Accelerated liver water T1 mapping using single-shot continuous inversion-recovery spiral imaging

PURPOSE

Liver T1 mapping techniques typically require long breath holds or long scan time in free-breathing, need correction for B 1 + inhomogeneities and process composite (water and fat) signals. The purpose of this work is to accelerate the multi-slice acquisition of liver water selective T1 (wT1) mapping in a single breath hold, improving the k-space sampling efficiency.

METHODS

The proposed continuous inversion-recovery (IR) Look-Locker methodology combines a single-shot gradient echo spiral readout, Dixon processing and a dictionary-based analysis for liver wT1 mapping at 3 T. The sequence parameters were adapted to obtain short scan times. The influence of fat, B 1 + inhomogeneities and TE on the estimation of T1 was first assessed using simulations. The proposed method was then validated in a phantom and in 10 volunteers, comparing it with MRS and the modified Look-Locker inversion-recovery (MOLLI) method. Finally, the clinical feasibility was investigated by comparing wT1 maps with clinical scans in nine patients.

RESULTS

The phantom results are in good agreement with MRS. The proposed method encodes the IR-curve for the liver wT1 estimation, is minimally sensitive to B 1 + inhomogeneities and acquires one slice in 1.2 s. The volunteer results confirmed the multi-slice capability of the proposed method, acquiring nine slices in a breath hold of 11 s. The present work shows robustness to B 1 + inhomogeneities (wT 1 , No B 1 + = 1.07 wT 1 , B 1 + - 45.63 , R 2 = 0.99 ) , good repeatability (wT 1 , 2 ° = 1 . 0 wT 1 , 1 ° - 2.14 , R 2 = 0.96 ) and is in better agreement with MRS (wT 1 = 0.92 wT 1 MRS + 103.28 , R 2 = 0.38 ) than is MOLLI (wT 1 MOLLI = 0.76 wT 1 MRS + 254.43 , R 2 = 0.44 ) . The wT1 maps in patients captured diverse lesions, thus showing their clinical feasibility.

CONCLUSION

A single-shot spiral acquisition can be combined with a continuous IR Look-Locker method to perform rapid repeatable multi-slice liver water T1 mapping at a rate of 1.2 s per slice without a B 1 + map. The proposed method is suitable for nine-slice liver clinical applications acquired in a single breath hold of 11 s.

Longitudinal MR-based proton-density fat fraction (PDFF) and T2* for the assessment of associations between bone marrow changes and myelotoxic chemotherapy

OBJECTIVES

MR imaging-based proton density fat fraction (PDFF) and T2* imaging has shown to be useful for the evaluation of degenerative changes in the spine. Therefore, the aim of this study was to investigate the influence of myelotoxic chemotherapy on the PDFF and T2* of the thoracolumbar spine in comparison to changes in bone mineral density (BMD).

METHODS

In this study, 19 patients were included who had received myelotoxic chemotherapy (MC) and had received a MR imaging scan of the thoracolumbar vertebrates before and after the MC. Every patient was matched for age, sex, and time between the MRI scans to two controls without MC. All patients underwent 3-T MR imaging including the thoracolumbar spine comprising chemical shift encoding-based water-fat imaging to extract PDFF and T2* maps. Moreover, trabecular BMD values were determined before and after chemotherapy. Longitudinal changes in PDFF and T2* were evaluated and compared to changes in BMD.

RESULTS

Absolute mean differences of PDFF values between scans before and after MC were at 8.7% (p = 0.01) and at -0.5% (p = 0.57) in the control group, resulting in significantly higher changes in PDFF in patients with MC (p = 0.008). BMD and T2* values neither showed significant changes in patients with nor in those without myelotoxic chemotherapy (p = 0.15 and p = 0.47). There was an inverse, yet non-significant correlation between changes in PDFF and BMD found in patients with myelotoxic chemotherapy (r = -0.41, p = 0.12).

CONCLUSION

Therefore, PDFF could be a useful non-invasive biomarker in order to detect changes in the bone marrow in patients receiving myelotoxic therapy.

CLINICAL RELEVANCE STATEMENT

Using PDFF as a non-invasive biomarker for early bone marrow changes in oncologic patients undergoing myelotoxic treatment may help enable more targeted countermeasures at commencing states of bone marrow degradation and reduce risks of possible fragility fractures.

KEY POINTS

Quantifying changes in bone marrow fat fraction, as well as T2* caused by myelotoxic pharmaceuticals using proton density fat fraction, is feasible. Proton density fat fraction could potentially be established as a non-invasive biomarker for early bone marrow changes in oncologic patients undergoing myelotoxic treatment.

Comparison of Virtual Non-Contrast and True Non-Contrast CT Images Obtained by Dual-Layer Spectral CT in COPD Patients

Chronic obstructive pulmonary disease (COPD) is one of the leading causes of death. Recent studies have underlined the importance of non-contrast-enhanced chest CT scans not only for emphysema progression quantification, but for correlation with clinical outcomes as well. As about 40 percent of the 300 million CT scans per year are contrast-enhanced, no proper emphysema quantification is available in a one-stop-shop approach for patients with known or newly diagnosed COPD. Since the introduction of spectral imaging (e.g., dual-energy CT scanners), it has been possible to create virtual non-contrast-enhanced images (VNC) from contrast-enhanced images, making it theoretically possible to offer proper COPD imaging despite contrast enhancing. This study is aimed towards investigating whether these VNC images are comparable to true non-contrast-enhanced images (TNC), thereby reducing the radiation exposure of patients and usage of resources in hospitals. In total, 100 COPD patients with two scans, one with (VNC) and one without contrast media (TNC), within 8 weeks or less obtained by a spectral CT using dual-layer technology, were included in this retrospective study. TNC and VNC were compared according to their voxel-density histograms. While the comparison showed significant differences in the low attenuated volumes (LAVs) of TNC and VNC regarding the emphysema threshold of -950 Houndsfield Units (HU), the 15th and 10th percentiles of the LAVs used as a proxy for pre-emphysema were comparable. Upon further investigation, the threshold-based LAVs (-950 HU) of TNC and VNC were comparable in patients with a water equivalent diameter (DW) below 270 mm. The study concludes that VNC imaging may be a viable option for assessing emphysema progression in COPD patients, particularly those with a normal body mass index (BMI). Further, pre-emphysema was generally comparable between TNC and VNC. This approach could potentially reduce radiation exposure and hospital resources by making additional TNC scans obsolete.

Preserving fairness and diagnostic accuracy in private large-scale AI models for medical imaging

BACKGROUND

Artificial intelligence (AI) models are increasingly used in the medical domain. However, as medical data is highly sensitive, special precautions to ensure its protection are required. The gold standard for privacy preservation is the introduction of differential privacy (DP) to model training. Prior work indicates that DP has negative implications on model accuracy and fairness, which are unacceptable in medicine and represent a main barrier to the widespread use of privacy-preserving techniques. In this work, we evaluated the effect of privacy-preserving training of AI models regarding accuracy and fairness compared to non-private training.

METHODS

We used two datasets: (1) A large dataset (N = 193,311) of high quality clinical chest radiographs, and (2) a dataset (N = 1625) of 3D abdominal computed tomography (CT) images, with the task of classifying the presence of pancreatic ductal adenocarcinoma (PDAC). Both were retrospectively collected and manually labeled by experienced radiologists. We then compared non-private deep convolutional neural networks (CNNs) and privacy-preserving (DP) models with respect to privacy-utility trade-offs measured as area under the receiver operating characteristic curve (AUROC), and privacy-fairness trade-offs, measured as Pearson's r or Statistical Parity Difference.

RESULTS

We find that, while the privacy-preserving training yields lower accuracy, it largely does not amplify discrimination against age, sex or co-morbidity. However, we find an indication that difficult diagnoses and subgroups suffer stronger performance hits in private training.

CONCLUSIONS

Our study shows that - under the challenging realistic circumstances of a real-life clinical dataset - the privacy-preserving training of diagnostic deep learning models is possible with excellent diagnostic accuracy and fairness.

Development of an image-based Random Forest classifier for prediction of surgery duration of laparoscopic sigmoid resections

PURPOSE

Sigmoid diverticulitis is a disease with a high socioeconomic burden, accounting for a high number of left-sided colonic resections worldwide. Modern surgical scheduling relies on accurate prediction of operation times to enhance patient care and optimize healthcare resources. This study aims to develop a predictive model for surgery duration in laparoscopic sigmoid resections, based on preoperative CT biometric and demographic patient data.

METHODS

This retrospective single-center cohort study included 85 patients who underwent laparoscopic sigmoid resection for diverticular disease. Potentially relevant procedure-specific anatomical parameters recommended by a surgical expert were measured in preoperative CT imaging. After random split into training and test set (75% / 25%) multiclass logistic regression was performed and a Random Forest classifier was trained on CT imaging parameters, patient age, and sex in the training cohort to predict categorized surgery duration. The models were evaluated in the test cohort using established performance metrics including receiver operating characteristics area under the curve (AUROC).

RESULTS

The Random Forest model achieved a good average AUROC of 0.78. It allowed a very good prediction of long (AUROC = 0.89; specificity 0.71; sensitivity 1.0) and short (AUROC = 0.81; specificity 0.77; sensitivity 0.56) procedures. It clearly outperformed the multiclass logistic regression model (AUROC: average = 0.33; short = 0.31; long = 0.22).

CONCLUSION

A Random Forest classifier trained on demographic and CT imaging biometric patient data could predict procedure duration outliers of laparoscopic sigmoid resections. Pending validation in a multicenter study, this approach could potentially improve procedure scheduling in visceral surgery and be scaled to other procedures.

Prognostic value of deep learning-derived body composition in advanced pancreatic cancer-a retrospective multicenter study

BACKGROUND

Despite the prognostic relevance of cachexia in pancreatic cancer, individual body composition has not been routinely integrated into treatment planning. In this multicenter study, we investigated the prognostic value of sarcopenia and myosteatosis automatically extracted from routine computed tomography (CT) scans of patients with advanced pancreatic ductal adenocarcinoma (PDAC).

PATIENTS AND METHODS

We retrospectively analyzed clinical imaging data of 601 patients from three German cancer centers. We applied a deep learning approach to assess sarcopenia by the abdominal muscle-to-bone ratio (MBR) and myosteatosis by the ratio of abdominal inter- and intramuscular fat to muscle volume. In the pooled cohort, univariable and multivariable analyses were carried out to analyze the association between body composition markers and overall survival (OS). We analyzed the relationship between body composition markers and laboratory values during the first year of therapy in a subgroup using linear regression analysis adjusted for age, sex, and American Joint Committee on Cancer (AJCC) stage.

RESULTS

Deep learning-derived MBR [hazard ratio (HR) 0.60, 95% confidence interval (CI) 0.47-0.77, P < 0.005] and myosteatosis (HR 3.73, 95% CI 1.66-8.39, P < 0.005) were significantly associated with OS in univariable analysis. In multivariable analysis, MBR (P = 0.019) and myosteatosis (P = 0.02) were associated with OS independent of age, sex, and AJCC stage. In a subgroup, MBR and myosteatosis were associated with albumin and C-reactive protein levels after initiation of therapy. Additionally, MBR was also associated with hemoglobin and total protein levels.

CONCLUSIONS

Our work demonstrates that deep learning can be applied across cancer centers to automatically assess sarcopenia and myosteatosis from routine CT scans. We highlight the prognostic role of our proposed markers and show a strong relationship with protein levels, inflammation, and anemia. In clinical practice, automated body composition analysis holds the potential to further personalize cancer treatment.

Repeatability and reproducibility of apparent exchange rate measurements in yeast cell phantoms using filter-exchange imaging

OBJECTIVES

Development of a protocol for validation and quality assurance of filter-exchange imaging (FEXI) pulse sequences with well-defined and reproducible phantoms.

MATERIALS AND METHODS

A FEXI pulse sequence was implemented on a 7 T preclinical MRI scanner. Six experiments in three different test categories were established for sequence validation, demonstration of the reproducibility of phantoms and the measurement of induced changes in the apparent exchange rate (AXR). First, an ice-water phantom was used to investigate the consistency of apparent diffusion coefficient (ADC) measurements with different diffusion filters. Second, yeast cell phantoms were utilized to validate the determination of the AXR in terms of repeatability (same phantom and session), reproducibility (separate but comparable phantoms in different sessions) and directionality of diffusion encodings. Third, the yeast cell phantoms were, furthermore, used to assess potential AXR bias because of altered cell density and temperature. In addition, a treatment experiment with aquaporin inhibitors was performed to evaluate the influence of these compounds on the cell membrane permeability in yeast cells.

RESULTS

FEXI-based ADC measurements of an ice-water phantom were performed for three different filter strengths, showed good agreement with the literature value of 1.099 × 10-3 mm2/s and had a maximum coefficient of variation (CV) of 0.55% within the individual filter strengths. AXR estimation in a single yeast cell phantom and imaging session with five repetitions resulted in an overall mean value of (1.49 ± 0.05) s-1 and a CV of 3.4% between the chosen regions of interest. For three separately prepared phantoms, AXR measurements resulted in a mean value of (1.50 ± 0.04) s-1 and a CV of 2.7% across the three phantoms, demonstrating high reproducibility. Across three orthogonal diffusion directions, a mean value of (1.57 ± 0.03) s-1 with a CV of 1.9% was detected, consistent with isotropy of AXR in yeast cells. Temperature and AXR were linearly correlated (R2 = 0.99) and an activation energy EA of 37.7 kJ/mol was determined by Arrhenius plot. Furthermore, a negative correlation was found between cell density (as determined by the reference ADC/fe) and AXR (R2 = 0.95). The treatment experiment resulted in significantly decreased AXR values at different temperatures in the treated sample compared to the untreated control indicating an inhibiting effect.

CONCLUSIONS

Using ice-water and yeast cell-based phantoms, a protocol for the validation of FEXI pulse sequences was established for the assessment of stability, repeatability, reproducibility and directionality. In addition, a strong dependence of AXR on cell density and temperature was shown. As AXR is an emerging novel imaging biomarker, the suggested protocol will be useful for quality assurance of AXR measurements within a study and potentially across multiple sites.

Multimodal graph attention network for COVID-19 outcome prediction

When dealing with a newly emerging disease such as COVID-19, the impact of patient- and disease-specific factors (e.g., body weight or known co-morbidities) on the immediate course of the disease is largely unknown. An accurate prediction of the most likely individual disease progression can improve the planning of limited resources and finding the optimal treatment for patients. In the case of COVID-19, the need for intensive care unit (ICU) admission of pneumonia patients can often only be determined on short notice by acute indicators such as vital signs (e.g., breathing rate, blood oxygen levels), whereas statistical analysis and decision support systems that integrate all of the available data could enable an earlier prognosis. To this end, we propose a holistic, multimodal graph-based approach combining imaging and non-imaging information. Specifically, we introduce a multimodal similarity metric to build a population graph that shows a clustering of patients. For each patient in the graph, we extract radiomic features from a segmentation network that also serves as a latent image feature encoder. Together with clinical patient data like vital signs, demographics, and lab results, these modalities are combined into a multimodal representation of each patient. This feature extraction is trained end-to-end with an image-based Graph Attention Network to process the population graph and predict the COVID-19 patient outcomes: admission to ICU, need for ventilation, and mortality. To combine multiple modalities, radiomic features are extracted from chest CTs using a segmentation neural network. Results on a dataset collected in Klinikum rechts der Isar in Munich, Germany and the publicly available iCTCF dataset show that our approach outperforms single modality and non-graph baselines. Moreover, our clustering and graph attention increases understanding of the patient relationships within the population graph and provides insight into the network's decision-making process.

Pulmonary Findings in Hospitalized COVID-19 Patients Assessed by Lung Ultrasonography (LUS) - A Prospective Registry Study

PURPOSE

This prospective two-centre study investigated localisation-dependent lesion patterns in COVID-19 with standard lung ultrasonography (LUS) and their relationship with thoracic computed tomography (CT) and clinical parameters.

MATERIALS AND METHODS

Between April 2020 and April 2021, 52 SARS-CoV-2-positive patients in two hospitals were examined by means of LUS for "B-lines", fragmented pleura, consolidation and air bronchogram in 12 lung regions and for pleural effusions. A newly developed LUS score based on the number of features present was correlated with clinical parameters (respiration, laboratory parameters) and the CT and analysed with respect to the 30- and 60-day outcome. All patients were offered an outpatient LUS follow-up.

RESULTS

The LUS and CT showed a bilateral, partially posteriorly accentuated lesion distribution pattern. 294/323 (91%) of CT-detected lesions were pleural. The LUS score showed an association with respiratory status and C-reactive protein; the correlation with the CT score was weak (Spearman's rho = 0.339, p < 0.001). High LUS scores on admission were also observed in patients who were discharged within 30 days. LUS during follow-up showed predominantly declining LUS scores.

CONCLUSION

The LUS score reflected the clinical condition of the patients. No conclusion could be made on the prognostic value of the LUS, because of the low event rate. The LUS and CT score showed no sufficient correlation. This is probably due to different physical principles, which is why LUS could be of complementary value.

A distinct stimulatory cDC1 subpopulation amplifies CD8+ T cell responses in tumors for protective anti-cancer immunity

Type 1 conventional dendritic cells (cDC1) can support T cell responses within tumors but whether this determines protective versus ineffective anti-cancer immunity is poorly understood. Here, we use imaging-based deep learning to identify intratumoral cDC1-CD8+ T cell clustering as a unique feature of protective anti-cancer immunity. These clusters form selectively in stromal tumor regions and constitute niches in which cDC1 activate TCF1+ stem-like CD8+ T cells. We identify a distinct population of immunostimulatory CCR7neg cDC1 that produce CXCL9 to promote cluster formation and cross-present tumor antigens within these niches, which is required for intratumoral CD8+ T cell differentiation and expansion and promotes cancer immune control. Similarly, in human cancers, CCR7neg cDC1 interact with CD8+ T cells in clusters and are associated with patient survival. Our findings reveal an intratumoral phase of the anti-cancer T cell response orchestrated by tumor-residing cDC1 that determines protective versus ineffective immunity and could be exploited for cancer therapy.

Comparison of Magnetic Resonance Imaging and Endoscopic Ultrasound in the Sizing of Intraductal Papillary Mucinous Neoplasia of the Pancreas

OBJECTIVES

Because IPMNs are potentially malignant, surveillance of IPMN is recommended by magnetic resonance imaging (MRI) and endoscopic ultrasound (EUS). The aim of the study was the evaluation of the concordance between EUS and MRI regarding cyst size.

METHODS

Retrospective data analysis was done for patients with IPMN in whom EUS and MRI were performed simultaneously (≤60 days). The measured cyst size of both procedures was compared by Bland-Altman plots. Agreement of cyst localization and dilation of main pancreatic duct was assessed using kappa statistics.

RESULTS

Fifty-nine cases were evaluated (median age, 71 years; 65% female; median time interval between both investigations, 17 days). The mean difference of IPMN maximal diameter between EUS and MRI was 0.55 mm with a prediction interval of -9.20 to +10.29 mm for 95% of the expected differences. There was strong interobserver agreement regarding cyst localization ( κ = 0.669, P = 1.06e -13 ) and the width of main pancreatic duct (<5, 5-9, and ≥10 mm; κ = 0.676 caput, κ = 0.823 corpus).

CONCLUSIONS

We found a clinically relevant difference in cyst size comparing EUS and MRI. Therefore, alternating EUS and MRI for follow-up of the "worrisome feature" size growth is not reasonable.

A deep learning model enables accurate prediction and quantification of pulmonary edema from chest X-rays

BACKGROUND

A quantitative assessment of pulmonary edema is important because the clinical severity can range from mild impairment to life threatening. A quantitative surrogate measure, although invasive, for pulmonary edema is the extravascular lung water index (EVLWI) extracted from the transpulmonary thermodilution (TPTD). Severity of edema from chest X-rays, to date is based on the subjective classification of radiologists. In this work, we use machine learning to quantitatively predict the severity of pulmonary edema from chest radiography.

METHODS

We retrospectively included 471 X-rays from 431 patients who underwent chest radiography and TPTD measurement within 24 h at our intensive care unit. The EVLWI extracted from the TPTD was used as a quantitative measure for pulmonary edema. We used a deep learning approach and binned the data into two, three, four and five classes increasing the resolution of the EVLWI prediction from the X-rays.

RESULTS

The accuracy, area under the receiver operating characteristic curve (AUROC) and Mathews correlation coefficient (MCC) in the binary classification models (EVLWI < 15, ≥ 15) were 0.93 (accuracy), 0.98 (AUROC) and 0.86(MCC). In the three multiclass models, the accuracy ranged between 0.90 and 0.95, the AUROC between 0.97 and 0.99 and the MCC between 0.86 and 0.92.

CONCLUSION

Deep learning can quantify pulmonary edema as measured by EVLWI with high accuracy.

Spectrally selective bSSFP using off-resonant RF excitations permits high spatiotemporal resolution 3D metabolic imaging of hyperpolarized [1-13 C]Pyruvate-to-[1-13 C]lactate conversion

PURPOSE

To develop a high spatiotemporal resolution 3D dynamic pulse sequence for preclinical imaging of hyperpolarized [1-¹³ C]pyruvate-to-[1-¹³ C]lactate metabolism at 7T.

METHODS

A standard 3D balanced SSFP (bSSFP) sequence was modified to enable alternating-frequency excitations. RF pulses with 2.33 ms duration and 900 Hz FWHM were placed off-resonance of the target metabolites, [1-¹³ C]pyruvate (by approximately -245 Hz) and [1-¹³ C]lactate (by approximately 735 Hz), to selectively excite those resonances. Relatively broad bandwidth (compared to those metabolites' chemical shift offset) permits a short TR of 6.29 ms, enabling higher spatiotemporal resolution. Bloch equation simulations of the bSSFP response profile guided the sequence parameter selection to minimize spectral contamination between metabolites and preserve magnetization over time.

RESULTS

Bloch equation simulations, phantom studies, and in vivo studies demonstrated that the two target resonances could be cleanly imaged without substantial bSSFP banding artifacts and with little spectral contamination between lactate and pyruvate and from pyruvate hydrate. High spatiotemporal resolution 3D images were acquired of in vivo pyruvate-lactate metabolism in healthy wild-type and endogenous pancreatic tumor-bearing mice, with 1.212 s acquisition time per single-metabolite image and (1.75 mm)³ isotropic voxels with full mouse abdomen 56 × 28 × 21 mm³ FOV and fully-sampled k-space. Kidney and tumor lactate/pyruvate ratios of two consecutive measurements in one animal, 1 h apart, were consistent.

CONCLUSION

Spectrally selective bSSFP using off-resonant RF excitations can provide high spatio-temporal resolution 3D dynamic images of pyruvate-lactate metabolic conversion.

Profile of the multicenter cohort of the German Cancer Consortium's Clinical Communication Platform

Treatment concepts in oncology are becoming increasingly personalized and diverse. Successively, changes in standards of care mandate continuous monitoring of patient pathways and clinical outcomes based on large, representative real-world data. The German Cancer Consortium's (DKTK) Clinical Communication Platform (CCP) provides such opportunity. Connecting fourteen university hospital-based cancer centers, the CCP relies on a federated IT-infrastructure sourcing data from facility-based cancer registry units and biobanks. Federated analyses resulted in a cohort of 600,915 patients, out of which 232,991 were incident since 2013 and for which a comprehensive documentation is available. Next to demographic data (i.e., age at diagnosis: 2.0% 0-20 years, 8.3% 21-40 years, 30.9% 41-60 years, 50.1% 61-80 years, 8.8% 81+ years; and gender: 45.2% female, 54.7% male, 0.1% other) and diagnoses (five most frequent tumor origins: 22,523 prostate, 18,409 breast, 15,575 lung, 13,964 skin/malignant melanoma, 9005 brain), the cohort dataset contains information about therapeutic interventions and response assessments and is connected to 287,883 liquid and tissue biosamples. Focusing on diagnoses and therapy-sequences, showcase analyses of diagnosis-specific sub-cohorts (pancreas, larynx, kidney, thyroid gland) demonstrate the analytical opportunities offered by the cohort's data. Due to its data granularity and size, the cohort is a potential catalyst for translational cancer research. It provides rapid access to comprehensive patient groups and may improve the understanding of the clinical course of various (even rare) malignancies. Therefore, the cohort may serve as a decisions-making tool for clinical trial design and contributes to the evaluation of scientific findings under real-world conditions.

The Liver Tumor Segmentation Benchmark (LiTS)

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://medicaldecathlon.com/. In addition, both data and online evaluation are accessible via https://competitions.codalab.org/competitions/17094.

Development and Validation of a Deep Learning Algorithm to Differentiate Colon Carcinoma From Acute Diverticulitis in Computed Tomography Images

IMPORTANCE

Differentiating between malignant and benign etiology in large-bowel wall thickening on computed tomography (CT) images can be a challenging task. Artificial intelligence (AI) support systems can improve the diagnostic accuracy of radiologists, as shown for a variety of imaging tasks. Improvements in diagnostic performance, in particular the reduction of false-negative findings, may be useful in patient care.

OBJECTIVE

To develop and evaluate a deep learning algorithm able to differentiate colon carcinoma (CC) and acute diverticulitis (AD) on CT images and analyze the impact of the AI-support system in a reader study.

DESIGN, SETTING, AND PARTICIPANTS

In this diagnostic study, patients who underwent surgery between July 1, 2005, and October 1, 2020, for CC or AD were included. Three-dimensional (3-D) bounding boxes including the diseased bowel segment and surrounding mesentery were manually delineated and used to develop a 3-D convolutional neural network (CNN). A reader study with 10 observers of different experience levels was conducted. Readers were asked to classify the testing cohort under reading room conditions, first without and then with algorithmic support.

MAIN OUTCOMES AND MEASURES

To evaluate the diagnostic performance, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for all readers and reader groups with and without AI support. Metrics were compared using the McNemar test and relative and absolute predictive value comparisons.

RESULTS

A total of 585 patients (AD: n = 267, CC: n = 318; mean [SD] age, 63.2 [13.4] years; 341 men [58.3%]) were included. The 3-D CNN reached a sensitivity of 83.3% (95% CI, 70.0%-96.6%) and specificity of 86.6% (95% CI, 74.5%-98.8%) for the test set, compared with the mean reader sensitivity of 77.6% (95% CI, 72.9%-82.3%) and specificity of 81.6% (95% CI, 77.2%-86.1%). The combined group of readers improved significantly with AI support from a sensitivity of 77.6% to 85.6% (95% CI, 81.3%-89.3%; P < .001) and a specificity of 81.6% to 91.3% (95% CI, 88.1%-94.5%; P < .001). Artificial intelligence support significantly reduced the number of false-negative and false-positive findings (NPV from 78.5% to 86.4% and PPV from 80.9% to 90.8%; P < .001).

CONCLUSIONS AND RELEVANCE

The findings of this study suggest that a deep learning model able to distinguish CC and AD in CT images as a support system may significantly improve the diagnostic performance of radiologists, which may improve patient care.

Functional noninvasive detection of glycolytic pancreatic ductal adenocarcinoma

BACKGROUND

Pancreatic ductal adenocarcinoma (PDAC) lacks effective treatment options beyond chemotherapy. Although molecular subtypes such as classical and QM (quasi-mesenchymal)/basal-like with transcriptome-based distinct signatures have been identified, deduced therapeutic strategies and targets remain elusive. Gene expression data show enrichment of glycolytic genes in the more aggressive and therapy-resistant QM subtype. However, whether the glycolytic transcripts are translated into functional glycolysis that could further be explored for metabolic targeting in QM subtype is still not known.

METHODS

We used different patient-derived PDAC model systems (conventional and primary patient-derived cells, patient-derived xenografts (PDX), and patient samples) and performed transcriptional and functional metabolic analysis. These included RNAseq and Illumina HT12 bead array, in vitro Seahorse metabolic flux assays and metabolic drug targeting, and in vivo hyperpolarized [1-¹³C]pyruvate and [1-¹³C]lactate magnetic resonance spectroscopy (HP-MRS) in PDAC xenografts.

RESULTS

We found that glycolytic metabolic dependencies are not unambiguously functionally exposed in all QM PDACs. Metabolic analysis demonstrated functional metabolic heterogeneity in patient-derived primary cells and less so in conventional cell lines independent of molecular subtype. Importantly, we observed that the glycolytic product lactate is actively imported into the PDAC cells and used in mitochondrial oxidation in both classical and QM PDAC cells, although more actively in the QM cell lines. By using HP-MRS, we were able to noninvasively identify highly glycolytic PDAC xenografts by detecting the last glycolytic enzymatic step and prominent intra-tumoral [1-¹³C]pyruvate and [1-¹³C]lactate interconversion in vivo.

CONCLUSION

Our study adds functional metabolic phenotyping to transcriptome-based analysis and proposes a functional approach to identify highly glycolytic PDACs as candidates for antimetabolic therapeutic avenues.

Angpt2/Tie2 autostimulatory loop controls tumorigenesis

Invasive nonfunctioning (NF) pituitary neuroendocrine tumors (PitNETs) are non‐resectable neoplasms associated with frequent relapses and significant comorbidities. As the current therapies of NF‐PitNETs often fail, new therapeutic targets are needed. The observation that circulating angiopoietin‐2 (ANGPT2) is elevated in patients with NF‐PitNET and correlates with tumor aggressiveness prompted us to investigate the ANGPT2/TIE2 axis in NF‐PitNETs in the GH3 PitNET cell line, primary human NF‐PitNET cells, xenografts in zebrafish and mice, and in MENX rats, the only autochthonous NF‐PitNET model. We show that PitNET cells express a functional TIE2 receptor and secrete bioactive ANGPT2, which promotes, besides angiogenesis, tumor cell growth in an autocrine and paracrine fashion. ANGPT2 stimulation of TIE2 in tumor cells activates downstream cell proliferation signals, as previously demonstrated in endothelial cells (ECs). Tie2 gene deletion blunts PitNETs growth in xenograft models, and pharmacological inhibition of Angpt2/Tie2 signaling antagonizes PitNETs in primary cell cultures, tumor xenografts in mice, and in MENX rats. Thus, the ANGPT2/TIE2 axis provides an exploitable therapeutic target in NF‐PitNETs and possibly in other tumors expressing ANGPT2/TIE2. The ability of tumor cells to coopt angiogenic signals classically viewed as EC‐specific expands our view on the microenvironmental cues that are essential for tumor progression.

Feature Robustness and Diagnostic Capabilities of Convolutional Neural Networks Against Radiomics Features in Computed Tomography Imaging

MATERIALS AND METHODS

Imaging phantoms were scanned twice on 3 computed tomography scanners from 2 different manufactures with varying tube voltages and currents. Phantoms were segmented, and features were extracted using PyRadiomics and a pretrained CNN. After standardization the concordance correlation coefficient (CCC), mean feature variance, feature range, and the coefficient of variant were calculated to assess feature robustness. In addition, the cosine similarity was calculated for the vectorized activation maps for an exemplary phantom. For the in vivo comparison, the radiomics and CNN features of 30 patients with hepatocellular carcinoma (HCC) and 30 patients with hepatic colon carcinoma metastasis were compared.

RESULTS

In total, 851 radiomics features and 256 CNN features were extracted for each phantom. For all phantoms, the global CCC of the CNN features was above 98%, whereas the highest CCC for the radiomics features was 36%. The mean feature variance and feature range was significantly lower for the CNN features. Using a coefficient of variant ≤0.2 as a threshold to define robust features and averaging across all phantoms 346 of 851 (41%) radiomics features and 196 of 256 (77%) CNN features were found to be robust. The cosine similarity was greater than 0.98 for all scanner and parameter variations. In the retrospective analysis, 122 of the 256 CNN (49%) features showed significant differences between HCC and hepatic colon metastasis.

DISCUSSION

Convolutional neural network features were more stable compared with radiomics features against technical variations. Moreover, the possibility of tumor entity differentiation based on CNN features was shown. Combined with visualization methods, CNN features are expected to increase reproducibility of quantitative image representations. Further studies are warranted to investigate the impact of feature stability on radiological image-based prediction of clinical outcomes.

Abstract PO-070: Longitudinal precision oncology platform to identify chemotherapy-induced vulnerabilities in pancreatic cancer

Pancreatic ductal adenocarcinoma (PDAC) remains a devastating disease with poor survival rates as almost all patients develop resistance towards chemotherapy and molecular-informed targeted therapies are reserved to a few. Here, we aim to establish a longitudinal precision oncology platform with a multi-dimensional characterization of PDAC biopsies including genomic, transcriptomic as well as functional analyses to identify and exploit treatment-induced vulnerabilities. In order to investigate adaptive processes of tumors under treatment we aimed to generate PDAC patient-derived organoids (PDOs) and 2D cell lines before and after chemotherapy. Therefore, we enrolled a patient with borderline resectable PDAC who received neoadjuvant FOLFIRINOX. Endoscopic fine needle (pre-FFX) and surgical biopsies (post-FFX) were used to generate PDOs and 2D cells. Whole exome sequencing (WES) and RNA sequencing data of the pre-FFX and post-FFX organoids were compared in order to evaluate the genetic landscape and PDAC subtypes. 2D cells were subjected to an unbiased automated drug screening of 415 compounds to investigate FFX-induced vulnerabilities. Top targets were validated manually in the 2D cells and organoids. Although transcriptional subtyping classified both PDOs as classical PDAC, gene set enrichment analysis (GSEA) revealed a reduced pathway activation linked to the basal-like phenotype such as KRAS signaling in the post-FFX organoids. WES did not show major differences in the genetic landscape of the tumor pre- and post-FFX induction suggesting a plasticity process rather than a clonal selection during chemotherapy. Importantly, post-FFX cells exhibited an increased sensitivity in the unbiased drug screening towards MEK and EGFR inhibition compared to pre-FFX cells. 2D cells and organoids were treated with different MEK inhibitors (MEKi) for validation and post-FFX cells showed a highly increased response compared to the treatment-naïve cells, as well. Interestingly, when placed into the context of a panel of 15 primary PDAC cell lines the pre-FFX cells cluster with highly MEKi resistant PDAC cells whereas post-FFX cells belong to the most sensitive cell lines. In sum, integrating functional layers into personalized medicine allowed us to identify chemotherapy-induced vulnerabilities as potent targeted therapy options in PDAC. Thus, this longitudinal precision oncology platform harbors a unique opportunity to understand adaptive processes in tumor evolution and/or treatment-imposed pressure in PDAC patients.

Citation Format: Katja Peschke, Hannah Jakubowski, Arlett Schäfer, Carlo Maurer, Sebastian Lange, Felix Orben, Raquel Bernad, Felix Harder, Matthias Eiber, Rupert Öllinger, Melissa Schlitter, Wilko Weichert, Veit Phillip, Christoph Schlag, Roland Schmid, Rickmer Braren, Bo Kong, Ekin Demir, Helmut Friess, Roland Rad, Dieter Saur, Günter Schneider, Maximilian Reichert. Longitudinal precision oncology platform to identify chemotherapy-induced vulnerabilities in pancreatic cancer [abstract]. In: Proceedings of the AACR Virtual Special Conference on Pancreatic Cancer; 2021 Sep 29-30. Philadelphia (PA): AACR; Cancer Res 2021;81(22 Suppl):Abstract nr PO-070.

Joint Imaging Platform for Federated Clinical Data Analytics

PURPOSE

Image analysis is one of the most promising applications of artificial intelligence (AI) in health care, potentially improving prediction, diagnosis, and treatment of diseases. Although scientific advances in this area critically depend on the accessibility of large-volume and high-quality data, sharing data between institutions faces various ethical and legal constraints as well as organizational and technical obstacles.

METHODS

The Joint Imaging Platform (JIP) of the German Cancer Consortium (DKTK) addresses these issues by providing federated data analysis technology in a secure and compliant way. Using the JIP, medical image data remain in the originator institutions, but analysis and AI algorithms are shared and jointly used. Common standards and interfaces to local systems ensure permanent data sovereignty of participating institutions.

RESULTS

The JIP is established in the radiology and nuclear medicine departments of 10 university hospitals in Germany (DKTK partner sites). In multiple complementary use cases, we show that the platform fulfills all relevant requirements to serve as a foundation for multicenter medical imaging trials and research on large cohorts, including the harmonization and integration of data, interactive analysis, automatic analysis, federated machine learning, and extensibility and maintenance processes, which are elementary for the sustainability of such a platform.

CONCLUSION

The results demonstrate the feasibility of using the JIP as a federated data analytics platform in heterogeneous clinical information technology and software landscapes, solving an important bottleneck for the application of AI to large-scale clinical imaging data.

Correlation of in vivo imaging to morphomolecular pathology in translational research: challenge accepted

Correlation of in vivo imaging to histomorphological pathology in animal models requires comparative interdisciplinary expertise of different fields of medicine. From the morphological point of view, there is an urgent need to improve histopathological evaluation in animal model-based research to expedite translation into clinical applications. While different other fields of translational science were standardized over the last years, little was done to improve the pipeline of experimental pathology to ensure reproducibility based on pathological expertise in experimental animal models with respect to defined guidelines and classifications. Additionally, longitudinal analyses of preclinical models often use a variety of imaging methods and much more attention should be drawn to enable for proper co-registration of in vivo imaging methods with the ex vivo morphological read-outs. Here we present the development of the Comparative Experimental Pathology (CEP) unit embedded in the Institute of Pathology of the Technical University of Munich during the Collaborative Research Center 824 (CRC824) funding period together with selected approaches of histomorphological techniques for correlation of in vivo imaging to morphomolecular pathology.

Efficient, high-performance semantic segmentation using multi-scale feature extraction

The success of deep learning in recent years has arguably been driven by the availability of large datasets for training powerful predictive algorithms. In medical applications however, the sensitive nature of the data limits the collection and exchange of large-scale datasets. Privacy-preserving and collaborative learning systems can enable the successful application of machine learning in medicine. However, collaborative protocols such as federated learning require the frequent transfer of parameter updates over a network. To enable the deployment of such protocols to a wide range of systems with varying computational performance, efficient deep learning architectures for resource-constrained environments are required. Here we present MoNet, a small, highly optimized neural-network-based segmentation algorithm leveraging efficient multi-scale image features. MoNet is a shallow, U-Net-like architecture based on repeated, dilated convolutions with decreasing dilation rates. We apply and test our architecture on the challenging clinical tasks of pancreatic segmentation in computed tomography (CT) images as well as brain tumor segmentation in magnetic resonance imaging (MRI) data. We assess our model’s segmentation performance and demonstrate that it provides performance on par with compared architectures while providing superior out-of-sample generalization performance, outperforming larger architectures on an independent validation set, while utilizing significantly fewer parameters. We furthermore confirm the suitability of our architecture for federated learning applications by demonstrating a substantial reduction in serialized model storage requirement as a surrogate for network data transfer. Finally, we evaluate MoNet’s inference latency on the central processing unit (CPU) to determine its utility in environments without access to graphics processing units. Our implementation is publicly available as free and open-source software.

Bcl3 Couples Cancer Stem Cell Enrichment With Pancreatic Cancer Molecular Subtypes

BACKGROUND & AIMS

The existence of different subtypes of pancreatic ductal adenocarcinoma (PDAC) and their correlation with patient outcome have shifted the emphasis on patient classification for better decision-making algorithms and personalized therapy. The contribution of mechanisms regulating the cancer stem cell (CSC) population in different subtypes remains unknown.

METHODS

Using RNA-seq, we identified B-cell CLL/lymphoma 3 (BCL3), an atypical nf-κb signaling member, as differing in pancreatic CSCs. To determine the biological consequences of BCL3 silencing in vivo and in vitro, we generated bcl3-deficient preclinical mouse models as well as murine cell lines and correlated our findings with human cell lines, PDX models, and 2 independent patient cohorts. We assessed the correlation of bcl3 expression pattern with clinical parameters and subtypes.

RESULTS

Bcl3 was significantly down-regulated in human CSCs. Recapitulating this phenotype in preclinical mouse models of PDAC via BCL3 genetic knockout enhanced tumor burden, metastasis, epithelial to mesenchymal transition, and reduced overall survival. Fluorescence-activated cell sorting analyses, together with oxygen consumption, sphere formation, and tumorigenicity assays, all indicated that BCL3 loss resulted in CSC compartment expansion promoting cellular dedifferentiation. Overexpression of BCL3 in human PDXs diminished tumor growth by significantly reducing the CSC population and promoting differentiation. Human PDACs with low BCL3 expression correlated with increased metastasis, and BCL3-negative tumors correlated with lower survival and nonclassical subtypes.

CONCLUSIONS

We demonstrate that bcl3 impacts pancreatic carcinogenesis by restraining CSC expansion and by curtailing an aggressive and metastatic tumor burden in PDAC across species. Levels of BCL3 expression are a useful stratification marker for predicting subtype characterization in PDAC, thereby allowing for personalized therapeutic approaches.

SARS-CoV-2 serology increases diagnostic accuracy in CT-suspected, PCR-negative COVID-19 patients during pandemic

Background

In the absence of PCR detection of SARS-CoV-2 RNA, accurate diagnosis of COVID-19 is challenging. Low-dose computed tomography (CT) detects pulmonary infiltrates with high sensitivity, but findings may be non-specific. This study assesses the diagnostic value of SARS-CoV-2 serology for patients with distinct CT features but negative PCR.

Methods

IgM/IgG chemiluminescent immunoassay was performed for 107 patients with confirmed (group A: PCR + ; CT ±) and 46 patients with suspected (group B: repetitive PCR-; CT +) COVID-19, admitted to a German university hospital during the pandemic’s first wave. A standardized, in-house CT classification of radiological signs of a viral pneumonia was used to assess the probability of COVID-19.

Results

Seroconversion rates (SR) determined on day 5, 10, 15, 20 and 25 after symptom onset (SO) were 8%, 25%, 65%, 76% and 91% for group A, and 0%, 10%, 19%, 37% and 46% for group B, respectively; (p < 0.01). Compared to hospitalized patients with a non-complicated course (non-ICU patients), seroconversion tended to occur at lower frequency and delayed in patients on intensive care units. SR of patients with CT findings classified as high certainty for COVID-19 were 8%, 22%, 68%, 79% and 93% in group A, compared with 0%, 15%, 28%, 50% and 50% in group B (p < 0.01). SARS-CoV-2 serology established a definite diagnosis in 12/46 group B patients. In 88% (8/9) of patients with negative serology > 14 days after symptom onset (group B), clinico-radiological consensus reassessment revealed probable diagnoses other than COVID-19. Sensitivity of SARS-CoV-2 serology was superior to PCR > 17d after symptom onset.

Conclusions

Approximately one-third of patients with distinct COVID-19 CT findings are tested negative for SARS-CoV-2 RNA by PCR rendering correct diagnosis difficult. Implementation of SARS-CoV-2 serology testing alongside current CT/PCR-based diagnostic algorithms improves discrimination between COVID-19-related and non-related pulmonary infiltrates in PCR negative patients. However, sensitivity of SARS-CoV-2 serology strongly depends on the time of testing and becomes superior to PCR after the 2^nd week following symptom onset.

PALLD mutation in a European family conveys a stromal predisposition for familial pancreatic cancer

BACKGROUNDPancreatic cancer is one of the deadliest cancers, with low long-term survival rates. Despite recent advances in treatment, it is important to identify and screen high-risk individuals for cancer prevention. Familial pancreatic cancer (FPC) accounts for 4%-10% of pancreatic cancers. Several germline mutations are related to an increased risk and might offer screening and therapy options. In this study, we aimed to identity of a susceptibility gene in a family with FPC.METHODSWhole exome sequencing and PCR confirmation was performed on the surgical specimen and peripheral blood of an index patient and her sister in a family with high incidence of pancreatic cancer, to identify somatic and germline mutations associated with familial pancreatic cancer. Compartment-specific gene expression data and immunohistochemistry were also queried.RESULTSThe identical germline mutation of the PALLD gene (NM_001166108.1:c.G154A:p.D52N) was detected in the index patient with pancreatic cancer and the tumor tissue of her sister. Whole genome sequencing showed similar somatic mutation patterns between the 2 sisters. Apart from the PALLD mutation, commonly mutated genes that characterize pancreatic ductal adenocarcinoma were found in both tumor samples. However, the 2 patients harbored different somatic KRAS mutations (G12D and G12V). Healthy siblings did not have the PALLD mutation, indicating a disease-specific impact. Compartment-specific gene expression data and IHC showed expression in cancer-associated fibroblasts (CAFs).CONCLUSIONWe identified a germline mutation of the palladin (PALLD) gene in 2 siblings in Europe, affected by familial pancreatic cancer, with a significant overexpression in CAFs, suggesting that stromal palladin could play a role in the development, maintenance, and/or progression of pancreatic cancer.FUNDINGDFG SFB 1321.

Hyperpolarized 13C Spectroscopy with Simple Slice-and-Frequency-Selective Excitation

Hyperpolarized ¹³C nuclear magnetic resonance spectroscopy can characterize in vivo tissue metabolism, including preclinical models of cancer and inflammatory disease. Broad bandwidth radiofrequency excitation is often paired with free induction decay readout for spectral separation, but quantification of low-signal downstream metabolites using this method can be impeded by spectral peak overlap or when frequency separation of the detected peaks exceeds the excitation bandwidth. In this work, alternating frequency narrow bandwidth (250 Hz) slice-selective excitation was used for ¹³C spectroscopy at 7 T in a subcutaneous xenograft rat model of human pancreatic cancer (PSN1) to improve quantification while measuring the dynamics of injected hyperpolarized [1-¹³C]lactate and its metabolite [1-¹³C]pyruvate. This method does not require sophisticated pulse sequences or specialized radiofrequency and gradient pulses, but rather uses nominally spatially offset slices to produce alternating frequency excitation with simpler slice-selective radiofrequency pulses. Additionally, point-resolved spectroscopy was used to calibrate the ¹³C frequency from the thermal proton signal in the target region. This excitation scheme isolates the small [1-¹³C]pyruvate peak from the similar-magnitude tail of the much larger injected [1-¹³C]lactate peak, facilitates quantification of the [1-¹³C]pyruvate signal, simplifies data processing, and could be employed for other substrates and preclinical models.

Deep Convolutional Neural Network-Assisted Feature Extraction for Diagnostic Discrimination and Feature Visualization in Pancreatic Ductal Adenocarcinoma (PDAC) versus Autoimmune Pancreatitis (AIP)

The differentiation of autoimmune pancreatitis (AIP) and pancreatic ductal adenocarcinoma (PDAC) poses a relevant diagnostic challenge and can lead to misdiagnosis and consequently poor patient outcome. Recent studies have shown that radiomics-based models can achieve high sensitivity and specificity in predicting both entities. However, radiomic features can only capture low level representations of the input image. In contrast, convolutional neural networks (CNNs) can learn and extract more complex representations which have been used for image classification to great success. In our retrospective observational study, we performed a deep learning-based feature extraction using CT-scans of both entities and compared the predictive value against traditional radiomic features. In total, 86 patients, 44 with AIP and 42 with PDACs, were analyzed. Whole pancreas segmentation was automatically performed on CT-scans during the portal venous phase. The segmentation masks were manually checked and corrected if necessary. In total, 1411 radiomic features were extracted using PyRadiomics and 256 features (deep features) were extracted using an intermediate layer of a convolutional neural network (CNN). After feature selection and normalization, an extremely randomized trees algorithm was trained and tested using a two-fold shuffle-split cross-validation with a test sample of 20% (n = 18) to discriminate between AIP or PDAC. Feature maps were plotted and visual difference was noted. The machine learning (ML) model achieved a sensitivity, specificity, and ROC-AUC of 0.89 ± 0.11, 0.83 ± 0.06, and 0.90 ± 0.02 for the deep features and 0.72 ± 0.11, 0.78 ± 0.06, and 0.80 ± 0.01 for the radiomic features. Visualization of feature maps indicated different activation patterns for AIP and PDAC. We successfully trained a machine learning model using deep feature extraction from CT-images to differentiate between AIP and PDAC. In comparison to traditional radiomic features, deep features achieved a higher sensitivity, specificity, and ROC-AUC. Visualization of deep features could further improve the diagnostic accuracy of non-invasive differentiation of AIP and PDAC.

[Artificial intelligence and machine learning in oncologic imaging]

Machine learning (ML) is entering many areas of society, including medicine. This transformation has the potential to drastically change medicine and medical practice. These aspects become particularly clear when considering the different stages of oncologic patient care and the involved interdisciplinary and intermodality interactions. In recent publications, computers-in collaboration with humans or alone-have been outperforming humans regarding tumor identification, tumor classification, estimating prognoses, and evaluation of treatments. In addition, ML algorithms, e.g., artificial neural networks (ANNs), which constitute the drivers behind many of the latest achievements in ML, can deliver this level of performance in a reproducible, fast, and inexpensive manner. In the future, artificial intelligence applications will become an integral part of the medical profession and offer advantages for oncologic diagnostics and treatment.

MCL-1 gains occur with high frequency in lung adenocarcinoma and can be targeted therapeutically

Evasion of programmed cell death represents a critical form of oncogene addiction in cancer cells. Understanding the molecular mechanisms underpinning cancer cell survival despite the oncogenic stress could provide a molecular basis for potential therapeutic interventions. Here we explore the role of pro-survival genes in cancer cell integrity during clonal evolution in non-small cell lung cancer (NSCLC). We identify gains of MCL-1 at high frequency in multiple independent NSCLC cohorts, occurring both clonally and subclonally. Clonal loss of functional TP53 is significantly associated with subclonal gains of MCL-1. In mice, tumour progression is delayed upon pharmacologic or genetic inhibition of MCL-1. These findings reveal that MCL-1 gains occur with high frequency in lung adenocarcinoma and can be targeted therapeutically.

Implementing cell-free DNA of pancreatic cancer patient-derived organoids for personalized oncology

One of the major challenges in using pancreatic cancer patient-derived organoids (PDOs) in precision oncology is the time from biopsy to functional characterization. This is particularly true for endoscopic ultrasound-guided fine-needle aspiration biopsies, typically resulting in specimens with limited tumor cell yield. Here, we tested conditioned media of individual PDOs for cell-free DNA to detect driver mutations already early on during the expansion process to accelerate the genetic characterization of PDOs as well as subsequent functional testing. Importantly, genetic alterations detected in the PDO supernatant, collected as early as 72 hours after biopsy, recapitulate the mutational profile of the primary tumor, indicating suitability of this approach to subject PDOs to drug testing in a reduced time frame. In addition, we demonstrated that this workflow was practicable, even in patients for whom the amount of tumor material was not sufficient for molecular characterization by established means. Together, our findings demonstrate that generating PDOs from very limited biopsy material permits molecular profiling and drug testing. With our approach, this can be achieved in a rapid and feasible fashion with broad implications in clinical practice.

[Strategy for university emergency room management at the beginning of an epidemic using COVID-19 as an example]

Durch die weltweit steigenden Zahlen an „coronavirus disease 2019“(COVID-19)-Infektionen besteht für sämtliche Kliniken die Aufgabe, sich der Herausforderung einer Pandemie zu stellen. Es gilt insbesondere auch für die Notaufnahmen, sich auf vollständig veränderte Arbeitsabläufe vorzubereiten und sie umzusetzen. Dies betrifft insbesondere den Bereich Patientenscreening und -selektion (Triage). Auch mit anderen Fachbereichen wie der Hygiene, Infektiologie oder Virologie muss Hand in Hand zusammengearbeitet werden, um vor, während und nach Abschluss der Diagnostik entsprechende Behandlungskonzepte zu realisieren. Darüber hinaus sind Kommunikation und Qualitäts- und Risikomanagement nebst den klinischen Bereichen von hoher Relevanz. Dieser Artikel beschreibt an einem Beispiel, wie sich Notaufnahmen hier am Beispiel COVID-19 (coronavirus disease 2019) konkret und praxisnah auf eine Pandemie vorbereiten können.

Strongyloides stercoralis hyperinfection syndrome presenting as mechanical ileus after short-course oral steroids for chronic obstructive pulmonary disease (COPD) exacerbation

We report a case of a fatal Strongyloides stercoralis hyperinfection syndrome (SHS) in a migrant from Kenya, who had been living in Germany for three decades. A short-course oral steroid treatment for Chronic Obstructive Pulmonary Disease (COPD) exacerbation had been administered four weeks prior to the presentation. The initial clinical and radiological findings suggested a mechanical small bowel obstruction as a cause of ileus. Our case highlights the importance of maintaining a high index of suspicion for strongyloidiasis in patients from endemic areas even years after they left the country of origin. It demonstrates that even a five-day course of prednisolone is able to trigger SHS in patients with underlying strongyloidiasis. History of frequent previous administration of oral prednisolone for COPD exacerbations in our case raises the question why and how the last steroid regimen provoked SHS. SHS can present with multiple gastrointestinal symptoms including ileus and the absence of eosinophilia during the whole course of the disease should not lower the level of suspicion in the appropriate clinical setting.

Impact of 18F-FDG-PET/CT on the identification of regional lymph node metastases and delineation of the primary tumor in esophageal squamous cell carcinoma patients

Purpose

In patients undergoing chemoradiation for esophageal squamous cell carcinoma (ESCC), the extent of elective nodal irradiation (ENI) is still discussed controversially. This study aimed to analyze patterns of lymph node metastases and their correlation with the primary tumor using ¹⁸F‑fludeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) scans.

Methods

102 ESCC patients with pre-treatment FDG-PET/CT scans were evaluated retrospectively. After exclusion of patients with low FDG uptake and patients without FDG-PET-positive lymph node metastases (LNM), 76 patients were included in the final analysis. All LNM were assigned to 16 pre-defined anatomical regions and classified according to their position relative to the primary tumor (above, at the same height, or below the primary tumor). In addition, the longitudinal distance to the primary tumor was measured for all LNM above or below the primary tumor. The craniocaudal extent (i.e., length) of the primary tumor was measured using FDG-PET imaging (L_PET) and also based on all other available clinical and imaging data (endoscopy, computed tomography, biopsy results) except FDG-PET (L_CT/EUS).

Results

Significantly more LNM were identified with ¹⁸F‑FDG-PET/CT (177 LNM) compared to CT alone (131 LNM, p < 0.001). The most common sites of LNM were paraesophageal (63% of patients, 37% of LNM) and paratracheal (33% of patients, 20% of LNM), while less than 5% of patients had supraclavicular, subaortic, diaphragmatic, or hilar LNM. With regard to the primary tumor, 51% of LNM were at the same height, while 25% and 24% of lymph node metastases were above and below the primary tumor, respectively. For thirty-three LNM (19%), the distance to the primary tumor was larger than 4 cm. No significant difference was seen between L_CT/EUS (median 6 cm) and L_PET (median 6 cm, p = 0.846)

Conclusion

¹⁸F‑FDG-PET can help to identify subclinical lymph node metastases which are located outside of recommended radiation fields. PET-based involved-field irradiation might be the ideal compromise between small treatment volumes and decreasing the risk of undertreatment of subclinical metastatic lymph nodes and should be further evaluated.

Differential Diagnosis for Pancreatic Cysts in CT Scans Using Densely-Connected Convolutional Networks

The lethal nature of pancreatic ductal adenocarcinoma (PDAC) calls for early differential diagnosis of pancreatic cysts, which are identified in up to 16% of normal subjects, and some of them may develop into PDAC. Pancreatic cysts have a large variation in size and shape, and the precise segmentation of them remains rather challenging, which restricts the computer-aided interpretation of CT images acquired for differential diagnosis. We propose a computer-aided framework for early differential diagnosis of pancreatic cysts without pre-segmenting the lesions using densely-connected convolutional networks (Dense-Net). The Dense-Net learns high-level features from whole abnormal pancreas and builds mappings between medical imaging appearance to different pathological types of pancreatic cysts. To enhance the clinical applicability, we integrate saliency maps in the framework to assist the physicians to understand the decision of the deep learning method. The test on a cohort of 206 patients with 4 pathologically confirmed subtypes of pancreatic cysts has achieved an overall accuracy of 72.8%, which is significantly higher than the baseline accuracy of 48.1%. The superior performance on this challenging dataset strongly supports the clinical potential of our developed method.

[A primer on machine learning]

BACKGROUND

The methods of machine learning and artificial intelligence are slowly but surely being introduced in everyday medical practice. In the future, they will support us in diagnosis and therapy and thus improve treatment for the benefit of the individual patient. It is therefore important to deal with this topic and to develop a basic understanding of it.

OBJECTIVES

This article gives an overview of the exciting and dynamic field of machine learning and serves as an introduction to some methods primarily from the realm of supervised learning. In addition to definitions and simple examples, limitations are discussed.

CONCLUSIONS

The basic principles behind the methods are simple. Nevertheless, due to their high dimensional nature, the factors influencing the results are often difficult or impossible to understand by humans. In order to build confidence in the new technologies and to guarantee their safe application, we need explainable algorithms and prospective effectiveness studies.

[A primer on radiomics]

CLINICAL ISSUE

The reproducible and exhaustive extraction of information from radiological images is a central task in the practice of radiology. Dynamic developments in the fields of artificial intelligence (AI) and machine learning are introducing new methods for this task. Radiomics is one such method and offers new opportunities and challenges for the future of radiology.

METHODOLOGICAL INNOVATIONS

Radiomics describes the quantitative evaluation, interpretation, and clinical assessment of imaging markers in radiological data. Components of a radiomics analysis are data acquisition, data preprocessing, data management, segmentation of regions of interest, computation and selection of imaging markers, as well as the development of a radiomics model used for diagnosis and prognosis. This article explains these components and aims at providing an introduction to the field of radiomics while highlighting existing limitations.

MATERIALS AND METHODS

This article is based on a selective literature search with the PubMed search engine.

ASSESSMENT

Even though radiomics applications have yet to arrive in routine clinical practice, the quantification of radiological data in terms of radiomics is underway and will increase in the future. This holds the potential for lasting change in the discipline of radiology. Through the successful extraction and interpretation of all the information encoded in radiological images the next step in the direction of a more personalized, future-oriented form of medicine can be taken.

Combined DCE-MRI- and FDG-PET enable histopathological grading prediction in a rat model of hepatocellular carcinoma

PURPOSE

To test combined dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and 18F-FDG positron emission tomography (FDG-PET)-derived parameters for prediction of histopathological grading in a rat Diethyl Nitrosamine (DEN)-induced hepatocellular carcinoma (HCC) model.

METHODS

15 male Wistar rats, aged 10 weeks were treated with oral DEN 0.01 % in drinking water and monitored until HCCs were detectable. DCE-MRI and PET were performed consecutively on small animal scanners. 38 tumors were identified and manually segmented based on HCC-specific contrast enhancement patterns. Grading (G2/3: 24 tumors, G1:14 tumors) alongside other histopathological parameters, tumor volume, contrast agent and 18F-FDG uptake metrics were noted. Class imbalance was addressed using SMOTE and collinearity was removed using hierarchical clustering and principal component analysis. A logistic regression model was fit separately to the individual parameter groups (DCE-MRI-derived, PET-derived, tumor volume) and the combined parameters.

RESULTS

The combined model using all imaging-derived parameters achieved a mean ± STD sensitivity of 0.88 ± 0.16, specificity of 0.70 ± 0.20 and AUC of 0.90 ± 0.03. No correlation was found between tumor grading and tumor volume, morphology, necrosis, extracellular matrix, immune cell infiltration or underlying liver fibrosis.

CONCLUSION

A combination of DCE-MRI- and 18F-FDG-PET-derived parameters provides high accuracy for histopathological grading of hepatocellular carcinoma in a relevant translational model system.

A machine learning model for the prediction of survival and tumor subtype in pancreatic ductal adenocarcinoma from preoperative diffusion-weighted imaging

Background

To develop a supervised machine learning (ML) algorithm predicting above- versus below-median overall survival (OS) from diffusion-weighted imaging-derived radiomic features in patients with pancreatic ductal adenocarcinoma (PDAC).

Methods

One hundred two patients with histopathologically proven PDAC were retrospectively assessed as training cohort, and 30 prospectively accrued and retrospectively enrolled patients served as independent validation cohort (IVC). Tumors were segmented on preoperative apparent diffusion coefficient (ADC) maps, and radiomic features were extracted. A random forest ML algorithm was fit to the training cohort and tested in the IVC. Histopathological subtype of tumor samples was assessed by immunohistochemistry in 21 IVC patients. Individual radiomic feature importance was evaluated by assessment of tree node Gini impurity decrease and recursive feature elimination. Fisher’s exact test, 95% confidence intervals (CI), and receiver operating characteristic area under the curve (ROC-AUC) were used.

Results

The ML algorithm achieved 87% sensitivity (95% IC 67.3–92.7), 80% specificity (95% CI 74.0–86.7), and ROC-AUC 90% for the prediction of above- versus below-median OS in the IVC. Heterogeneity-related features were highly ranked by the model. Of the 21 patients with determined histopathological subtype, 8/9 patients predicted to experience below-median OS exhibited the quasi-mesenchymal subtype, whilst 11/12 patients predicted to experience above-median OS exhibited a non-quasi-mesenchymal subtype (p < 0.001).

Conclusion

ML application to ADC radiomics allowed OS prediction with a high diagnostic accuracy in an IVC. The high overlap of clinically relevant histopathological subtypes with model predictions underlines the potential of quantitative imaging in PDAC pre-operative subtyping and prognosis.

Electronic supplementary material

The online version of this article (10.1186/s41747-019-0119-0) contains supplementary material, which is available to authorized users.

A machine learning algorithm predicts molecular subtypes in pancreatic ductal adenocarcinoma with differential response to gemcitabine-based versus FOLFIRINOX chemotherapy

PURPOSE

Development of a supervised machine-learning model capable of predicting clinically relevant molecular subtypes of pancreatic ductal adenocarcinoma (PDAC) from diffusion-weighted-imaging-derived radiomic features.

METHODS

The retrospective observational study assessed 55 surgical PDAC patients. Molecular subtypes were defined by immunohistochemical staining of KRT81. Tumors were manually segmented and 1606 radiomic features were extracted with PyRadiomics. A gradient-boosted-tree algorithm was trained on 70% of the patients (N = 28) and tested on 30% (N = 17) to predict KRT81+ vs. KRT81- tumor subtypes. A gradient-boosted survival regression model was fit to the disease-free and overall survival data. Chemotherapy response and survival were assessed stratified by subtype and radiomic signature. Radiomic feature importance was ranked.

RESULTS

The mean±STDEV sensitivity, specificity and ROC-AUC were 0.90±0.07, 0.92±0.11, and 0.93±0.07, respectively. The mean±STDEV concordance indices between the disease-free and overall survival predicted by the model based on the radiomic parameters and actual patient survival were 0.76±0.05 and 0.71±0.06, respectively. Patients with a KRT81+ subtype experienced significantly diminished median overall survival compared to KRT81- patients (7.0 vs. 22.6 months, HR 4.03, log-rank-test P = <0.001) and a significantly improved response to gemcitabine-based chemotherapy over FOLFIRINOX (10.14 vs. 3.8 months median overall survival, HR 2.33, P = 0.037) compared to KRT81- patients, who responded significantly better to FOLFIRINOX over gemcitabine-based treatment (30.8 vs. 13.4 months median overall survival, HR 2.41, P = 0.027). Entropy was ranked as the most important radiomic feature.

CONCLUSIONS

The machine-learning based analysis of radiomic features enables the prediction of subtypes of PDAC, which are highly relevant for disease-free and overall patient survival and response to chemotherapy.

Oncogenic Akt-FOXO3 loop favors tumor-promoting modes and enhances oxidative damage-associated hepatocellular carcinogenesis

BACKGROUND

Hepatocellular carcinoma (HCC) is the most prevalent primary liver cancer, accounting for 80-90% of cases. Mutations are commonly found in the signaling regulating the PI3K/Akt pathway, leading to oncogenic cell proliferation and survival. Key transcription factors that are negatively regulated downstream of PI3K/Akt are members of the forkhead box O family (FOXO). FOXOs were initially considered as tumor suppressors by inducing cell cycle arrest and apoptosis. However, there is increasing evidence showing that FOXOs, especially FOXO3, can support tumorigenesis.

METHODS

To understand the roles of FOXO3 in liver tumorigenesis and hepatocarcinogenesis, we analyzed HCC patient specimens and also established a doxycycline-regulated transgenic mouse model with hepatocyte-specific FOXO3 expression in a constitutively active form.

RESULTS

We found that FOXO3 protein is significantly overexpressed and activated in livers of HCC patients. Hepatic activation of FOXO3 induced extensive hepatic damage and elevated gene expression of several HCC-associated factors. Furthermore, FOXO3 expression enhanced hepatotoxicin-induced tumorigenesis. Mechanistically, FOXO3 activation caused oxidative stress and DNA damage and triggered positive feedback-loop for Akt activation as well as mTORC2 activation. Interestingly, FOXO3 activated not only reactive oxygen species (ROS)-promoting pathways, but also ROS-eliminating systems, which can be associated with the activation of the pentose phosphate pathway.

CONCLUSIONS

FOXO3 is a master regulator of ROS in a 'carrot and stick' manner; on one side avoiding cellular crisis while also supporting hepatocellular carcinogenesis. Clinically, we suggest analyzing FOXO3 activation status in patients with liver diseases, in addition to PI3K/Akt signaling. Personalized therapy of FOXO3 inhibition may be a reasonable, depending on the activation status of FOXO3.

Autoimmune Pancreatitis Type 1 Associated with a Pancreatic Pseudocyst

Pancreatic cystic lesions comprise diverse entities with different histopathological characteristics. Differential diagnosis is often challenging. Autoimmune pancreatitis (AIP) is usually not considered an underlying pathology in the differential diagnosis of peri-/pancreatic pseudo-/cystic lesions. We report the case of a 73-year-old male with diffuse pancreatic enlargement and an adjacent cystic lesion (60 × 80 mm) on computed tomography scan. Based on these imaging findings and an elevated serum IgG4 concentration, AIP complicated by a pancreatic pseudocyst was diagnosed, and treatment with glucocorticoids was started. Regular follow-ups showed a good response to treatment with regression of the pancreatic pseudocyst and remittent pancreatic swelling.

Pancreatic cancer detection and characterization-state of the art cross-sectional imaging and imaging data analysis

Pancreatic ductal adenocarcinoma (PDAC) represents a deadly disease, prognosticated to become the 2nd most common cause of cancer related death in the western world by 2030. State of the art radiologic high-resolution cross-sectional imaging by computed tomography (CT) and magnetic resonance imaging (MRI) represent advanced techniques for early lesion detection, pre-therapeutic patient staging and therapy response monitoring. In light of molecular taxonomies currently under development, the implementation of advanced imaging data post-processing pipelines and the integration of imaging and clinical data for the development of risk assessment and clinical decision support tools are required. This review will present the current state of cross-sectional radiologic imaging and image post-processing related to PDAC.

Neoadjuvant versus definitive chemoradiation in patients with squamous cell carcinoma of the esophagus

Background

Multimodal treatment with neoadjuvant chemoradiation followed by surgery (nCRT + S) is the treatment of choice for patients with locally advanced or node-positive esophageal squamous cell carcinoma (E-SCC). Those who are unsuitable or who decline surgery can be treated with definitive chemoradiation (dCRT). This study compares the oncologic outcome of nCRT + S and dCRT in E-SCC patients.

Methods

Between 2011 and 2017, 95 patients with E-SCC were scheduled for dCRT or nCRT+ S with IMRT at our department. Patients undergoing dCRT received at least 50 Gy and those undergoing nCRT + S received at least 41.4 Gy. All patients received simultaneous chemotherapy with either carboplatin and paclitaxel or cisplatin and 5-fluoruracil. We retrospectively compared baseline characteristics and oncologic outcome including overall survival (OS), progression-free survival (PFS) and site of failure between both treatment groups.

Results

Patients undergoing dCRT were less likely to have clinically suspected lymph node metastases (85% vs. 100%, p = 0.019) than patients undergoing nCRT + S and had more proximally located tumors (median distance from dental arch to cranial tumor border 20 cm vs. 26 cm, p < 0.001). After a median follow up of 25.6 months for surviving patients, no significant differences for OS and PFS were noticed comparing nCRT + S and dCRT. However, the rate of local tumor recurrence was significantly higher in patients treated with dCRT than in those treated with nCRT + S (38% vs. 10%, p = 0.002). Within a multivariate Cox regression model, age, tumor location, and tumor grading were the only independent parameters affecting OS and PFS. In addition to that, proximal tumor location was the only parameter independently associated with an increased risk for local treatment failure.

Conclusion

In E-SCC patients treated with either dCRT or nCRT + S, a higher rate of local tumor recurrence was seen in patients treated with dCRT than in patients treated with nCRT + S. There was at least a trend towards an improved OS and PFS in patients undergoing nCRT + S. However, this should be interpreted with caution, because proximal tumor location was the only parameter independently affecting the risk of local tumor recurrence.

Comparison of definite chemoradiation therapy with carboplatin/paclitaxel or cisplatin/5-fluoruracil in patients with squamous cell carcinoma of the esophagus

Background

While neoadjuvant chemoradiation therapy (nCRT) with subsequent surgery is the treatment of choice for patients with locally advanced or node-positive squamous cell carcinoma of the esophagus (SCC) suitable for surgery, patients who are unsuitable for surgery or who refuse surgery should be treated with definite chemoradiation therapy (dCRT). Purpose of this study was to compare toxicity and oncologic outcome of dCRT with either cisplatin and 5-fluoruracil (CDDP/5FU) or carboplatin and paclitaxel (Carb/TAX) in patients with SCC.

Methods

Twenty-two patients who received dCRT with carboplatin (AUC2, weekly) and paclitaxel (50 mg per square meter of body-surface area, weekly) were retrospectively compared to 25 patients who were scheduled for dCRT with cisplatin (20 mg/m²/d) and 5-fluoruracil (500 mg/m²/d) on day 1–5 and day 29–33. For the per-protocol (PP) analysis, PP treatment was defined as complete radiation therapy with at least 54Gy and at least three complete cycles of Carb/TAX or complete radiation therapy with at least 54Gy and at least one complete cycle of CDDP/5FU. While patients who were scheduled for dCRT with Carb/TAX received a significantly higher total radiation dose (median dose 59.4Gy vs. 54Gy, p < 0.001) than patients who were scheduled for dCRT with CDDP/5FU, no significant differences were seen for other parameters (age, sex, TNM-stage, grading and tumor extension).

Results

Forty-seven patients (25 patients treated with CDDP/5FU and 22 patients treated with Carb/TAX) were evaluated for the intention-to-treat (ITT) analysis and 41 of 47 patients (23 patients treated with CDDP/5FU and 18 patients treated with Carb/TAX) were evaluated for the PP analysis. Severe myelotoxicity (≥ III°) was seen in 52% (CDDP/5FU) and 55% of patients (Carb/TAX), respectively (p = 1.000). In the univariate binary logistic regression analysis, patients age was the only factor associated with an increased risk of ≥ III° myelotoxicity (hazard ratio 1.145, 95% CI 1.035; 1.266; p = 0.009). Regarding treatment efficiency, no significant differences were seen for overall survival (OS) and freedom from relapse (FFR) between both treatment groups.

Conclusion

Myelotoxicity and oncologic outcome under dCRT were not different for patients with SCC of the esophagus treated with either CDDP/5FU or Carb/TAX. The putative equivalence of dCRT with Carb/TAX in this setting should be further investigated in prospective trials. However, our data reveal that the risk of significant myelotoxicity increases with patient age and therefore other chemotherapy regimens might be evaluated in elderly patients.

Dual layer computed tomography: Reduction of metal artefacts from posterior spinal fusion using virtual monoenergetic imaging

INTRODUCTION

To evaluate the clinical potential of dual layer computed tomography (DLCT) for posterior fusions of the thoracic and lumbar spine and determine the optimal keV-settings for an improved overall image quality and effective reduction of metal artefacts affecting the implant inheriting vertebral body, the spinal canal, the paravertebral muscle and aorta.

METHODS AND MATERIALS

Twenty patients with posterior thoracic and lumbar spinal fusion, who underwent a 120kVp- DLCT scan were included in this study. Two independent readers evaluated axial 0.9 mm slides with soft tissue and bone window settings. Image quality of the conventional scan was compared to virtual monoenergetic images (VMI) at 40, 60, 80, 100,120, 140, 160, 180 and 200 keV. Diagnostic image quality was assessed on a four point Likert-scale overall, as well as specifically for the implant inheriting bone, paravertebral muscle, spinal canal or aorta. The Hounsfield Units (HU) of the area with the most pronounced streak artefact as well as HU of a reference area containing fat and muscle were documented for each keV-setting and compared to the conventional image. SNR and CNR were calculated for each of the four anatomic areas. Statistical analysis was conducted for the total collective and separately for the thoracic and lumbar spine level.

RESULTS

Starting from 80 keV qualitative analysis revealed significant improvement of overall image quality and benefit for each tissue separately compared to the conventional images (CI) (p-values in the range from <0.001 to 0.005). 180 keV was considered the optimal monoenergetic setting regarding the overall image quality. For the assessment of the implant inheriting bone, the spinal canal, paravertebral muscle and aorta 200, 180, 160 and 180 keV were rated to be the most sufficient. Our results reveal high inter-reader agreement for qualitative evaluations (intra-class correlation coefficients >0.927; p < 0.05). HU values within the most pronounced streak artefact increased significantly with higher keV (p < 0.001), while there was no significant alteration of HU within the reference area. A decrease in SNR and CNR for higher VMI was revealed by our results.

CONCLUSION

VMIs of higher energies provide significant reduction of metallic artefacts from posterior spinal fusions. Dedicated keV settings to evaluate either the implant inheriting bone, the spinal canal,adjacent muscle or aorta - structures, which are frequently of particular interest after posterior spinal fusion - are recommended. In addition, an optimal keV for an improved overall image quality is proposed.