Highlights • FAST-PET/MRI provides equivalent diagnostic performance for whole-body restaging as PET/CT. • FAST-PET/MRI offers markedly reduced radiation exposure compared to full-dose PET/CT. • ...FAST-PET/MRI is a high-quality alternative for evaluation of gynecological cancer patients.
The aim of this study was to investigate the potential of multiparametric
F-FDG PET/MR imaging as a platform for radiomics analysis and machine learning algorithms based on primary cervical cancers ...to predict N- and M-stage in patients.
A total of 30 patients with histopathological confirmation of primary and untreated cervical cancer were prospectively enrolled for a multiparametric
F-FDG PET/MR examination, comprising a dedicated protocol for imaging of the female pelvis. The primary tumor in the uterine cervix was manually segmented on post-contrast T1-weighted images. Quantitative features were extracted from the segmented tumors using the Radiomic Image Processing Toolbox for the R software environment for statistical computing and graphics. 45 different image features were calculated from non-enhanced as well as post-contrast T1-weighted TSE images, T2-weighted TSE images, the ADC map, the parametric Ktrans, Kep, Ve and iAUC maps and PET images, respectively. Statistical analysis and modeling was performed using Python 3.5 and the scikit-learn software machine learning library for the Python programming language.
Prediction of M-stage was superior when compared to N-stage. Prediction of M-stage using SVM with SVM-RFE as feature selection obtained the highest performance providing sensitivity of 91 % and specificity of 92 %. Using receiver operating characteristic (ROC) analysis of the pooled predictions, the area under the curve (AUC) was 0.97. Prediction of N-stage using RBF-SVM with MIFS as feature selection reached sensitivity of 83 %, specificity of 67 % and an AUC of 0.82.
M- and N-stage can be predicted based on isolated radiomics analyses of the primary tumor in cervical cancers, thus serving as a template for noninvasive tumor phenotyping and patient stratification using high-dimensional feature vectors extracted from multiparametric PET/MRI data.
· Radiomics analysis based on multiparametric PET/MRI enables prediction of the metastatic status of cervical cancers. · Prediction of M-stage is superior to N-stage. · Multiparametric PET/MRI displays a valuable platform for radiomics analyses .
Objectives
To compare
18
FFDG PET/MRI with PET/CT for the assessment of bone lesions in oncologic patients.
Methods
This prospective study included 67 patients with solid tumours scheduled for ...PET/CT with
18
FFDG who also underwent a whole-body PET/MRI scan. The datasets (PET/CT, PET/MRI) were rated by two readers regarding lesion conspicuity (four-point scale) and diagnostic confidence (five-point scale). Median scores were compared using the Wilcoxon test.
Results
Bone metastases were present in ten patients (15 %), and benign bone lesions in 15 patients (22 %). Bone metastases were predominantly localized in the pelvis (18 lesions, 38 %) and the spine (14 lesions, 29 %). Benign bone lesions were exclusively osteosclerotic and smaller than the metastases (mean size 6 mm vs. 23 mm). While PET/CT allowed identification of 45 of 48 bone metastases (94 %), PET/MRI allowed identification of all bone metastases (100 %). Conspicuity of metastases was high for both modalities with significantly better results using PET/MRI (
p
< 0.05). Diagnostic confidence in lesion detection was high for both modalities without a significant difference. In benign lesions, conspicuity and diagnostic confidence were significantly higher with PET/CT (
p
< 0.05).
Conclusions
18
FFDG PET/MRI shows high potential for the assessment of bone metastases by offering superior lesion conspicuity when compared to PET/CT. In hypersclerotic, benign bone lesions PET/CT still sets the reference.
Key Points
•
PET/MRI and PET/CT are of equal value for the identification of disease-positive patients
•
PET/MRI offers higher lesion conspicuity as well as diagnostic confidence
•
PET/MRI is an attractive new alternative for the assessment of bone metastases
Highlights • Both 18F-FDG PET/CT and 18F-FDG PET/MRI provide a comparable diagnostic ability for detection of primary cancer and metastases in CUP-syndrome. • PET/CT and PET/MRI showed comparably ...high lesion conspicuity and diagnostic confidence, offering superior assessment of pulmonary lesions in PET/CT and of cervical lesions in PET/MRI. • Considering the significantly lower dose of ionizing radiation, PET/MRI may serve as a powerful alternative to PET/CT in the future, particularly for therapy monitoring and/or surveillance considering the long-term cumulative dose.
Ziel dieser Studie war die Evaluierung des prädiktiven Potenzials der Radiomics-Analyse zur Bestimmung des N- und M-Stadiums des primären Zervixkarzinoms anhand multiparametrischer
...F-FDG-PET/MRT-Bildgebung.
30 Patientinnen mit einem histologisch gesicherten, primären und therapienaiven Zervixkarzinom unterzogen sich einer multiparametrischen
F-FDG-PET/MRT-Untersuchung unter Verwendung eines dedizierten Untersuchungsprotokolls des weiblichen Beckens. Nach Segmentierung der Primärtumoren wurden quantitative Bildparameter mittels der Radiomic-Image-Processing-Toolbox bestimmt. Insgesamt wurden 45 verschiedene quantitative Bildmerkmale jeweils anhand der T2-gewichteten TSE-Sequenzen, der nativen und kontrastmittelgestützten T1-gewichteten TSE-Sequenzen, der ADC-Map, verschiedenen Perfusionsparametern (Ktrans, Kep, Ve and iAUC) und den
F-FDG-PET-Datensätzen für jeden Tumor extrahiert. Die statistische Analyse zur Bestimmung des N- und M-Stadiums erfolgte unter der Verwendung der Python 3.5 und Scikit-learn-Software-Bibliothek für maschinelles Lernen.
Insgesamt zeigte sich eine höhere Genauigkeit zur Prädiktion des korrekten M-Stadiums im Vergleich zum N-Stadium. Zur Prädiktion des korrekten M-Stadiums zeigten sich unter der Verwendung von SVM und SVM-RFE zur Feature-Auswahl die besten Ergebnisse mit einer Sensitivität von 91 %, einer Spezifität von 92 % und einer Fläche unter der Kurve (AUC) von 0,97. Die höchste Genauigkeit für die Bestimmung des N-Stadiums erfolgte unter der Verwendung von RBF-SVM und MIFS zur Feature-Auswahl mit einer Sensitivität von 83 %, einer Spezifität von 67 % und einer Fläche unter der Kurve (AUC) von 0,82.
Die Radiomics-Analyse von multiparametrischen PET/MR-Datensätzen ermöglicht eine präzise Prädiktion des M- und N-Stadiums von Patientinnen mit primärem Zervixkarzinom und könnte damit supportiv zur nichtinvasiven Tumor-Phänotypisierung und Patientenstratifizierung eingesetzt werden.
· Die Radiomics-Analyse der multiparametrischen PET/MRT ermöglicht die Prädiktion des Metastasierungsstatus des Zervixkarzinoms.. · Die Prädiktion des M-Stadiums ist der Prädiktion des N-Stadiums überlegen.. · Die multiparametrische PET/MRT bietet eine valide Plattform für Radiomics-Analysen..
· Umutlu L, Nensa F, Demircioglu A et al. Radiomics Analysis of Multiparametric PET/MRI for N- and M-Staging in Patients with Primary Cervical Cancer. Fortschr Röntgenstr 2020; 192: 754 - 763.
PET/MR imaging of pelvic malignancies Wetter, Axel, M.D; Grüneisen, Johannes, M.D; Umutlu, Lale, M.D
European journal of radiology,
09/2017, Volume:
94
Journal Article
Peer reviewed
Highlights • Integrated PET/MRI with simultaneous acquisition of PET and MRI is an emerging and promising technique in oncologic imaging • Imaging of female and male pelvic oncologic diseases like ...cervical cancer and prostate cancer requires a high soft tissue contrast and make these entities especially suitable for PET/MR imaging • This review article highlights recent publications of PET/MR imaging in both entities
We aimed to analyze the diagnostic accuracy of preoperative CT-guided biopsy to identify patients that might profit from neoadjuvant chemotherapy in a specialized high-volume sarcoma center.
We ...retrospectively reviewed all patients with suspected soft tissue tumors of the abdomen cavity including the retroperitoneum, who received CT-guided biopsy followed by surgical tumor resection. Sensitivity, specificity, PPV and NPV were calculated in all patients with abdominal sarcomas at our hospital. A subgroup analysis was performed for patients with liposarcoma.
A total of 82 patients (35 female, 47 male, age: 62.0 ± 14.7) received preoperative CT-guided biopsy followed by surgical resection. Overall accordance of CT-guided biopsy to identify final histology was 77 %. CT-guided biopsy revealed the diagnosis of liposarcoma in 23 patients whereas final analysis of the surgical specimen identified liposarcoma in 29 patients. Here, sensitivity, specificity, PPV and NPV was 79.3 %, 100.0 %, 100.0 % and 89.8 % respectively. Subgroup analysis revealed a better accuracy for correctly identifying patients with well-differentiated liposarcoma than patients with dedifferentiated liposarcoma (75.0 % vs 62.5 %). In patients with other sarcoma, sensitivity, specificity, PPV, NPV and diagnostic accuracy was 87.5 %, 95.5 %, 82.4 % and 96.9 %, respectively.
CT-guided biopsy in a specialized high-volume sarcoma center is an accurate and effective method to assess patients with abdominal sarcoma and especially abdominal liposarcoma. Therefore, it is an indispensable tool in the pretherapeutic workup process. Nevertheless, our study underlines the previously reported difficulties in dedifferentiated liposarcoma diagnostics, whereby these patient cohort would profit the most from a neoadjuvant therapy regime.
Purpose
To compare the sensitivity and specificity of 18F-fluordesoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT), 18F-FDG PET/magnetic resonance (18F-FDG PET/MR) and ...18F-FDG PET/MR including diffusion weighted imaging (DWI) in the detection of sentinel lymph node metastases in patients suffering from malignant melanoma.
Material & Methods
Fifty-two patients with malignant melanoma (female:
n
= 30, male:
n
= 22, mean age 50.5 ± 16.0 years, mean tumor thickness 2.28 ± 1.97 mm) who underwent 18F-FDG PET/CT and subsequent PET/MR & DWI for distant metastasis staging were included in this retrospective study. After hybrid imaging, lymphoscintigraphy including single photon emission computed tomography/CT (SPECT/CT) was performed to identify the sentinel lymph node prior to sentinel lymph node biopsy (SLNB). In a total of 87 sentinel lymph nodes in 64 lymph node basins visible on SPECT/CT, 17 lymph node metastases were detected by histopathology. In separate sessions PET/CT, PET/MR, and PET/MR & DWI were assessed for sentinel lymph node metastases by two independent readers. Discrepant results were resolved in a consensus reading. Sensitivities, specificities, positive predictive values and negative predictive values were calculated with histopathology following SPECT/CT guided SLNB as a reference standard.
Results
Compared with histopathology, lymph nodes were true positive in three cases, true negative in 65 cases, false positive in three cases and false negative in 14 cases in PET/CT. PET/MR was true positive in four cases, true negative in 63 cases, false positive in two cases and false negative in 13 cases. Hence, we observed a sensitivity, specificity, positive predictive value and negative predictive value of 17.7, 95.6, 50.0 and 82.3% for PET/CT and 23.5, 96.9, 66.7 and 82.3% for PET/MR. In DWI, 56 sentinel lymph node basins could be analyzed. Here, the additional analysis of DWI led to two additional false positive findings, while the number of true positive findings could not be increased.
Conclusion
In conclusion, integrated 18F-FDG PET/MR does not reliably differentiate N-positive from N-negative melanoma patients. Additional DWI does not increase the sensitivity of 18F-FDG PET/MR. Hence, sentinel lymph node biopsy cannot be replaced by 18F-FDG-PE/MR or 18F-FDG-PET/CT.