SUVmax of FDG PET-CT Can Be Used As An Identifier of Lesion for AI To Interpret Radiology Reports

2020 ◽  
Author(s):  
Kenji Hirata ◽  
Osamu Manabe ◽  
Keiichi Magota ◽  
Sho Furuya ◽  
Tohru Shiga ◽  
...  
Keyword(s):  
Fdg Pet ◽  
Standardized Uptake Value ◽  
Local Maximum ◽  
Ct Images ◽  
Whole Body ◽  
Training Dataset ◽  
Imaging Biomarkers ◽  
Radiology Reports ◽  
Pet Ct ◽  
Fdg Pet Ct

Abstract Background Radiology reports contribute not only to the particular patient, but also to constructing massive training dataset in the era of artificial intelligence (AI). The maximum standardized uptake value (SUVmax) is often described in daily radiology reports of FDG PET-CT. If SUVmax can be used as an identifier of lesion, that would greatly help AI interpret radiology reports. We aimed to clarify whether the lesion can be localized using SUVmax written in radiology reports.Methods The institutional review board approved this retrospective study. We investigated a total of 112 lesions from 30 FDG PET-CT images acquired with 3 different scanners. SUVmax was calculated from DICOM files based on the latest Quantitative Imaging Biomarkers Alliance (QIBA) publication. The voxels showing the given SUVmax were exhaustively searched in the whole-body images and counted. SUVmax was provided with 5 different degrees of precision: integer (e.g., 3), 1st decimal places (DP) (3.1), 2nd DP (3.14), 3rd DP (3.142), and 4th DP (3.1416). For instance, when SUVmax=3.14 was given, the voxels with 3.135≤SUVmax<3.145 were extracted. We also evaluated whether local maximum restriction could improve the identifying performance, where only the voxels showing the highest intensity within some neighborhood were considered. We defined that “identical detection” was achieved when only single voxel satisfied the criterion.Results A total of 112 lesions from 30 FDG PET-CT images were investigated. SUVmax ranged from 1.3 to 49.1 (median = 5.6, IQR = 5.2). Generally, when larger and more precise SUVmax values were given, fewer voxels satisfied the criterion. The local maximum restriction was very effective. When SUVmax was determined to 4 decimal places (e.g., 3.1416) and the local maximum restriction was applied, identical detection was achieved in 33.3% (lesions with SUVmax<2), 79.5% (2≤SUVmax<5), and 97.8% (5≤SUVmax) of lesions.Conclusions SUVmax of FDG PET-CT can be used as an identifier to localize the lesion if precise SUVmax is provided and local maximum restriction was applied, although the lesions showing SUVmax<2 were difficult to identify. The proposed method may have potential to make use of radiology reports retrospectively for constructing training datasets for AI.

scholarly journals A Preliminary Study to Use SUVmax of FDG PET-CT as an Identifier of Lesion for Artificial Intelligence

2021 ◽  
Vol 8 ◽  
Author(s):  
Kenji Hirata ◽  
Osamu Manabe ◽  
Keiichi Magota ◽  
Sho Furuya ◽  
Tohru Shiga ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Fdg Pet ◽  
Standardized Uptake Value ◽  
Local Maximum ◽  
Ct Images ◽  
Whole Body ◽  
Imaging Biomarkers ◽  
Pet Ct ◽  
Preliminary Study ◽  
Fdg Pet Ct

Background: Diagnostic reports contribute not only to the particular patient, but also to constructing massive training dataset in the era of artificial intelligence (AI). The maximum standardized uptake value (SUVmax) is often described in daily diagnostic reports of [18F] fluorodeoxyglucose (FDG) positron emission tomography (PET) – computed tomography (CT). If SUVmax can be used as an identifier of lesion, that would greatly help AI interpret diagnostic reports. We aimed to clarify whether the lesion can be localized using SUVmax strings.Methods: The institutional review board approved this retrospective study. We investigated a total of 112 lesions from 30 FDG PET-CT images acquired with 3 different scanners. SUVmax was calculated from DICOM files based on the latest Quantitative Imaging Biomarkers Alliance (QIBA) publication. The voxels showing the given SUVmax were exhaustively searched in the whole-body images and counted. SUVmax was provided with 5 different degrees of precision: integer (e.g., 3), 1st decimal places (DP) (3.1), 2nd DP (3.14), 3rd DP (3.142), and 4th DP (3.1416). For instance, when SUVmax = 3.14 was given, the voxels with 3.135 ≤ SUVmax &lt; 3.145 were extracted. We also evaluated whether local maximum restriction could improve the identifying performance, where only the voxels showing the highest intensity within some neighborhood were considered. We defined that “identical detection” was achieved when only single voxel satisfied the criterion.Results: A total of 112 lesions from 30 FDG PET-CT images were investigated. SUVmax ranged from 1.3 to 49.1 (median = 5.6). Generally, when larger and more precise SUVmax values were given, fewer voxels satisfied the criterion. The local maximum restriction was very effective. When SUVmax was determined to 4 decimal places (e.g., 3.1416) and the local maximum restriction was applied, identical detection was achieved in 33.3% (lesions with SUVmax &lt; 2), 79.5% (2 ≤ SUVmax &lt; 5), and 97.8% (5 ≤ SUVmax) of lesions.Conclusion: In this preliminary study, SUVmax of FDG PET-CT could be used as an identifier to localize the lesion if precise SUVmax is provided and local maximum restriction was applied, although the lesions showing SUVmax &lt; 2 were difficult to identify. The proposed method may have potential to make use of diagnostic reports retrospectively for constructing training datasets for AI.

scholarly journals Multi-task weak supervision enables anatomically-resolved abnormality detection in whole-body FDG-PET/CT

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Sabri Eyuboglu ◽  
Geoffrey Angus ◽  
Bhavik N. Patel ◽  
Anuj Pareek ◽  
Guido Davidzon ◽  
...  
Keyword(s):  
Fdg Pet ◽  
Location Estimation ◽  
Supervised Machine Learning ◽  
Whole Body ◽  
Free Text ◽  
Abnormality Detection ◽  
Weak Supervision ◽  
Radiology Reports ◽  
Pet Ct ◽  
Fdg Pet Ct

AbstractComputational decision support systems could provide clinical value in whole-body FDG-PET/CT workflows. However, limited availability of labeled data combined with the large size of PET/CT imaging exams make it challenging to apply existing supervised machine learning systems. Leveraging recent advancements in natural language processing, we describe a weak supervision framework that extracts imperfect, yet highly granular, regional abnormality labels from free-text radiology reports. Our framework automatically labels each region in a custom ontology of anatomical regions, providing a structured profile of the pathologies in each imaging exam. Using these generated labels, we then train an attention-based, multi-task CNN architecture to detect and estimate the location of abnormalities in whole-body scans. We demonstrate empirically that our multi-task representation is critical for strong performance on rare abnormalities with limited training data. The representation also contributes to more accurate mortality prediction from imaging data, suggesting the potential utility of our framework beyond abnormality detection and location estimation.

scholarly journals Prognostic Value of Metabolic Parameters Measured By 18F-FDG PET/CT In Patients With Metastatic Cutaneous Malignant Melanoma

2021 ◽  
Author(s):  
Ruihe Lai ◽  
Chong Jiang ◽  
Zhaoqun Chu ◽  
Zhengyang Zhou ◽  
Yue Teng ◽  
...  
Keyword(s):  
Malignant Melanoma ◽  
Fdg Pet ◽  
Standardized Uptake Value ◽  
Cutaneous Malignant Melanoma ◽  
Metabolic Parameters ◽  
Whole Body ◽  
Optimal Cutoff ◽  
Cutoff Values ◽  
Pet Ct ◽  
Fdg Pet Ct

Abstract Purpose: The purpose of this study was to investigate the prognostic relevance of metabolic parameters measured using 18F-FDG PET/CT in patients with metastatic cutaneous malignant melanoma (CMM).Materials and Methods: The prognostic impact of whole-body metabolic tumor volume (wMTV), whole-body tumor lesion glycolysis (wTLG), maximum standardized uptake value (SUVmax) and mean standardized uptake value (SUVmean) was evaluated in 42 metastatic CMM patients who underwent 18F-FDG PET/CT. The metabolic parameters were dichotomized by optimal cutoff values using time-dependent receiver operating characteristic (ROC) curves. In addition, univariate and multivariate analyses of the metabolic parameters were performed using the Kaplan-Meier method and Cox proportional hazards models.Results: The optimal cutoff values for disease-free survival (DFS) were 4.63 for SUVmax, 3.31 for SUVmean, 8.22 cm3 for wMTV, and 18.22 for wTLG. The optimal cutoff values for melanoma-specific survival (MSS) were 4.77 for SUVmax, 3.31 for SUVmean, 22.32 cm3 for wMTV, and 51.37 for wTLG. Thirty-two (72%) of the 42 patients experienced recurrence during the follow-up period, and 21 patients (50%) died from the disease. In univariate analysis, SUVmax greater than 4.63 (p= 0.025) and SUVmean greater than 3.31 (p= 0.011) affected DFS, while SUVmax greater than 4.77 (p= 0.039), wMTV greater than 22.32 (p= 0.023) and wMTV greater than 51.37 (p= 0.016) affected MSS. In multivariate analysis after adjustment for the effects of clinical parameters, SUVmax was the best predictive factor for DFS (p = 0.016), and SUVmax, wMTV and wTLG were the best predictive factors for MSS (p = 0.023, p = 0.018, and p = 0.007).Conclusions: SUVmax appears to be a strong independent prognostic factor for recurrence in metastatic CMM, and SUVmax, wMTV and wTLG were found to be the best predictive markers for melanoma-specific death.

scholarly journals Utility of flouro-deoxy-glucose positron emission tomography/computed tomography in the diagnostic and staging evaluation of patients with primary CNS lymphoma

CNS Oncology ◽  
2019 ◽  
Vol 8 (4) ◽  
pp. CNS46 ◽  
Author(s):  
Meetakshi Gupta ◽  
Tejpal Gupta ◽  
Nilendu Purandare ◽  
Venkatesh Rangarajan ◽  
Ameya Puranik ◽  
...  
Keyword(s):  
Fdg Pet ◽  
Standardized Uptake Value ◽  
Emission Tomography ◽  
Whole Body ◽  
Cns Lymphoma ◽  
Maximum Standardized Uptake Value ◽  
Positron Emission ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

Aim: To prospectively assess the clinical utility of pretreatment flouro-deoxy-glucose positron emission tomography/computed tomography (18F-FDG-PET/CT) in patients with primary central nervous system (CNS) lymphoma (PCNSL). Materials & methods: Patients with suspected/proven PCNSL underwent baseline whole-body 18F-FDG-PET/CT. Maximum standardized uptake value and tumor/normal tissue ratios were compared between CNS lymphoma and other histological diagnoses. Results: The mean maximum standardized uptake value (27.5 vs 18.2; p = 0.001) and mean tumor/normal tissue ratio (2.34 vs 1.53; p < 0.001) of CNS lymphoma was significantly higher than other histologic diagnoses. Five of 50 (10%) patients with biopsy-proven CNS lymphomas had pathologically increased FDG-uptake at extraneuraxial sites uncovering systemic lymphoma. Conclusion: Pretreatment whole-body 18F-FDG-PET/CT provides valuable complementary information in the diagnostic and staging evaluation of patients with PCNSL to guide therapeutic decision-making.

scholarly journals Comparison of different images in gross target volume delineating on VX2 nasopharyngeal transplantation tumor models.

2019 ◽  
Vol 5 (suppl) ◽  
pp. 127-127
Author(s):  
QingLian Wen ◽  
ZhangQiang Xiang
Keyword(s):  
Nasopharyngeal Carcinoma ◽  
Fdg Pet ◽  
Rabbit Model ◽  
Standardized Uptake Value ◽  
Target Volume ◽  
Ct Images ◽  
Pathological Examination ◽  
Flt Pet ◽  
Pet Ct ◽  
Fdg Pet Ct

127 Background: To determine the optimum conditions for diagnosis of nasopharyngeal carcinoma, we established VX2 rabbit model to delineate gross target volume (GTV) in different imaging methods. Methods:The orthotopic nasopharyngeal carcinoma (NPC) was established in sixteen New Zealand rabbits. After 7-days inoculation, the rabbits were examined by CT scanning and then sacrificed for pathological examination. To achieve the best delineation, different GTVs of CT, MRI, 18F-FDG PET/CT, and 18F-FLT PET/CT images were correlated with pathological GTV (GTVp). Results: We found 45% and 60% of the maximum standardized uptake value (SUVmax) as the optimal SUV threshold for the target volume of NPC in 18F-FDG PET/CT and 18F-FLT PET/CT images, respectively (GTVFDG45% and GTVFLT60%). Moreover, the GTVMRI and GTVCT were significantly higher than the GTVp ( P ≤ 0.05), while the GTVFDG45% and especially GTVFLT60% were similar to the GTVp ( R = 0.892 and R = 0.902, respectively; P ≤ 0.001). Conclusions: Notably, the results suggested that 18F-FLT PET/CT could reflect the tumor boundaries more accurately than 18F-FDG PET/CT, MRI and CT, which makes 18F-FLT PET-CT more advantageous for the clinical delineation of the target volume in NPC. Keywords: Nasopharyngeal carcinoma; Gross tumor volume; Magnetic resonance imaging, Computed tomography; 18F-FLT PET/CT; 18F-FDG PET/CT

Multi-modality imaging of uveal melanomas using combined PET/CT, high-resolution PET and MR imaging

2008 ◽  
Vol 47 (02) ◽  
pp. 73-79 ◽  
Author(s):  
U. Pietrzyk ◽  
C. Knoess ◽  
S. Vollmar ◽  
K. Wienhard ◽  
L. Kracht ◽  
...  
Keyword(s):  
High Resolution ◽  
Fdg Pet ◽  
Ct Images ◽  
Ct Imaging ◽  
Whole Body ◽  
Dynamic Mode ◽  
Pet Ct ◽  
Fdg Pet Ct ◽  
Tumour Activity ◽  
Uveal Melanomas

SummaryWe investigated the efficacy of combined FDG-PET/CT imaging for the diagnosis of small-size uveal melanomas and the feasibility of combining separate, high-resolution (HR) FDG-PET with MRI for its improved localization and detection. Patients, methods: 3 patients with small-size uveal melanomas (0.2–1.5 ml) were imaged on a combined whole-body PET/CT, a HR brain-PET, and a 1.5 T MRI. Static, contrast-enhanced FDG-PET/CT imaging was performed of head and torso with CT contrast enhancement. HR PET imaging was performed in dynamic mode 0–180 min post-injection of FDG. MRI imaging was performed using a high-resolution small-loop-coil placed over the eye in question with T2–3D-TSE and T1–3D-SE with 18 ml Gd-contrast. Patients had their eyes shaded during the scans. Lesion visibility on high-resolution FDGPET images was graded for confidence: 1: none, 2: suggestive, 3: clear. Mean tumour activity was calculated for summed image frames that resulted in confidence grades 2 and 3. Whole-body FDG-PET/CT images were reviewed for lesions. PET-MRI and PET/ CT-MRI images of the head were co-registered for potentially improved lesion delineation. Results: Whole-body FDG-PET/CT images of 3/3 patients were positive for uveal melanomas and negative for disseminated disease. HR FDG-PET was positive already in the early time frames. One patient exhibited rising tumour activity with increasing uptake time on FDG-PET. MRI images of the eye were co-registered successfully to FDG-PET/CT using a manual alignment approach. Conclusions: Small-size uveal melanomas can be detected with whole-body FDG-PET/CT. This feasibility study suggests the exploration of HR FDG-PET in order to provide additional diagnostic information on patients with uveal melanomas. First results support extended uptake times and high-sensitivity PET for improved tumour visibility. MRI/PET co-registration is feasible and provides correlated functional and anatomical information that may support alternative therapy regimens.

18F-FDG PET/CT imaging of vulva cancer recurrence: A comparison of PET-derived metabolic parameters between women with and without HIV infection

2020 ◽  
Vol 59 (06) ◽  
pp. 419-427
Author(s):  
Kgomotso M.G. Mokoala ◽  
Ismaheel O. Lawal ◽  
Thabo Lengana ◽  
Gbenga O. Popoola ◽  
Tebatso M.G. Boshomane ◽  
...  
Keyword(s):  
Hiv Infection ◽  
Fdg Pet ◽  
Cancer Recurrence ◽  
Standardized Uptake Value ◽  
Whole Body ◽  
Metabolic Tumour Volume ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct ◽  
Vulva Cancer

Abstract Objective To assess the patterns of recurrence of vulva cancer on 18F-FDG PET/CT and to compare the 18F-FDG PET metabolic metrics in patients with and without Human Immunodeficiency Virus (HIV). Methods Maximum standardized uptake value (SUVmax), mean standardized uptake value (SUVmean), metabolic tumour volume (MTV and total lesion glycolysis (TLG) were obtained on Flourine-18 Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography (18F-FDG PET/CT) images of women referred with suspected or confirmed vulva cancer recurrence. We compared HIV-infected and HIV-uninfected patients regarding pattern disease recurrence, age at diagnosis, and the PET-derived metabolic indices. Results We analyzed 33 patients with a mean age 50.76 ± 15.78 including 21 HIV-infected women. The majority of patients (94 %) had squamous cell carcinoma and 84.85 % were Blacks. Of the HIV-infected individuals, the median CD4 count was 526.0 cells/mm3 (IQR: 379.0–729.0). HIV infected patients were younger than the HIV uninfected at the time of diagnosis: 40.50 ± 8.87 vs 66.54 ± 9.71 respectively, p < 0.001. We found a local (vulvar) recurrence rate of 75.8 %. Nodal pelvic recurrences were higher in the HIV-infected patients than in the HIV uninfected patients (70 % vs 30 %, p = 0.027). Three patients had distant metastasis and all three were HIV-infected. There was a higher whole-body MTV and TLG among HIV-infected women compared with HIV-uninfected women, 103.39 vs 17.58 and 852.64 vs 101.79, respectively (p < 0.05 for both). Conclusion HIV-infected women are diagnosed with vulva cancer at a younger age. HIV-infected patients had a higher rate of pelvic lymph node recurrence. There is a higher tumor burden at vulva cancer recurrence among women with HIV infection.

scholarly journals How many digits after decimal point are needed to use SUVmax as an identifier of tumors on FDG PET-CT?

2020 ◽  
Author(s):  
Kenji Hirata ◽  
Osamu Manabe ◽  
Keiichi Magota ◽  
Sho Furuya ◽  
Tohru Shiga ◽  
...  
Keyword(s):  
Fdg Pet ◽  
Standardized Uptake Value ◽  
Local Maximum ◽  
Institutional Review Board ◽  
Maximum Standardized Uptake Value ◽  
Institutional Review ◽  
Single Voxel ◽  
Pet Ct ◽  
Fdg Pet Ct ◽  
The Given

Abstract PurposeThe maximum standardized uptake value (SUVmax) is often described in daily clinical reports of FDG PET-CT. We investigated whether it would be possible to localize the voxel automatically based on the SUVmax.MethodsThe institutional review board approved this retrospective study. We investigated a total of 112 lesions from 30 FDG PET-CT images acquired with 3 different scanners. The number of voxels showing the given SUVmax was counted, where SUVmax was provided with various degrees of precision, such as 3, 3.1, 3.14, 3.142. The effects of local maximum restriction, where only local maximum voxels were chosen, were evaluated.ResultsSUVmax ranged from 1.3 to 49.1 (median = 5.6, IQR = 5.2). Generally, when larger and more precise SUVmax values were given, fewer voxels were included in the range. The local maximum restriction was very effective. When SUVmax was determined to 4 decimal places (e.g., 3.1416) and the local maximum restriction was applied, 33.3% (lesions with SUVmax<2), 79.5% (2≤SUVmax<5), and 97.8% of lesions (5≤SUVmax) were successfully identified (i.e., only a single voxel satisfied the criteria).ConclusionsIn FDG PET-CT, SUVmax can be used to localize the lesion if a large and precise SUVmax is provided.

scholarly journals Evolutionary dynamics at the tumor edge reveal metabolic imaging biomarkers

2021 ◽  
Vol 118 (6) ◽  
pp. e2018110118
Author(s):  
Juan Jiménez-Sánchez ◽  
Jesús J. Bosque ◽  
Germán A. Jiménez Londoño ◽  
David Molina-García ◽  
Álvaro Martínez ◽  
...  
Keyword(s):  
Cancer Patients ◽  
Fdg Pet ◽  
Evolutionary Dynamics ◽  
Standardized Uptake Value ◽  
Ct Images ◽  
Metabolic Imaging ◽  
Imaging Biomarkers ◽  
Imaging Data ◽  
Human Cancers ◽  
Pet Ct

Human cancers are biologically and morphologically heterogeneous. A variety of clonal populations emerge within these neoplasms and their interaction leads to complex spatiotemporal dynamics during tumor growth. We studied the reshaping of metabolic activity in human cancers by means of continuous and discrete mathematical models and matched the results to positron emission tomography (PET) imaging data. Our models revealed that the location of increasingly active proliferative cellular spots progressively drifted from the center of the tumor to the periphery, as a result of the competition between gradually more aggressive phenotypes. This computational finding led to the development of a metric, normalized distance from 18F-fluorodeoxyglucose (18F-FDG) hotspot to centroid (NHOC), based on the separation from the location of the activity (proliferation) hotspot to the tumor centroid. The NHOC metric can be computed for patients using 18F-FDG PET–computed tomography (PET/CT) images where the voxel of maximum uptake (standardized uptake value [SUV]max) is taken as the activity hotspot. Two datasets of 18F-FDG PET/CT images were collected, one from 61 breast cancer patients and another from 161 non–small-cell lung cancer patients. In both cohorts, survival analyses were carried out for the NHOC and for other classical PET/CT-based biomarkers, finding that the former had a high prognostic value, outperforming the latter. In summary, our work offers additional insights into the evolutionary mechanisms behind tumor progression, provides a different PET/CT-based biomarker, and reveals that an activity hotspot closer to the tumor periphery is associated to a worst patient outcome.

scholarly journals How many digits after decimal point are needed to use SUVmax as an identifier of tumors on FDG PET-CT?

2020 ◽  
Author(s):  
Kenji Hirata ◽  
Osamu Manabe ◽  
Keiichi Magota ◽  
Sho Furuya ◽  
Tohru Shiga ◽  
...  
Keyword(s):  
Fdg Pet ◽  
Standardized Uptake Value ◽  
Local Maximum ◽  
Institutional Review Board ◽  
Maximum Standardized Uptake Value ◽  
Institutional Review ◽  
Single Voxel ◽  
Pet Ct ◽  
Fdg Pet Ct ◽  
The Given

Abstract Purpose The maximum standardized uptake value (SUVmax) is often described in daily clinical reports of FDG PET-CT. We investigated whether it would be possible to localize the voxel automatically based on the SUVmax. Methods The institutional review board approved this retrospective study. We investigated a total of 112 lesions from 30 FDG PET-CT images acquired with 3 different scanners. The number of voxels showing the given SUVmax was counted, where SUVmax was provided with various degrees of precision, such as 3, 3.1, 3.14, 3.142. The effects of local maximum restriction, where only local maximum voxels were chosen, were evaluated. Results SUVmax ranged from 1.3 to 49.1 (median = 5.6, IQR = 5.2). Generally, when larger and more precise SUVmax values were given, fewer voxels were included in the range. The local maximum restriction was very effective. When SUVmax was determined to 4 decimal places (e.g., 3.1416) and the local maximum restriction was applied, 33.3% (lesions with SUVmax<2), 79.5% (2≤SUVmax<5), and 97.8% of lesions (5≤SUVmax) were successfully identified (i.e., only a single voxel satisfied the criteria). Conclusions In FDG PET-CT, SUVmax can be used to localize the lesion if a large and precise SUVmax is provided.

Sign in / Sign up

Export Citation Format

Share Document