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: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: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: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
Project description:The aim of this study was to assess the risk of atherosclerosis in patients with lung cancer compared to patients with extrapulmonary malignancies using 18F-fluorodeoxyglucose-positron emission tomography/computed tomography (FDG-PET/CT). We hypothesized that patients with lung cancer would demonstrate increased FDG uptake in the thoracic aorta compared to patients with extrapulmonary cancers. Thirty-four lung cancer patients (21 male, 13 female, 64.1 ± 12.9 yo) were retrospectively compared to seventy-eight patients with extrapulmonary malignancies (46 male, 32 female, 59.6 ± 12.8 yo). Average maximum standardized uptake value (avgSUVmax) and maximum target-to-blood pool ratio (TBRmax) were measured by mapping regions of interest of the ascending aorta, aortic arch, and descending aorta. Two-tailed Student's t-test was used to assess the differences in avgSUVmax and TBRmax between the two groups and between smokers and non-smokers. Age and gender distribution between the groups were not statistically different. AvgSUVmax and TBRmax were statistically significant increase in lung cancer patients compared to extrapulmonary cancer patients in the ascending aorta, aortic arch, and descending aorta, suggesting a lung cancer-associated increased risk of atherosclerosis development. AvgSUVmax was not significantly different between smokers and non-smokers in all sections of the thoracic aorta. Moving forward, large, prospective studies that directly compare PET data between different malignancies of different stages will help determine the role of FDG-PET/CT in assessing paraneoplastic vascular disease.
| S-EPMC7936247 | biostudies-literature
Project description:ObjectiveIn patients with a history of lymphoma who demonstrate palatine tonsil uptake on posttreatment PET/CT (positron emission tomography/computed tomography), tonsillectomy is often performed to evaluate for lymphoma recurrence. However, predictive clinical and imaging factors for true tonsil recurrence in this setting are not well established; this will be explored herein.Study designRetrospective case series.SettingPatients treated at a tertiary medical center from January 2008 to May 2020.MethodsChart review was performed on all patients with a history of treated lymphoma in clinical remission who presented for evaluation of abnormal PET/CT imaging findings and subsequently underwent tonsillectomy.ResultsAmong 15 patients who met inclusion criteria, 14 had benign findings on surgical pathology, yielding a false-positive rate of 93%. The patient with malignancy was identified on biopsy after inconclusive surgical pathology and is the only documented case of recurrence in this specific patient population throughout the literature. The patient presented with B symptoms, irregularly shaped tonsils, increased lymph node activity on PET/CT, and uptrending bilateral tonsil activity but with one of the lowest maximum standardized uptake values of the cohort. The singular distinguishing feature for the patient with recurrent disease was a prior tonsil biopsy suspicious for recurrence, which prompted the otolaryngology referral.ConclusionPET/CT lacks specificity in identifying lymphoma recurrence in the oropharynx. Clinical and radiographic features that were previously considered concerning for recurrence are most likely not indicative of malignancy in this patient population. Our findings call into question whether tonsillectomy should be routinely performed in this patient population.
| S-EPMC8600558 | biostudies-literature
Project description:At present, 18F-fluorodesoxyglucose (18FDG) positron emission tomography (PET)/computed tomography (CT) cannot be used to omit a bone marrow biopsy (BMB) among initial staging procedures in follicular lymphoma (FL). The additional diagnostic value of skeletal textural features on baseline 18FDG-PET/CT in diffuse large B-cell lymphoma (DLBCL) patients has given promising results. The aim of this study is to evaluate the value of 18FDG-PET/CT radiomics for the diagnosis of bone marrow involvement (BMI) in FL patients. This retrospective bicentric study enrolled newly diagnosed FL patients addressed for baseline 18FDG PET/CT. For visual assessment, examinations were considered positive in cases of obvious bone focal uptakes. For textural analysis, the skeleton volumes of interest (VOIs) were automatically extracted from segmented CT images and analysed using LifeX software. BMB and visual assessment were taken as the gold standard: BMB -/PET - patients were considered as bone-NEGATIVE patients, whereas BMB +/PET -, BMB -/PET + and BMB +/PET + patients were considered bone-POSITIVE patients. A LASSO regression algorithm was used to select features of interest and to build a prediction model. Sixty-six consecutive patients were included: 36 bone-NEGATIVE (54.5%) and 30 bone-POSITIVE (45.5%). The LASSO regression found variance_GLCM, correlation_GLCM, joint entropy_GLCM and busyness_NGLDM to have nonzero regression coefficients. Based on ROC analysis, a cut-off equal to - 0.190 was found to be optimal for the diagnosis of BMI using PET pred.score. The corresponding sensitivity, specificity, PPV and NPV values were equal to 70.0%, 83.3%, 77.8% and 76.9%, respectively. When comparing the ROC AUCs with using BMB alone, visual PET assessment or PET pred.score, a significant difference was found between BMB versus visual PET assessments (p = 0.010) but not between BMB and PET pred.score assessments (p = 0.097). Skeleton texture analysis is worth exploring to improve the performance of 18FDG-PET/CT for the diagnosis of BMI at baseline in FL patients.
| S-EPMC8664828 | biostudies-literature
Project description:Invasive lobular carcinoma (ILC) demonstrates lower conspicuity on 18F-FDG PET than the more common invasive ductal carcinoma. Other molecular imaging methods may be needed for evaluation of this malignancy. As ILC is nearly always (95%) estrogen receptor (ER)-positive, ER-targeting PET tracers such as 16α-18F-fluoroestradiol (18F-FES) may have value. We reviewed prospective trials at Memorial Sloan Kettering Cancer Center using 18F-FES PET/CT to evaluate metastatic ILC patients with synchronous 18F-FDG and 18F-FES PET/CT imaging, which allowed a head-to-head comparison of these 2 PET tracers. Methods: Six prospective clinical trials using 18F-FES PET/CT in patients with metastatic breast cancer were performed at Memorial Sloan Kettering Cancer Center from 2008 to 2019. These trials included 92 patients, of whom 14 (15%) were of ILC histology. Seven of 14 patients with ILC had 18F-FDG PET/CT performed within 5 wk of the research 18F-FES PET/CT and no intervening change in management. For these 7 patients, the 18F-FES and 18F-FDG PET/CT studies were analyzed to determine the total number of tracer-avid lesions, organ systems of involvement, and SUVmax of each organ system for both tracers. Results: In the 7 comparable pairs of scans, there were a total of 254 18F-FES-avid lesions (SUVmax, 2.6-17.9) and 111 18F-FDG-avid lesions (SUVmax, 3.3-9.9) suggestive of malignancy. For 5 of 7 (71%) ILC patients, 18F-FES PET/CT detected more metastatic lesions than 18F-FDG PET/CT. In the same 5 of 7 patients, the SUVmax of 18F-FES-avid lesions was greater than the SUVmax of 18F-FDG-avid lesions. One patient had 18F-FES-avid metastases with no corresponding 18F-FDG-avid metastases. There were no patients with 18F-FDG-avid distant metastases without 18F-FES-avid distant metastases, although in one patient liver metastases were evident on 18F-FDG but not on 18F-FES PET. Conclusion: 18F-FES PET/CT compared favorably with 18F-FDG PET/CT for detection of metastases in patients with metastatic ILC. Larger prospective trials of 18F-FES PET/CT in ILC should be considered to evaluate ER-targeted imaging for clinical value in patients with this histology of breast cancer.
| S-EPMC8049349 | biostudies-literature