Accurate FDG PET tumor segmentation using the peritumoral halo layer method: a study in patients with esophageal squamous cell carcinoma

Predictive value of tumoral and peritumoral radiomic features in neoadjuvant chemotherapy response for breast cancer: a retrospective study

BACKGROUND

Neoadjuvant chemotherapy (NACT) improves surgical outcomes for breast cancer patients, with pathologic complete response (pCR) correlated with enhanced survival. The role of radiomics, particularly from peritumoral tissue, in predicting pCR remains under investigation.

METHODS

This retrospective study analyzed radiomic features from pretreatment dynamic contrast-enhanced breast MRI scans of 150 patients undergoing NACT. A proportional approach was used to define peritumoral zones, assessed both with a 10% and 30% extension, allowing more standardized assessments relative to the tumor size. Radiomic features were evaluated alongside clinical and biological data to predict pCR. The association of clinical/biological and radiomic features with pCR to NACT was evaluated using univariate and multivariate analysis, logistic regression, and a random forest model. A clinical/biological model, a radiomic model, and a combined clinical/biological and 4 radiomic models for predicting the response to NACT were constructed. Area under the curve (AUC) and 95% confidence intervals (CIs) were used to assess the performance of the models.

RESULTS

Ninety-five patients (average age 47 years) were finally included. HER2 + , basal-like molecular subtypes, and a high level of Ki67 (≥ 20%) were associated with a higher likelihood of pCR to NACT. The combined clinical-biological-radiomic model, especially with a 10% peritumoral extension, showed improved predictive accuracy (AUC 0.76, CI 0.65-0.85) compared to models using clinical-biological data alone (AUC 0.73, CI 0.63-0.83).

CONCLUSIONS

Integrating peritumoral radiomic features with clinical and biological data enhances the prediction of pCR to NACT, underscoring the potential of a multifaceted approach in treatment personalization.

Tc-99m DMSA SPECT for Follow-Up of Non-Operative Treatments in Renal Injuries: A Prospective Single-Center Study

OBJECTIVE

The assessment of cortical integrity following renal injuries with planar Tc-99m dimercaptosuccinic acid (DMSA) scintigraphy depends on measuring relatively decreased cortical uptake (i.e., split renal function [SRF]). We analyzed the additive values of the volumetric and quantitative analyses of the residual cortical integrity using single-photon emission computed tomography (SPECT) compared to the planar scintigraphy.

MATERIALS AND METHODS

This prospective study included 47 patients (male:female, 32:15; age, 47 ± 22 years) who had non-operatively managed renal injuries and underwent DMSA planar and SPECT imaging 3-6 months after the index injury. In addition to planar SRF, SPECT SRF, cortical volume, and absolute cortical uptake were measured for the injured kidney and both kidneys together. The correlations of planar SRF with SPECT SRF and those of SRF with volumetric/quantitative parameters obtained with SPECT were analyzed. The association of SPECT parameters with renal function, grades of renal injuries, and the risk of renal failure was also analyzed.

RESULTS

SPECT SRF was significantly lower than planar SRF, with particularly higher biases in severe renal injuries. Planar and SPECT SRF (dichotomized with a cutoff of 45%) showed 19%-36% of discrepancies with volumetric and quantitative DMSA indices (when dichotomized as either high or low). Absolute cortical uptake of the injured kidney best correlated with glomerular filtration rate (GFR) at follow-up (ρ = 0.687, P < 0.001) with significant stepwise decreases by GFR strata (90 and 60 mL/min/1.73 m²). Total renal cortical uptake was significantly lower in patients with moderate-to-high risk of renal failure than those with low risk. However, SRF did not reflect GFR decrease below 60 mL/min/1.73 m² or the risk of renal failure, regardless of planar or SPECT (count- or volume-based SRF) imaging.

CONCLUSION

Quantitative measurements of renal cortical integrity assessed with DMSA SPECT can provide more clinically relevant and comprehensive information than planar imaging or SRF alone.

Prediction of Microsatellite Instability in Colorectal Cancer Using a Machine Learning Model Based on PET/CT Radiomics

PURPOSE

We investigated the feasibility of preoperative ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography (PET)/computed tomography (CT) radiomics with machine learning to predict microsatellite instability (MSI) status in colorectal cancer (CRC) patients.

MATERIALS AND METHODS

Altogether, 233 patients with CRC who underwent preoperative FDG PET/CT were enrolled and divided into training (n=139) and test (n=94) sets. A PET-based radiomics signature (rad_score) was established to predict the MSI status in patients with CRC. The predictive ability of the rad_score was evaluated using the area under the receiver operating characteristic curve (AUROC) in the test set. A logistic regression model was used to determine whether the rad_score was an independent predictor of MSI status in CRC. The predictive performance of rad_score was compared with conventional PET parameters.

RESULTS

The incidence of MSI-high was 15 (10.8%) and 10 (10.6%) in the training and test sets, respectively. The rad_score was constructed based on the two radiomic features and showed similar AUROC values for predicting MSI status in the training and test sets (0.815 and 0.867, respectively; p=0.490). Logistic regression analysis revealed that the rad_score was an independent predictor of MSI status in the training set. The rad_score performed better than metabolic tumor volume when assessed using the AUROC (0.867 vs. 0.794, p=0.015).

CONCLUSION

Our predictive model incorporating PET radiomic features successfully identified the MSI status of CRC, and it also showed better performance than the conventional PET image parameters.

Prognostic value of fibroblast activation protein expressing tumor volume calculated from [68 Ga]Ga-FAPI PET/CT in patients with esophageal squamous cell carcinoma

BACKGROUND

This study aimed to investigate the prognostic value of semiquantitative parameters derived from [68 Ga]Ga-fibroblast activation protein inhibitor (FAPI) PET/CT for patients with esophageal squamous cell carcinoma (ESCC) treated with definitive chemoradiotherapy.

METHODS

We conducted a retrospective analysis on patients from a prospective parent study (NCT04416165). A total of 45 patients with locally advanced ESCC who underwent [68 Ga]Ga-FAPI from December 2019 to March 2021 were included. The maximum standard uptake value (SUVmax), gross tumor volume (GTV), and total lesion-FAPI (TL-FAPI) of the primary tumor were calculated from the corresponding PET/CT image. Unpaired parameters were compared using Student's t test or the Mann-Whitney U test. Paired parameters were compared using the paired t test or the Wilcoxon matched-pairs signed-rank test. Kaplan-Meier curves were generated to calculate progression-free survival (PFS) and overall survival (OS) rates, and Cox regression analysis was performed to determine which PET/CT parameters were prognostic factors for PFS and/or OS.

RESULTS

Thirty-four of the 45 patients met the criteria, and the median follow-up time was 24 months (16-29 months). SUVmax-FAPI, GTVFAPI, and TL-FAPI in patients with stage T4 tumors were significantly higher than those in patients with stage T2/T3 tumors (all P < 0.01). In the univariate Cox regression analysis, T stage, N stage, GTVFAPI, and TL-FAPI were associated with PFS, and T stage, GTVFAPI, and TL-FAPI were associated with OS. Upon multivariable analysis, GTVFAPI was an independent prognostic factor for both PFS (hazard ratio (HR), 5.76; 95% confidence interval (CI), 2.13-15.57, P = 0.001) and OS (HR, 4.96; 95% CI, 2.55-18.79, P = 0.001).

CONCLUSION

This pilot study revealed that [68 Ga]Ga-FAPI PET/CT may have prognostic value for patients with ESCC treated with definitive chemoradiotherapy. It may aid in personalized patient management by steering treatment modifications before therapy. Prospective studies with larger samples and longer observation periods are needed.

Positron emission tomography/computed tomography using 2-deoxy-2-fluoro-18-fluoro-D-glucose peri-tumoral halo uptake layer method outperforms magnetic resonance imaging and ultrasound methods in tumor size measurement of breast cancer

As a non-invasive method, positron emission tomography (PET)/computed tomography (CT) using 2-deoxy-2-fluoro-18-fluoro-D-glucose (18F-FDG) is applied as a useful modality in the diagnosis of breast cancer. By evaluating glucose metabolism, this method can also be used in staging, restaging and post-therapeutic response evaluation. To evaluate the reliability of the ¹⁸F-FDG PET/CT-based peri-tumoral halo uptake layer (PHL) method for assessing tumor size, a total of 79 female patients with breast cancer who underwent ¹⁸F-FDG PET/CT, breast ultrasound and magnetic resonance imaging (MRI) evaluations were included in the present study. Upon examination by two independent nuclear medicine radiologists, tumor sizes were estimated by ¹⁸F-FDG PET/CT using margins defined as the inner line of the PHL. Pathological tumor sizes were evaluated on the direction of largest diameter indicated by previous imaging examination, which were also utilized as final standards. Statistical analysis of the results suggested that ¹⁸F-FDG PET/CT had a more linear correlation with pathology compared with breast ultrasound (r²=0.89 vs. 0.73) and MRI (r²=0.89 vs. 0.69) in terms of tumor size estimation, including a significantly lower bias in size difference relative to pathology. ¹⁸F-FDG PET/CT also exhibited improved performance compared with breast ultrasound and MRI in T stage assessment. These results indicated that the ¹⁸F-FDG PET/CT-based PHL method was superior to breast ultrasound and MRI, and that it provides sufficient reliability and high accuracy for measuring tumor size in patients with breast cancer.