Explainable Precision Medicine in Breast MRI: A Combined Radiomics and Deep Learning Approach for the Classification of Contrast Agent Uptake.

In DCE-MRI, the degree of contrast uptake in normal fibroglandular tissue, i.e., background parenchymal enhancement (BPE), is a crucial biomarker linked to breast cancer risk and treatment outcome. In accordance with the Breast Imaging Reporting & Data System (BI-RADS), it should be visually classified into four classes. The susceptibility of such an assessment to inter-reader variability highlights the urgent need for a standardized classification algorithm. In this retrospective study, the first post-contrast subtraction images for 27 healthy female subjects were included. The BPE was classified slice-wise by two expert radiologists. The extraction of radiomic features from segmented BPE was followed by dataset splitting and dimensionality reduction. The latent representations were then utilized as inputs to a deep neural network classifying BPE into BI-RADS classes. The network's predictions were elucidated at the radiomic feature level with Shapley values. The deep neural network achieved a BPE classification accuracy of 84 ± 2% (p-value < 0.00001). Most of the misclassifications involved adjacent classes. Different radiomic features were decisive for the prediction of each BPE class underlying the complexity of the decision boundaries. A highly precise and explainable pipeline for BPE classification was achieved without user- or algorithm-dependent radiomic feature selection.

Automatic Detection of Post-Operative Clips in Mammography Using a U-Net Convolutional Neural Network.

BACKGROUND: After breast conserving surgery (BCS), surgical clips indicate the tumor bed and, thereby, the most probable area for tumor relapse. The aim of this study was to investigate whether a U-Net-based deep convolutional neural network (dCNN) may be used to detect surgical clips in follow-up mammograms after BCS. METHODS: 884 mammograms and 517 tomosynthetic images depicting surgical clips and calcifications were manually segmented and classified. A U-Net-based segmentation network was trained with 922 images and validated with 394 images. An external test dataset consisting of 39 images was annotated by two radiologists with up to 7 years of experience in breast imaging. The network's performance was compared to that of human readers using accuracy and interrater agreement (Cohen's Kappa). RESULTS: The overall classification accuracy on the validation set after 45 epochs ranged between 88.2% and 92.6%, indicating that the model's performance is comparable to the decisions of a human reader. In 17.4% of cases, calcifications have been misclassified as post-operative clips. The interrater reliability of the model compared to the radiologists showed substantial agreement (κreader1 = 0.72, κreader2 = 0.78) while the readers compared to each other revealed a Cohen's Kappa of 0.84, thus showing near-perfect agreement. CONCLUSIONS: With this study, we show that surgery clips can adequately be identified by an AI technique. A potential application of the proposed technique is patient triage as well as the automatic exclusion of post-operative cases from PGMI (Perfect, Good, Moderate, Inadequate) evaluation, thus improving the quality management workflow.

Multi-Energy Low-Kiloelectron Volt versus Single-Energy Low-Kilovolt Images for Endoleak Detection at CT Angiography of the Aorta.

Purpose To compare image quality, diagnostic performance, and conspicuity between single-energy and multi-energy images for endoleak detection at CT angiography (CTA) after endovascular aortic repair (EVAR). Materials and Methods In this single-center prospective randomized controlled trial, individuals undergoing CTA after EVAR between August 2020 and May 2022 were allocated to imaging using either low-kilovolt single-energy images (SEI; 80 kV, group A) or low-kiloelectron volt virtual monoenergetic images (VMI) at 40 and 50 keV from multi-energy CT (80/Sn150 kV, group B). Scan protocols were dose matched (volume CT dose index: mean, 4.5 mGy ± 1.8 [SD] vs 4.7 mGy ± 1.3, P = .41). Contrast-to-noise ratio (CNR) was measured. Two expert radiologists established the reference standard for the presence of endoleaks. Detection and conspicuity of endoleaks and subjective image quality were assessed by two different blinded radiologists. Interreader agreement was calculated. Nonparametric statistical tests were used. Results A total of 125 participants (mean age, 76 years ± 8; 103 men) were allocated to groups A (n = 64) and B (n = 61). CNR was significantly lower for 40-keV VMI (mean, 19.1; P = .048) and 50-keV VMI (mean, 16.8; P < .001) as compared with SEI (mean, 22.2). In total, 45 endoleaks were present (A: 23 vs B: 22). Sensitivity for endoleak detection was higher for SEI (82.6%, 19 of 23; P = .88) and 50-keV VMI (81.8%, 18 of 22; P = .90) as compared with 40-keV VMI (77.3%, 17 of 22). Specificity was comparable among groups (SEI: 92.7%, 38 of 41; both VMI energies: 92.3%, 35 of 38; P = .99), with an interreader agreement of 1. Conspicuity of endoleaks was comparable between SEI (median, 2.99) and VMI (both energies: median, 2.87; P = .04). Overall subjective image quality was rated significantly higher for SEI (median, 4 [IQR, 4-4) as compared with 40 and 50 keV (both energies: median, 4 [IQR, 3-4]; P < .001). Conclusion SEI demonstrated higher image quality and comparable diagnostic accuracy as compared with 50-keV VMI for endoleak detection at CTA after EVAR. Keywords: Aneurysms, CT, CT Angiography, Vascular, Aorta, Technology Assessment, Multidetector CT, Abdominal Aortic Aneurysms, Endoleaks, Perigraft Leak Supplemental material is available for this article. © RSNA, 2024.

Diagnostic value of T1- and T2-weighted 3-Tesla MRI for postmortem detection and age stage classification of myocardial infarction.

The aims of this study are to retrospectively evaluate the diagnostic value of T1- and T2-weighted 3-T magnetic resonance imaging (MRI) for postmortem detection of myocardial infarction (MI) in terms of sensitivity and specificity and to compare the MRI appearance of the infarct area with age stages. Postmortem MRI examinations (n = 88) were retrospectively reviewed for the presence or absence of MI by two raters blinded to the autopsy results. The sensitivity and specificity were calculated using the autopsy results as the gold standard. A third rater, who was not blinded to the autopsy findings, reviewed all cases in which MI was detected at autopsy for MRI appearance (hypointensity, isointensity, hyperintensity) of the infarct area and the surrounding zone. Age stages (peracute, acute, subacute, chronic) were assigned based on the literature and compared with the age stages reported in the autopsy reports. The interrater reliability between the two raters was substantial (κ = 0.78). Sensitivity was 52.94% (both raters). Specificity was 85.19% and 92.59%. In 34 decedents, autopsy identified an MI (peracute: n = 7, acute: n = 25, chronic: n = 2). Of 25 MI classified as acute at autopsy, MRI classified peracute in four cases and subacute in nine cases. In two cases, MRI suggested peracute MI, which was not detected at autopsy. MRI could help to classify the age stage and may indicate the area for sampling for further microscopic examination. However, the low sensitivity requires further additional MRI techniques to increase the diagnostic value.

Quantitative Study on the Breast Density and the Volume of the Mammary Gland According to the Patient's Age and Breast Quadrant.

OBJECTIVES: Breast density is considered an independent risk factor for the development of breast cancer. This study aimed to quantitatively assess the percent breast density (PBD) and the mammary glands volume (MGV) according to the patient's age and breast quadrant. We propose a regression model to estimate PBD and MGV as a function of the patient's age. METHODS: The breast composition in 1027 spiral breast CT (BCT) datasets without soft tissue masses, calcifications, or implants from 517 women (57 ± 8 years) were segmented. The breast tissue volume (BTV), MGV, and PBD of the breasts were measured in the entire breast and each of the four quadrants. The three breast composition features were analyzed in the seven age groups, from 40 to 74 years in 5-year intervals. A logarithmic model was fitted to the BTV, and a multiplicative inverse model to the MGV and PBD as a function of age was established using a least-squares method. RESULTS: The BTV increased from 545 ± 345 to 676 ± 412 cm3, and the MGV and PBD decreased from 111 ± 164 to 57 ± 43 cm3 and from 21 ± 21 to 11 ± 9%, respectively, from the youngest to the oldest group (p < 0.05). The average PBD over all ages were 14 ± 13%. The regression models could predict the BTV, MGV, and PBD based on the patient's age with residual standard errors of 386 cm3, 67 cm3, and 13%, respectively. The reduction in MGV and PBD in each quadrant followed the ones in the entire breast. CONCLUSIONS: The PBD and MGV computed from BCT examinations provide important information for breast cancer risk assessment in women. The study quantified the breast mammary gland reduction and density decrease over the entire breast. It established mathematical models to estimate the breast composition features-BTV, MGV, and PBD, as a function of the patient's age.

Generalizable attention U-Net for segmentation of fibroglandular tissue and background parenchymal enhancement in breast DCE-MRI.

OBJECTIVES: Development of automated segmentation models enabling standardized volumetric quantification of fibroglandular tissue (FGT) from native volumes and background parenchymal enhancement (BPE) from subtraction volumes of dynamic contrast-enhanced breast MRI. Subsequent assessment of the developed models in the context of FGT and BPE Breast Imaging Reporting and Data System (BI-RADS)-compliant classification. METHODS: For the training and validation of attention U-Net models, data coming from a single 3.0-T scanner was used. For testing, additional data from 1.5-T scanner and data acquired in a different institution with a 3.0-T scanner was utilized. The developed models were used to quantify the amount of FGT and BPE in 80 DCE-MRI examinations, and a correlation between these volumetric measures and the classes assigned by radiologists was performed. RESULTS: To assess the model performance using application-relevant metrics, the correlation between the volumes of breast, FGT, and BPE calculated from ground truth masks and predicted masks was checked. Pearson correlation coefficients ranging from 0.963 ± 0.004 to 0.999 ± 0.001 were achieved. The Spearman correlation coefficient for the quantitative and qualitative assessment, i.e., classification by radiologist, of FGT amounted to 0.70 (p < 0.0001), whereas BPE amounted to 0.37 (p = 0.0006). CONCLUSIONS: Generalizable algorithms for FGT and BPE segmentation were developed and tested. Our results suggest that when assessing FGT, it is sufficient to use volumetric measures alone. However, for the evaluation of BPE, additional models considering voxels' intensity distribution and morphology are required. CRITICAL RELEVANCE STATEMENT: A standardized assessment of FGT density can rely on volumetric measures, whereas in the case of BPE, the volumetric measures constitute, along with voxels' intensity distribution and morphology, an important factor. KEY POINTS: • Our work contributes to the standardization of FGT and BPE assessment. • Attention U-Net can reliably segment intricately shaped FGT and BPE structures. • The developed models were robust to domain shift.

Transurethral injection of autologous muscle precursor cells for treatment of female stress urinary incontinence: a prospective phase I clinical trial.

INTRODUCTION AND HYPOTHESIS: The purpose was to investigate the safety and feasibility of transurethral injections of autologous muscle precursor cells (MPCs) into the external urinary sphincter (EUS) to treat stress urinary incontinence (SUI) in female patients. METHODS: Prospective and randomised phase I clinical trial. Standardised 1-h pad test, International Consultation on Incontinence Questionnaire-Urinary Incontinence Short Form (ICIQ-UI-SF), urodynamic study, and MRI of the pelvis were performed at baseline and 6 months after treatment. MPCs gained through open muscle biopsy were transported to a GMP facility for processing and cell expansion. The final product was injected into the EUS via a transurethral ultrasound-guided route. Primary outcomes were defined as any adverse events (AEs) during follow-up. Secondary outcomes were functional, questionnaire, and radiological results. RESULTS: Ten female patients with SUI grades I-II were included in the study and 9 received treatment. Out of 8 AEs, 3 (37.5%) were potentially related to treatment and treated conservatively: 1 urinary tract infection healed with antibiotics treatment, 1 dysuria and 1 discomfort at biopsy site. Functional urethral length under stress was 25 mm at baseline compared with 30 mm at 6 months' follow-up (p=0.009). ICIQ-UI-SF scores improved from 7 points at baseline to 4 points at follow-up (p=0.035). MRI of the pelvis revealed no evidence of tumour or necrosis, whereas the diameter of the EUS muscle increased from 1.8 mm at baseline to 1.9 mm at follow-up (p=0.009). CONCLUSION: Transurethral injections of autologous MPCs into the EUS for treatment of SUI in female patients can be regarded as safe and feasible. Only a minimal number of expected and easily treatable AEs were documented.

Detection of microcalcifications in photon-counting dedicated breast-CT using a deep convolutional neural network: Proof of principle.

OBJECTIVE: In this study, we investigate the feasibility of a deep Convolutional Neural Network (dCNN), trained with mammographic images, to detect and classify microcalcifications (MC) in breast-CT (BCT) images. METHODS: This retrospective single-center study was approved by the local ethics committee. 3518 icons generated from 319 mammograms were classified into three classes: "no MC" (1121), "probably benign MC" (1332), and "suspicious MC" (1065). A dCNN was trained (70% of data), validated (20%), and tested on a "real-world" dataset (10%). The diagnostic performance of the dCNN was tested on a subset of 60 icons, generated from 30 mammograms and 30 breast-CT images, and compared to human reading. ROC analysis was used to calculate diagnostic performance. Moreover, colored probability maps for representative BCT images were calculated using a sliding-window approach. RESULTS: The dCNN reached an accuracy of 98.8% on the "real-world" dataset. The accuracy on the subset of 60 icons was 100% for mammographic images, 60% for "no MC", 80% for "probably benign MC" and 100% for "suspicious MC". Intra-class correlation between the dCNN and the readers was almost perfect (0.85). Kappa values between the two readers (0.93) and the dCNN were almost perfect (reader 1: 0.85 and reader 2: 0.82). The sliding-window approach successfully detected suspicious MC with high image quality. The diagnostic performance of the dCNN to classify benign and suspicious MC was excellent with an AUC of 93.8% (95% CI 87, 4%-100%). CONCLUSION: Deep convolutional networks can be used to detect and classify benign and suspicious MC in breast-CT images.

Systematic analysis of changes in radiomics features during dynamic breast-MRI: Evaluation of specific biomarkers.

OBJECTIVES: In this retrospective, single-center study we investigate the changes of radiomics features during dynamic breast-MRI for healthy tissue compared to benign and malignant lesions. METHODS: 60 patients underwent breast-MRI using a dynamic 3D gradient-echo sequence. Changes of 34 texture features (TF) in 30 benign and 30 malignant lesions were calculated for 5 dynamic datasets and corresponding 4 subtraction datasets. Statistical analysis was performed with ANOVA, and systematic changes in features were described by linear and polynomial regression models. RESULTS: ANOVA revealed significant differences (p < 0.05) between normal tissue and lesions in 13 TF, compared to 9 TF between benign and malignant lesions. Most TF showed significant differences in early dynamic and subtraction datasets. TF associated with homogeneity were suitable to discriminate between healthy parenchyma and lesions, whereas run-length features were more suitable to discriminate between benign and malignant lesions. Run length nonuniformity (RLN) was the only feature able to distinguish between all three classes with an AUC of 88.3%. Characteristic changes were observed with a systematic increase or decrease for most TF with mostly polynomial behavior. Slopes showed earlier peaks in malignant lesions, compared to benign lesions. Mean values for the coefficient of determination were higher during subtraction sequences, compared to dynamic sequences (benign: 0.98 vs 0. 72; malignant: 0.94 vs 0.74). CONCLUSIONS: TF of breast lesions follow characteristic patterns during dynamic breast-MRI, distinguishing benign from malignant lesions. Early dynamic and subtraction datasets are particularly suitable for texture analysis in breast-MRI. Features associated with tissue homogeneity seem to be indicative of benign lesions.

BI-RADS-Based Classification of Mammographic Soft Tissue Opacities Using a Deep Convolutional Neural Network.

The aim of this study was to investigate the potential of a machine learning algorithm to classify breast cancer solely by the presence of soft tissue opacities in mammograms, independent of other morphological features, using a deep convolutional neural network (dCNN). Soft tissue opacities were classified based on their radiological appearance using the ACR BI-RADS atlas. We included 1744 mammograms from 438 patients to create 7242 icons by manual labeling. The icons were sorted into three categories: "no opacities" (BI-RADS 1), "probably benign opacities" (BI-RADS 2/3) and "suspicious opacities" (BI-RADS 4/5). A dCNN was trained (70% of data), validated (20%) and finally tested (10%). A sliding window approach was applied to create colored probability maps for visual impression. Diagnostic performance of the dCNN was compared to human readout by experienced radiologists on a "real-world" dataset. The accuracies of the models on the test dataset ranged between 73.8% and 89.8%. Compared to human readout, our dCNN achieved a higher specificity (100%, 95% CI: 85.4-100%; reader 1: 86.2%, 95% CI: 67.4-95.5%; reader 2: 79.3%, 95% CI: 59.7-91.3%), and the sensitivity (84.0%, 95% CI: 63.9-95.5%) was lower than that of human readers (reader 1:88.0%, 95% CI: 67.4-95.4%; reader 2:88.0%, 95% CI: 67.7-96.8%). In conclusion, a dCNN can be used for the automatic detection as well as the standardized and observer-independent classification of soft tissue opacities in mammograms independent of the presence of microcalcifications. Human decision making in accordance with the BI-RADS classification can be mimicked by artificial intelligence.

Radiomics in photon-counting dedicated breast CT: potential of texture analysis for breast density classification.

BACKGROUND: We investigated whether features derived from texture analysis (TA) can distinguish breast density (BD) in spiral photon-counting breast computed tomography (PC-BCT). METHODS: In this retrospective single-centre study, we analysed 10,000 images from 400 PC-BCT examinations of 200 patients. Images were categorised into four-level density scale (a-d) using Breast Imaging Reporting and Data System (BI-RADS)-like criteria. After manual definition of representative regions of interest, 19 texture features (TFs) were calculated to analyse the voxel grey-level distribution in the included image area. ANOVA, cluster analysis, and multinomial logistic regression statistics were used. A human readout then was performed on a subset of 60 images to evaluate the reliability of the proposed feature set. RESULTS: Of the 19 TFs, 4 first-order features and 7 second-order features showed significant correlation with BD and were selected for further analysis. Multinomial logistic regression revealed an overall accuracy of 80% for BD assessment. The majority of TFs systematically increased or decreased with BD. Skewness (rho -0.81), as a first-order feature, and grey-level nonuniformity (GLN, -0.59), as a second-order feature, showed the strongest correlation with BD, independently of other TFs. Mean skewness and GLN decreased linearly from density a to d. Run-length nonuniformity (RLN), as a second-order feature, showed moderate correlation with BD, but resulted in redundant being correlated with GLN. All other TFs showed only weak correlation with BD (range -0.49 to 0.49, p < 0.001) and were neglected. CONCLUSION: TA of PC-BCT images might be a useful approach to assess BD and may serve as an observer-independent tool.

Detecting Abnormal Axillary Lymph Nodes on Mammograms Using a Deep Convolutional Neural Network.

The purpose of this study was to determine the feasibility of a deep convolutional neural network (dCNN) to accurately detect abnormal axillary lymph nodes on mammograms. In this retrospective study, 107 mammographic images in mediolateral oblique projection from 74 patients were labeled to three classes: (1) "breast tissue", (2) "benign lymph nodes", and (3) "suspicious lymph nodes". Following data preprocessing, a dCNN model was trained and validated with 5385 images. Subsequently, the trained dCNN was tested on a "real-world" dataset and the performance compared to human readers. For visualization, colored probability maps of the classification were calculated using a sliding window approach. The accuracy was 98% for the training and 99% for the validation set. Confusion matrices of the "real-world" dataset for the three classes with radiological reports as ground truth yielded an accuracy of 98.51% for breast tissue, 98.63% for benign lymph nodes, and 95.96% for suspicious lymph nodes. Intraclass correlation of the dCNN and the readers was excellent (0.98), and Kappa values were nearly perfect (0.93-0.97). The colormaps successfully detected abnormal lymph nodes with excellent image quality. In this proof-of-principle study in a small patient cohort from a single institution, we found that deep convolutional networks can be trained with high accuracy and reliability to detect abnormal axillary lymph nodes on mammograms.

Potential of Photon-Counting Detector CT for Radiation Dose Reduction for the Assessment of Interstitial Lung Disease in Patients With Systemic Sclerosis.

OBJECTIVE: The aim of this study was to determine the potential of photon-counting detector computed tomography (PCD-CT) for radiation dose reduction compared with conventional energy-integrated detector CT (EID-CT) in the assessment of interstitial lung disease (ILD) in systemic sclerosis (SSc) patients. METHODS: In this retrospective study, SSc patients receiving a follow-up noncontrast chest examination on a PCD-CT were included between May 2021 and December 2021. Baseline scans were generated on a dual-source EID-CT by selecting the tube current-time product for each of the 2 x-ray tubes to obtain a 100% (D 100 ), a 66% (D 66 ), and a 33% dose image (D 33 ) from the same data set. Slice thickness and kernel were adjusted between the 2 scans. Image noise was assessed by placing a fixed region of interest in the subcutaneous fat. Two independent readers rated subjective image quality (5-point Likert scale), presence, extent, diagnostic confidence, and accuracy of SSc-ILD. D 100 interpreted by a radiologist with 22 years of experience served as reference standard. Interobserver agreement was calculated with Cohen κ, and mean variables were compared by a paired t test. RESULTS: Eighty patients (mean 56 ± 14; 64 women) were included. Although CTDI vol of PCD-CT was comparable to D 33 (0.72 vs 0.76 mGy, P = 0.091), mean image noise of PCD-CT was comparable to D 100 (131 ± 15 vs 113 ± 12, P > 0.05). Overall subjective image quality of PCD-CT was comparable to D 100 (4.72 vs 4.71; P = 0.874). Diagnostic accuracy was higher in PCD-CT compared with D 33 /D 66 (97.6% and 92.5%/96.3%, respectively) and comparable to D 100 (98.1%). CONCLUSIONS: With PCD-CT, a radiation dose reduction of 66% compared with EID-CT is feasible, without penalty in image quality and diagnostic performance for the evaluation of ILD.

Quantum Iterative Reconstruction for Abdominal Photon-counting Detector CT Improves Image Quality.

Background An iterative reconstruction (IR) algorithm was introduced for clinical photon-counting detector (PCD) CT. Purpose To investigate the image quality and the optimal strength level of a quantum IR algorithm (QIR; Siemens Healthcare) for virtual monoenergetic images and polychromatic images (T3D) in a phantom and in patients undergoing portal venous abdominal PCD CT. Materials and Methods In this retrospective study, noise power spectrum (NPS) was measured in a water-filled phantom. Consecutive oncologic patients who underwent portal venous abdominal PCD CT between March and April 2021 were included. Virtual monoenergetic images at 60 keV and T3D were reconstructed without QIR (QIR-off; reference standard) and with QIR at four levels (QIR 1-4; index tests). Global noise index, contrast-to-noise ratio (CNR), and voxel-wise CT attenuation differences were measured. Noise and texture, artifacts, diagnostic confidence, and overall quality were assessed qualitatively. Conspicuity of hypodense liver lesions was rated by four readers. Parametric (analyses of variance, paired t tests) and nonparametric tests (Friedman, post hoc Wilcoxon signed-rank tests) were used to compare quantitative and qualitative image quality among reconstructions. Results In the phantom, NPS showed unchanged noise texture across reconstructions with maximum spatial frequency differences of 0.01 per millimeter. Fifty patients (mean age, 59 years ± 16 [standard deviation]; 31 women) were included. Global noise index was reduced from QIR-off to QIR-4 by 45% for 60 keV and by 44% for T3D (both, P < .001). CNR of the liver improved from QIR-off to QIR-4 by 74% for 60 keV and by 69% for T3D (both, P < .001). No evidence of difference was found in mean attenuation of fat and liver (P = .79-.84) and on a voxel-wise basis among reconstructions. Qualitatively, QIR-4 outperformed all reconstructions in every category for 60 keV and T3D (P value range, <.001 to .01). All four readers rated QIR-4 superior to other strengths for lesion conspicuity (P value range, <.001 to .04). Conclusion In portal venous abdominal photon-counting detector CT, an iterative reconstruction algorithm (QIR; Siemens Healthcare) at high strength levels improved image quality by reducing noise and improving contrast-to-noise ratio and lesion conspicuity without compromising image texture or CT attenuation values. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Sinitsyn in this issue.

Applied Machine Learning in Spiral Breast-CT: Can We Train a Deep Convolutional Neural Network for Automatic, Standardized and Observer Independent Classification of Breast Density?

The aim of this study was to investigate the potential of a machine learning algorithm to accurately classify parenchymal density in spiral breast-CT (BCT), using a deep convolutional neural network (dCNN). In this retrospectively designed study, 634 examinations of 317 patients were included. After image selection and preparation, 5589 images from 634 different BCT examinations were sorted by a four-level density scale, ranging from A to D, using ACR BI-RADS-like criteria. Subsequently four different dCNN models (differences in optimizer and spatial resolution) were trained (70% of data), validated (20%) and tested on a "real-world" dataset (10%). Moreover, dCNN accuracy was compared to a human readout. The overall performance of the model with lowest resolution of input data was highest, reaching an accuracy on the "real-world" dataset of 85.8%. The intra-class correlation of the dCNN and the two readers was almost perfect (0.92) and kappa values between both readers and the dCNN were substantial (0.71-0.76). Moreover, the diagnostic performance between the readers and the dCNN showed very good correspondence with an AUC of 0.89. Artificial Intelligence in the form of a dCNN can be used for standardized, observer-independent and reliable classification of parenchymal density in a BCT examination.

[Pulmonary nodules and pneumonia : A diagnostic guideline]. / Pulmonale Rundherde und Pneumonie : Ein diagnostischer Leitfaden.

BACKGROUND: Chest X­ray is one of the most frequent examinations in radiology and its interpretation is considered part of the basic knowledge of every radiologist. OBJECTIVES: The purpose of this article is to recognize common signs and patterns of pneumonias and pseudonodules in chest X­rays and to provide a diagnostic guideline for young radiologists. MATERIALS AND METHODS: Recent studies and data are analyzed and an overview of the most common signs and patterns in chest X­ray is provided. RESULTS: Knowledge about common signs and patterns in chest X­ray is helpful in the diagnosis of pneumonias and can be indicative for the cause of an infection. However, those signs are often unspecific and should, therefore, be set in clinical content. Computed tomography is becoming increasingly important in the primary diagnosis of pulmonary lesions because of its much higher sensitivity. CONCLUSION: Chest X­ray is still the first-line modality in the diagnosis of pneumonia and pulmonary nodules; however, radiologists should be aware of its limitations.