Development and Evaluation of Deep Learning Models for Automated Estimation of Myelin Maturation Using Pediatric Brain MRI Scans.

Purpose: To predict the corresponding age of myelin maturation from brain MRI scans in infants and young children by using a deep learning algorithm and to build upon previously published models. Materials and Methods: Brain MRI scans acquired between January 1, 2011, and March 17, 2021, in our institution in patients aged 0-3 years were retrospectively retrieved from the archive. An ensemble of two-dimensional (2D) and three-dimensional (3D) convolutional neural network models was trained and internally validated in 710 patients to predict myelin maturation age on the basis of radiologist-generated labels. The model ensemble was tested on an internal dataset of 123 patients and two external datasets of 226 (0-25 months of age) and 383 (0-2 months of age) healthy children and infants, respectively. Mean absolute error (MAE) and Pearson correlation coefficients were used to assess model performance. Results: The 2D, 3D, and 2D-plus-3D ensemble models showed MAE values of 1.43, 2.55, and 1.77 months, respectively, on the internal test set, values of 2.26, 2.27, and 1.22 months on the first external test set, and values of 0.44, 0.27, and 0.31 months on the second external test set. The ensemble model outperformed the previous state-of-the-art model on the same external test set (MAE = 1.22 vs 2.09 months). Conclusion: The proposed deep learning model accurately predicted myelin maturation age using pediatric brain MRI scans and may help reduce the time needed to complete this task, as well as interobserver variability in radiologist predictions.Keywords: Pediatrics, MR Imaging, CNS, Brain/Brain Stem, Convolutional Neural Network (CNN), Artificial Intelligence, Pediatric Imaging, Myelin Maturation, Brain MRI, Neuroradiology Supplemental material is available for this article. © RSNA, 2023.

3D-printed iodine-ink CT phantom for radiomics feature extraction - advantages and challenges.

BACKGROUND: To test and validate novel CT techniques, such as texture analysis in radiomics, repeat measurements are required. Current anthropomorphic phantoms lack fine texture and true anatomic representation. 3D-printing of iodinated ink on paper is a promising phantom manufacturing technique. Previously acquired or artificially created CT data can be used to generate realistic phantoms. PURPOSE: To present the design process of an anthropomorphic 3D-printed iodine ink phantom, highlighting the different advantages and pitfalls in its use. To analyze the phantom's X-ray attenuation properties, and the influences of the printing process on the imaging characteristics, by comparing it to the original input dataset. METHODS: Two patient CT scans and artificially generated test patterns were combined in a single dataset for phantom printing and cropped to a size of 26 × 19 × 30 cm3 . This DICOM dataset was printed on paper using iodinated ink. The phantom was CT-scanned and compared to the original image dataset used for printing the phantom. The water-equivalent diameter of the phantom was compared to that of a patient cohort (N = 104). Iodine concentrations in the phantom were measured using dual-energy CT. 86 radiomics features were extracted from 10 repeat phantom scans and the input dataset. Features were compared using a histogram analysis and a PCA individually and overall, respectively. The frequency content was compared using the normalized spectrum modulus. RESULTS: Low density structures are depicted incorrectly, while soft tissue structures show excellent visual accordance with the input dataset. Maximum deviations of around 30 HU between the original dataset and phantom HU values were observed. The phantom has X-ray attenuation properties comparable to a lightweight adult patient (∼54 kg, BMI 19 kg/m2 ). Iodine concentrations in the phantom varied between 0 and 50 mg/ml. PCA of radiomics features shows different tissue types separate in similar areas of PCA representation in the phantom scans as in the input dataset. Individual feature analysis revealed systematic shift of first order radiomics features compared to the original dataset, while some higher order radiomics features did not. The normalized frequency modulus |f(ω)| of the phantom data agrees well with the original data. However, all frequencies systematically occur more frequently in the phantom compared to the maximum of the spectrum modulus than in the original data set, especially for mid-frequencies (e.g., for ω = 0.3942 mm-1 , |f(ω)|original  = 0.09 * |fmax |original and |f(ω)|phantom  = 0.12 * |fmax |phantom ). CONCLUSIONS: 3D-iodine-ink-printing technology can be used to print anthropomorphic phantoms with a water-equivalent diameter of a lightweight adult patient. Challenges include small residual air enclosures and the fidelity of HU values. For soft tissue, there is a good agreement between the HU values of the phantom and input data set. Radiomics texture features of the phantom scans are similar to the input data set, but systematic shifts of radiomics features in first order features, due to differences in HU values, need to be considered. The paper substrate influences the spatial frequency distribution of the phantom scans. This phantom type is of very limited use for dual-energy CT analyses.

Visual and quantitative assessment of hip implant-related metal artifacts at low field MRI: a phantom study comparing a 0.55-T system with 1.5-T and 3-T systems.

BACKGROUND: To investigate hip implant-related metal artifacts on a 0.55-T system compared with 1.5-T and 3-T systems. METHODS: Total hip arthroplasty made of three different alloys were evaluated in a water phantom at 0.55, 1.5, and 3 T using routine protocols. Visually assessment (VA) was performed by three readers using a Likert scale from 0 (no artifacts) to 6 (extremely severe artifacts). Quantitative assessment (QA) was performed using the coefficient of variation (CoV) and the fraction of voxels within a threshold of the mean signal intensity compared to an automatically defined region of interest (FVwT). Agreement was evaluated using intra/inter-class correlation coefficient (ICC). RESULTS: Interreader agreement of VA was strong-to-moderate (ICC 0.74-0.82). At all field strengths (0.55-T/1.5-T/3-T), artifacts were assigned a lower score for titanium (Ti) alloys (2.44/2.9/2.7) than for stainless steel (Fe-Cr) (4.1/3.9/5.1) and cobalt-chromium (Co-Cr) alloys (4.1/4.1/5.2) (p < 0.001 for both). Artifacts were lower for 0.55-T and 1.5-T than for 3-T systems, for all implants (p ≤ 0.049). A strong VA-to-QA correlation was found (r = 0.81; p < 0.001); CoV was lower for Ti alloys than for Fe-Cr and Co-Cr alloys at all field strengths. The FVwT showed a negative correlation with VA (-0.68 < r < -0.84; p < 0.001). CONCLUSIONS: Artifact intensity was lowest for Ti alloys at 0.55 T. For other alloys, it was similar at 0.55 T and 1.5 T, higher at 3 T. Despite an inferior gradient system and a larger bore width, the 0.55-T system showed the same artifact intensity of the 1.5-T system.

Metal implants on abdominal CT: does split-filter dual-energy CT provide additional value over iterative metal artifact reduction?

PURPOSE: To assess image quality and metal artifact reduction in split-filter dual-energy CT (sfDECT) of the abdomen with hip or spinal implants using virtual monoenergetic images (VMI) and iterative metal artifact reduction algorithm (iMAR). METHODS: 102 portal-venous abdominal sfDECTs of patients with hip (n = 71) or spinal implants (n = 31) were included in this study. Images were reconstructed as 120kVp-equivalent images (Mixed) and VMI (40-190 keV), with and without iMAR. Quantitative artifact and image noise was measured using 12 different ROIs. Subjective image quality was rated by two readers using a five-point Likert-scale in six categories, including overall image quality and vascular contrast. RESULTS: Lowest quantitative artifact in both hip and spinal implants was measured in VMI190keV-iMAR. However, it was not significantly lower than in MixediMAR (for all ROIs, p = 1.00), which were rated best for overall image quality (hip: 1.00 [IQR: 1.00-2.00], spine: 3.00 [IQR:2.00-3.00]). VMI50keV-iMAR was rated best for vascular contrast (hip: 1.00 [IQR: 1.00-2.00], spine: 2.00 [IQR: 1.00-2.00]), which was significantly better than Mixed (both, p < 0.001). VMI50keV-iMAR provided superior overall image quality compared to Mixed for hip (1.00 vs 2.00, p < 0.001) and similar diagnostic image quality for spinal implants (2.00 vs 2.00, p = 0.51). CONCLUSION: For abdominal sfDECT with hip or spinal implants MixediMAR images should be used. High keV VMI do not further improve image quality. IMAR allows the use of low keV images (VMI50keV) to improve vascular contrast, compared to Mixed images.

Natural Language Processing and Graph Theory: Making Sense of Imaging Records in a Novel Representation Frame.

BACKGROUND: A concise visualization framework of related reports would increase readability and improve patient management. To this end, temporal referrals to prior comparative exams are an essential connection to previous exams in written reports. Due to unstructured narrative texts' variable structure and content, their extraction is hampered by poor computer readability. Natural language processing (NLP) permits the extraction of structured information from unstructured texts automatically and can serve as an essential input for such a novel visualization framework. OBJECTIVE: This study proposes and evaluates an NLP-based algorithm capable of extracting the temporal referrals in written radiology reports, applies it to all the radiology reports generated for 10 years, introduces a graphical representation of imaging reports, and investigates its benefits for clinical and research purposes. METHODS: In this single-center, university hospital, retrospective study, we developed a convolutional neural network capable of extracting the date of referrals from imaging reports. The model's performance was assessed by calculating precision, recall, and F1-score using an independent test set of 149 reports. Next, the algorithm was applied to our department's radiology reports generated from 2011 to 2021. Finally, the reports and their metadata were represented in a modulable graph. RESULTS: For extracting the date of referrals, the named-entity recognition (NER) model had a high precision of 0.93, a recall of 0.95, and an F1-score of 0.94. A total of 1,684,635 reports were included in the analysis. Temporal reference was mentioned in 53.3% (656,852/1,684,635), explicitly stated as not available in 21.0% (258,386/1,684,635), and omitted in 25.7% (317,059/1,684,635) of the reports. Imaging records can be visualized in a directed and modulable graph, in which the referring links represent the connecting arrows. CONCLUSIONS: Automatically extracting the date of referrals from unstructured radiology reports using deep learning NLP algorithms is feasible. Graphs refined the selection of distinct pathology pathways, facilitated the revelation of missing comparisons, and enabled the query of specific referring exam sequences. Further work is needed to evaluate its benefits in clinics, research, and resource planning.

Performance of a deep learning tool to detect missed aortic dilatation in a large chest CT cohort.

Purpose: Thoracic aortic (TA) dilatation (TAD) is a risk factor for acute aortic syndrome and must therefore be reported in every CT report. However, the complex anatomy of the thoracic aorta impedes TAD detection. We investigated the performance of a deep learning (DL) prototype as a secondary reading tool built to measure TA diameters in a large-scale cohort. Material and methods: Consecutive contrast-enhanced (CE) and non-CE chest CT exams with "normal" TA diameters according to their radiology reports were included. The DL-prototype (AIRad, Siemens Healthineers, Germany) measured the TA at nine locations according to AHA guidelines. Dilatation was defined as >45 mm at aortic sinus, sinotubular junction (STJ), ascending aorta (AA) and proximal arch and >40 mm from mid arch to abdominal aorta. A cardiovascular radiologist reviewed all cases with TAD according to AIRad. Multivariable logistic regression (MLR) was used to identify factors (demographics and scan parameters) associated with TAD classification by AIRad. Results: 18,243 CT scans (45.7% female) were successfully analyzed by AIRad. Mean age was 62.3 ± 15.9 years and 12,092 (66.3%) were CE scans. AIRad confirmed normal diameters in 17,239 exams (94.5%) and reported TAD in 1,004/18,243 exams (5.5%). Review confirmed TAD classification in 452/1,004 exams (45.0%, 2.5% total), 552 cases were false-positive but identification was easily possible using visual outputs by AIRad. MLR revealed that the following factors were significantly associated with correct TAD classification by AIRad: TAD reported at AA [odds ratio (OR): 1.12, p < 0.001] and STJ (OR: 1.09, p = 0.002), TAD found at >1 location (OR: 1.42, p = 0.008), in CE exams (OR: 2.1-3.1, p < 0.05), men (OR: 2.4, p = 0.003) and patients presenting with higher BMI (OR: 1.05, p = 0.01). Overall, 17,691/18,243 (97.0%) exams were correctly classified. Conclusions: AIRad correctly assessed the presence or absence of TAD in 17,691 exams (97%), including 452 cases with previously missed TAD independent from contrast protocol. These findings suggest its usefulness as a secondary reading tool by improving report quality and efficiency.

Associations between fully-automated, 3D-based functional analysis of the left atrium and classification schemes in atrial fibrillation.

BACKGROUND: Atrial fibrillation (AF) has been linked to left atrial (LA) enlargement. Whereas most studies focused on 2D-based estimation of static LA volume (LAV), we used a fully-automatic convolutional neural network (CNN) for time-resolved (CINE) volumetry of the whole LA on cardiac MRI (cMRI). Aim was to investigate associations between functional parameters from fully-automated, 3D-based analysis of the LA and current classification schemes in AF. METHODS: We retrospectively analyzed consecutive AF patients who underwent cMRI on 1.5T systems including a stack of oblique-axial CINE series covering the whole LA. The LA was automatically segmented by a validated CNN. In the resulting volume-time curves, maximum, minimum and LAV before atrial contraction were automatically identified. Active, passive and total LA emptying fractions (LAEF) were calculated and compared to clinical classifications (AF Burden score (AFBS), increased stroke risk (CHA2DS2VASc≥2), AF type (paroxysmal/persistent), EHRA score, and AF risk factors). Moreover, multivariable linear regression models (mLRM) were used to identify associations with AF risk factors. RESULTS: Overall, 102 patients (age 61±9 years, 17% female) were analyzed. Active LAEF (LAEF_active) decreased significantly with an increase of AFBS (minimal: 44.0%, mild: 36.2%, moderate: 31.7%, severe: 20.8%, p<0.003) which was primarily caused by an increase of minimum LAV. Likewise, LAEF_active was lower in patients with increased stroke risk (30.7% vs. 38.9%, p = 0.002). AF type and EHRA score did not show significant differences between groups. In mLRM, a decrease of LAEF_active was associated with higher age (per year: -0.3%, p = 0.02), higher AFBS (per category: -4.2%, p<0.03) and heart failure (-12.1%, p<0.04). CONCLUSIONS: Fully-automatic morphometry of the whole LA derived from cMRI showed significant relationships between LAEF_active with increased stroke risk and severity of AFBS. Furthermore, higher age, higher AFBS and presence of heart failure were independent predictors of reduced LAEF_active, indicating its potential usefulness as an imaging biomarker.

Initial experience with AI Pathway Companion: Evaluation of dashboard-enhanced clinical decision making in prostate cancer screening.

PURPOSE: Rising complexity of patients and the consideration of heterogeneous information from various IT systems challenge the decision-making process of urological oncologists. Siemens AI Pathway Companion is a decision support tool that provides physicians with comprehensive patient information from various systems. In the present study, we examined the impact of providing organized patient information in comprehensive dashboards on information quality, effectiveness, and satisfaction of physicians in the clinical decision-making process. METHODS: Ten urologists in our department performed the entire diagnostic workup to treatment decision for 10 patients in the prostate cancer screening setting. Expenditure of time, information quality, and user satisfaction during the decision-making process with AI Pathway Companion were recorded and compared to the current workflow. RESULTS: A significant reduction in the physician's expenditure of time for the decision-making process by -59.9% (p < 0,001) was found using the software. System usage showed a high positive effect on evaluated information quality parameters completeness (Cohen's d of 2.36), format (6.15), understandability (2.64), as well as user satisfaction (4.94). CONCLUSION: The software demonstrated that comprehensive organization of information improves physician's effectiveness and satisfaction in the clinical decision-making process. Further development is needed to map more complex patient pathways, such as the follow-up treatment of prostate cancer.

Considerations on Baseline Generation for Imaging AI Studies Illustrated on the CT-Based Prediction of Empyema and Outcome Assessment.

For AI-based classification tasks in computed tomography (CT), a reference standard for evaluating the clinical diagnostic accuracy of individual classes is essential. To enable the implementation of an AI tool in clinical practice, the raw data should be drawn from clinical routine data using state-of-the-art scanners, evaluated in a blinded manner and verified with a reference test. Three hundred and thirty-five consecutive CTs, performed between 1 January 2016 and 1 January 2021 with reported pleural effusion and pathology reports from thoracocentesis or biopsy within 7 days of the CT were retrospectively included. Two radiologists (4 and 10 PGY) blindly assessed the chest CTs for pleural CT features. If needed, consensus was achieved using an experienced radiologist's opinion (29 PGY). In addition, diagnoses were extracted from written radiological reports. We analyzed these findings for a possible correlation with the following patient outcomes: mortality and median hospital stay. For AI prediction, we used an approach consisting of nnU-Net segmentation, PyRadiomics features and a random forest model. Specificity and sensitivity for CT-based detection of empyema (n = 81 of n = 335 patients) were 90.94 (95%-CI: 86.55-94.05) and 72.84 (95%-CI: 61.63-81.85%) in all effusions, with moderate to almost perfect interrater agreement for all pleural findings associated with empyema (Cohen's kappa = 0.41-0.82). Highest accuracies were found for pleural enhancement or thickening with 87.02% and 81.49%, respectively. For empyema prediction, AI achieved a specificity and sensitivity of 74.41% (95% CI: 68.50-79.57) and 77.78% (95% CI: 66.91-85.96), respectively. Empyema was associated with a longer hospital stay (median = 20 versus 14 days), and findings consistent with pleural carcinomatosis impacted mortality.

Automated lung vessel segmentation reveals blood vessel volume redistribution in viral pneumonia.

PURPOSE: It is known from histology studies that lung vessels are affected in viral pneumonia. However, their diagnostic potential as a chest CT imaging parameter has only rarely been exploited. The purpose of this study is to develop a robust method for automated lung vessel segmentation and morphology analysis and apply it to a large chest CT dataset. METHODS: In total, 509 non-enhanced chest CTs (NECTs) and 563 CT pulmonary angiograms (CTPAs) were included. Sub-groups were patients with healthy lungs (group_NORM, n = 634) and those RT-PCR-positive for Influenza A/B (group_INF, n = 159) and SARS-CoV-2 (group_COV, n = 279). A lung vessel segmentation algorithm (LVSA) based on traditional image processing was developed, validated with a point-of-interest approach, and applied to a large clinical dataset. Total blood vessel volume in lung (TBV) and the blood vessel volume percentage (BV%) of three blood vessel size types were calculated and compared between groups: small (BV5%, cross-sectional area < 5 mm2), medium (BV5-10%, 5-10 mm2) and large (BV10%, >10 mm2). RESULTS: Sensitivity of the LVSA was 84.6% (95 %CI: 73.9-95.3) for NECTs and 92.8% (95 %CI: 90.8-94.7) for CTPAs. In viral pneumonia, besides an increased TBV, the main finding was a significantly decreased BV5% in group_COV (n = 14%) and group_INF (n = 15%) compared to group_NORM (n = 18%) [p < 0.001]. At the same time, BV10% was increased (group_COV n = 15% and group_INF n = 14% vs. group_NORM n = 11%; p < 0.001). CONCLUSION: In COVID-19 and Influenza, the blood vessel volume is redistributed from small to large vessels in the lung. Automated LSVA allows researchers and clinicians to derive imaging parameters for large amounts of CTs. This can enhance the understanding of vascular changes, particularly in infectious lung diseases.

Assessing radiomics feature stability with simulated CT acquisitions.

Medical imaging quantitative features had once disputable usefulness in clinical studies. Nowadays, advancements in analysis techniques, for instance through machine learning, have enabled quantitative features to be progressively useful in diagnosis and research. Tissue characterisation is improved via the "radiomics" features, whose extraction can be automated. Despite the advances, stability of quantitative features remains an important open problem. As features can be highly sensitive to variations of acquisition details, it is not trivial to quantify stability and efficiently select stable features. In this work, we develop and validate a Computed Tomography (CT) simulator environment based on the publicly available ASTRA toolbox ( www.astra-toolbox.com ). We show that the variability, stability and discriminative power of the radiomics features extracted from the virtual phantom images generated by the simulator are similar to those observed in a tandem phantom study. Additionally, we show that the variability is matched between a multi-center phantom study and simulated results. Consequently, we demonstrate that the simulator can be utilised to assess radiomics features' stability and discriminative power.

Atri-U: assisted image analysis in routine cardiovascular magnetic resonance volumetry of the left atrium.

BACKGROUND: Artificial intelligence can assist in cardiac image interpretation. Here, we achieved a substantial reduction in time required to read a cardiovascular magnetic resonance (CMR) study to estimate left atrial volume without compromising accuracy or reliability. Rather than deploying a fully automatic black-box, we propose to incorporate the automated LA volumetry into a human-centric interactive image-analysis process. METHODS AND RESULTS: Atri-U, an automated data analysis pipeline for long-axis cardiac cine images, computes the atrial volume by: (i) detecting the end-systolic frame, (ii) outlining the endocardial borders of the LA, (iii) localizing the mitral annular hinge points and constructing the longitudinal atrial diameters, equivalent to the usual workup done by clinicians. In every step human interaction is possible, such that the results provided by the algorithm can be accepted, corrected, or re-done from scratch. Atri-U was trained and evaluated retrospectively on a sample of 300 patients and then applied to a consecutive clinical sample of 150 patients with various heart conditions. The agreement of the indexed LA volume between Atri-U and two experts was similar to the inter-rater agreement between clinicians (average overestimation of 0.8 mL/m2 with upper and lower limits of agreement of - 7.5 and 5.8 mL/m2, respectively). An expert cardiologist blinded to the origin of the annotations rated the outputs produced by Atri-U as acceptable in 97% of cases for step (i), 94% for step (ii) and 95% for step (iii), which was slightly lower than the acceptance rate of the outputs produced by a human expert radiologist in the same cases (92%, 100% and 100%, respectively). The assistance of Atri-U lead to an expected reduction in reading time of 66%-from 105 to 34 s, in our in-house clinical setting. CONCLUSIONS: Our proposal enables automated calculation of the maximum LA volume approaching human accuracy and precision. The optional user interaction is possible at each processing step. As such, the assisted process sped up the routine CMR workflow by providing accurate, precise, and validated measurement results.

Fully automated guideline-compliant diameter measurements of the thoracic aorta on ECG-gated CT angiography using deep learning.

BACKGROUND: Manually performed diameter measurements on ECG-gated CT-angiography (CTA) represent the gold standard for diagnosis of thoracic aortic dilatation. However, they are time-consuming and show high inter-reader variability. Therefore, we aimed to evaluate the accuracy of measurements of a deep learning-(DL)-algorithm in comparison to those of radiologists and evaluated measurement times (MT). METHODS: We retrospectively analyzed 405 ECG-gated CTA exams of 371 consecutive patients with suspected aortic dilatation between May 2010 and June 2019. The DL-algorithm prototype detected aortic landmarks (deep reinforcement learning) and segmented the lumen of the thoracic aorta (multi-layer convolutional neural network). It performed measurements according to AHA-guidelines and created visual outputs. Manual measurements were performed by radiologists using centerline technique. Human performance variability (HPV), MT and DL-performance were analyzed in a research setting using a linear mixed model based on 21 randomly selected, repeatedly measured cases. DL-algorithm results were then evaluated in a clinical setting using matched differences. If the differences were within 5 mm for all locations, the cases was regarded as coherent; if there was a discrepancy >5 mm at least at one location (incl. missing values), the case was completely reviewed. RESULTS: HPV ranged up to ±3.4 mm in repeated measurements under research conditions. In the clinical setting, 2,778/3,192 (87.0%) of DL-algorithm's measurements were coherent. Mean differences of paired measurements between DL-algorithm and radiologists at aortic sinus and ascending aorta were -0.45±5.52 and -0.02±3.36 mm. Detailed analysis revealed that measurements at the aortic root were over-/underestimated due to a tilted measurement plane. In total, calculated time saved by DL-algorithm was 3:10 minutes/case. CONCLUSIONS: The DL-algorithm provided coherent results to radiologists at almost 90% of measurement locations, while the majority of discrepent cases were located at the aortic root. In summary, the DL-algorithm assisted radiologists in performing AHA-compliant measurements by saving 50% of time per case.

Toward a Platform for Structured Data Acquisition in Oncology: A Pilot Study on Prostate Cancer Screening.

INTRODUCTION: Physicians spend an ever-rising amount of time to collect relevant information from highly variable medical reports and integrate them into the patient's health condition. OBJECTIVES: We compared synoptic reporting based on data elements to narrative reporting in order to evaluate its capabilities to collect and integrate clinical information. METHODS: We developed a novel system to align medical reporting to data integration requirements and tested it in prostate cancer screening. We compared expenditure of time, data quality, and user satisfaction for data acquisition, integration, and evaluation. RESULTS: In a total of 26 sessions, 2 urologists, 2 radiologists, and 2 pathologists conducted the diagnostic work-up for prostate cancer screening with both narrative reporting and the novel system. The novel system led to a significantly reduced time for collection and integration of patient information (91%, p < 0.001), reporting in radiology (44%, p < 0.001) and pathology (33%, p = 0.154). The system usage showed a high positive effect on evaluated data quality parameters completeness, format, understandability, as well as user satisfaction. CONCLUSION: This study provides evidence that synoptic reporting based on data elements is effectively reducing time for collection and integration of patient information. Further research is needed to assess the system's impact for different patient journeys.

Automated Detection of Pancreatic Cystic Lesions on CT Using Deep Learning.

Pancreatic cystic lesions (PCL) are a frequent and underreported incidental finding on CT scans and can transform into neoplasms with devastating consequences. We developed and evaluated an algorithm based on a two-step nnU-Net architecture for automated detection of PCL on CTs. A total of 543 cysts on 221 abdominal CTs were manually segmented in 3D by a radiology resident in consensus with a board-certified radiologist specialized in abdominal radiology. This information was used to train a two-step nnU-Net for detection with the performance assessed depending on lesions' volume and location in comparison to three human readers of varying experience. Mean sensitivity was 78.8 ± 0.1%. The sensitivity was highest for large lesions with 87.8% for cysts ≥220 mm3 and for lesions in the distal pancreas with up to 96.2%. The number of false-positive detections for cysts ≥220 mm3 was 0.1 per case. The algorithm's performance was comparable to human readers. To conclude, automated detection of PCL on CTs is feasible. The proposed model could serve radiologists as a second reading tool. All imaging data and code used in this study are freely available online.

Deep learning-based automated detection of pulmonary embolism on CT pulmonary angiograms: No significant effects on report communication times and patient turnaround in the emergency department nine months after technical implementation.

OBJECTIVES: Rapid communication of CT exams positive for pulmonary embolism (PE) is crucial for timely initiation of anticoagulation and patient outcome. It is unknown if deep learning automated detection of PE on CT Pulmonary Angiograms (CTPA) in combination with worklist prioritization and an electronic notification system (ENS) can improve communication times and patient turnaround in the Emergency Department (ED). METHODS: In 01/2019, an ENS allowing direct communication between radiology and ED was installed. Starting in 10/2019, CTPAs were processed by a deep learning (DL)-powered algorithm for detection of PE. CTPAs acquired between 04/2018 and 06/2020 (n = 1808) were analysed. To assess the impact of the ENS and the DL-algorithm, radiology report reading times (RRT), radiology report communication time (RCT), time to anticoagulation (TTA), and patient turnaround times (TAT) in the ED were compared for three consecutive time periods. Performance measures of the algorithm were calculated on a per exam level (sensitivity, specificity, PPV, NPV, F1-score), with written reports and exam review as ground truth. RESULTS: Sensitivity of the algorithm was 79.6 % (95 %CI:70.8-87.2%), specificity 95.0 % (95 %CI:92.0-97.1%), PPV 82.2 % (95 %CI:73.9-88.3), and NPV 94.1 % (95 %CI:91.4-96 %). There was no statistically significant reduction of any of the observed times (RRT, RCT, TTA, TAT). CONCLUSION: DL-assisted detection of PE in CTPAs and ENS-assisted communication of results to referring physicians technically work. However, the mere clinical introduction of these tools, even if they exhibit a good performance, is not sufficient to achieve significant effects on clinical performance measures.

The Discriminative Power and Stability of Radiomics Features With Computed Tomography Variations: Task-Based Analysis in an Anthropomorphic 3D-Printed CT Phantom.

OBJECTIVES: The aims of this study were to determine the stability of radiomics features against computed tomography (CT) parameter variations and to study their discriminative power concerning tissue classification using a 3D-printed CT phantom based on real patient data. MATERIALS AND METHODS: A radiopaque 3D phantom was developed using real patient data and a potassium iodide solution paper-printing technique. Normal liver tissue and 3 lesion types (benign cyst, hemangioma, and metastasis) were manually annotated in the phantom. The stability and discriminative power of 86 radiomics features were assessed in measurements taken from 240 CT series with 8 parameter variations of reconstruction algorithms, reconstruction kernels, slice thickness, and slice spacing. Pairwise parameter group and pairwise tissue class comparisons were performed using Wilcoxon signed rank tests. RESULTS: In total, 19,264 feature stability tests and 8256 discriminative power tests were performed. The 8 CT parameter variation pairwise group comparisons had statistically significant differences on average in 78/86 radiomics features. On the other hand, 84% of the univariate radiomics feature tests had a successful and statistically significant differentiation of the 4 classes of liver tissue. The 86 radiomics features were ranked according to the cumulative sum of successful stability and discriminative power tests. CONCLUSIONS: The differences in radiomics feature values obtained from different types of liver tissue are generally greater than the intraclass differences resulting from CT parameter variations.

Evaluation of liver fibrosis and cirrhosis on the basis of quantitative T1 mapping: Are acute inflammation, age and liver volume confounding factors?

PURPOSE: To evaluate potential confounding factors in the quantitative assessment of liver fibrosis and cirrhosis using T1 relaxation times. METHODS: The study population is based on a radiology-information-system database search for abdominal MRI performed from July 2018 to April 2019 at our institution. After applying exclusion criteria 200 (59 ±â€¯16 yrs) remaining patients were retrospectively included. 93 patients were defined as liver-healthy, 40 patients without known fibrosis or cirrhosis, and 67 subjects had a clinically or biopsy-proven liver fibrosis or cirrhosis. T1 mapping was performed using a slice based look-locker approach. A ROI based analysis of the left and the right liver was performed. Fat fraction, R2*, liver volume, laboratory parameters, sex, and age were evaluated as potential confounding factors. RESULTS: T1 values were significantly lower in healthy subjects without known fibrotic changes (1.5 T MRI: 575 ±â€¯56 ms; 3 T MRI: 857 ±â€¯128 ms) compared to patients with acute liver disease (1.5 T MRI: 657 ±â€¯73 ms, p < 0.0001; 3 T MRI: 952 ±â€¯37 ms, p = 0.028) or known fibrosis or cirrhosis (1.5 T MRI: 644 ±â€¯83 ms, p < 0.0001; 3 T MRI: 995 ±â€¯150 ms, p = 0.018). T1 values correlated moderately with the Child-Pugh stage at 1.5 T (p = 0.01, ρ = 0.35). CONCLUSION: T1 mapping is a capable predictor for detection of liver fibrosis and cirrhosis. Especially age is not a confounding factor and, hence, age-independent thresholds can be defined. Acute liver diseases are confounding factors and should be ruled out before employing T1-relaxometry based thresholds to screen for patients with liver fibrosis or cirrhosis.

Automated CT Lung Density Analysis of Viral Pneumonia and Healthy Lungs Using Deep Learning-Based Segmentation, Histograms and HU Thresholds.

CT patterns of viral pneumonia are usually only qualitatively described in radiology reports. Artificial intelligence enables automated and reliable segmentation of lungs with chest CT. Based on this, the purpose of this study was to derive meaningful imaging biomarkers reflecting CT patterns of viral pneumonia and assess their potential to discriminate between healthy lungs and lungs with viral pneumonia. This study used non-enhanced and CT pulmonary angiograms (CTPAs) of healthy lungs and viral pneumonia (SARS-CoV-2, influenza A/B) identified by radiology reports and RT-PCR results. After deep learning segmentation of the lungs, histogram-based and threshold-based analyses of lung attenuation were performed and compared. The derived imaging biomarkers were correlated with parameters of clinical and biochemical severity (modified WHO severity scale; c-reactive protein). For non-enhanced CTs (n = 526), all imaging biomarkers significantly differed between healthy lungs and lungs with viral pneumonia (all p < 0.001), a finding that was not reproduced for CTPAs (n = 504). Standard deviation (histogram-derived) and relative high attenuation area [600-0 HU] (HU-thresholding) differed most. The strongest correlation with disease severity was found for absolute high attenuation area [600-0 HU] (r = 0.56, 95% CI = 0.46-0.64). Deep-learning segmentation-based histogram and HU threshold analysis could be deployed in chest CT evaluation for the differentiating of healthy lungs from AP lungs.

AI-based detection and classification of distal radius fractures using low-effort data labeling: evaluation of applicability and effect of training set size.

OBJECTIVES: To evaluate the performance of a deep convolutional neural network (DCNN) in detecting and classifying distal radius fractures, metal, and cast on radiographs using labels based on radiology reports. The secondary aim was to evaluate the effect of the training set size on the algorithm's performance. METHODS: A total of 15,775 frontal and lateral radiographs, corresponding radiology reports, and a ResNet18 DCNN were used. Fracture detection and classification models were developed per view and merged. Incrementally sized subsets served to evaluate effects of the training set size. Two musculoskeletal radiologists set the standard of reference on radiographs (test set A). A subset (B) was rated by three radiology residents. For a per-study-based comparison with the radiology residents, the results of the best models were merged. Statistics used were ROC and AUC, Youden's J statistic (J), and Spearman's correlation coefficient (ρ). RESULTS: The models' AUC/J on (A) for metal and cast were 0.99/0.98 and 1.0/1.0. The models' and residents' AUC/J on (B) were similar on fracture (0.98/0.91; 0.98/0.92) and multiple fragments (0.85/0.58; 0.91/0.70). Training set size and AUC correlated on metal (ρ = 0.740), cast (ρ = 0.722), fracture (frontal ρ = 0.947, lateral ρ = 0.946), multiple fragments (frontal ρ = 0.856), and fragment displacement (frontal ρ = 0.595). CONCLUSIONS: The models trained on a DCNN with report-based labels to detect distal radius fractures on radiographs are suitable to aid as a secondary reading tool; models for fracture classification are not ready for clinical use. Bigger training sets lead to better models in all categories except joint affection. KEY POINTS: • Detection of metal and cast on radiographs is excellent using AI and labels extracted from radiology reports. • Automatic detection of distal radius fractures on radiographs is feasible and the performance approximates radiology residents. • Automatic classification of the type of distal radius fracture varies in accuracy and is inferior for joint involvement and fragment displacement.