Cooperative AI training for cardiothoracic segmentation in computed tomography: An iterative multi-center annotation approach.

PURPOSE: Radiological reporting is transitioning to quantitative analysis, requiring large-scale multi-center validation of biomarkers. A major prerequisite and bottleneck for this task is the voxelwise annotation of image data, which is time-consuming for large cohorts. In this study, we propose an iterative training workflow to support and facilitate such segmentation tasks, specifically for high-resolution thoracic CT data. METHODS: Our study included 132 thoracic CT scans from clinical practice, annotated by 13 radiologists. In three iterative training experiments, we aimed to improve and accelerate segmentation of the heart and mediastinum. Each experiment started with manual segmentation of 5-25 CT scans, which served as training data for a nnU-Net. Further iterations incorporated AI pre-segmentation and human correction to improve accuracy, accelerate the annotation process, and reduce human involvement over time. RESULTS: Results showed consistent improvement in AI model quality with each iteration. Resampled datasets improved the Dice similarity coefficients for both the heart (DCS 0.91 [0.88; 0.92]) and the mediastinum (DCS 0.95 [0.94; 0.95]). Our AI models reduced human interaction time by 50 % for heart and 70 % for mediastinum segmentation in the most potent iteration. A model trained on only five datasets achieved satisfactory results (DCS > 0.90). CONCLUSIONS: The iterative training workflow provides an efficient method for training AI-based segmentation models in multi-center studies, improving accuracy over time and simultaneously reducing human intervention. Future work will explore the use of fewer initial datasets and additional pre-processing methods to enhance model quality.

[Is JAK inhibition an option in the treatment of interstitial lung disease in rheumatoid arthritis?] / Ist JAK-Hemmung eine Option in der Behandlung der interstitiellen Lungenerkrankung bei einer rheumatoiden Arthritis?

A 69-year-old male patient with seropositive erosive rheumatoid arthritis (RA) presented to our clinic due to progressive dyspnea. High-resolution computed tomography (HRCT) and immunological bronchioalveolar lavage revealed ground-glass opacities and a lymphocytic alveolitis caused by interstitial lung disease (ILD) in RA. Considering previous forms of treatment, disease-modifying antirheumatic drug (DMARD) treatment was switched to tofacitinib. Tofacitinib treatment demonstrated a 33% reduction in ground-glass opacities by artificial intelligence-based quantification of pulmonary HRCT over the course of 6 months, which was associated with an improvement in dyspnea symptoms. In conclusion, tofacitinib represents an effective anti-inflammatory therapeutic option in the treatment of RA-ILD.

Computer-assisted image-based risk analysis and planning in lung surgery - a review.

In this paper, we give an overview on current trends in computer-assisted image-based methods for risk analysis and planning in lung surgery and present our own developments with a focus on computed tomography (CT) based algorithms and applications. The methods combine heuristic, knowledge based image processing algorithms for segmentation, quantification and visualization based on CT images of the lung. Impact for lung surgery is discussed regarding risk assessment, quantitative assessment of resection strategies, and surgical guiding. In perspective, we discuss the role of deep-learning based AI methods for further improvements.

When Treatment of Pulmonary Emphysema with Endobronchial Valves Did Not Work: Evaluation of Quantitative CT Analysis and Pulmonary Function Tests Before and After Valve Explantation.

Purpose: To investigate changes in quantitative CT analysis (QCT) and pulmonary function tests (PFT) in pulmonary emphysema patients who required premature removal of endobronchial valves (EBV). Patients and Methods: Our hospital's medical records listed 274 patients with high-grade COPD (GOLD stages 3 and 4) and pulmonary emphysema who were treated with EBV to reduce lung volume. Prior to intervention, a complete evaluation was performed that included quantitative computed tomography analysis (QCT) of scans acquired at full inspiration and full expiration, pulmonary function tests (PFT), and paraclinical findings (6-minute walking distance test (6MWDT) and quality of life questionnaires). In 41 of these 274 patients, EBV treatment was unsuccessful and the valves had to be removed for various reasons. A total of 10 of these 41 patients ventured a second attempt at EBV therapy and underwent complete reevaluation. In our retrospective study, results from three time points were compared: Before EBV implantation (BL), after EBV implantation (TP2), and after EBV explantation (TP3). QCT parameters included lung volume, total emphysema score (TES, ie, the emphysema index) and the 15th percentile of lung attenuation (P15) for the whole lung and each lobe separately. Differences in these parameters between inspiration and expiration were calculated (Vol. Diff (%), TES Diff (%), P15 Diff (%)). The results of PFT and further clinical tests were taken from the patient's records. Results: We found persistent therapy effect in the target lobe even after valve explantation together with a compensatory hyperinflation of the rest of the lung. As a result of these two divergent effects, the volume of the total lung remained rather constant. Furthermore, there was a slight deterioration of the emphysema score for the whole lung, whereas the TES of the target lobe persistently improved. Conclusion: Interestingly, we found evidence that, contrary to our expectations, unsuccessful EBV therapy can have a persistent positive effect on target lobe QCT scores.

Automated Assessment of COVID-19 Reporting and Data System and Chest CT Severity Scores in Patients Suspected of Having COVID-19 Using Artificial Intelligence.

Background The coronavirus disease 2019 (COVID-19) pandemic has spread across the globe with alarming speed, morbidity, and mortality. Immediate triage of patients with chest infections suspected to be caused by COVID-19 using chest CT may be of assistance when results from definitive viral testing are delayed. Purpose To develop and validate an artificial intelligence (AI) system to score the likelihood and extent of pulmonary COVID-19 on chest CT scans using the COVID-19 Reporting and Data System (CO-RADS) and CT severity scoring systems. Materials and Methods The CO-RADS AI system consists of three deep-learning algorithms that automatically segment the five pulmonary lobes, assign a CO-RADS score for the suspicion of COVID-19, and assign a CT severity score for the degree of parenchymal involvement per lobe. This study retrospectively included patients who underwent a nonenhanced chest CT examination because of clinical suspicion of COVID-19 at two medical centers. The system was trained, validated, and tested with data from one of the centers. Data from the second center served as an external test set. Diagnostic performance and agreement with scores assigned by eight independent observers were measured using receiver operating characteristic analysis, linearly weighted κ values, and classification accuracy. Results A total of 105 patients (mean age, 62 years ± 16 [standard deviation]; 61 men) and 262 patients (mean age, 64 years ± 16; 154 men) were evaluated in the internal and external test sets, respectively. The system discriminated between patients with COVID-19 and those without COVID-19, with areas under the receiver operating characteristic curve of 0.95 (95% CI: 0.91, 0.98) and 0.88 (95% CI: 0.84, 0.93), for the internal and external test sets, respectively. Agreement with the eight human observers was moderate to substantial, with mean linearly weighted κ values of 0.60 ± 0.01 for CO-RADS scores and 0.54 ± 0.01 for CT severity scores. Conclusion With high diagnostic performance, the CO-RADS AI system correctly identified patients with COVID-19 using chest CT scans and assigned standardized CO-RADS and CT severity scores that demonstrated good agreement with findings from eight independent observers and generalized well to external data. © RSNA, 2020 Supplemental material is available for this article.

Quantitative CT Analysis in Patients with Pulmonary Emphysema: Do Calculated Differences Between Full Inspiration and Expiration Correlate with Lung Function?

Purpose: The aim of this retrospective study was to evaluate correlations between parameters of quantitative computed tomography (QCT) analysis, especially the 15th percentile of lung attenuation (P15), and parameters of clinical tests in a large group of patients with pulmonary emphysema. Patients and Methods: One hundred and seventy-two patients with pulmonary emphysema and chronic obstructive pulmonary disease (COPD) global initiative for chronic obstructive lung disease (GOLD) stage 3 or 4 were assessed by nonenhanced thin-section CT scans in full inspiratory and expiratory breath-hold, pulmonary function test (PFT), a 6-minute walk test (6MWT), and quality of life questionnaires (SGRQ and CAT). QCT parameters included total lung volume (TLV), total emphysema score (TES), and P15, all measured at inspiration (IN) and expiration (EX). Differences between inspiration and expiration were calculated for TLV (TLVDiff), TES (TESDiff), and P15 (P15Diff). Spearman correlation analysis was performed. Results: CT-measured lung volume in inspiration (TLVIN) correlated strongly with spirometry-measured total lung capacity (TLC) (r=0.81, p<0.001) and moderately to strongly with residual volume (RV), forced vital capacity (FVC), and forced expiratory volume in 1 second (FEV1)/FVC (r=0.60, 0.56, and -0.49, each p<0.001). Lung volume in expiration (TLVEX) correlated moderately to strongly with TLC, RV and FEV1/FVC ratio (r=0.75, 0.66, and -0.43, each p<0.001). TES and P15 showed stronger correlations with the carbon monoxide transfer coefficient (KCO%) (r= -0.42, 0.44, both p<0.001), when measured during expiration. P15Diff correlated moderately with KCO% and carbon monoxide diffusing capacity (DLCO%) (r= 0.41, 0.40, both p<0.001). The 6MWT and most QCT parameters showed significant differences between COPD GOLD 3 and 4 groups. Conclusion: Our results suggest that QCT can help predict the severity of lung function decrease in patients with pulmonary emphysema and COPD GOLD 3 or 4. Some QCT parameters, including P15EX and P15Diff, correlated moderately to strongly with parameters of pulmonary function tests.

Evaluation of a deformable registration algorithm for subsequent lung computed tomography imaging during radiochemotherapy.

PURPOSE: Rating both a lung segmentation algorithm and a deformable image registration (DIR) algorithm for subsequent lung computed tomography (CT) images by different evaluation techniques. Furthermore, investigating the relative performance and the correlation of the different evaluation techniques to address their potential value in a clinical setting. METHODS: Two to seven subsequent CT images (69 in total) of 15 lung cancer patients were acquired prior, during, and after radiochemotherapy. Automated lung segmentations were compared to manually adapted contours. DIR between the first and all following CT images was performed with a fast algorithm specialized for lung tissue registration, requiring the lung segmentation as input. DIR results were evaluated based on landmark distances, lung contour metrics, and vector field inconsistencies in different subvolumes defined by eroding the lung contour. Correlations between the results from the three methods were evaluated. RESULTS: Automated lung contour segmentation was satisfactory in 18 cases (26%), failed in 6 cases (9%), and required manual correction in 45 cases (66%). Initial and corrected contours had large overlap but showed strong local deviations. Landmark-based DIR evaluation revealed high accuracy compared to CT resolution with an average error of 2.9 mm. Contour metrics of deformed contours were largely satisfactory. The median vector length of inconsistency vector fields was 0.9 mm in the lung volume and slightly smaller for the eroded volumes. There was no clear correlation between the three evaluation approaches. CONCLUSIONS: Automatic lung segmentation remains challenging but can assist the manual delineation process. Proven by three techniques, the inspected DIR algorithm delivers reliable results for the lung CT data sets acquired at different time points. Clinical application of DIR demands a fast DIR evaluation to identify unacceptable results, for instance, by combining different automated DIR evaluation methods.