RÉSUMÉ
OBJECTIVES: The randomized TOmosynthesis plus SYnthesized MAmmography (TOSYMA) screening trial has shown that digital breast tomosynthesis plus synthesized mammography (DBT + SM) is superior to digital mammography (DM) in invasive breast cancer detection varying with breast density. On the other hand, the overall average glandular dose (AGD) of DBT is higher than that of DM. Comparing the DBT + SM and DM trial arm, we analyzed here the mean AGD and their determinants per breast density category and related them to the respective invasive cancer detection rates (iCDR). METHODS: TOSYMA screened 99,689 women aged 50 to 69 years. Compression force, resulting breast thickness, the calculated AGD obtained from each mammography device, and previously published iCDR were used for comparisons across breast density categories in the two trial arms. RESULTS: There were 196,622 exposures of 49,227 women (DBT + SM) and 197,037 exposures of 49,132 women (DM) available for analyses. Mean breast thicknesses declined from breast density category A (fatty) to D (extremely dense) in both trial arms. However, while the mean AGD in the DBT + SM arm declined concomitantly from category A (2.41 mGy) to D (1.89 mGy), it remained almost unchanged in the DM arm (1.46 and 1.51 mGy, respectively). In relative terms, the AGD elevation in the DBT + SM arm (64.4% (A), by 44.5% (B), 27.8% (C), and 26.0% (D)) was lowest in dense breasts where, however, the highest iCDR were observed. CONCLUSION: Women with dense breasts may specifically benefit from DBT + SM screening as high cancer detection is achieved with only moderate AGD elevations. CLINICAL RELEVANCE STATEMENT: TOSYMA suggests a favorable constellation for screening with digital breast tomosynthesis plus synthesized mammography (DBT + SM) in dense breasts when weighing average glandular dose elevation against raised invasive breast cancer detection rates. There is potential for density-, i.e., risk-adapted population-wide breast cancer screening with DBT + SM. KEY POINTS: Breast thickness declines with visually increasing density in digital mammography (DM) and digital breast tomosynthesis (DBT). Average glandular doses of DBT decrease with increasing density; digital mammography shows lower and more constant values. With the smallest average glandular dose difference in dense breasts, DBT plus SM had the highest difference in invasive breast cancer detection rates.
RÉSUMÉ
In this study, we sought to evaluate the capabilities of radiomics and machine learning in predicting seropositivity in patients with suspected autoimmune encephalitis (AE) from MR images obtained at symptom onset. In 83 patients diagnosed with AE between 2011 and 2022, manual bilateral segmentation of the amygdala was performed on pre-contrast T2 images using 3D Slicer open-source software. Our sample of 83 patients contained 43 seropositive and 40 seronegative AE cases. Images were obtained at our tertiary care center and at various secondary care centers in North Rhine-Westphalia, Germany. The sample was randomly split into training data and independent test data. A total of 107 radiomic features were extracted from bilateral regions of interest (ROIs). Automated machine learning (AutoML) was used to identify the most promising machine learning algorithms. Feature selection was performed using recursive feature elimination (RFE) and based on the determination of the most important features. Selected features were used to train various machine learning algorithms on 100 different data partitions. Performance was subsequently evaluated on independent test data. Our radiomics approach was able to predict the presence of autoantibodies in the independent test samples with a mean AUC of 0.90, a mean accuracy of 0.83, a mean sensitivity of 0.84 and a mean specificity of 0.82, with Lasso regression models yielding the most promising results. These results indicate that radiomics-based machine learning could be a promising tool in predicting the presence of autoantibodies in suspected AE patients. Given the implications of seropositivity for definitive diagnosis of suspected AE cases, this may expedite diagnostic workup even before results from specialized laboratory testing can be obtained. Furthermore, in conjunction with recent publications, our results indicate that characterization of AE subtypes by use of radiomics may become possible in the future, potentially allowing physicians to tailor treatment in the spirit of personalized medicine even before laboratory workup is completed.
RÉSUMÉ
BACKGROUND: We investigated differences in intracranial embolus distribution through communicating arteries in relation to supra-aortic vessel (SAV) patency. METHODS: For this experimental analysis, we created a silicone model of the extracranial and intracranial circulations using a blood-mimicking fluid under physiological pulsatile flow. We examined the sequence of embolus lodgment on injecting 104 frangible clot analogues (406 emboli) through the right internal carotid artery (CA) as SAV patency changed: (a) all SAV patent (baseline), (b) emboli from a CA occlusion, (c) emboli contralateral to a CA occlusion and (d) occlusion of the posterior circulation. The statistical analysis included a descriptive analysis of thrombi location after occlusion (absolute and relative frequencies). Sequences of occlusions were displayed in Sankey flow charts for the four SAV conditions. Associations between SAV conditions and occlusion location were tested by Fisher's exact test. Two-sided p values were compared with a significance level of 0.05. RESULTS: The total number of emboli was 406 (median fragments/clot: 4 (IQR: 3-5)). Embolus lodgment was dependent on SAV patency (p<0.0001). In all scenarios, embolism lodging in the anterior cerebral artery (ACA) occurred after a previous middle cerebral artery (MCA) embolism (MCA first lodge: 96%, 100/104). The rate of ipsilateral ACA embolism was 28.9% (28/97) at baseline, decreasing significantly when emboli originated from an occluded CA (16%, 14/88). There were more bihemispheric embolisations in cases of contralateral CA occlusion (37%, 45/122), with bilateral ACA embolisms preceding contralateral MCA embolism in 56% of cases (14/25 opposite MCA and ACA embolism). CONCLUSIONS: All emboli in the ACA occurred after a previous ipsilateral MCA embolism. Bihemispheric embolisms were rare, except when there was a coexisting occlusion in either CA, particularly in cases of a contralateral CA occlusion.
RÉSUMÉ
Knowledge of thrombus behavior and visualization on MRI in acute ischemic stroke is less than optimal. However, MRI sequences could be enhanced based on the typical T1 and T2 relaxation times of the target tissues, which mainly determine their signal intensities on imaging. We studied the relaxation times of a broad spectrum of clot analogs along with their image characteristics of three sequences analyzed: a T1-weighted turbo inversion-recovery sequence (T1w Turbo IR), a T1-weighted turbo spin echo with fat suppression (T1w TSE SPIR), and a T2-weighted 3D TSE with magnetization refocusing to remove T1 dependence (T2w TSE DRIVE). We compared their imaging behavior with the intensity values of normal brain tissue using the same imaging protocols as for clots. Each histological and biochemical clot component contributed to each of the relaxation times. Overall, histological composition correlated strongly with T1 times, and iron content, specifically, with T2 relaxation time. Using decision trees, fibrin content was selected as the primary biomarker for T1 relaxation times, inducing an increase. Up to four clot subgroups could be defined based on its distinctive T1 relaxation time. Clot signal intensity in the T1 and T2-weighted images varied significantly according to T1 and T2 relaxation times. Moreover, in comparison with normal brain tissue intensity values, T2w DRIVE images depict thrombi according to the principle of the more fibrin, the higher the intensity, and in T1w TSE, the more erythrocytes, the higher the intensity. These findings could facilitate improvements in MRI sequences for clot visualization and indicate that T2w DRIVE and T1w TSE sequences should depict the vast majority of acute ischemic stroke thrombi as more hyperintense than surrounding tissues.
Sujet(s)
Accident vasculaire cérébral ischémique , Imagerie par résonance magnétique , Thrombose , Imagerie par résonance magnétique/méthodes , Humains , Accident vasculaire cérébral ischémique/imagerie diagnostique , Accident vasculaire cérébral ischémique/anatomopathologie , Thrombose/imagerie diagnostique , Encéphale/imagerie diagnostique , Encéphale/anatomopathologie , Fibrine/métabolisme , Traitement d'image par ordinateurRÉSUMÉ
The mutated enzyme isocitrate dehydrogenase (IDH) 1 and 2 has been detected in various tumor entities such as gliomas and can convert α-ketoglutarate into the oncometabolite 2-hydroxyglutarate (2-HG). This neuro-oncologically significant metabolic product can be detected by MR spectroscopy and is therefore suitable for noninvasive glioma classification and therapy monitoring.This paper provides an up-to-date overview of the methodology and relevance of 1H-MR spectroscopy (MRS) in the oncological primary and follow-up diagnosis of gliomas. The possibilities and limitations of this MR spectroscopic examination are evaluated on the basis of the available literature.By detecting 2-HG, MRS can in principle offer a noninvasive alternative to immunohistological analysis thus avoiding surgical intervention in some cases. However, in addition to an adapted and optimized examination protocol, the individual measurement conditions in the examination region are of decisive importance. Due to the inherently small signal of 2-HG, unfavorable measurement conditions can influence the reliability of detection. · MR spectroscopy enables the non-invasive detection of 2-hydroxyglutarate.. · The measurement of this metabolite allows the detection of an IDH mutation in gliomas.. · The choice of MR examination method is particularly important.. · Detection reliability is influenced by glioma size, necrotic tissue and the existing measurement conditions.. · Bauer J, Raum HN, Kugel H et al. 2-Hydroxyglutarate as an MR spectroscopic predictor of an IDH mutation in gliomas. Fortschr Röntgenstr 2024; DOI 10.1055/a-2285-4923.
RÉSUMÉ
OBJECTIVES: Regarding the 2021 World Health Organization (WHO) classification of central nervous system (CNS) tumors, the isocitrate dehydrogenase (IDH) mutation status is one of the most important factors for CNS tumor classification. The aim of our study is to analyze which of the commonly used magnetic resonance imaging (MRI) sequences is best suited to obtain this information non-invasively using radiomics-based machine learning models. We developed machine learning models based on different MRI sequences and determined which of the MRI sequences analyzed yields the highest discriminatory power in predicting the IDH mutation status. MATERIAL AND METHODS: In our retrospective IRB-approved study, we used the MRI images of 106 patients with histologically confirmed gliomas. The MRI images were acquired using the T1 sequence with and without administration of a contrast agent, the T2 sequence, and the Fluid-Attenuated Inversion Recovery (FLAIR) sequence. To objectively compare performance in predicting the IDH mutation status as a function of the MRI sequence used, we included only patients in our study cohort for whom MRI images of all four sequences were available. Seventy-one of the patients had an IDH mutation, and the remaining 35 patients did not have an IDH mutation (IDH wild-type). For each of the four MRI sequences used, 107 radiomic features were extracted from the corresponding MRI images by hand-delineated regions of interest. Data partitioning into training data and independent test data was repeated 100 times to avoid random effects associated with the data partitioning. Feature preselection and subsequent model development were performed using Random Forest, Lasso regression, LDA, and Naïve Bayes. The performance of all models was determined with independent test data. RESULTS: Among the different approaches we examined, the T1-weighted contrast-enhanced sequence was found to be the most suitable for predicting IDH mutations status using radiomics-based machine learning models. Using contrast-enhanced T1-weighted MRI images, our seven-feature model developed with Lasso regression achieved a mean area under the curve (AUC) of 0.846, a mean accuracy of 0.792, a mean sensitivity of 0.847, and a mean specificity of 0.681. The administration of contrast agents resulted in a significant increase in the achieved discriminatory power. CONCLUSIONS: Our analyses show that for the prediction of the IDH mutation status using radiomics-based machine learning models, among the MRI images acquired with the commonly used MRI sequences, the contrast-enhanced T1-weighted images are the most suitable.
RÉSUMÉ
PURPOSE: To evaluate the benefit of a contrast-enhanced computed tomography (CT) radiomics-based model for predicting response and survival in patients with colorectal liver metastases treated with transarterial Yttrium-90 radioembolization (TARE). MATERIALS AND METHODS: Fifty-one patients who underwent TARE were included in this single-center retrospective study. Response to treatment was assessed using the Response Evaluation Criteria in Solid Tumors (RECIST 1.1) at 3-month follow-up. Patients were stratified as responders (complete/partial response and stable disease, n = 24) or non-responders (progressive disease, n = 27). Radiomic features (RF) were extracted from pre-TARE CT after segmentation of the liver tumor volume. A model was built based on a radiomic signature consisting of reliable RFs that allowed classification of response using multivariate logistic regression. Patients were assigned to high- or low-risk groups for disease progression after TARE according to a cutoff defined in the model. Kaplan-Meier analysis was performed to analyze survival between high- and low-risk groups. RESULTS: Two independent RF [Energy, Maximal Correlation Coefficient (MCC)], reflecting tumor heterogeneity, discriminated well between responders and non-responders. In particular, patients with higher magnitude of voxel values in an image (Energy), and texture complexity (MCC), were more likely to fail TARE. For predicting treatment response, the area under the receiver operating characteristic curve of the radiomics-based model was 0.75 (95% CI 0.48-1). The high-risk group had a shorter overall survival than the low-risk group (3.4 vs. 6.4 months, p < 0.001). CONCLUSION: Our CT radiomics model may predict the response and survival outcome by quantifying tumor heterogeneity in patients treated with TARE for colorectal liver metastases.
Sujet(s)
Tumeurs du côlon , Tumeurs du foie , Tumeurs du rectum , Humains , Études rétrospectives , , Radio-isotopes de l'yttrium/usage thérapeutique , Tumeurs du foie/imagerie diagnostique , Tumeurs du foie/radiothérapieRÉSUMÉ
Importance: Biological psychiatry aims to understand mental disorders in terms of altered neurobiological pathways. However, for one of the most prevalent and disabling mental disorders, major depressive disorder (MDD), no informative biomarkers have been identified. Objective: To evaluate whether machine learning (ML) can identify a multivariate biomarker for MDD. Design, Setting, and Participants: This study used data from the Marburg-Münster Affective Disorders Cohort Study, a case-control clinical neuroimaging study. Patients with acute or lifetime MDD and healthy controls aged 18 to 65 years were recruited from primary care and the general population in Münster and Marburg, Germany, from September 11, 2014, to September 26, 2018. The Münster Neuroimaging Cohort (MNC) was used as an independent partial replication sample. Data were analyzed from April 2022 to June 2023. Exposure: Patients with MDD and healthy controls. Main Outcome and Measure: Diagnostic classification accuracy was quantified on an individual level using an extensive ML-based multivariate approach across a comprehensive range of neuroimaging modalities, including structural and functional magnetic resonance imaging and diffusion tensor imaging as well as a polygenic risk score for depression. Results: Of 1801 included participants, 1162 (64.5%) were female, and the mean (SD) age was 36.1 (13.1) years. There were a total of 856 patients with MDD (47.5%) and 945 healthy controls (52.5%). The MNC replication sample included 1198 individuals (362 with MDD [30.1%] and 836 healthy controls [69.9%]). Training and testing a total of 4 million ML models, mean (SD) accuracies for diagnostic classification ranged between 48.1% (3.6%) and 62.0% (4.8%). Integrating neuroimaging modalities and stratifying individuals based on age, sex, treatment, or remission status does not enhance model performance. Findings were replicated within study sites and also observed in structural magnetic resonance imaging within MNC. Under simulated conditions of perfect reliability, performance did not significantly improve. Analyzing model errors suggests that symptom severity could be a potential focus for identifying MDD subgroups. Conclusion and Relevance: Despite the improved predictive capability of multivariate compared with univariate neuroimaging markers, no informative individual-level MDD biomarker-even under extensive ML optimization in a large sample of diagnosed patients-could be identified.
Sujet(s)
Trouble dépressif majeur , Humains , Femelle , Mâle , Trouble dépressif majeur/imagerie diagnostique , Trouble dépressif majeur/anatomopathologie , Imagerie par tenseur de diffusion , Études de cohortes , Reproductibilité des résultats , Imagerie par résonance magnétique , Marqueurs biologiquesSujet(s)
Tumeurs du sein , Mammographie , Humains , Tumeurs du sein/imagerie diagnostique , Mammographie/méthodes , Femelle , Sensibilité et spécificité , Amélioration d'image radiographique/méthodes , Dépistage précoce du cancer/méthodes , Biais de l'observateur , Dépistage de masse/méthodes , Adulte d'âge moyenRÉSUMÉ
BACKGROUND: Magnetic resonance imaging (MRI) studies on major depressive disorder (MDD) have predominantly found short-term electroconvulsive therapy (ECT)-related gray matter volume (GMV) increases, but research on the long-term stability of such changes is missing. Our aim was to investigate long-term GMV changes over a 2-year period after ECT administration and their associations with clinical outcome. METHODS: In this nonrandomized longitudinal study, patients with MDD undergoing ECT (n = 17) are assessed three times by structural MRI: Before ECT (t0), after ECT (t1) and 2 years later (t2). A healthy (n = 21) and MDD non-ECT (n = 33) control group are also measured three times within an equivalent time interval. A 3(group) × 3(time) ANOVA on whole-brain level and correlation analyses with clinical outcome variables is performed. RESULTS: Analyses yield a significant group × time interaction (pFWE < 0.001) resulting from significant volume increases from t0 to t1 and decreases from t1 to t2 in the ECT group, e.g., in limbic areas. There are no effects of time in both control groups. Volume increases from t0 to t1 correlate with immediate and delayed symptom increase, while volume decreases from t1 to t2 correlate with long-term depressive outcome (all p ⩽ 0.049). CONCLUSIONS: Volume increases induced by ECT appear to be a transient phenomenon as volume strongly decreased 2 years after ECT. Short-term volume increases are associated with less symptom improvement suggesting that the antidepressant effect of ECT is not due to volume changes. Larger volume decreases are associated with poorer long-term outcome highlighting the interplay between disease progression and structural changes.
Sujet(s)
Trouble dépressif majeur , Électroconvulsivothérapie , Humains , Trouble dépressif majeur/imagerie diagnostique , Trouble dépressif majeur/thérapie , Trouble dépressif majeur/anatomopathologie , Électroconvulsivothérapie/méthodes , Dépression , Études longitudinales , Encéphale/imagerie diagnostique , Encéphale/anatomopathologie , Imagerie par résonance magnétique/méthodesRÉSUMÉ
OBJECTIVES: The aim of this proof-of-principle study combining data analysis and computer simulation was to evaluate the robustness of apparent diffusion coefficient (ADC) values for lymph node classification in prostate cancer under conditions comparable to clinical practice. MATERIALS AND METHODS: To assess differences in ADC and inter-rater variability, ADC values of 359 lymph nodes in 101 patients undergoing simultaneous prostate-specific membrane antigen (PSMA)-PET/MRI were retrospectively measured by two blinded readers and compared in a node-by-node analysis with respect to lymph node status. In addition, a phantom and 13 patients with 86 lymph nodes were prospectively measured on two different MRI scanners to analyze inter-scanner agreement. To estimate the diagnostic quality of the ADC in real-world application, a computer simulation was used to emulate the blurring caused by scanner and reader variability. To account for intra-individual correlation, the statistical analyses and simulations were based on linear mixed models. RESULTS: The mean ADC of lymph nodes showing PSMA signals in PET was markedly lower (0.77 × 10-3 mm2/s) compared to inconspicuous nodes (1.46 × 10-3 mm2/s, p < 0.001). High inter-reader agreement was observed for ADC measurements (ICC 0.93, 95%CI [0.92, 0.95]). Good inter-scanner agreement was observed in the phantom study and confirmed in vivo (ICC 0.89, 95%CI [0.84, 0.93]). With a median AUC of 0.95 (95%CI [0.92, 0.97]), the simulation study confirmed the diagnostic potential of ADC for lymph node classification in prostate cancer. CONCLUSION: Our model-based simulation approach implicates a high potential of ADC for lymph node classification in prostate cancer, even when inter-rater and inter-scanner variability are considered. CLINICAL RELEVANCE STATEMENT: The ADC value shows a high diagnostic potential for lymph node classification in prostate cancer. The robustness to scanner and reader variability implicates that this easy to measure and widely available method could be readily integrated into clinical routine. KEY POINTS: ⢠The diagnostic value of the apparent diffusion coefficient (ADC) for lymph node classification in prostate cancer is unclear in the light of inter-rater and inter-scanner variability. ⢠Metastatic and inconspicuous lymph nodes differ significantly in ADC, resulting in a high diagnostic potential that is robust to inter-scanner and inter-rater variability. ⢠ADC has a high potential for lymph node classification in prostate cancer that is maintained under conditions comparable to clinical practice.
Sujet(s)
Noeuds lymphatiques , Métastase lymphatique , Tumeurs de la prostate , Humains , Mâle , Tumeurs de la prostate/imagerie diagnostique , Tumeurs de la prostate/anatomopathologie , Métastase lymphatique/imagerie diagnostique , Sujet âgé , Adulte d'âge moyen , Noeuds lymphatiques/imagerie diagnostique , Noeuds lymphatiques/anatomopathologie , Études rétrospectives , Fantômes en imagerie , Imagerie par résonance magnétique de diffusion/méthodes , Tomographie par émission de positons/méthodes , Simulation numérique , Études prospectives , Imagerie multimodale/méthodes , Biais de l'observateurRÉSUMÉ
Background Breast cancer screening with digital breast tomosynthesis (DBT) plus synthesized mammography (SM) increases invasive tumor detection compared with digital mammography (DM). However, it is not known how the prognostic characteristics of the cancers detected with the two screening approaches differ. Purpose To compare invasive breast cancers detected with DBT plus SM (test arm) versus DM (control arm) screening with regard to tumor stage, histologic grade, patient age, and breast density. Materials and Methods This exploratory subanalysis of the Tomosynthesis plus Synthesized Mammography (TOSYMA) study, which is a multicenter randomized controlled trial embedded in the German mammography screening program, recruited women aged 50-70 years from July 2018 to December 2020. It compared invasive cancer detection rates (iCDRs), rate differences, and odds ratios (ORs) between the arms stratified by Union for International Cancer Control (UICC) stage (I vs II-IV), histologic grade (1 vs 2 or 3), age group (50-59 vs 60-70 years), and Breast Imaging Reporting and Data System categories of breast density (A or B vs C or D). Results In total, 49 462 (median age, 57 years [IQR, 53-62 years]) and 49 669 (median age, 57 years [IQR, 53-62 years]) participants were allocated to DBT plus SM and DM screening, respectively. The iCDR of stage I tumors with DBT plus SM was 51.6 per 10 000 women (255 of 49 462) and with DM it was 30.0 per 10 000 women (149 of 49 669). DBT plus SM depicted more stage I tumors with grade 2 or 3 (166 of 49 462, 33.7 per 10 000 women) than DM (106 of 49 669, 21.3 per 10 000 women; rate difference, +12.3 per 10 000 women [95% CI: 0.3, 24.9]; OR, 1.6 [95% CI: 0.9, 2.7]). DBT plus SM achieved the highest iCDR of stage I tumors with grade 2 or 3 among women aged 60-70 years with dense breasts (41 of 7364, 55.4 per 10 000 women; rate difference, +21.6 per 10 000 women [95% CI: -21.1, 64.3]; OR, 1.6 [95% CI: 0.6, 4.5]). Conclusion DBT plus SM screening appears to lead to higher detection of early-stage invasive breast cancers of grade 2 or 3 than DM screening, with the highest rate among women aged 60-70 years with dense breasts. Clinical trial registration no. NCT03377036 © RSNA, 2023 See also the editorial by Ha and Chang in this issue.
Sujet(s)
Tumeurs du sein , Mammographie , Femelle , Humains , Adulte d'âge moyen , Mammographie/méthodes , Tumeurs du sein/imagerie diagnostique , Densité mammaire , Pronostic , Dépistage précoce du cancer/méthodes , Dépistage de masse/méthodesRÉSUMÉ
BACKGROUND: Splenic lesions are rare and mostly incidental findings on cross-sectional imaging. Most lesions are of benign nature and can be correctly identified based on imaging characteristics. Further, invasive evaluation is only necessary in cases of splenic lesions with uncertain or potentially malignant etiology. METHOD: While in most cases a correct diagnosis can be made from computed tomography (CT), (additional) magnetic resonance imaging (MRI) can aid in the identification of lesions. As these lesions are rare, only a few of the differential diagnoses are regularly diagnosed in the clinical routine. RESULT AND CONCLUSION: This review presents the differential diagnoses of splenic lesions, including imaging characteristics and a flowchart to determine the right diagnosis. In conjunction with laboratory results and clinical symptoms, histological workup is necessary only in a few cases, especially in incidental findings. In these cases, image-guided biopsies should be preferred over splenectomy, if possible. KEY POINTS: · Splenic lesions are rare and are usually incidental findings on abdominal imaging. · CT imaging and MRI imaging are the diagnostic tools of choice for the further workup of splenic lesions. · Based on their image morphological characteristics, a large number of splenic lesions can be assigned to one entity and do not need histological analysis.
RÉSUMÉ
PURPOSE: In meningiomas, TERT promotor mutations are rare but qualify the diagnosis of anaplasia, directly impacting adjuvant therapy. Effective screening for patients at risk for promotor mutations could enable more targeted molecular analyses and improve diagnosis and treatment. METHODS: Semiautomatic segmentation of intracranial grade 2/3 meningiomas was performed on preoperative magnetic resonance imaging. Discriminatory power to predict TERT promoter mutations was analyzed using a random forest algorithm with an increasing number of radiomic features. Two final models with five and eight features with both fixed and differing radiomics features were developed and adjusted to eliminate random effects and to avoid overfitting. RESULTS: A total of 117 image sets including training (N = 94) and test data (N = 23) were analyzed. To eliminate random effects and demonstrate the robustness of our approach, data partitioning and subsequent model development and testing were repeated a total of 100 times (each time with repartitioned training and independent test data). The established five- and eight-feature models with both fixed and different radiomics features enabled the prediction of TERT with similar but excellent performance. The five-feature (different/fixed) model predicted TERT promotor mutation status with a mean AUC of 91.8%/94.3%, mean accuracy of 85.5%/88.9%, mean sensitivity of 88.6%/91.4%, mean specificity of 83.2%/87.0%, and a mean Cohen's Kappa of 71.0%/77.7%. The eight-feature (different/fixed) model predicted TERT promotor mutation status with a mean AUC of 92.7%/94.6%, mean accuracy of 87.3%/88.9%, mean sensitivity of 89.6%/90.6%, mean specificity of 85.5%/87.5%, and a mean Cohen's Kappa of 74.4%/77.6%. Of note, the addition of further features of up to N = 8 only slightly increased the performance. CONCLUSIONS: Radiomics-based machine learning enables prediction of TERT promotor mutation status in meningiomas with excellent discriminatory performance. Future analyses in larger cohorts should include grade 1 lesions as well as additional molecular alterations.
RÉSUMÉ
BACKGROUND: Portal vein embolization (PVE) is used to induce remnant liver hypertrophy prior to major hepatectomy. The purpose of this study was to evaluate the predictive value of baseline computed tomography (CT) data for future remnant liver (FRL) hypertrophy after PVE. METHODS: In this retrospective study, all consecutive patients undergoing right-sided PVE with or without hepatic vein embolization between 2018 and 2021 were included. CT volumetry was performed before and after PVE to assess standardized FRL volume (sFRLV). Radiomic features were extracted from baseline CT after segmenting liver (without tumor), spleen and bone marrow. For selecting features that allow classification of response (hypertrophy ≥ 1.33), a stepwise dimension reduction was performed. Logistic regression models were fitted and selected features were tested for their predictive value. Decision curve analysis was performed on the test dataset. RESULTS: A total of 53 patients with liver tumor were included in this study. sFRLV increased significantly after PVE, with a mean hypertrophy of FRL of 1.5 ± 0.3-fold. sFRLV hypertrophy ≥ 1.33 was reached in 35 (66%) patients. Three independent radiomic features, i.e. liver-, spleen- and bone marrow-associated, differentiated well between responders and non-responders. A logistic regression model revealed the highest accuracy (area under the curve 0.875) for the prediction of response, with sensitivity of 1.0 and specificity of 0.5. Decision curve analysis revealed a positive net benefit when applying the model. CONCLUSIONS: This proof-of-concept study provides first evidence of a potential predictive value of baseline multi-organ radiomics CT data for FRL hypertrophy after PVE.
Sujet(s)
Embolisation thérapeutique , Tumeurs du foie , Humains , Veine porte/anatomopathologie , Études rétrospectives , Foie/chirurgie , Hépatectomie/méthodes , Tumeurs du foie/chirurgie , Hypertrophie/anatomopathologie , Hypertrophie/chirurgie , Résultat thérapeutiqueRÉSUMÉ
BACKGROUND: With metabolic alterations of the tumor microenvironment (TME) contributing to cancer progression, metastatic spread and response to targeted therapies, non-invasive and repetitive imaging of tumor metabolism is of major importance. The purpose of this study was to investigate whether multiparametric chemical exchange saturation transfer magnetic resonance imaging (CEST-MRI) allows to detect differences in the metabolic profiles of the TME in murine breast cancer models with divergent degrees of malignancy and to assess their response to immunotherapy. METHODS: Tumor characteristics of highly malignant 4T1 and low malignant 67NR murine breast cancer models were investigated, and their changes during tumor progression and immune checkpoint inhibitor (ICI) treatment were evaluated. For simultaneous analysis of different metabolites, multiparametric CEST-MRI with calculation of asymmetric magnetization transfer ratio (MTRasym) at 1.2 to 2.0 ppm for glucose-weighted, 2.0 ppm for creatine-weighted and 3.2 to 3.6 ppm for amide proton transfer- (APT-) weighted CEST contrast was conducted. Ex vivo validation of MRI results was achieved by 1H nuclear magnetic resonance spectroscopy, matrix-assisted laser desorption/ionization mass spectrometry imaging with laser postionization and immunohistochemistry. RESULTS: During tumor progression, the two tumor models showed divergent trends for all examined CEST contrasts: While glucose- and APT-weighted CEST contrast decreased and creatine-weighted CEST contrast increased over time in the 4T1 model, 67NR tumors exhibited increased glucose- and APT-weighted CEST contrast during disease progression, accompanied by decreased creatine-weighted CEST contrast. Already three days after treatment initiation, CEST contrasts captured response to ICI therapy in both tumor models. CONCLUSION: Multiparametric CEST-MRI enables non-invasive assessment of metabolic signatures of the TME, allowing both for estimation of the degree of tumor malignancy and for assessment of early response to immune checkpoint inhibition.
Sujet(s)
Créatine , Tumeurs , Animaux , Souris , Immunothérapie , Imagerie par résonance magnétique , Amides , Glucose , Inhibiteurs de points de contrôle immunitairesRÉSUMÉ
ATRX is an important molecular marker according to the 2021 WHO classification of adult-type diffuse glioma. We aim to predict the ATRX mutation status non-invasively using radiomics-based machine learning models on MRI and to determine which MRI sequence is best suited for this purpose. In this retrospective study, we used MRI images of patients with histologically confirmed glioma, including the sequences T1w without and with the administration of contrast agent, T2w, and the FLAIR. Radiomics features were extracted from the corresponding MRI images by hand-delineated regions of interest. Data partitioning into training data and independent test data was repeated 100 times to avoid random effects. Feature preselection and subsequent model development were performed using Lasso regression. The T2w sequence was found to be the most suitable and the FLAIR sequence the least suitable for predicting ATRX mutations using radiomics-based machine learning models. For the T2w sequence, our seven-feature model developed with Lasso regression achieved a mean AUC of 0.831, a mean accuracy of 0.746, a mean sensitivity of 0.772, and a mean specificity of 0.697. In conclusion, for the prediction of ATRX mutation using radiomics-based machine learning models, the T2w sequence is the most suitable among the commonly used MRI sequences.
RÉSUMÉ
Our aim is to investigate the added value of automated machine learning (AutoML) for potential future applications in cancer diagnostics. Using two important diagnostic questions, the non-invasive determination of IDH mutation status and ATRX status, we analyze whether it is possible to use AutoML to develop models that are comparable in performance to conventional machine learning models (ML) developed by experts. For this purpose, we develop AutoML models using different feature preselection methods and compare the results with previously developed conventional ML models. The cohort used for our study comprises T2-weighted MRI images of 124 patients with histologically confirmed gliomas. Using AutoML, we were able to develop sophisticated models in a very short time with only a few lines of computer code. In predicting IDH mutation status, we obtained a mean AUC of 0.7400 and a mean AUPRC of 0.8582. ATRX mutation status was predicted with very similar discriminatory power, with a mean AUC of 0.7810 and a mean AUPRC of 0.8511. In both cases, AutoML was even able to achieve a discriminatory power slightly above that of the respective conventionally developed models in a very short computing time, thus making such methods accessible to non-experts in the near future.
RÉSUMÉ
Repeated hospitalizations are a characteristic of severe disease courses in patients with affective disorders (PAD). To elucidate how a hospitalization during a nine-year follow-up in PAD affects brain structure, a longitudinal case-control study (mean [SD] follow-up period 8.98 [2.20] years) was conducted using structural neuroimaging. We investigated PAD (N = 38) and healthy controls (N = 37) at two sites (University of Münster, Germany, Trinity College Dublin, Ireland). PAD were divided into two groups based on the experience of in-patient psychiatric treatment during follow-up. Since the Dublin-patients were outpatients at baseline, the re-hospitalization analysis was limited to the Münster site (N = 52). Voxel-based morphometry was employed to examine hippocampus, insula, dorsolateral prefrontal cortex and whole-brain gray matter in two models: (1) group (patients/controls)×time (baseline/follow-up) interaction; (2) group (hospitalized patients/not-hospitalized patients/controls)×time interaction. Patients lost significantly more whole-brain gray matter volume of superior temporal gyrus and temporal pole compared to HC (pFWE = 0.008). Patients hospitalized during follow-up lost significantly more insular volume than healthy controls (pFWE = 0.025) and more volume in their hippocampus compared to not-hospitalized patients (pFWE = 0.023), while patients without re-hospitalization did not differ from controls. These effects of hospitalization remained stable in a smaller sample excluding patients with bipolar disorder. PAD show gray matter volume decline in temporo-limbic regions over nine years. A hospitalization during follow-up comes with intensified gray matter volume decline in the insula and hippocampus. Since hospitalizations are a correlate of severity, this finding corroborates and extends the hypothesis that a severe course of disease has detrimental long-term effects on temporo-limbic brain structure in PAD.
Sujet(s)
Trouble bipolaire , Imagerie par résonance magnétique , Humains , Études cas-témoins , Imagerie par résonance magnétique/méthodes , Encéphale/imagerie diagnostique , Substance grise/imagerie diagnostique , Trouble bipolaire/imagerie diagnostique , HospitalisationRÉSUMÉ
BACKGROUND: Response assessment of targeted cancer therapies is becoming increasingly challenging, as it is not adequately assessable with conventional morphological and volumetric analyses of tumor lesions. The tumor microenvironment is particularly constituted by tumor vasculature which is altered by various targeted therapies. The aim of this study was to noninvasively assess changes in tumor perfusion and vessel permeability after targeted therapy in murine models of breast cancer with divergent degrees of malignancy. METHODS: Low malignant 67NR or highly malignant 4T1 tumor-bearing mice were treated with either the multi-kinase inhibitor sorafenib or immune checkpoint inhibitors (ICI, combination of anti-PD1 and anti-CTLA4). Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) with i.v. injection of albumin-binding gadofosveset was conducted on a 9.4 T small animal MRI. Ex vivo validation of MRI results was achieved by transmission electron microscopy, immunohistochemistry and laser ablation-inductively coupled plasma-mass spectrometry. RESULTS: Therapy-induced changes in tumor vasculature differed between low and highly malignant tumors. Sorafenib treatment led to decreased tumor perfusion and endothelial permeability in low malignant 67NR tumors. In contrast, highly malignant 4T1 tumors demonstrated characteristics of a transient window of vascular normalization with an increase in tumor perfusion and permeability early after therapy initiation, followed by decreased perfusion and permeability parameters. In the low malignant 67NR model, ICI treatment also mediated vessel-stabilizing effects with decreased tumor perfusion and permeability, while ICI-treated 4T1 tumors exhibited increasing tumor perfusion with excessive vascular leakage. CONCLUSION: DCE-MRI enables noninvasive assessment of early changes in tumor vasculature after targeted therapies, revealing different response patterns between tumors with divergent degrees of malignancy. DCE-derived tumor perfusion and permeability parameters may serve as vascular biomarkers that allow for repetitive examination of response to antiangiogenic treatment or immunotherapy.