As a reliable preoperative predictor for microvascular invasion (MVI) and disease-free survival (DFS) is lacking, we developed a radiomics nomogram of
18
FFDG PET/CT to predict MVI status and DFS in ...patients with very-early- and early-stage (BCLC 0, BCLC A) hepatocellular carcinoma (HCC).
Methods
Patients (
N
= 80) with BCLC0-A HCC who underwent
18
FFDG PET/CT before surgery were enrolled in this retrospective study and were randomized to a training cohort and a validation cohort. Texture features from patients obtained using Lifex software in the training cohort were subjected to LASSO regression to select the most useful predictive features of MVI and DFS. Then, the radiomics nomogram was constructed using the radiomics signature and clinical features and further validated.
Results
To predict MVI, the
18
FFDG PET/CT radiomics signature consisted of five texture features from the PET and six texture features from CT. The signature was significantly associated with MVI status in the training cohort (
P
= 0.001). None of the clinical features was independent predictors for MVI status (
P
> 0.05). The area under the curve value of the M-PET/CT model was 0.891 (95% CI: 0.799–0.984) in the training cohort and showed good discrimination and calibration. To predict DFS, the
18
FFDG PET/CT radiomics nomogram (D-PET/CT model) and a clinicopathologic nomogram were built in the training cohort. The D-PET/CT model, which integrated the D-PET/CT radiomics signature with INR and TB, provided better predictive performance (C-index: 0.831, 95% CI: 0.761–0.900) and larger net benefits than the simple clinical model, as determined by decision curve analyses.
Conclusion
The newly developed
18
FFDG PET/CT radiomics signature was an independent biomarker for the estimation of MVI and DFS in patients with very-early- and early-stage HCC. Moreover, PET/CT nomogram, which incorporated the radiomics signature of
18
FFDG PET/CT and clinical risk factors in patients with very-early- and early-stage HCC, performed better for individualized DFS estimation, which might enable a step forward in precise medicine.
Purpose
We aim to accurately differentiate between active pulmonary tuberculosis (TB) and lung cancer (LC) based on radiomics and semantic features as extracted from pre-treatment positron emission ...tomography/X-ray computed tomography (PET/CT) images.
Procedures
A total of 174 patients (77/97 pulmonary TB/LC as confirmed by pathology) were retrospectively selected, with 122 in the training cohort and 52 in the validation cohort. Four hundred eighty-seven radiomics features were initially extracted to quantify phenotypic characteristics of the lesion region in both PET and CT images. Eleven semantic features were additionally defined by two experienced nuclear medicine physicians. Feature selection was performed in 5 steps to enable derivation of robust and effective signatures. Multivariable logistic regression analysis was subsequently used to develop a radiomics nomogram. The calibration, discrimination, and clinical usefulness of the nomogram were evaluated in both the training and independent validation cohorts.
Results
The individualized radiomics nomogram, which combined PET/CT radiomics signature with semantic features, demonstrated good calibration and significantly improved the diagnostic performance with respect to the semantic model alone or PET/CT signature alone in training cohort (AUC 0.97
vs.
0.94 or 0.91,
p
= 0.0392 or 0.0056), whereas did not significantly improve the performance in validation cohort (AUC 0.93
vs.
0.89 or 0.91,
p
= 0.3098 or 0.3323).
Conclusion
The radiomics nomogram showed potential for individualized differential diagnosis between solid active pulmonary TB and solid LC, although the improvement of performance was not significant relative to semantic model.
Facile automatic production is important for the application of prostate-specific membrane antigen (PSMA) tracers in clinical practice. We developed a new
18
F-AlF-labelled PSMA probe—
18
...F-AlF-PSMA-NF—and explore its automated production method and potential value in clinical settings.
18
F-AlF-PSMA-NF was prepared using an automated method with dimethylformamide (DMF) as the solvent in a positron emission tomography (PET)-MF-2 V-IT-I synthesizer. Tracer characteristics were examined both in vitro and in vivo. Micro-PET/computed tomography (CT) was performed to investigate the utility of
18
F-AlF-PSMA-NF for imaging PSMA-positive tumours in vivo.
18
F-AlF-PSMA-NF was prepared automatically within 35 min with a non-attenuation correction yield of 37.9 ± 11.2%. The tracer was hydrophilic, had a high affinity for PSMA (Kd = 2.58 ± 0.81 nM), and showed stability in both in vitro and in vivo conditions
.
In the cellular experiments,
18
F-AlF-PSMA-NF uptake in PSMA-positive LNCaP cells was significantly higher than that in PSMA-negative PC-3 cells (
P
< 0.001), and could be blocked by excess ZJ-43—a PSMA inhibitor (
P
< 0.001). LNCaP tumours were clearly visualized by
18
F-AlF-PSMA-NF on micro-PET/CT, with a high level of uptake (13.72 ± 2.01 percent injected dose per gram of tissue %ID/g) and high tumour/muscle ratio (close to 50:1). The PSMA-positive LNCaP tumours had a significantly higher uptake than PSMA-negative PC-3 tumours
(
13.72 ± 2.01%ID/g
vs.
1.07 ± 0.48%ID/g,
t
= 10.382,
P
< 0.001), and could be blocked by ZJ-43 (13.72 ± 2.01%ID/g
vs.
2.77 ± 1.44%ID/g,
t
= 8.14,
P
< 0.001). A new
18
F-AlF-labelled PSMA probe—
18
F-AlF-PSMA-NF—was successfully developed and can be prepared automatically. It has the biological characteristics resembling that of a PSMA-based probe and can potentially be used in clinical settings.
Purpose
To establish and validate a regional lymph node (LN) metastasis prediction model of colorectal cancer (CRC) based on
18
F-FDG PET/CT and radiomic features using machine-learning methods.
...Methods
A total of 199 colorectal cancer patients underwent pre-therapy diagnostic
18
F-FDG PET/CT scans and CRC radical surgery. The Chang-Gung Image Texture Analysis toolbox (CGITA) was used to extract 70 PET radiomic features reflecting
18
F-FDG uptake heterogeneity of tumors. The least absolute shrinkage and selection operator (LASSO) algorithm was used to select radiomic features and develop a radiomic signature score (Rad-score). The training set was used to establish five machine-learning prediction models and the test set was used to test the efficacy of the models. The effectiveness of the models was compared by ROC analysis.
Results
The CRC patients were divided into a training set (
n
= 144) and a test set (
n
= 55). Two radiomic features were selected to build the Rad-score. Five machine-learning algorithms including logistic regression, support vector machine (SVM), random forest, neural network and eXtreme gradient boosting (XGBoost) were used to established models. Among the five machine-learning models, logistic regression (AUC 0.866, 95% CI 0.808–0.925) and XGBoost (AUC 0.903, 95% CI 0.855–0.951) models performed the best. In the training set, the AUC of these two models were significantly higher than that of the LN metastasis status reported by
18
F-FDG PET/CT for differentiating positive and negative regional LN metastases in CRC (all
p
< 0.05). Good efficacy of the above two models was also achieved in the test set. We created a nomogram based on the logistic regression model that visualized the results and provided an easy-to-use method for predicting regional LN metastasis in patients with CRC.
Conclusion
In this study, five machine-learning models for preoperative prediction of regional LN metastasis of CRC based on
18
F-FDG PET/CT and PET-based radiomic features were successfully developed and validated. Among them, the logistic regression and XGBoost models performed the best, with higher efficacy than
18
F-FDG PET/CT in both the training and test sets.
Purpose
Compare the value of imaging using positron
18
F-labeled fibroblast activation protein inhibitor-42 (
18
F-FAPI-42) and
18
F-labeled deoxyglucose (
18
F-FDG) for assessment of AKI.
Procedures
...This study analyzed cancer patients who received
18
F-FAPI-42 and
18
F-FDG PET/CT imaging. Eight patients had AKI with bilateral ureteral obstruction (BUO), eight had BUO (CKD1–2) with no acute kidney disease (AKD), and eight had no ureteral obstruction (UO) with normal renal function. The average standardized uptake value (SUV
ave
) of the renal parenchyma (RP-SUV
ave
), the blood pool SUV
ave
(B- SUV
ave
), SUV
ave
in the highest region of the renal collective system (RCS-SUV
ave
), and the highest serum creatinine level (top SCr) were recorded.
Results
The
18
F-FAPI-42 and
18
F-FDG results showed that radiotracer of renal parenchyma was more concentrated in the AKI group than in the other two groups, whereas the RP-SUV
ave
from
18
F-FAPI-42 was higher than that from
18
F-FDG in the AKI group (all
P
< 0.05).
18
F-FAPI-42 imaging in the AKI group showed uptake by the renal parenchyma with a diffuse increase, but very little radiotracer in the renal collecting system, similar to a “super kidney scan.” The renal parenchyma also had an increase of SUV
ave
, with accumulation of radiotracer in the renal collecting system. AKI was more severe when a patient had a “super kidney scan” in both kidneys (
P
< 0.05). The B-SUV
ave
level was higher in the AKI group than in the other two groups in
18
F-FAPI-42 (both
P
< 0.05).
Conclusions
18
F-FAPI-42 imaging had higher RP-SUV
ave
than
18
F-FDG imaging in cancer patients who had BUO with AKI. An increased renal parenchyma uptake in both kidneys and low radiotracer distribution in the collecting system suggest more severe AKI.
To develop and validate the imbalanced data correction based PET/CT radiomics model for predicting lymph node metastasis (LNM) in clinical stage T1 lung adenocarcinoma (LUAD).
A total of 183 patients ...(148/35 non-metastasis/LNM) with pathologically confirmed LUAD were retrospectively included. The cohorts were divided into training vs. validation cohort in a ratio of 7:3. A total of 487 radiomics features were extracted from PET and CT components separately for radiomics model construction. Four clinical features and seven PET/CT radiological features were extracted for traditional model construction. To balance the distribution of majority (non-metastasis) class and minority (LNM) class, the imbalance-adjustment strategies using ten data re-sampling methods were adopted. Three multivariate models (denoted as Traditional, Radiomics, and Combined) were constructed using multivariable logistic regression analysis, where the combined model incorporated all of the significant clinical, radiological, and radiomics features. One hundred times repeated Monte Carlo cross-validation was used to assess the application order of feature selection and imbalance-adjustment strategies in the machine learning pipeline. Prediction performance of each model was evaluated using the area under the receiver operating characteristic curve (AUC) and Geometric mean score (G-mean).
A total of 2 clinical parameters, 2 radiological features, 3 PET, and 5 CT radiomics features were significantly associated with LNM. The combined model with Edited Nearest Neighbors (ENN) re-sampling methods showed strong prediction performance than traditional model or radiomics model with the AUC of 0.94 (95%CI = 0.86-0.97) vs. 0.89 (95%CI = 0.79-0.93), 0.92 (95%CI = 0.85-0.97), and G-mean of 0.88 vs. 0.82, 0.80 in the training cohort, and the AUC of 0.75 (95%CI = 0.57-0.91) vs. 0.68 (95%CI = 0.36-0.83), 0.71 (95%CI = 0.48-0.83) and G-mean of 0.76 vs. 0.64, 0.51 in the validation cohort. The combination of performing feature selection before data re-sampling obtains a better result than the reverse combination (AUC 0.76 ± 0.06 vs. 0.70 ± 0.07,
<0.001).
The combined model (consisting of age, histological type, C/T ratio, MATV, and radiomics signature) integrated with ENN re-sampling methods had strong lymph node metastasis prediction performance for imbalance cohorts in clinical stage T1 LUAD. Radiomics signatures extracted from PET/CT images could provide complementary prediction information compared with traditional model.
Objective
This study aimed to compare
68
GaGa-FAPI-04/
18
FFAPI-42 PET/CT with
18
FFDG PET/CT in the evaluation of initial gastric cancer.
Methods
We retrospectively compared
68
GaGa-FAPI-04/
18
...FFAPI-42 PET/CT with
18
FFDG PET/CT in patients with initial gastric cancer from September 2020 to March 2021. Lesion detectability and the uptake of lesions quantified by the maximum standardized uptake value (SUVmax) and target-to-background ratio (TBR) were compared between the two modalities using the Wilcoxon signed-rank test, Mann–Whitney
U
test, and McNemar’s chi-square test.
Results
A total of 61 patients (37 males, aged 23–81 years) were included, of which 22 underwent radical gastrectomy. For primary lesions, higher uptake of
68
GaGa-FAPI-04/
18
FFAPI-42 was observed compared to
18
FFDG (median SUVmax, 14.60 vs 4.35,
p <
0.001), resulting in higher positive detection using
68
GaGa-FAPI-04/
18
FFAPI-42 PET/CT than
18
FFDG PET/CT (95.1% vs 73.8%,
p <
0.001), particularly for tumors with signet-ring cell carcinoma (SRCC) (96.4% vs 57.1%,
p
< 0.001).
68
GaGa-FAPI-04/
18
FFAPI-42 PET/CT detected more positive lymph nodes than
18
FFDG PET/CT (637 vs 407). However, both modalities underestimated N staging compared to pathological N staging.
68
GaGa-FAPI-04/
18
FFAPI-42 PET/CT showed a higher sensitivity (92.3% vs 53.8%,
p
= 0.002) and peritoneal cancer index score (18 vs 3,
p
< 0.001) in peritoneum metastasis and other suspect metastases compared to
18
FFDG PET/CT.
Conclusion
Our findings indicate that
68
GaGa-FAPI-04/
18
FFAPI-42 PET/CT outperformed
18
FFDG PET/CT in the evaluation of primary tumors with SRCC and peritoneum metastasis in initial gastric cancer. However, no clinically useful improvement was seen in N staging.
Key Points
•
The uptake of
68
GaGa-FAPI-04/
18
FFAPI-42 in primary tumor and metastasis was intensely higher than that of
18
FFDG (p < 0.001) in 61 patients with initial gastric cancer
.
•
68
GaGa-FAPI-04/
18
FFAPI-42 PET/CT had a higher sensitivity detection in primary tumors (95.1% vs 73.8%, p < 0.001) and peritoneal metastases (92.3% vs 53.8%, p = 0.002) than
18
FFDG PET/CT
.
•
68
GaGa-FAPI-04/
18
FFAPI-42 PET/CT depicted more positive lymph nodes than
18
FFDG PET/CT (637 vs 407); however, both underestimated N staging compared to pathological N staging
.
Purpose
Hepatocellular carcinoma (HCC) remains one of the most challenging diseases worldwide. Glypican-3 (GPC-3) is a cell surface proteoglycan that is overexpressed on the membrane of HCC cells. ...The purpose of this study was to develop a target-specific radiofluorinated peptide for positron emission tomography (PET) imaging of GPC3 expression in hepatocellular carcinoma.
Procedures
New GPC3-binding peptides (GP2076 and GP2633) were radiolabeled with F-18 using Al
18
FF labeling approach, and the resulting PET probes were subsequently subject to biological evaluations. A highly hydrophilic linker was incorporated into GP2633 with an aim of reducing the probe uptake in liver and increasing tumor-to-liver (T/L) contrast. Both GP2076 and GP2633 were radiolabeled using Al
18
FF chelation approach. The binding affinity, octanol/water partition coefficient, cellular uptake and efflux, and stability of both F-18 labeled peptides were tested. Tumor targeting efficacy and biodistribution of Al
18
FF-GP2076 and Al
18
FF-GP2633 were determined by PET imaging in HCC-bearing mice. Immunohistochemistry analyses were performed to compare the findings from PET scans.
Results
Al
18
FF-GP2076 and Al
18
FF-GP2633 were rapidly radiosynthesized within 20 min in excellent radiochemical purity (> 97 %). Al
18
FF-GP2633 was determined to be more hydrophilic than Al
18
FF-GP2076 in terms of octanol/water partition coefficient. Both Al
18
FF-GP2076 and Al
18
FF-GP2633 demonstrated good
in vitro
and
in vivo
stability and binding specificity to GPC3-positive HepG2 cells. For PET imaging, Al
18
FF-GP2633 exhibited enhanced uptake in HepG2 tumor (%ID/g 3.37 ± 0.35
vs.
2.13 ± 0.55,
P
= 0.031) and reduced accumulation in liver (%ID/g 1.70 ± 0.26
vs.
3.70 ± 0.98,
P
= 0.027) at 60 min post-injection (pi) as compared to Al
18
FF-GP2076, resulting in significantly improved tumor-to-liver (T/L) contrast (ratio 2.00 ± 0.18
vs.
0.59 ± 0.14,
P
= 0.0004). Higher uptake of Al
18
FF-GP2633 in GPC3-positive HepG2 tumor was observed as compared to GPC3-negative McA-RH7777 tumor (%ID/g 3.37 ± 0.35
vs.
1.64 ± 0.03,
P
= 0.001) at 60 min pi, confirming GPC3-specific accumulation of Al
18
FF-GP2633 in HepG2 tumor.
Conclusion
The results demonstrated that Al
18
FF-GP2633 is a promising probe for PET imaging of GPC3 expression in HCC. Convenient preparation, excellent GPC3 specificity in HCC, and favorable excretion profile of Al
18
FF-GP2633 warrant further investigation for clinical translation. PET imaging with a GPC3-specific probe would provide clinicians with vital diagnostic information that could have a significant impact on the management of HCC patients.
Background In the present study, we investigated the value of .sup.18F-fibroblast-activation protein inhibitor (FAPI) positron emission tomography/computed tomography (.sup.18F-FAPI-42 PET/CT) to ...preoperative evaluations of appendiceal neoplasms and management for patients. Methods This single-center retrospective clinical study, including 16 untreated and 6 treated patients, was performed from January 2022 to May 2023 at Southern Medical University Nanfang Hospital. Histopathologic examination and imaging follow-up served as the reference standard. .sup.18F-FAPI-42 PET/CT was compared to .sup.18F-fluorodeoxyglucose (.sup.18F-FDG) PET/CT and contrast-enhanced CT (CE-CT) in terms of maximal standardized uptake value (SUVmax), diagnostic efficacy and impact on treatment decisions. Results The accurate detection of primary tumors and peritoneal metastases were improved from 28.6% (4/14) and 50% (8/16) for CE-CT, and 43.8% (7/16) and 85.0% (17/20) for .sup.18F-FDG PET/CT, to 87.5% (14/16) and 100% (20/20) for .sup.18F-FAPI-42 PET/CT. Compared to .sup.18F-FDG PET/CT, .sup.18F-FAPI-42 PET/CT detected more regions infiltrated by peritoneal metastases (108 vs. 43), thus produced a higher peritoneal cancer index (PCI) score (median PCI: 12 vs. 5, P < 0.01). .sup.18F-FAPI-42 PET/CT changed the intended treatment plans in 35.7% (5/14) of patients compared to CE-CT and 25% (4/16) of patients compared to .sup.18F-FDG PET/CT but did not improve the management of patients with recurrent tumors. Conclusions The present study revealed that .sup.18F-FAPI-42 PET/CT can supplement CE-CT and .sup.18F-FDG PET/CT to provide a more accurate detection of appendiceal neoplasms and improved treatment decision making for patients. Keywords: Appendiceal neoplasm, .sup.18F-FAPI-42, Contrast-enhanced CT, .sup.18F-FDG, PET/CT