Weakly supervised deep learning for determining the prognostic value of 18F-FDG PET/CT in extranodal natural killer/T cell lymphoma, nasal type.
Ontology highlight
ABSTRACT: Purpose
To develop a weakly supervised deep learning (WSDL) method that could utilize incomplete/missing survival data to predict the prognosis of extranodal natural killer/T cell lymphoma, nasal type (ENKTL) based on pretreatment 18F-FDG PET/CT results.Methods
One hundred and sixty-seven patients with ENKTL who underwent pretreatment 18F-FDG PET/CT were retrospectively collected. Eighty-four patients were followed up for at least 2 years (training set = 64, test set = 20). A WSDL method was developed to enable the integration of the remaining 83 patients with incomplete/missing follow-up information in the training set. To test generalization, these data were derived from three types of scanners. Prediction similarity index (PSI) was derived from deep learning features of images. Its discriminative ability was calculated and compared with that of a conventional deep learning (CDL) method. Univariate and multivariate analyses helped explore the significance of PSI and clinical features.Results
PSI achieved area under the curve scores of 0.9858 and 0.9946 (training set) and 0.8750 and 0.7344 (test set) in the prediction of progression-free survival (PFS) with the WSDL and CDL methods, respectively. PSI threshold of 1.0 could significantly differentiate the prognosis. In the test set, WSDL and CDL achieved prediction sensitivity, specificity, and accuracy of 87.50% and 62.50%, 83.33% and 83.33%, and 85.00% and 75.00%, respectively. Multivariate analysis confirmed PSI to be an independent significant predictor of PFS in both the methods.Conclusion
The WSDL-based framework was more effective for extracting 18F-FDG PET/CT features and predicting the prognosis of ENKTL than the CDL method.
SUBMITTER: Guo R
PROVIDER: S-EPMC7896833 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Positron emission tomography-computed tomography (PET/CT) is widely used for initial staging and monitoring treatment responses in Hodgkin and diffuse large B-cell lymphoma. However, its prognostic value in extranodal natural killer (NK)/T-cell lymphoma (ENKL) remains unclear. Here, we conducted a retrospective study to determine the impact of PET/CT in ENKL. Fifty-two patients newly diagnosed with ENKL were enrolled. Baseline maximum standardized uptake values (SUVmax), whole-body metabolic tumor volume (WBMTV) and whole-body total lesion glycolysis (WBTLG) were recorded. Additionally, interim PET/CT (I-PET) and end-of-treatment PET/CT (E-PET) results were scored using a 5-point scale. Patients were divided into groups using baseline parameter cut-off values; significant differences were found in overall survival (OS) and progression-free survival (PFS) between the high and low WBMTV and WBTLG groups and in OS between the two SUVmax groups. Positive I-PET and E-PET results predicted inferior PFS and OS. A multivariate analysis showed that baseline WBTLG, I-PET and E-PET results were associated with PFS and OS, and baseline SUVmax was an independent predictor of OS. Thus, baseline WBTLG, I-PET and E-PET results are good predictors of PFS and OS in ENKL patients who received L-asparaginase/pegaspargase in their first-line treatment, and baseline SUVmax is a valuable tool for assessing OS.
| S-EPMC5259805 | biostudies-literature
Project description:BackgroundThe clinical diagnosis of deep sternal wound infection (DSWI) is supported by imaging findings including 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG-PET/CT). To avoid misinterpretation due to normal post-surgery inflammation we assessed normal imaging findings in non-infected patients after sternotomy.MethodsThis is a prospective cohort study including non-infectious patients with sternotomy. All patients underwent 18F-FDG-PET/CT at either 5 weeks (group 1), 12 weeks (group 2) or 52 weeks (group 3) post-surgery. 18F-FDG uptake was scored visually in five categories and assessed quantitatively.ResultsA total of 44 patients were included. Sternal mean SUVmax was 7.34 (± 1.86), 5.22 (± 2.55) and 3.20 (± 1.80) in group 1, 2 and 3, respectively (p < 0.01). Sternal mean SUVmean was 3.84 (± 1.00), 2.69 (± 1.32) and 1.71 (± 0.98) in group 1, 2 and 3 (p < 0.01). All patients in group 1 had elevated uptake whereas group 2 and 3 showed 2/15 (13%) and 11/20 (55%) patients respectively with no elevated uptake. Group 3 still showed an elevated uptake pattern in in 9/20 (45%) and in 3/9 (33%) with a high-grade diffuse uptake pattern.ConclusionThis study shows significant lower sternal 18F-FDG at 55 weeks compared to 5 weeks post-sternotomy however elevated uptake patterns may persist.
| S-EPMC10261398 | biostudies-literature
Project description:To evaluate the prognostic value of the baseline SUVmax of F-FDG PET-CT in extranodal natural killer/T-cell lymphoma (NKTCL) patients.From January 2010 to December 2015, 141 extranodal NKTCL patients with staging F-FDG PET-CT scan were divided into two group based on SUVmax cutoff value obtained from operating characteristic (ROC) curves. All the patients received radiotherapy, chemotherapy or chemoradiation. Survival analysis was performed on the basis of SUVmax.The median baseline SUVmax of the tumors was 11.67 (range 2.6-34.6). The ROC curves showed that the optimal cutoff of the baseline SUVmax was 9.65. The patients were divided into two groups: low SUV group (SUVmax < 9.65) and high SUV group (SUVmax ≥ 9.65). Patients in high SUV group were more likely to have invasive disease outside the nasal cavity (P < .001), poorer ECOG scores (P = .012) and higher LDH levels (P = .034). The univariate survival analyses indicated that high SUVmax was a poor prognostic factor for overall survival (OS, P = .038), progression free survival (PFS, P = .006) and distant relapse free survival (DRFS, P = .001), but not for local recurrence free survival (LRFS, P > .05). These results were consistent with that of the survival analyses using the Kaplan-Meier method. The multivariate survival analyses showed that the baseline SUVmax was no longer a prognostic factor for OS (HR 1.99, 95% CI 0.81-4.88, P = .135), but it still indicated worse PFS (HR 2.6, 95% CI 1.24-5.46, P = .012) and DRFS (HR 4.58, 95% CI 1.83-11.46, P = .001) independent of other variables.For extranodal NKTCL patients, a higher baseline SUVmax of F-FDG PET-CT was associated with more aggressive clinical features. An SUVmax ≥ 9.65 was an independent poor prognostic factor for DRFS and PFS. Thus, the baseline SUVmax may be a valuable tool to help identify patients with a high risk of disease progression.
| S-EPMC7489640 | biostudies-literature
Project description:Knowledge of the within-subject variability of 18F-FDG PET/MRI measurements is necessary for proper interpretation of quantitative PET or MRI metrics in the context of therapeutic efficacy assessments with integrated PET/MRI scanners. The goal of this study was to determine the test-retest repeatability of these metrics on PET/MRI, with comparison to similar metrics acquired by PET/CT. Methods: This prospective study enrolled subjects with pathology-proven pelvic malignancies. Baseline imaging consisted of PET/CT immediately followed by PET/MRI, using a single 370-MBq 18F-FDG dose. Repeat imaging was performed within 7 d using an identical imaging protocol, with no oncologic therapy between sessions. PET imaging on both scanners consisted of a list-mode acquisition at a single pelvic station. The MRI consisted of 2-point Dixon imaging for attenuation correction, standard sequences for anatomic correlation, and diffusion-weighted imaging. PET data were statically reconstructed using various frame durations and minimizing uptake time differences between sessions. SUV metrics were extracted for both PET/CT and PET/MRI in each imaging session. Apparent diffusion coefficient (ADC) metrics were extracted for both PET/MRI sessions. Results: The study cohort consisted of 14 subjects (13 female, 1 male) with various pelvic cancers (11 cervical, 2 rectal, 1 endometrial). For SUVmax, the within-subject coefficient of variation (wCV) appeared higher for PET/CT (8.5%-12.8%) than PET/MRI (6.6%-8.7%) across all PET reconstructions, though with no significant repeatability differences (all P values ≥ 0.08) between modalities. For lean body mass-adjusted SUVpeak, the wCVs appeared similar for PET/CT (9.9%-11.5%) and PET/MRI (9.2%-11.3%) across all PET reconstructions, again with no significant repeatability differences (all P values ≥ 0.14) between modalities. For PET/MRI, the wCV for ADCmedian of 3.5% appeared lower than the wCVs for SUVmax (6.6%-8.7%) and SULpeak (9.2%-11.3%), though without significant repeatability differences (all P values ≥ 0.23). Conclusion: For solid tumors of the pelvis, the repeatability of the evaluated SUV and ADC metrics on 18F-FDG PET/MRI is both acceptably high and similar to previously published values for 18F-FDG PET/CT and MRI, supporting the use of 18F-FDG PET/MRI for quantitative oncologic treatment response assessments.
| S-EPMC6681694 | biostudies-literature
Project description:BackgroundIdiopathic normal pressure hydrocephalus (iNPH) is an important and treatable cause of neurologic impairment. Diagnosis is complicated due to symptoms overlapping with other age related disorders. The pathophysiology underlying iNPH is not well understood. We explored FDG-PET abnormalities in iNPH patients in order to determine if FDG-PET may serve as a biomarker to differentiate iNPH from common neurodegenerative disorders.MethodsWe retrospectively compared 18F-FDG PET-CT imaging patterns from seven iNPH patients (mean age 74 ± 6 years) to age and sex matched controls, as well as patients diagnosed with clinical Alzheimer's disease dementia (AD), Dementia with Lewy Bodies (DLB) and Parkinson's Disease Dementia (PDD), and behavioral variant frontotemporal dementia (bvFTD). Partial volume corrected and uncorrected images were reviewed separately.ResultsPatients with iNPH, when compared to controls, AD, DLB/PDD, and bvFTD, had significant regional hypometabolism in the dorsal striatum, involving the caudate and putamen bilaterally. These results remained highly significant after partial volume correction.ConclusionsIn this study, we report a FDG-PET pattern of hypometabolism in iNPH involving the caudate and putamen with preserved cortical metabolism. This pattern may differentiate iNPH from degenerative diseases and has the potential to serve as a biomarker for iNPH in future studies. These findings also further our understanding of the pathophysiology underlying the iNPH clinical presentation.
| S-EPMC5987871 | biostudies-literature
Project description:BackgroundMagnetic resonance imaging (MRI) plays an important role in the diagnosis of leptomeningeal metastases (LM); however, some sub-centimeter lesions may be missed. Positron emission tomography/computed tomography (PET/CT) has a high sensitivity and may play a synergistic role with MRI in diagnosing spinal LM (SLM). We aimed to retrospectively evaluate the detection of SLM with 18F-fluorodeoxyglucose PET/CT (18F-FDG PET/CT) compared to that of whole spinal cord MRI in a single center.MethodsPatients with SLM who had undergone 18F-FDG PET/CT and MRI were enrolled. 18F-FDG PET/CT imaging findings were independently reviewed by 2 nuclear medicine physicians. 18F-FDG PET/CT findings of SLMs were described. A consistency test was conducted to assess the patient-based diagnostic results obtained by the 2 physicians. Patient-based sensitivity, accuracy, and specificity in diagnosing SLM between 18F-FDG PET/CT and MRI of the whole spinal cord were compared using the chi-square or Fisher's exact test. A P value of <0.05 was considered statistically significant. The receiver operating characteristic (ROC) curve was obtained to assess the diagnostic performance of maximum standardized uptake value (SUVmax) to diagnose SLM.ResultsA total of 16 patients with SLM were included in this study from October 2010 to April 2022. The primary tumor involved the lungs, liver, ovaries, prostate, esophagus, and unknown primary site. The mean age of patients, including 13 males and 3 females, was 57.8±11.2 (range, 34-73) years. Of 16 patients with SLM, 10 had nodular diseases, 2 had linear diseases, and 4 had mixed diseases. The kappa value of the consistency test of the 2 radiologists' diagnostic results was 0.765. The patient-based sensitivity, specificity, and accuracy of 18F-FDG PET/CT in diagnosing SLM were 87.5%, 89.2%, and 88.7%, respectively and those of whole spinal cord MRI were 75.0%, 100.0%, and 92.5%, respectively. There were no significant differences in sensitivity, specificity, and accuracy between the 2 methods, with P values of 0.654, 0.115, and 0.506, respectively. However, more nodular diseases were observed on PET/CT. The area under the ROC curve (AUC) for the prediction of SLM by SUVmax was 0.907 [95% confidence interval (CI): 0.831-0.983]. When SUVmax ≥2.45, the Youden index was the largest, and the sensitivity and specificity were 89.3% and 75.7%, respectively.Conclusions18F-FDG PET/CT is a good choice of imaging modality for assessing SLM. In the diagnosis of SLMs, PET/CT and enhanced MRI can play a better synergistic role.
| S-EPMC10585555 | biostudies-literature
Project description:Backgroundsignificance of incidental thyroid 2-deoxy-2-[18F]fluoro-D-glucose ([18F]FDG) uptake on positron emission tomography/computed tomography (PET/CT) scans remains controversial. We aimed to evaluate the ability of [18F]FDG-PET/CT texture analysis to predict final diagnosis in thyroid incidentaloma.MethodsWe retrospectively evaluated medical records of all patients who performed a [18F]FDG-PET/CT from January 2012 to October 2016. Those patients who presented a thyroid incidentaloma described in the medical records and performed a fine needle aspiration in our institution were considered for the analysis. Cytological and/or histological results were used as reference standard to define the final diagnosis. In case of negative cytology, the nodule was considered benign. In case of non-diagnostic or inconclusive results ultrasound, follow-up and further cytology/histology were used as final diagnosis. For suspected or positive cytological result, histology was used as reference standard. PET images were segmented using a General Electric AW workstation running PET VCAR software (GE Healthcare, Waukesha, WI, USA) settled with a threshold of 40% SUVmax. LifeX software (http://www.lifexsoft.org) was used to perform texture analysis. Statistical analysis was performed with R package (https://www.r-project.org).ResultsWe identified 55 patients with incidental thyroid [18F]FDG uptake. Five patients were excluded from the analysis because a final diagnosis was not available. Thirty-two out of 50 patients had benign nodules while in 18/50 cases a malignancy (primary thyroid cancer = 15, metastases = 3) was diagnosed. Conventional PET parameters and histogram-based features were calculated for all 50 patients, while other matrices-based features were available for 28/50 patients. SUVmax and skewness resulted significantly different in benign and malignant nodules (p = 0.01 and = 0.02, respectively). Using ROC analysis, seven features were identified as potential predictors. Among all the textural features tested, skewness showed the best area under the curve (=?0.66). SUV-based parameters resulted in the highest specificity while MTV, TLG, skewness and kurtosis, as well as correlationGLCM resulted better in sensitivity.Conclusions[18F]FDG-PET/CT texture analysis seems to be a promising approach to stratify the patients with thyroid incidentaloma identified on PET scans, with respect to the risk of the diagnosis of a malignant thyroid nodule and thus, could refine the selection of the patients to be referred for cytology.
| S-EPMC5954705 | biostudies-literature
Project description:BackgroundBoth bone metastases and multiple myeloma (MM) are malignant diseases that can appear osteolytic on imaging and are difficult to differentiate. While positron emission tomography/computed tomography (PET/CT) has been demonstrated useful for the diagnosis of various bone lesions, correlations between PET/CT and histopathology and these diseases are unclear. This retrospective study investigated the optimal cutoff standardized uptake value (SUV) to differentiate MM and bone metastasis.MethodsPatients with newly diagnosed osteolytic lesions (n = 344) and suspected malignancy underwent both fluorodeoxyglucose (FDG) PET/CT and biopsy/surgery. FDG uptake and morphologic changes (e.g., soft tissue mass formation) were compared with pathological results.ResultsA total of 8896 osteolytic lesions were evaluated. The SUVmax of MM osteolytic lesions (1.6 ± 0.7) was significantly lower than that of bone metastases (5.5 ± 2.7; p = 0.000). The best cutoff SUVmax for differentiating MM and bone metastasis was 2.65 (sensitivity 86.1%, specificity 94.7%; p = 0.000). The SUVmax of bone lesions of soft tissue mass was higher than that for pure osteolytic lesions (p = 0.000). A greater percentage of patients with bone metastasis had a soft tissue mass (7%) than did patients with MM (2%). The mean SUVmax of bone metastases was 5.5 ± 2.7 (0.4-30.4); that of primary tumors was 7.5 ± 4.2 (1.0-28.5). The SUVmax of bone metastases significantly correlated with the SUVmax of primary tumors (r = 0.532; p = 0.000).ConclusionsFDG PET/CT is a valuable tool to differentiate osteolytic lesions. The best cutoff value of SUVmax for differentiating MM from bone metastasis is 2.65. The significant correlation between the SUVmax of bone metastasis and that of primary tumors is helpful for detecting primary tumors.
| S-EPMC7393436 | biostudies-literature
Project description:Purpose[18F]FDG PET/CT in multiple myeloma (MM) is currently the best technology to demonstrate patchy and extramedullary disease. However, [18F]FDG PET has some limitations, and imaging with alternative tracers should be explored. In this study, we aimed to evaluate the performance of [18F]fluciclovine PET compared to [18F]FDG PET in newly diagnosed MM patients.ProceduresThirteen newly diagnosed transplant eligible MM patients were imaged both with [18F]FDG PET/CT and [18F]fluciclovine PET/CT within 1 week in a prospective study. The subjects were visually assessed positive or negative for disease. The number of lesions and the SUVmax of selected lesions were measured for both tracers. Furthermore, tracer uptake ratios were obtained by dividing lesion SUVmax by blood or bone marrow SUVmax. Between-group differences and correlations were assessed with paired t-tests and Pearson tests. Bone marrow SUVs were compared to bone marrow plasma cell percentage in biopsy samples.ResultsNine subjects were assessed positively by [18F]FDG PET (69%) and 12 positives by [18F]fluciclovine PET (92%). All positive subjects had [18F]fluciclovine scans that were qualitatively scored as easier to interpret visually than the [18F]FDG scans. The number of lesions was also higher; seven of nine subjects with distinct hot spots on [18F]fluciclovine PET had fewer or no visible lesions on [18F]FDG PET. The mean lesion SUVmax values were 8.2 and 3.8 for [18F]fluciclovine and [18F]FDG, respectively. The mean tumour to blood values were 6.4 and 2.0 for [18F]fluciclovine and [18F]FDG, and the mean ratios between tumour and bone marrow were 2.1 and 1.5 for [18F]fluciclovine and [18F]FDG. The lesion SUVmax and ratios were significantly higher for [18F]fluciclovine (all p < 0.01). Local [18F]fluciclovine SUVmax or SUVmean values in os ilium and the percentage of plasma cells in bone marrow biopsies were linearly correlated (p = 0.048). There were no significant correlations between [18F]FDG SUVs and plasma cells (p = 0.82).ConclusionsBased on this pilot study, [18F]fluciclovine is a promising tracer for MM. The visual and semi-quantitative evaluations indicate that [18F]fluciclovine PET/CT can out-perform [18F]FDG PET/CT at diagnosis.
| S-EPMC9581841 | biostudies-literature
Project description:BackgroundThere is evidence that metabolic disease burden in lymphoma influences patient outcome. However, the impact of disease severity on the cardiovascular system is unknown.ObjectivesThe aim of this study was to examine whether lymphoma is associated with arterial inflammation by investigating the relationship between disease metabolic burden and arterial fluorodeoxyglucose (FDG) uptake.MethodsSixty-two chemotherapy-naïve patients with active Hodgkin's or non-Hodgkin's lymphoma were matched (2:1) to individual control groups of lymphoma patients previously treated and free of active disease. All groups underwent 18F-FDG position emission tomography-computed tomography imaging. Disease severity was quantified by metabolic tumor volume (MTV) and total lesion glycolysis corresponding to standardized uptake values (SUVs) ≥41% or ≥2.5 of the maximum SUV within lymphoma regions, and aortic FDG uptake was quantified through the target-to-background ratio (TBR). Inflammatory and disease severity biomarkers were also measured.ResultsMTV and total lesion glycolysis measurements were significantly correlated with inflammatory and disease biomarkers. Aortic TBR was higher in patients with active non-Hodgkin's lymphoma compared with control subjects (median difference 0.51; 95% confidence interval [CI]: 0.28 to 0.78; p < 0.001). Similarly, patients with active Hodgkin's lymphoma had higher values of aortic TBR compared with control subjects (median difference 0.31; 95% CI: 0.15 to 0.49; p < 0.001). In addition, aortic TBR was modestly increased in patients with stage III to IV disease compared with those with stage I to II disease (median aortic TBR: 2.23 [interquartile range: 2.01 to 2.54] vs. 2.06 [interquartile range: 1.83 to 2.27; p = 0.050). In multivariable analysis, aortic FDG uptake and MTV≥2.5 values were independently associated (β = 0.425; 95% CI: 0.189 to 0.662; p = 0.001; R2 = 0.208), as were aortic FDG uptake and MTV≥41% (β = 0.407; 95% CI: 0.167 to 0.649, p = 0.001; R2 = 0.191).ConclusionsAortic wall FDG uptake is related with disease severity indicative of a possible vascular effect of lymphoma. This work highlights a new potential role of molecular imaging in cardio-oncology for evaluating disease severity and its consequences on the vasculature.
| S-EPMC8352324 | biostudies-literature