ChatGPT yields low accuracy in determining LI-RADS scores based on free-text and structured radiology reports in German language.

Background: To investigate the feasibility of the large language model (LLM) ChatGPT for classifying liver lesions according to the Liver Imaging Reporting and Data System (LI-RADS) based on MRI reports, and to compare classification performance on structured vs. unstructured reports. Methods: LI-RADS classifiable liver lesions were included from German written structured and unstructured MRI reports with report of size, location, and arterial phase contrast enhancement as minimum inclusion requirements. The findings sections of the reports were propagated to ChatGPT (GPT-3.5), which was instructed to determine LI-RADS scores for each classifiable liver lesion. Ground truth was established by two radiologists in consensus. Agreement between ground truth and ChatGPT was assessed with Cohen's kappa. Test-retest reliability was assessed by passing a subset of n = 50 lesions five times to ChatGPT, using the intraclass correlation coefficient (ICC). Results: 205 MRIs from 150 patients were included. The accuracy of ChatGPT at determining LI-RADS categories was poor (53% and 44% on unstructured and structured reports). The agreement to the ground truth was higher (k = 0.51 and k = 0.44), the mean absolute error in LI-RADS scores was lower (0.5 ± 0.5 vs. 0.6 ± 0.7, p < 0.05), and the test-retest reliability was higher (ICC = 0.81 vs. 0.50), in free-text compared to structured reports, respectively, although structured reports comprised the minimum required imaging features significantly more frequently (Chi-square test, p < 0.05). Conclusions: ChatGPT attained only low accuracy when asked to determine LI-RADS scores from liver imaging reports. The superior accuracy and consistency throughout free-text reports might relate to ChatGPT's training process. Clinical relevance statement: Our study indicates both the necessity of optimization of LLMs for structured clinical data input and the potential of LLMs for creating machine-readable labels based on large free-text radiological databases.

Pipeline Vantage Embolization Device for the treatment of intracranial aneurysms: A systematic review and meta-analysis.

OBJECTIVE: The Pipeline Vantage Embolization Device (PVED) is a novel coated flow diverter with reduced wire diameters to improve neoendothelialization and stent porosity. This systematic review evaluates the safety and efficacy of the PVED based on the current literature. METHODS: Following the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines, a thorough literature search was conducted using PubMed, EMBASE, and Cochrane. The random effects model was used to calculate estimates with major neurological complications within 30 days of treatment as the primary safety endpoint and ≤1-year complete occlusion rate as the primary efficacy endpoint. RESULTS: Six single-arm studies (5 retrospective, 1 prospective) with 392 patients and 439 aneurysms (6.8% ruptured) were included. Antiplatelet regimens varied, but dual antiplatelet therapy was administered in the majority. The pooled technical success rate was 99.0% (95%CI, 98.0%-100%) with an average of 1.2 devices implanted per procedure. Balloon angioplasty was performed in 17.0% (95%CI, 6.4-27.6%) and adjunctive coiling in 28.0% (95%CI, 17.8-38.2%), with significant heterogeneity for both variables. Pooled estimates for major neurological complications were 3.5% (95%CI, 1.7%-5.2%) with total ischemic events in 4.1% (95% CI, 1.6%-6.6%) and hemorrhagic events in 1.0% (95% CI, 0.0%-1.9%). The rate of complete angiographic occlusion was 75.7% (95%CI, 70.7%-80.6%) at a mean follow-up of 7 months, with in-stent stenoses in 8.1% (95%CI, 4.5%-11.8%). CONCLUSIONS: The safety and efficacy profile of the PVED appears comparable to competing devices, with potentially fewer complications than first-generation flow diverters. Long-term and comparative studies are needed to further confirm these results.

Feasibility, Safety, and Efficacy of Endovascular vs. Surgical Treatment of Unruptured Multi-Sac Intracranial Aneurysms in a Single-Center Retrospective Series.

PURPOSE: Multi-sac aneurysms (MSAs) are not uncommon, but studies on their management are scarce. This study aims to evaluate and compare the feasibility, safety, and efficacy of MSAs treated with either clipping or coiling after interdisciplinary case discussion at our center. MATERIALS AND METHODS: We retrospectively analyzed MSAs treated by microsurgical clipping, coiling, or stent-assisted coiling (SAC). Treatment modalities, complications, angiographic results, and clinical outcomes were evaluated. Major neurological events were defined as a safety endpoint and complete occlusion as an efficacy endpoint. RESULTS: Ninety patients (mean age, 53.2±11.0 years; 73 [81.1%] females) with MSAs met our inclusion criteria (clipping, 50; coiling, 19; SAC, 21). Most aneurysms were located in the middle cerebral artery (48.9%). All clipping procedures were technically successful, but endovascular treatment failed in 1 coiling case, and a switch from coiling to SAC was required in 2 cases. The major event rates were 4.0% after clipping (1 major stroke and 1 intracranial hemorrhage) and 0% after endovascular therapy (P=0.667). At mid-term angiographic follow-up (mean 12.0±8.9 months), all 37 followed clipped aneurysms were completely occluded, compared to 8/17 (41.7%) after coiling and 11/15 (73.3%) after SAC (P<0.001). Coiling was significantly associated with incomplete occlusion in the adjusted analysis (odds ratio, 11.7; 95% confidence interval, 2.7-52.6; P=0.001). CONCLUSION: Both endovascular and surgical treatment were feasible and safe for MSAs. As coiling was associated with comparatively high recanalization rates, endovascular treatment may be preferred with stent support.

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.

Treatment of intracranial aneurysms with large-diameter (≥5.5 mm) Derivo Embolization Devices, with particular focus on 7 and 8 mm diameter devices.

OBJECTIVE: There are few studies on flow diverters with diameters >5 mm. We present our preliminary experience with the 5.5-8 mm Derivo Embolization Device (DED) implants for the treatment of cerebral aneurysms. METHODS: A consecutive series of 26 patients (median age: 60 years) treated for 32 aneurysms in 26 procedures was retrospectively analyzed for procedural characteristics, complications, and mid-term angiographic results. RESULTS: The median aneurysm size was 10.5 mm, 2 of 30 (6%) aneurysms were ruptured and 9 (28%) had a fusiform or dissecting morphology. DED implantation was performed in the internal carotid artery in 18 of 26 (69%) procedures and in the vertebrobasilar artery in 8 (31%). Device deployment failed in 1 (4%) procedure. The 7 and 8 mm implants were successfully deployed in 5 cases. Additional balloon angioplasty or stent implantation was performed in 3 (12%) cases to improve wall apposition. Complications included 1 (4%) major stroke and 2 (8%) minor strokes. Angiographic follow up at a mean of 6 months showed complete occlusion in 8 of30 (27%) aneurysms and favorable occlusion in 14 (47%). CONCLUSIONS: The use of large diameter DEDs was safe and feasible. The mid-term occlusion rates are acceptable considering the complex subset of aneurysms studied. Further studies are warranted to define the indications for large-diameter DEDs and to evaluate their long-term efficacy.

Long-term Safety and Efficacy of the Derivo Embolization Device in a Single-center Series.

PURPOSE: This study analyzes the long-term clinical and angiographic outcomes of the Derivo Embolization Device (DED), an advanced flow diverter device with an electropolished surface, for the treatment of intracranial aneurysms. METHODS: A consecutive series of 101 patients (mean age: 58 years, 72% female) treated with the DED for 122 aneurysms at a single center between 2017 and 2023 was retrospectively analyzed for major (change in National Institutes of Health Stroke Scale [NIHSS] score ≥ 4 points) and minor (change in NIHSS score < 4 points) neurological events, procedural morbidity (increase of at least one point on the modified Rankin Scale), and angiographic results. RESULTS: There were 14 (11%) recurrent aneurysms, 15 (12%) ruptured aneurysms, 26 (21%) posterior circulation aneurysms and 16 (13%) fusiform or dissecting aneurysms. Device deployment failed in 1 case (1%). Procedure-related symptomatic procedural complications consisted of 2 (2%) major events (1 major stroke and 1 vessel perforation with intracranial hemorrhage and infarction) and 6 minor events (6 minor strokes). Procedural morbidity was 5%. There were no late ischemic or hemorrhagic events during follow-up. Complete and favorable aneurysm occlusion was achieved in 54% (40/74) and 62% (46/74) at a mean of 5 months, 71% (27/38) and 87% (33/38) at a mean of 12 months, and 76% (25/33) and 97% (32/33) at a mean of 35 months, respectively. CONCLUSION: The results demonstrate progressive aneurysm occlusion beyond 12 months after DED implantation with an almost 100% favorable occlusion rate. Procedural morbidity was low and there were no late complications.

Safety and efficacy of coated flow diverters in the treatment of ruptured intracranial aneurysms: a retrospective multicenter study.

BACKGROUND: This multicenter study evaluated the safety and efficacy of coated flow diverters (cFDs) for the treatment of ruptured intracranial aneurysms. METHODS: Consecutive patients treated with different cFDs for ruptured aneurysms under tirofiban at eight neurovascular centers between 2016 and 2023 were retrospectively analyzed. The majority of patients were loaded with dual antiplatelet therapy after the treatment. Aneurysm occlusion was determined using the O'Kelly-Marotta (OKM) grading scale. Primary outcome measures were major procedural complications and aneurysmal rebleeding during hospitalization. RESULTS: The study included 60 aneurysms (posterior circulation: 28 (47%)) with a mean size of 5.8±4.7 mm. Aneurysm morphology was saccular in 28 (47%), blister-like in 12 (20%), dissecting in 13 (22%), and fusiform in 7 (12%). Technical success was 100% with a mean of 1.1 cFDs implanted per aneurysm. Adjunctive coiling was performed in 11 (18%) aneurysms. Immediate contrast retention was observed in 45 (75%) aneurysms. There was 1 (2%) major procedural complication (a major stroke, eventually leading to death) and no aneurysmal rebleeding. A good outcome (modified Rankin Scale 0-2) was achieved in 40 (67%) patients. At a mean follow-up of 6 months, 27/34 (79%) aneurysms were completely occluded (OKM D), 3/34 (9%) had an entry remnant (OKM C), and 4/34 (12%) had residual filling (OKM A or B). There was 1 (3%) severe in-stent stenosis during follow-up that was treated with balloon angioplasty. CONCLUSIONS: Treatment of ruptured aneurysms with cFDs was reasonably safe and efficient and thus represents a valid treatment option, especially for complex cases.

Potential of GPT-4 for Detecting Errors in Radiology Reports: Implications for Reporting Accuracy.

Background Errors in radiology reports may occur because of resident-to-attending discrepancies, speech recognition inaccuracies, and large workload. Large language models, such as GPT-4 (ChatGPT; OpenAI), may assist in generating reports. Purpose To assess effectiveness of GPT-4 in identifying common errors in radiology reports, focusing on performance, time, and cost-efficiency. Materials and Methods In this retrospective study, 200 radiology reports (radiography and cross-sectional imaging [CT and MRI]) were compiled between June 2023 and December 2023 at one institution. There were 150 errors from five common error categories (omission, insertion, spelling, side confusion, and other) intentionally inserted into 100 of the reports and used as the reference standard. Six radiologists (two senior radiologists, two attending physicians, and two residents) and GPT-4 were tasked with detecting these errors. Overall error detection performance, error detection in the five error categories, and reading time were assessed using Wald χ2 tests and paired-sample t tests. Results GPT-4 (detection rate, 82.7%;124 of 150; 95% CI: 75.8, 87.9) matched the average detection performance of radiologists independent of their experience (senior radiologists, 89.3% [134 of 150; 95% CI: 83.4, 93.3]; attending physicians, 80.0% [120 of 150; 95% CI: 72.9, 85.6]; residents, 80.0% [120 of 150; 95% CI: 72.9, 85.6]; P value range, .522-.99). One senior radiologist outperformed GPT-4 (detection rate, 94.7%; 142 of 150; 95% CI: 89.8, 97.3; P = .006). GPT-4 required less processing time per radiology report than the fastest human reader in the study (mean reading time, 3.5 seconds ± 0.5 [SD] vs 25.1 seconds ± 20.1, respectively; P < .001; Cohen d = -1.08). The use of GPT-4 resulted in lower mean correction cost per report than the most cost-efficient radiologist ($0.03 ± 0.01 vs $0.42 ± 0.41; P < .001; Cohen d = -1.12). Conclusion The radiology report error detection rate of GPT-4 was comparable with that of radiologists, potentially reducing work hours and cost. © RSNA, 2024 See also the editorial by Forman in this issue.

Immediate angiographic control after intra-arterial nimodipine administration underestimates the vasodilatory effect.

Intra-arterial nimodipine administration is a widely used rescue therapy for cerebral vasospasm. Although it is known that its effect sets in with delay, there is little evidence in current literature. Our aim was to prove that the maximal vasodilatory effect is underestimated in direct angiographic controls. We reviewed all cases of intra-arterial nimodipine treatment for subarachnoid hemorrhage-related cerebral vasospasm between January 2021 and December 2022. Inclusion criteria were availability of digital subtraction angiography runs before and after nimodipine administration and a delayed run for the most affected vessel at the end of the procedure to decide on further escalation of therapy. We evaluated nimodipine dose, timing of administration and vessel diameters. Delayed runs were performed in 32 cases (19 patients) with a mean delay of 37.6 (± 16.6) min after nimodipine administration and a mean total nimodipine dose of 4.7 (± 1.2) mg. Vessel dilation was more pronounced in delayed vs. immediate controls, with greater changes in spastic vessel segments (n = 31: 113.5 (± 78.5%) vs. 32.2% (± 27.9%), p < 0.0001) vs. non-spastic vessel segments (n = 32: 23.1% (± 13.5%) vs. 13.3% (± 10.7%), p < 0.0001). In conclusion intra-arterially administered nimodipine seems to exert a delayed vasodilatory effect, which should be considered before escalation of therapy.

The worldwide COVID-19 pandemic caused a decline in sonographic examinations - is this a continuing trend?

PURPOSE: Due to the increasing number of COVID-19 infections since spring 2020 the patient care workflow underwent changes in Germany. To minimize face-to-face exposure and reduce infection risk, non-time-critical elective medical procedures were postponed. Since ultrasound examinations include non-time-critical elective examinations and often can be substituted by other imaging modalities not requiring direct patient contact, the number of examinations has declined significantly. The aim of this study is to quantify the baseline number of ultrasound examinations in the years before, during, and in the early post-pandemic period of the COVID-19 pandemic (since January 2015 to September 2023), and to measure the number of examinations at different German university hospitals. MATERIALS AND METHODS: The number of examinations was assessed based on a web-based database at all participating clinics at the indicated time points. RESULTS: N = 288 562 sonographic examinations from four sites were included in the present investigation. From January 2020 to June 2020, a significantly lower number of examinations of n = 591.21 vs. 698.43 (p = 0.01) per month and included center was performed. Also, excluding the initial pandemic period until June 2020, significantly fewer ultrasound examinations were performed compared to pre-pandemic years 648.1 vs. 698.4 (p < 0.05), per month and included center, while here differences between the individual centers were observed. In the late phase of the pandemic (n = 681.96) and in the post-pandemic phase (as defined by the WHO criteria from May 2023; n = 739.95), the number of sonographic examinations returned to pre-pandemic levels. CONCLUSION: The decline in the number of sonographic examinations caused by the COVID-19 pandemic was initially largely intentional and can be illustrated quantitatively. After an initial abrupt decline in sonographic examinations, the pre-pandemic levels could not be reached for a long time, which could be due to restructuring of patient care and follow-up treatment. In the post-pandemic phase, the pre-pandemic level has been achieved again. The reasons for a prolonged reduction in ultrasound examinations are discussed in this article. KEY POINTS: · During the pandemic, significantly fewer ultrasound examinations were performed in the included centers.. · The number of examinations could not be reach the pre-pandemic level for a long time, which could be due to restructuring of patient care and follow-up treatment.. · Identifying causes for sonographic exam reduction is crucial in pandemic preparedness to uphold healthcare quality and continuity for all patients.. · The prolonged decline in sonographic examinations during the pandemic does not represent a lasting trend, as evidenced by the return to pre-pandemic levels..

Standardization of a CT Protocol for Imaging Patients with Suspected COVID-19-A RACOON Project.

CT protocols that diagnose COVID-19 vary in regard to the associated radiation exposure and the desired image quality (IQ). This study aims to evaluate CT protocols of hospitals participating in the RACOON (Radiological Cooperative Network) project, consolidating CT protocols to provide recommendations and strategies for future pandemics. In this retrospective study, CT acquisitions of COVID-19 patients scanned between March 2020 and October 2020 (RACOON phase 1) were included, and all non-contrast protocols were evaluated. For this purpose, CT protocol parameters, IQ ratings, radiation exposure (CTDIvol), and central patient diameters were sampled. Eventually, the data from 14 sites and 534 CT acquisitions were analyzed. IQ was rated good for 81% of the evaluated examinations. Motion, beam-hardening artefacts, or image noise were reasons for a suboptimal IQ. The tube potential ranged between 80 and 140 kVp, with the majority between 100 and 120 kVp. CTDIvol was 3.7 ± 3.4 mGy. Most healthcare facilities included did not have a specific non-contrast CT protocol. Furthermore, CT protocols for chest imaging varied in their settings and radiation exposure. In future, it will be necessary to make recommendations regarding the required IQ and protocol parameters for the majority of CT scanners to enable comparable IQ as well as radiation exposure for different sites but identical diagnostic questions.

Aneurysm Treatment With the Pipeline Vantage Embolization Device in Retrospective Evaluation: Periprocedural Results from the Pipe-VADER Study.

OBJECTIVE: The Pipeline Vantage Embolization Device is a fourth-generation flow diverter with an antithrombotic coating and a reduced profile compared to previous Pipeline versions. The objective of this study was to evaluate the procedural feasibility, safety, and efficacy of this device. METHODS: The Pipe-VADER study was designed as a retrospective, observational study of consecutive patients treated with the Vantage at 3 neurovascular centers. Patient and aneurysm characteristics, procedural parameters, early complications, and extent of postinterventional contrast retention were analyzed on an intention-to-treat basis. RESULTS: Twenty-eight patients with 31 aneurysms (median size: 5.0 mm, posterior circulation: 4 [12.9%], ruptured: 5 [16.1%]) were included. The technical success rate was 100%, with multiple stents used in 4/30 (13.3%) procedures. Of the 30 procedures, adjunctive coiling was performed in 3 (10.0%) and balloon angioplasty in 2 (6.7%). Median procedure time was 62 minutes. Procedural ischemic stroke occured in 4 (13.3%) cases, whereof 2 were major strokes (6.6%). There were no hemorrhagic complications. Initial contrast retention was observed in 29/31 (93.5%) aneurysms. All 27 overstented side vessels were patent at the end of the procedure. Short-term follow-up (median: 5 months) showed complete and favorable occlusion rates of 70% (14/20) and 80% (16/20), respectively. CONCLUSIONS: The new Pipeline Vantage appears to be safe and feasible for the treatment of intracranial aneurysms and warrants further evaluation.

Physiological iodine uptake of the spine's bone marrow in dual-energy computed tomography - using artificial intelligence to define reference values based on 678 CT examinations of 189 individuals.

Purpose: The bone marrow's iodine uptake in dual-energy CT (DECT) is elevated in malignant disease. We aimed to investigate the physiological range of bone marrow iodine uptake after intravenous contrast application, and examine its dependence on vBMD, iodine blood pool, patient age, and sex. Method: Retrospective analysis of oncological patients without evidence of metastatic disease. DECT examinations were performed on a spectral detector CT scanner in portal venous contrast phase. The thoracic and lumbar spine were segmented by a pre-trained neural network, obtaining volumetric iodine concentration data [mg/ml]. vBMD was assessed using a phantomless, CE-certified software [mg/cm3]. The iodine blood pool was estimated by ROI-based measurements in the great abdominal vessels. A multivariate regression model was fit with the dependent variable "median bone marrow iodine uptake". Standardized regression coefficients (ß) were calculated to assess the impact of each covariate. Results: 678 consecutive DECT exams of 189 individuals (93 female, age 61.4 ± 16.0 years) were evaluated. AI-based segmentation provided volumetric data of 97.9% of the included vertebrae (n=11,286). The 95th percentile of bone marrow iodine uptake, as a surrogate for the upper margin of the physiological distribution, ranged between 4.7-6.4 mg/ml. vBMD (p <0.001, mean ß=0.50) and portal vein iodine blood pool (p <0.001, mean ß=0.43) mediated the strongest impact. Based thereon, adjusted reference values were calculated. Conclusion: The bone marrow iodine uptake demonstrates a distinct profile depending on vBMD, iodine blood pool, patient age, and sex. This study is the first to provide the adjusted reference values.

GPT-4 for Automated Determination of Radiological Study and Protocol based on Radiology Request Forms: A Feasibility Study.

Published under a CC BY 4.0 license.

Conventional and Deep-Learning-Based Image Reconstructions of Undersampled K-Space Data of the Lumbar Spine Using Compressed Sensing in MRI: A Comparative Study on 20 Subjects.

Compressed sensing accelerates magnetic resonance imaging (MRI) acquisition by undersampling of the k-space. Yet, excessive undersampling impairs image quality when using conventional reconstruction techniques. Deep-learning-based reconstruction methods might allow for stronger undersampling and thus faster MRI scans without loss of crucial image quality. We compared imaging approaches using parallel imaging (SENSE), a combination of parallel imaging and compressed sensing (COMPRESSED SENSE, CS), and a combination of CS and a deep-learning-based reconstruction (CS AI) on raw k-space data acquired at different undersampling factors. 3D T2-weighted images of the lumbar spine were obtained from 20 volunteers, including a 3D sequence (standard SENSE), as provided by the manufacturer, as well as accelerated 3D sequences (undersampling factors 4.5, 8, and 11) reconstructed with CS and CS AI. Subjective rating was performed using a 5-point Likert scale to evaluate anatomical structures and overall image impression. Objective rating was performed using apparent signal-to-noise and contrast-to-noise ratio (aSNR and aCNR) as well as root mean square error (RMSE) and structural-similarity index (SSIM). The CS AI 4.5 sequence was subjectively rated better than the standard in several categories and deep-learning-based reconstructions were subjectively rated better than conventional reconstructions in several categories for acceleration factors 8 and 11. In the objective rating, only aSNR of the bone showed a significant tendency towards better results of the deep-learning-based reconstructions. We conclude that CS in combination with deep-learning-based image reconstruction allows for stronger undersampling of k-space data without loss of image quality, and thus has potential for further scan time reduction.

Morphological appearance of the B.1.1.7 mutation of the novel coronavirus 2 (SARS-CoV-2) in chest CT.

Background: Diagnosing a coronavirus disease 2019 (COVID-19) infection with high specificity in chest computed tomography (CT) imaging is considered possible due to distinctive imaging features of COVID-19 pneumonia. Since other viral non-COVID pneumonia show mostly a different distribution pattern, it is reasonable to assume that the patterns observed caused by the novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are a consequence of its genetically encoded molecular properties when interacting with the respiratory tissue. As more mutations of the initial SARS-CoV-2 wild-type with varying aggressiveness have been detected in the course of 2021, it became obvious that its genome is in a state of transformation and therefore a potential modification of the specific morphological appearance in CT may occur. The aim of this study was to quantitatively analyze the morphological differences of the SARS-CoV-2-B.1.1.7 mutation and wildtype variant in CT scans of the thorax. Methods: We analyzed a dataset of 140 patients, which was divided into pneumonias caused by n=40 wildtype variants, n=40 B.1.1.7 variants, n=20 bacterial pneumonias, n=20 viral (non-COVID) pneumonias, and a test group of n=20 unremarkable CT examinations of the thorax. Semiautomated 3D segmentation of the lung tissue was performed for quantification of lung pathologies. The extent, ratio, and specific distribution of inflammatory affected lung tissue in each group were compared in a multivariate group analysis. Results: Lung segmentation revealed significant difference between the extent of ground glass opacities (GGO) or consolidation comparing SARS-CoV-2 wild-type and B.1.1.7 variant. Wildtype and B.1.1.7 variant showed both a symmetric distribution pattern of stage-dependent GGO and consolidation within matched COVID-19 stages. Viral non-COVID pneumonias had significantly fewer consolidations than the bacterial, but also than the COVID-19 B.1.1.7 variant groups. Conclusions: CT based segmentation showed no significant difference between the morphological appearance of the COVID-19 wild-type variant and the SARS-CoV-2 B.1.1.7 mutation. However, our approach allowed a semiautomatic quantification of bacterial and viral lung pathologies. Quantitative CT image analyses, such as the one presented, appear to be an important component of pandemic preparedness considering an organism with ongoing genetic change, to describe a potential arising change in CT morphological appearance of possible new upcoming COVID-19 variants of concern.

AI support for accurate and fast radiological diagnosis of COVID-19: an international multicenter, multivendor CT study.

OBJECTIVES: Differentiation between COVID-19 and community-acquired pneumonia (CAP) in computed tomography (CT) is a task that can be performed by human radiologists and artificial intelligence (AI). The present study aims to (1) develop an AI algorithm for differentiating COVID-19 from CAP and (2) evaluate its performance. (3) Evaluate the benefit of using the AI result as assistance for radiological diagnosis and the impact on relevant parameters such as accuracy of the diagnosis, diagnostic time, and confidence. METHODS: We included n = 1591 multicenter, multivendor chest CT scans and divided them into AI training and validation datasets to develop an AI algorithm (n = 991 CT scans; n = 462 COVID-19, and n = 529 CAP) from three centers in China. An independent Chinese and German test dataset of n = 600 CT scans from six centers (COVID-19 / CAP; n = 300 each) was used to test the performance of eight blinded radiologists and the AI algorithm. A subtest dataset (180 CT scans; n = 90 each) was used to evaluate the radiologists' performance without and with AI assistance to quantify changes in diagnostic accuracy, reporting time, and diagnostic confidence. RESULTS: The diagnostic accuracy of the AI algorithm in the Chinese-German test dataset was 76.5%. Without AI assistance, the eight radiologists' diagnostic accuracy was 79.1% and increased with AI assistance to 81.5%, going along with significantly shorter decision times and higher confidence scores. CONCLUSION: This large multicenter study demonstrates that AI assistance in CT-based differentiation of COVID-19 and CAP increases radiological performance with higher accuracy and specificity, faster diagnostic time, and improved diagnostic confidence. KEY POINTS: • AI can help radiologists to get higher diagnostic accuracy, make faster decisions, and improve diagnostic confidence. • The China-German multicenter study demonstrates the advantages of a human-machine interaction using AI in clinical radiology for diagnostic differentiation between COVID-19 and CAP in CT scans.

Assessment of COVID-19 lung involvement on computed tomography by deep-learning-, threshold-, and human reader-based approaches-an international, multi-center comparative study.

Background: The extent of lung involvement in coronavirus disease 2019 (COVID-19) pneumonia, quantified on computed tomography (CT), is an established biomarker for prognosis and guides clinical decision-making. The clinical standard is semi-quantitative scoring of lung involvement by an experienced reader. We aim to compare the performance of automated deep-learning- and threshold-based methods to the manual semi-quantitative lung scoring. Further, we aim to investigate an optimal threshold for quantification of involved lung in COVID pneumonia chest CT, using a multi-center dataset. Methods: In total 250 patients were included, 50 consecutive patients with RT-PCR confirmed COVID-19 from our local institutional database, and another 200 patients from four international datasets (n=50 each). Lung involvement was scored semi-quantitatively by three experienced radiologists according to the established chest CT score (CCS) ranging from 0-25. Inter-rater reliability was reported by the intraclass correlation coefficient (ICC). Deep-learning-based segmentation of ground-glass and consolidation was obtained by CT Pulmo Auto Results prototype plugin on IntelliSpace Discovery (Philips Healthcare, The Netherlands). Threshold-based segmentation of involved lung was implemented using an open-source tool for whole-lung segmentation under the presence of severe pathologies (R231CovidWeb, Hofmanninger et al., 2020) and consecutive quantitative assessment of lung attenuation. The best threshold was investigated by training and testing a linear regression of deep-learning and threshold-based results in a five-fold cross validation strategy. Results: Median CCS among 250 evaluated patients was 10 [6-15]. Inter-rater reliability of the CCS was excellent [ICC 0.97 (0.97-0.98)]. Best attenuation threshold for identification of involved lung was -522 HU. While the relationship of deep-learning- and threshold-based quantification was linear and strong (r2 deep-learning vs. threshold=0.84), both automated quantification methods translated to the semi-quantitative CCS in a non-linear fashion, with an increasing slope towards higher CCS (r2 deep-learning vs. CCS= 0.80, r2 threshold vs. CCS=0.63). Conclusions: The manual semi-quantitative CCS underestimates the extent of COVID pneumonia in higher score ranges, which limits its clinical usefulness in cases of severe disease. Clinical implementation of fully automated methods, such as deep-learning or threshold-based approaches (best threshold in our multi-center dataset: -522 HU), might save time of trained personnel, abolish inter-reader variability, and allow for truly quantitative, linear assessment of COVID lung involvement.