM

To evaluate primary and secondary pathologies of interest using an artificial intelligence (AI) platform, AI-Rad Companion, on low-dose computed tomography (CT) series from integrated positron-emission tomography (PET)/CT to detect CT findings that might be overlooked.

MATERIALS AND METHODS

One hundred and eighty-nine sequential patients who had undergone PET/CT were included. Images were evaluated using an ensemble of convolutional neural networks (AI-Rad Companion, Siemens Healthineers, Erlangen, Germany). The primary outcome was detection of pulmonary nodules for which the accuracy, identity, and intra-rater reliability was calculated. For secondary outcomes (binary detection of coronary artery calcium, aortic ectasia, vertebral height loss), accuracy and diagnostic performance were calculated.

RESULTS

The overall per-nodule accuracy for detection of lung nodules was 0.847. The overall sensitivity and specificity for detection of lung nodules was 0.915 and 0.781. The overall per-patient accuracy for AI detection of coronary artery calcium, aortic ectasia, and vertebral height loss was 0.979, 0.966, and 0.840, respectively. The sensitivity and specificity for coronary artery calcium was 0.989 and 0.969. The sensitivity and specificity for aortic ectasia was 0.806 and 1.

CONCLUSION

The neural network ensemble accurately assessed the number of pulmonary nodules and presence of coronary artery calcium and aortic ectasia on low-dose CT series of PET/CT. The neural network was highly specific for the diagnosis of vertebral height loss, but not sensitive. The use of the AI ensemble can help radiologists and nuclear medicine physicians to catch CT findings that might be overlooked.

Innovations in thoracic imaging: CT, radiomics, AI and x-ray velocimetry

In recent years, pulmonary imaging has seen enormous progress, with the introduction, validation and implementation of new hardware and software. There is a general trend from mere visual evaluation of radiological images to quantification of abnormalities and biomarkers, and assessment of ‘non visual’ markers that contribute to establishing diagnosis or prognosis. Important catalysts to these developments in thoracic imaging include new indications (like computed tomography [CT] lung cancer screening) and the COVID‐19 pandemic. This review focuses on developments in CT, radiomics, artificial intelligence (AI) and x‐ray velocimetry for imaging of the lungs. Recent developments in CT include the potential for ultra‐low‐dose CT imaging for lung nodules, and the advent of a new generation of CT systems based on photon‐counting detector technology. Radiomics has demonstrated potential towards predictive and prognostic tasks particularly in lung cancer, previously not achievable by visual inspection by radiologists, exploiting high dimensional patterns (mostly texture related) on medical imaging data. Deep learning technology has revolutionized the field of AI and as a result, performance of AI algorithms is approaching human performance for an increasing number of specific tasks. X‐ray velocimetry integrates x‐ray (fluoroscopic) imaging with unique image processing to produce quantitative four dimensional measurement of lung tissue motion, and accurate calculations of lung ventilation.

See relatedEditorial

Diagnostic performance of artificial intelligence approved for adults for the interpretation of pediatric chest radiographs

Artificial intelligence (AI) applied to pediatric chest radiographs are yet scarce. This study evaluated whether AI-based software developed for adult chest radiographs can be used for pediatric chest radiographs. Pediatric patients (≤ 18 years old) who underwent chest radiographs from March to May 2021 were included retrospectively. An AI-based lesion detection software assessed the presence of nodules, consolidation, fibrosis, atelectasis, cardiomegaly, pleural effusion, pneumothorax, and pneumoperitoneum. Using the pediatric radiologist’s results as standard reference, we assessed the diagnostic performance of the software. For the total 2273 chest radiographs, the AI-based software showed a sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of 67.2%, 91.1%, 57.7%, 93.9%, and 87.5%, respectively. Age was a significant factor for incorrect results (odds radio 0.821, 95% confidence interval 0.791–0.851). When we excluded cardiomegaly and children 2 years old or younger, sensitivity, specificity, PPV, NPV and accuracy significantly increased (86.4%, 97.9%, 79.7%, 98.7% and 96.9%, respectively, all p < 0.001). In conclusion, AI-based software developed with adult chest radiographs showed diagnostic accuracies up to 96.9% for pediatric chest radiographs when we excluded cardiomegaly and children 2 years old or younger. AI-based lesion detection software needs to be validated in younger children.

Prediction of Bronchopneumonia Inpatients' Total Hospitalization Expenses Based on BP Neural Network and Support Vector Machine Models

Objective

BP neural network (BPNN) model and support vector machine (SVM) model were used to predict the total hospitalization expenses of patients with bronchopneumonia.

Methods

A total of 355 patients with bronchopneumonia from January 2018 to December 2020 were collected and sorted out. The data set was randomly divided into a training set (n = 249) and a test set (n = 106) according to 7 : 3. The BPNN model and SVM model were constructed to analyze the predictors of total hospitalization expenses. The effectiveness was compared between these two prediction models.

Results

The top three influencing factors and their importance for predicting total hospitalization cost by the BPNN model were hospitalization days (0.477), age (0.154), and discharge department (0.083). The top 3 factors predicted by the SVM model were hospitalization days (0.215), age (0.196), and marital status (0.172). The area under the curve of these two models is 0.838 (95% CI: 0.755~0.921) and 0.889 (95% CI: 0.819~0.959), respectively.

Conclusion

Both the BPNN model and SVM model can predict the total hospitalization expenses of patients with bronchopneumonia, but the prediction effect of the SVM model is better than the BPNN model.

State-of-the-art review of lung imaging in cystic fibrosis with recommendations for pulmonologists and radiologists from the "iMAging managEment of cySTic fibROsis" (MAESTRO) consortium

OBJECTIVE

Imaging represents an important noninvasive means to assess cystic fibrosis (CF) lung disease, which remains the main cause of morbidity and mortality in CF patients. While the development of new imaging techniques has revolutionised clinical practice, advances have posed diagnostic and monitoring challenges. The authors aim to summarise these challenges and make evidence-based recommendations regarding imaging assessment for both clinicians and radiologists.

STUDY DESIGN

A committee of 21 experts in CF from the 10 largest specialist centres in Italy was convened, including a radiologist and a pulmonologist from each centre, with the overall aim of developing clear and actionable recommendations for lung imaging in CF. An a priori threshold of at least 80% of the votes was required for acceptance of each statement of recommendation.

RESULTS

After a systematic review of the relevant literature, the committee convened to evaluate 167 articles. Following five RAND conferences, consensus statements were developed by an executive subcommittee. The entire consensus committee voted and approved 28 main statements.

CONCLUSIONS

There is a need for international guidelines regarding the appropriate timing and selection of imaging modality for patients with CF lung disease; timing and selection depends upon the clinical scenario, the patient's age, lung function and type of treatment. Despite its ubiquity, the use of the chest radiograph remains controversial. Both computed tomography and magnetic resonance imaging should be routinely used to monitor CF lung disease. Future studies should focus on imaging protocol harmonisation both for computed tomography and for magnetic resonance imaging. The introduction of artificial intelligence imaging analysis may further revolutionise clinical practice by providing fast and reliable quantitative outcomes to assess disease status. To date, there is no evidence supporting the use of lung ultrasound to monitor CF lung disease.

Towards Accurate Point-of-Care Tests for Tuberculosis in Children

In childhood tuberculosis (TB), with an estimated 69% of missed cases in children under 5 years of age, the case detection gap is larger than in other age groups, mainly due to its paucibacillary nature and children’s difficulties in delivering sputum specimens. Accurate and accessible point-of-care tests (POCTs) are needed to detect TB disease in children and, in turn, reduce TB-related morbidity and mortality in this vulnerable population. In recent years, several POCTs for TB have been developed. These include new tools to improve the detection of TB in respiratory and gastric samples, such as molecular detection of Mycobacterium tuberculosis using loop-mediated isothermal amplification (LAMP) and portable polymerase chain reaction (PCR)-based GeneXpert. In addition, the urine-based detection of lipoarabinomannan (LAM), as well as imaging modalities through point-of-care ultrasonography (POCUS), are currently the POCTs in use. Further to this, artificial intelligence-based interpretation of ultrasound imaging and radiography is now integrated into computer-aided detection products. In the future, portable radiography may become more widely available, and robotics-supported ultrasound imaging is currently being trialed. Finally, novel blood-based tests evaluating the immune response using “omic-“techniques are underway. This approach, including transcriptomics, metabolomic, proteomics, lipidomics and genomics, is still distant from being translated into POCT formats, but the digital development may rapidly enhance innovation in this field. Despite these significant advances, TB-POCT development and implementation remains challenged by the lack of standard ways to access non-sputum-based samples, the need to differentiate TB infection from disease and to gain acceptance for novel testing strategies specific to the conditions and settings of use.