Integrating molecular and radiological screening tools during community-based active case-finding for tuberculosis and COVID-19 in southern Africa.

OBJECTIVES: To evaluate diagnostic yield and feasibility of integrating testing for TB and COVID-19 using molecular and radiological screening tools during community-based active case-finding (ACF). METHODS: Community-based participants with presumed TB and/or COVID-19 were recruited using a mobile clinic. Participants underwent simultaneous point-of-care (POC) testing for TB (sputum; Xpert Ultra) and COVID-19 (nasopharyngeal swabs; Xpert SARS-CoV-2). Sputum culture and SARS-CoV-2 RT-PCR served as reference standards. Participants underwent ultra-portable POC chest radiography with computer-aided detection (CAD). TB infectiousness was evaluated using smear microscopy, cough aerosol sampling studies (CASS), and chest radiographic cavity detection. Feasibility of POC testing was evaluated via user-appraisals. RESULTS: Six hundred and one participants were enrolled, with 144/601 (24.0%) reporting symptoms suggestive of TB and/or COVID-19. 16/144 (11.1%) participants tested positive for TB, while 10/144 (6.9%) tested positive for COVID-19 (2/144 [1.4%] had concurrent TB/COVID-19). Seven (7/16 [43.8%]) individuals with TB were probably infectious. Test-specific sensitivity and specificity (95% CI) were: Xpert Ultra 75.0% (42.8-94.5) and 96.9% (92.4-99.2); Xpert SARS-CoV-2 66.7% (22.3-95.7) and 97.1% (92.7-99.2). Area under the curve (AUC) for CAD4TB was 0.90 (0.82-0.97). User appraisals indicated POC Xpert to have 'good' user-friendliness. CONCLUSIONS: Integrating TB/COVID-19 screening during community-based ACF using POC molecular and radiological tools is feasible, has a high diagnostic yield, and can identity probably infectious persons.

Performance of AI to exclude normal chest radiographs to reduce radiologists' workload.

INTRODUCTION: This study investigates the performance of a commercially available artificial intelligence (AI) system to identify normal chest radiographs and its potential to reduce radiologist workload. METHODS: Retrospective analysis included consecutive chest radiographs from two medical centers between Oct 1, 2016 and Oct 14, 2016. Exclusions comprised follow-up exams within the inclusion period, bedside radiographs, incomplete images, imported radiographs, and pediatric radiographs. Three chest radiologists categorized findings into normal, clinically irrelevant, clinically relevant, urgent, and critical. A commercial AI system processed all radiographs, scoring 10 chest abnormalities on a 0-100 confidence scale. AI system performance was evaluated using the area under the ROC curve (AUC), assessing the detection of normal radiographs. Sensitivity was calculated for the default and a conservative operating point. the detection of negative predictive value (NPV) for urgent and critical findings, as well as the potential workload reduction, was calculated. RESULTS: A total of 2603 radiographs were acquired in 2141 unique patients. Post-exclusion, 1670 radiographs were analyzed. Categories included 479 normal, 332 clinically irrelevant, 339 clinically relevant, 501 urgent, and 19 critical findings. The AI system achieved an AUC of 0.92. Sensitivity for normal radiographs was 92% at default and 53% at the conservative operating point. At the conservative operating point, NPV was 98% for urgent and critical findings, and could result in a 15% workload reduction. CONCLUSION: A commercially available AI system effectively identifies normal chest radiographs and holds the potential to lessen radiologists' workload by omitting half of the normal exams from reporting. CLINICAL RELEVANCE STATEMENT: The AI system is able to detect half of all normal chest radiographs at a clinically acceptable operating point, thereby potentially reducing the workload for the radiologists by 15%. KEY POINTS: The AI system reached an AUC of 0.92 for the detection of normal chest radiographs. Fifty-three percent of normal chest radiographs were identified with a NPV of 98% for urgent findings. AI can reduce the workload of chest radiography reporting by 15%.

Nodule detection and generation on chest X-rays: NODE21 Challenge.

Pulmonary nodules may be an early manifestation of lung cancer, the leading cause of cancer-related deaths among both men and women. Numerous studies have established that deep learning methods can yield high-performance levels in the detection of lung nodules in chest X-rays. However, the lack of gold-standard public datasets slows down the progression of the research and prevents benchmarking of methods for this task. To address this, we organized a public research challenge, NODE21, aimed at the detection and generation of lung nodules in chest X-rays. While the detection track assesses state-of-the-art nodule detection systems, the generation track determines the utility of nodule generation algorithms to augment training data and hence improve the performance of the detection systems. This paper summarizes the results of the NODE21 challenge and performs extensive additional experiments to examine the impact of the synthetically generated nodule training images on the detection algorithm performance.

Computer-aided detection thresholds for digital chest radiography interpretation in tuberculosis diagnostic algorithms.

Objectives: Use of computer-aided detection (CAD) software is recommended to improve tuberculosis screening and triage, but threshold determination is challenging if reference testing has not been performed in all individuals. We aimed to determine such thresholds through secondary analysis of the 2019 Lesotho national tuberculosis prevalence survey. Methods: Symptom screening and chest radiographs were performed in participants aged ≥15 years; those symptomatic or with abnormal chest radiographs provided samples for Xpert MTB/RIF and culture testing. Chest radiographs were processed using CAD4TB version 7. We used six methodological approaches to deal with participants who did not have bacteriological test results to estimate pulmonary tuberculosis prevalence and assess diagnostic accuracy. Results: Among 17 070 participants, 5214 (31%) had their tuberculosis status determined; 142 had tuberculosis. Prevalence estimates varied between methodological approaches (0.83-2.72%). Using multiple imputation to estimate tuberculosis status for those eligible but not tested, and assuming those not eligible for testing were negative, a CAD4TBv7 threshold of 13 had a sensitivity of 89.7% (95% CI 84.6-94.8) and a specificity of 74.2% (73.6-74.9), close to World Health Organization (WHO) target product profile criteria. Assuming all those not tested were negative produced similar results. Conclusions: This is the first study to evaluate CAD4TB in a community screening context employing a range of approaches to account for unknown tuberculosis status. The assumption that those not tested are negative - regardless of testing eligibility status - was robust. As threshold determination must be context specific, our analytically straightforward approach should be adopted to leverage prevalence surveys for CAD threshold determination in other settings with a comparable proportion of eligible but not tested participants.

COVID-19 screening in low resource settings using artificial intelligence for chest radiographs and point-of-care blood tests.

Artificial intelligence (AI) systems for detection of COVID-19 using chest X-Ray (CXR) imaging and point-of-care blood tests were applied to data from four low resource African settings. The performance of these systems to detect COVID-19 using various input data was analysed and compared with antigen-based rapid diagnostic tests. Participants were tested using the gold standard of RT-PCR test (nasopharyngeal swab) to determine whether they were infected with SARS-CoV-2. A total of 3737 (260 RT-PCR positive) participants were included. In our cohort, AI for CXR images was a poor predictor of COVID-19 (AUC = 0.60), since the majority of positive cases had mild symptoms and no visible pneumonia in the lungs. AI systems using differential white blood cell counts (WBC), or a combination of WBC and C-Reactive Protein (CRP) both achieved an AUC of 0.74 with a suggested optimal cut-off point at 83% sensitivity and 63% specificity. The antigen-RDT tests in this trial obtained 65% sensitivity at 98% specificity. This study is the first to validate AI tools for COVID-19 detection in an African setting. It demonstrates that screening for COVID-19 using AI with point-of-care blood tests is feasible and can operate at a higher sensitivity level than antigen testing.

Incidental radiological findings during clinical tuberculosis screening in Lesotho and South Africa: a case series.

BACKGROUND: Chest X-ray offers high sensitivity and acceptable specificity as a tuberculosis screening tool, but in areas with a high burden of tuberculosis, there is often a lack of radiological expertise to interpret chest X-ray. Computer-aided detection systems based on artificial intelligence are therefore increasingly used to screen for tuberculosis-related abnormalities on digital chest radiographies. The CAD4TB software has previously been shown to demonstrate high sensitivity for chest X-ray tuberculosis-related abnormalities, but it is not yet calibrated for the detection of non-tuberculosis abnormalities. When screening for tuberculosis, users of computer-aided detection need to be aware that other chest pathologies are likely to be as prevalent as, or more prevalent than, active tuberculosis. However, non--tuberculosis chest X-ray abnormalities detected during chest X-ray screening for tuberculosis remain poorly characterized in the sub-Saharan African setting, with only minimal literature. CASE PRESENTATION: In this case series, we report on four cases with non-tuberculosis abnormalities detected on CXR in TB TRIAGE + ACCURACY (ClinicalTrials.gov Identifier: NCT04666311), a study in adult presumptive tuberculosis cases at health facilities in Lesotho and South Africa to determine the diagnostic accuracy of two potential tuberculosis triage tests: computer-aided detection (CAD4TB v7, Delft, the Netherlands) and C-reactive protein (Alere Afinion, USA). The four Black African participants presented with the following chest X-ray abnormalities: a 59-year-old woman with pulmonary arteriovenous malformation, a 28-year-old man with pneumothorax, a 20-year-old man with massive bronchiectasis, and a 47-year-old woman with aspergilloma. CONCLUSIONS: Solely using chest X-ray computer-aided detection systems based on artificial intelligence as a tuberculosis screening strategy in sub-Saharan Africa comes with benefits, but also risks. Due to the limitation of CAD4TB for non-tuberculosis-abnormality identification, the computer-aided detection software may miss significant chest X-ray abnormalities that require treatment, as exemplified in our four cases. Increased data collection, characterization of non-tuberculosis anomalies and research on the implications of these diseases for individuals and health systems in sub-Saharan Africa is needed to help improve existing artificial intelligence software programs and their use in countries with high tuberculosis burden.

Impact of a multi-disease integrated screening and diagnostic model for COVID-19, TB, and HIV in Lesotho.

The surge of the COVID-19 pandemic challenged health services globally, and in Lesotho, the HIV and tuberculosis (TB) services were similarly affected. Integrated, multi-disease diagnostic services were proposed solutions to mitigate these disruptions. We describe and evaluate the effect of an integrated, hospital-based COVID-19, TB and HIV screening and diagnostic model in two rural districts in Lesotho, during the period between December 2020 and August 2022. Adults, hospital staff, and children above 5 years attending two hospitals were pre-screened for COVID-19 and TB symptoms. After a positive pre-screening, participants were offered to enroll in a service model that included clinical evaluation, chest radiography, SARS-CoV-2, TB, and HIV testing. Participants diagnosed with COVID-19, TB, or HIV were contacted after 28 days to evaluate their health status and linkage to HIV and/or TB care services. Of the 179160 participants pre-screened, 6623(3.7%) pre-screened positive, and 4371(66%) were enrolled in this service model. Of the total 458 diagnoses, only 17 happened in children. One positive rapid antigen test for SARS-CoV-2 was found per 11 participants enrolled, one Xpert-positive TB case was diagnosed per 85 people enrolled, and 1 new HIV diagnosis was done per 182 people enrolled. Of the 321(82.9%) participants contacted after 28 days of diagnosis, 304(94.7%) reported to be healthy. Of the individuals that were newly diagnosed with HIV or TB, 18/24(75.0%) and 46/51(90.1%) started treatment within 28 days of the diagnosis. This screening and diagnostic model successfully maintained same-day, integrated COVID-19, TB, and HIV testing services, despite frequent disruptions caused by the surge of COVID-19 waves, healthcare seeking patterns, and the volatile context (social measures, travel restrictions, population lockdowns). There were positive effects in avoiding diagnostic delays and ensuring linkage to services, however, diagnostic yields for adults and children were low. To inform future preparedness plans, research will need to identify essential health interventions and how to optimize them along each phase of the emergency response.

Optimising computer aided detection to identify intra-thoracic tuberculosis on chest x-ray in South African children.

Diagnostic tools for paediatric tuberculosis remain limited, with heavy reliance on clinical algorithms which include chest x-ray. Computer aided detection (CAD) for tuberculosis on chest x-ray has shown promise in adults. We aimed to measure and optimise the performance of an adult CAD system, CAD4TB, to identify tuberculosis on chest x-rays from children with presumptive tuberculosis. Chest x-rays from 620 children <13 years enrolled in a prospective observational diagnostic study in South Africa, were evaluated. All chest x-rays were read by a panel of expert readers who attributed each with a radiological reference of either 'tuberculosis' or 'not tuberculosis'. Of the 525 chest x-rays included in this analysis, 80 (40 with a reference of 'tuberculosis' and 40 with 'not tuberculosis') were allocated to an independent test set. The remainder made up the training set. The performance of CAD4TB to identify 'tuberculosis' versus 'not tuberculosis' on chest x-ray against the radiological reference read was calculated. The CAD4TB software was then fine-tuned using the paediatric training set. We compared the performance of the fine-tuned model to the original model. Our findings were that the area under the receiver operating characteristic curve (AUC) of the original CAD4TB model, prior to fine-tuning, was 0.58. After fine-tuning there was an improvement in the AUC to 0.72 (p = 0.0016). In this first-ever description of the use of CAD to identify tuberculosis on chest x-ray in children, we demonstrate a significant improvement in the performance of CAD4TB after fine-tuning with a set of well-characterised paediatric chest x-rays. CAD has the potential to be a useful additional diagnostic tool for paediatric tuberculosis. We recommend replicating the methods we describe using a larger chest x-ray dataset from a more diverse population and evaluating the potential role of CAD to replace a human-read chest x-ray within treatment-decision algorithms for paediatric tuberculosis.

FRODO: An In-Depth Analysis of a System to Reject Outlier Samples From a Trained Neural Network.

An important limitation of state-of-the-art deep learning networks is that they do not recognize when their input is dissimilar to the data on which they were trained and proceed to produce outputs that will be unreliable or nonsensical. In this work, we describe FRODO (Free Rejection of Out-of-Distribution), a publicly available method that can be easily employed for any trained network to detect input data from a different distribution than is expected. FRODO uses the statistical distribution of intermediate layer outputs to define the expected in-distribution (ID) input image properties. New samples are judged based on the Mahalanobis distance (MD) of their layer outputs from the defined distribution. The method can be applied to any network, and we demonstrate the performance of FRODO in correctly rejecting OOD samples on three distinct architectures for classification, localization, and segmentation tasks in chest X-rays. A dataset of 21,576 X-ray images with 3,655 in-distribution samples is defined for testing. The remaining images are divided into four OOD categories of varying levels of difficulty, and performance at rejecting each type is evaluated using receiver operating characteristic (ROC) analysis. FRODO achieves areas under the ROC (AUC) of between 0.815 and 0.999 in distinguishing OOD samples of different types. This is shown to be comparable with the best-performing state-of-the-art method tested, with the substantial advantage that FRODO integrates seamlessly with any network and requires no extra model to be constructed and trained.

Learn2Reg: Comprehensive Multi-Task Medical Image Registration Challenge, Dataset and Evaluation in the Era of Deep Learning.

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration data set for comprehensive characterisation of deformable registration algorithms. A continuous evaluation will be possible at https://learn2reg.grand-challenge.org. Learn2Reg covers a wide range of anatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR), availability of annotations, as well as intra- and inter-patient registration evaluation. We established an easily accessible framework for training and validation of 3D registration methods, which enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. This paper describes datasets, tasks, evaluation methods and results of the challenge, as well as results of further analysis of transferability to new datasets, the importance of label supervision, and resulting bias. While no single approach worked best across all tasks, many methodological aspects could be identified that push the performance of medical image registration to new state-of-the-art performance. Furthermore, we demystified the common belief that conventional registration methods have to be much slower than deep-learning-based methods.

Explainable emphysema detection on chest radiographs with deep learning.

We propose a deep learning system to automatically detect four explainable emphysema signs on frontal and lateral chest radiographs. Frontal and lateral chest radiographs from 3000 studies were retrospectively collected. Two radiologists annotated these with 4 radiological signs of pulmonary emphysema identified from the literature. A patient with ≥2 of these signs present is considered emphysema positive. Using separate deep learning systems for frontal and lateral images we predict the presence of each of the four visual signs and use these to determine emphysema positivity. The ROC and AUC results on a set of 422 held-out cases, labeled by both radiologists, are reported. Comparison with a black-box model which predicts emphysema without the use of explainable visual features is made on the annotations from both radiologists, as well as the subset that they agreed on. DeLong's test is used to compare with the black-box model ROC and McNemar's test to compare with radiologist performance. In 422 test cases, emphysema positivity was predicted with AUCs of 0.924 and 0.946 using the reference standard from each radiologist separately. Setting model sensitivity equivalent to that of the second radiologist, our model has a comparable specificity (p = 0.880 and p = 0.143 for each radiologist respectively). Our method is comparable with the black-box model with AUCs of 0.915 (p = 0.407) and 0.935 (p = 0.291), respectively. On the 370 cases where both radiologists agreed (53 positives), our model achieves an AUC of 0.981, again comparable to the black-box model AUC of 0.972 (p = 0.289). Our proposed method can predict emphysema positivity on chest radiographs as well as a radiologist or a comparable black-box method. It additionally produces labels for four visual signs to ensure the explainability of the result. The dataset is publicly available at https://doi.org/10.5281/zenodo.6373392.

Automated estimation of total lung volume using chest radiographs and deep learning.

BACKGROUND: Total lung volume is an important quantitative biomarker and is used for the assessment of restrictive lung diseases. PURPOSE: In this study, we investigate the performance of several deep-learning approaches for automated measurement of total lung volume from chest radiographs. METHODS: About 7621 posteroanterior and lateral view chest radiographs (CXR) were collected from patients with chest CT available. Similarly, 928 CXR studies were chosen from patients with pulmonary function test (PFT) results. The reference total lung volume was calculated from lung segmentation on CT or PFT data, respectively. This dataset was used to train deep-learning architectures to predict total lung volume from chest radiographs. The experiments were constructed in a stepwise fashion with increasing complexity to demonstrate the effect of training with CT-derived labels only and the sources of error. The optimal models were tested on 291 CXR studies with reference lung volume obtained from PFT. Mean absolute error (MAE), mean absolute percentage error (MAPE), and Pearson correlation coefficient (Pearson's r) were computed. RESULTS: The optimal deep-learning regression model showed an MAE of 408 ml and an MAPE of 8.1% using both frontal and lateral chest radiographs as input. The predictions were highly correlated with the reference standard (Pearson's r = 0.92). CT-derived labels were useful for pretraining but the optimal performance was obtained by fine-tuning the network with PFT-derived labels. CONCLUSION: We demonstrate, for the first time, that state-of-the-art deep-learning solutions can accurately measure total lung volume from plain chest radiographs. The proposed model is made publicly available and can be used to obtain total lung volume from routinely acquired chest radiographs at no additional cost. This deep-learning system can be a useful tool to identify trends over time in patients referred regularly for chest X-ray.

Deep learning with robustness to missing data: A novel approach to the detection of COVID-19.

In the context of the current global pandemic and the limitations of the RT-PCR test, we propose a novel deep learning architecture, DFCN (Denoising Fully Connected Network). Since medical facilities around the world differ enormously in what laboratory tests or chest imaging may be available, DFCN is designed to be robust to missing input data. An ablation study extensively evaluates the performance benefits of the DFCN as well as its robustness to missing inputs. Data from 1088 patients with confirmed RT-PCR results are obtained from two independent medical facilities. The data includes results from 27 laboratory tests and a chest x-ray scored by a deep learning model. Training and test datasets are taken from different medical facilities. Data is made publicly available. The performance of DFCN in predicting the RT-PCR result is compared with 3 related architectures as well as a Random Forest baseline. All models are trained with varying levels of masked input data to encourage robustness to missing inputs. Missing data is simulated at test time by masking inputs randomly. DFCN outperforms all other models with statistical significance using random subsets of input data with 2-27 available inputs. When all 28 inputs are available DFCN obtains an AUC of 0.924, higher than any other model. Furthermore, with clinically meaningful subsets of parameters consisting of just 6 and 7 inputs respectively, DFCN achieves higher AUCs than any other model, with values of 0.909 and 0.919.

Deep learning for chest X-ray analysis: A survey.

Recent advances in deep learning have led to a promising performance in many medical image analysis tasks. As the most commonly performed radiological exam, chest radiographs are a particularly important modality for which a variety of applications have been researched. The release of multiple, large, publicly available chest X-ray datasets in recent years has encouraged research interest and boosted the number of publications. In this paper, we review all studies using deep learning on chest radiographs published before March 2021, categorizing works by task: image-level prediction (classification and regression), segmentation, localization, image generation and domain adaptation. Detailed descriptions of all publicly available datasets are included and commercial systems in the field are described. A comprehensive discussion of the current state of the art is provided, including caveats on the use of public datasets, the requirements of clinically useful systems and gaps in the current literature.

COVID-19 on Chest Radiographs: A Multireader Evaluation of an Artificial Intelligence System.

Background Chest radiography may play an important role in triage for coronavirus disease 2019 (COVID-19), particularly in low-resource settings. Purpose To evaluate the performance of an artificial intelligence (AI) system for detection of COVID-19 pneumonia on chest radiographs. Materials and Methods An AI system (CAD4COVID-XRay) was trained on 24 678 chest radiographs, including 1540 used only for validation while training. The test set consisted of a set of continuously acquired chest radiographs (n = 454) obtained in patients suspected of having COVID-19 pneumonia between March 4 and April 6, 2020, at one center (223 patients with positive reverse transcription polymerase chain reaction [RT-PCR] results, 231 with negative RT-PCR results). Radiographs were independently analyzed by six readers and by the AI system. Diagnostic performance was analyzed with the receiver operating characteristic curve. Results For the test set, the mean age of patients was 67 years ± 14.4 (standard deviation) (56% male). With RT-PCR test results as the reference standard, the AI system correctly classified chest radiographs as COVID-19 pneumonia with an area under the receiver operating characteristic curve of 0.81. The system significantly outperformed each reader (P < .001 using the McNemar test) at their highest possible sensitivities. At their lowest sensitivities, only one reader significantly outperformed the AI system (P = .04). Conclusion The performance of an artificial intelligence system in the detection of coronavirus disease 2019 on chest radiographs was comparable with that of six independent readers. © RSNA, 2020.

Computer aided detection of tuberculosis on chest radiographs: An evaluation of the CAD4TB v6 system.

There is a growing interest in the automated analysis of chest X-Ray (CXR) as a sensitive and inexpensive means of screening susceptible populations for pulmonary tuberculosis. In this work we evaluate the latest version of CAD4TB, a commercial software platform designed for this purpose. Version 6 of CAD4TB was released in 2018 and is here tested on a fully independent dataset of 5565 CXR images with GeneXpert (Xpert) sputum test results available (854 Xpert positive subjects). A subset of 500 subjects (50% Xpert positive) was reviewed and annotated by 5 expert observers independently to obtain a radiological reference standard. The latest version of CAD4TB is found to outperform all previous versions in terms of area under receiver operating curve (ROC) with respect to both Xpert and radiological reference standards. Improvements with respect to Xpert are most apparent at high sensitivity levels with a specificity of 76% obtained at a fixed 90% sensitivity. When compared with the radiological reference standard, CAD4TB v6 also outperformed previous versions by a considerable margin and achieved 98% specificity at the 90% sensitivity setting. No substantial difference was found between the performance of CAD4TB v6 and any of the various expert observers against the Xpert reference standard. A cost and efficiency analysis on this dataset demonstrates that in a standard clinical situation, operating at 90% sensitivity, users of CAD4TB v6 can process 132 subjects per day at an average cost per screen of $5.95 per subject, while users of version 3 process only 85 subjects per day at a cost of $8.38 per subject. At all tested operating points version 6 is shown to be more efficient and cost effective than any other version.

Automatic quantification of ischemic injury on diffusion-weighted MRI of neonatal hypoxic ischemic encephalopathy.

A fully automatic method for detection and quantification of ischemic lesions in diffusion-weighted MR images of neonatal hypoxic ischemic encephalopathy (HIE) is presented. Ischemic lesions are manually segmented by two independent observers in 1.5 T data from 20 subjects and an automatic algorithm using a random forest classifier is developed and trained on the annotations of observer 1. The algorithm obtains a median sensitivity and specificity of 0.72 and 0.99 respectively. F1-scores are calculated per subject for algorithm performance (median = 0.52) and observer 2 performance (median = 0.56). A paired t-test on the F1-scores shows no statistical difference between the algorithm and observer 2 performances. The method is applied to a larger dataset including 54 additional subjects scanned at both 1.5 T and 3.0 T. The algorithm findings are shown to correspond well with the injury pattern noted by clinicians in both 1.5 T and 3.0 T data and to have a strong relationship with outcome. The results of the automatic method are condensed to a single score for each subject which has significant correlation with an MR score assigned by experienced clinicians (p < 0.0001). This work represents a quantitative method of evaluating diffusion-weighted MR images in neonatal HIE and a first step in the development of an automatic system for more in-depth analysis and prognostication.

A survey of medical image registration - under review.

A retrospective view on the past two decades of the field of medical image registration is presented, guided by the article "A survey of medical image registration" (Maintz and Viergever, 1998). It shows that the classification of the field introduced in that article is still usable, although some modifications to do justice to advances in the field would be due. The main changes over the last twenty years are the shift from extrinsic to intrinsic registration, the primacy of intensity-based registration, the breakthrough of nonlinear registration, the progress of inter-subject registration, and the availability of generic image registration software packages. Two problems that were called urgent already 20 years ago, are even more urgent nowadays: Validation of registration methods, and translation of results of image registration research to clinical practice. It may be concluded that the field of medical image registration has evolved, but still is in need of further development in various aspects.

Computer-aided detection of pulmonary nodules: a comparative study using the public LIDC/IDRI database.

OBJECTIVES: To benchmark the performance of state-of-the-art computer-aided detection (CAD) of pulmonary nodules using the largest publicly available annotated CT database (LIDC/IDRI), and to show that CAD finds lesions not identified by the LIDC's four-fold double reading process. METHODS: The LIDC/IDRI database contains 888 thoracic CT scans with a section thickness of 2.5 mm or lower. We report performance of two commercial and one academic CAD system. The influence of presence of contrast, section thickness, and reconstruction kernel on CAD performance was assessed. Four radiologists independently analyzed the false positive CAD marks of the best CAD system. RESULTS: The updated commercial CAD system showed the best performance with a sensitivity of 82 % at an average of 3.1 false positive detections per scan. Forty-five false positive CAD marks were scored as nodules by all four radiologists in our study. CONCLUSIONS: On the largest publicly available reference database for lung nodule detection in chest CT, the updated commercial CAD system locates the vast majority of pulmonary nodules at a low false positive rate. Potential for CAD is substantiated by the fact that it identifies pulmonary nodules that were not marked during the extensive four-fold LIDC annotation process. KEY POINTS: • CAD systems should be validated on public, heterogeneous databases. • The LIDC/IDRI database is an excellent database for benchmarking nodule CAD. • CAD can identify the majority of pulmonary nodules at a low false positive rate. • CAD can identify nodules missed by an extensive two-stage annotation process.

Automated analysis of multi-channel EEG in preterm infants.

OBJECTIVE: To develop and validate two automatic methods for the detection of burst and interburst periods in preterm eight-channel electroencephalographs (EEG). To perform a detailed analysis of interobserver agreement on burst and interburst periods and use this as a benchmark for the performance of the automatic methods. To examine mathematical features of the EEG signal and their potential correlation with gestational age. METHODS: Multi-channel EEG from 36 infants, born at less than 30 weeks gestation was utilised, with a 10 min artifact-free epoch selected for each subject. Three independent expert observers annotated all EEG activity bursts in the dataset. Two automatic algorithms for burst/interburst detection were applied to the EEG data and their performances were analysed and compared with interobserver agreement. A total of 12 mathematical features of the EEG signal were calculated and correlated with gestational age. RESULTS: The mean interobserver agreement was found to be 77% while mean algorithm/observer agreement was 81%. Six of the mathematical features calculated (spectral entropy, Higuchi fractal dimension, spectral edge frequency, variance, extrema median and Hilberts transform amplitude) were found to have significant correlation with gestational age. CONCLUSIONS: Automatic detection of burst/interburst periods has been performed in multi-channel EEG of 36 preterm infants. The algorithm agreement with expert observers is found to be on a par with interobserver agreement. Mathematical features of EEG have been calculated which show significant correlation with gestational age. SIGNIFICANCE: Automatic analysis of preterm multi-channel EEG is possible. The methods described here have the potential to be incorporated into a fully automatic system to quantitatively assess brain maturity from preterm EEG.