Dataset Information

Vision transformer to differentiate between benign and malignant slices in ¹⁸F-FDG PET/CT.

ABSTRACT: Fluorine-18-fluorodeoxyglucose (¹⁸F-FDG) positron emission tomography (PET)/computed tomography (CT) is widely used for the detection, diagnosis, and clinical decision-making in oncological diseases. However, in daily medical practice, it is often difficult to make clinical decisions because of physiological FDG uptake or cancers with poor FDG uptake. False negative clinical diagnoses of malignant lesions are critical issues that require attention. In this study, Vision Transformer (ViT) was used to automatically classify ¹⁸F-FDG PET/CT slices as benign or malignant. This retrospective study included ¹⁸F-FDG PET/CT data of 207 (143 malignant and 64 benign) patients from a medical institute to train and test our models. The ViT model achieved an area under the receiver operating characteristic curve (AUC) of 0.90 [95% CI 0.89, 0.91], which was superior to the baseline Convolutional Neural Network (CNN) models (EfficientNet, 0.87 [95% CI 0.86, 0.88], P < 0.001; DenseNet, 0.87 [95% CI 0.86, 0.88], P < 0.001). Even when FDG uptake was low, ViT produced an AUC of 0.81 [95% CI 0.77, 0.85], which was higher than that of the CNN (DenseNet, 0.65 [95% CI 0.59, 0.70], P < 0.001). We demonstrated the clinical value of ViT by showing its sensitive analysis of easy-to-miss cases of oncological diseases.

SUBMITTER: Nishigaki D

PROVIDER: S-EPMC11004130 | biostudies-literature | 2024 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Vision transformer to differentiate between benign and malignant slices in <sup>18</sup>F-FDG PET/CT.

Nishigaki Daiki D Suzuki Yuki Y Watabe Tadashi T Katayama Daisuke D Kato Hiroki H Wataya Tomohiro T Kita Kosuke K Sato Junya J Tomiyama Noriyuki N Kido Shoji S

Scientific reports 20240409 1

Fluorine-18-fluorodeoxyglucose (<sup>18</sup>F-FDG) positron emission tomography (PET)/computed tomography (CT) is widely used for the detection, diagnosis, and clinical decision-making in oncological diseases. However, in daily medical practice, it is often difficult to make clinical decisions because of physiological FDG uptake or cancers with poor FDG uptake. False negative clinical diagnoses of malignant lesions are critical issues that require attention. In this study, Vision Transformer (V ...[more]

PMID: 38594295

Similar Datasets

Project description:Lung cancer mortality rate can be significantly reduced by up to 20% through routine low-dose computed tomography (LDCT) screening, which, however, has high sensitivity but low specificity, resulting in a high rate of false-positive nodules. Combining PET with CT may provide more accurate diagnosis for indeterminate screening-detected nodules. In this work, we investigated low-dose dynamic 18F-FDG PET in discrimination between benign and malignant nodules using a virtual clinical trial based on patient study with ground truth. Six patients with initial LDCT screening-detected lung nodules received 90 min single-bed PET scans following a 10 mCi FDG injection. Low-dose static and dynamic images were generated from under-sampled list-mode data at various count levels (100%, 50%, 10%, 5%, and 1%). A virtual clinical trial was performed by adding nodule population variability, measurement noise, and static PET acquisition start time variability to the time activity curves (TACs) of the patient data. We used receiver operating characteristic (ROC) analysis to estimate the classification capability of standardized uptake value (SUV) and net uptake constant K i from their simulated benign and malignant distributions. Various scan durations and start times (t *) were investigated in dynamic Patlak analysis to optimize simplified acquisition protocols with a population-based input function (PBIF). The area under curve (AUC) of ROC analysis was higher with increased scan duration and earlier t *. Highly similar results were obtained using PBIF to those using image-derived input function (IDIF). The AUC value for K i using optimized t * and scan duration with 10% dose was higher than that for SUV with 100% dose. Our results suggest that dynamic PET with as little as 1 mCi FDG could provide discrimination between benign and malignant lung nodules with higher than 90% sensitivity and specificity for patients similar to the pilot and simulated population in this study, with LDCT screening-detected indeterminate lung nodules.

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.

Project description:BackgroundExcellent performance characteristics of the Vision Quadra PET/CT, e.g. a substantial increase in sensitivity, allow for precise measurements of image-derived input functions (IDIF) and tissue time activity curves. Previously we have proposed a method for a reduced 30 min (as opposed to 60 min) whole body 18F-FDG Patlak PET imaging procedure using a previously published population-averaged input function (PIF) scaled to IDIF values at 30-60 min post-injection (p.i.). The aim of the present study was to apply this method using the Vision Quadra PET/CT, including the use of a PIF to allow for shortened scan durations.MethodsTwelve patients with suspected lung malignancy were included and received a weight-based injection of 18F-FDG. Patients underwent a 65-min dynamic PET acquisition which were reconstructed using European Association of Nuclear Medicine Research Ltd. (EARL) standards 2 reconstruction settings. A volume of interest (VOI) was placed in the ascending aorta (AA) to obtain the IDIF. An external PIF was scaled to IDIF values at 30-60, 40-60, and 50-60 min p.i., respectively, and parametric 18F-FDG influx rate constant (Ki) images were generated using a t* of 30, 40 or 50 min, respectively. Herein, tumour lesions as well as healthy tissues, i.e. liver, muscle tissue, spleen and grey matter, were segmented.ResultsGood agreement between the IDIF and corresponding PIF scaled to 30-60 min p.i. and 40-60 min p.i. was obtained with 7.38% deviation in Ki. Bland-Altman plots showed excellent agreement in Ki obtained using the PIF scaled to the IDIF at 30-60 min p.i. and at 40-60 min p.i. as all data points were within the limits of agreement (LOA) (- 0.004-0.002, bias: - 0.001); for the 50-60 min p.i. Ki, all except one data point fell in between the LOA (- 0.021-0.012, bias: - 0.005).ConclusionsParametric whole body 18F-FDG Patlak Ki images can be generated non-invasively on a Vision Quadra PET/CT system. In addition, using a scaled PIF allows for a substantial (factor 2 to 3) reduction in scan time without substantial loss of accuracy (7.38% bias) and precision (image quality and noise interference).

Dataset Information

Vision transformer to differentiate between benign and malignant slices in ¹⁸F-FDG PET/CT.

Publications

Vision transformer to differentiate between benign and malignant slices in <sup>18</sup>F-FDG PET/CT.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Dataset Information

Vision transformer to differentiate between benign and malignant slices in 18F-FDG PET/CT.

Publications

Vision transformer to differentiate between benign and malignant slices in <sup>18</sup>F-FDG PET/CT.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Vision transformer to differentiate between benign and malignant slices in ¹⁸F-FDG PET/CT.