Purpose
To assess the ability of radiomic features (RF) extracted from contrast-enhanced CT images (ceCT) and non-contrast-enhanced (non-ceCT) in discriminating histopathologic characteristics of ...pancreatic neuroendocrine tumors (panNET).
Methods
panNET contours were delineated on pre-surgical ceCT and non-ceCT. First- second- and higher-order RF (adjusted to eliminate redundancy) were extracted and correlated with histological panNET grade (G1 vs G2/G3), metastasis, lymph node invasion, microscopic vascular infiltration. Mann–Whitney with Bonferroni corrected
p
values assessed differences. Discriminative power of significant RF was calculated for each of the end-points. The performance of conventional-imaged-based-parameters was also compared to RF.
Results
Thirty-nine patients were included (mean age 55-years-old; 24 male). Mean diameters of the lesions were 24 × 27 mm. Sixty-nine RF were considered. Sphericity could discriminate high grade tumors (AUC = 0.79,
p
= 0.002). Tumor volume (AUC = 0.79,
p
= 0.003) and several non-ceCT and ceCT RF were able to identify microscopic vascular infiltration: voxel-alignment, neighborhood intensity-difference and intensity-size-zone families (AUC ≥ 0.75,
p
< 0.001); voxel-alignment, intensity-size-zone and co-occurrence families (AUC ≥ 0.78,
p
≤ 0.002), respectively). Non-ceCT neighborhood-intensity-difference (AUC = 0.75,
p
= 0.009) and ceCT intensity-size-zone (AUC = 0.73,
p
= 0.014) identified lymph nodal invasion; several non-ceCT and ceCT voxel-alignment family features were discriminative for metastasis (
p
< 0.01, AUC = 0.80–0.85). Conventional CT ‘necrosis’ could discriminate for microscopic vascular invasion (AUC = 0.76,
p
= 0.004) and ‘arterial vascular invasion’ for microscopic metastasis (AUC = 0.86,
p
= 0.001). No conventional-imaged-based-parameter was significantly associated with grade and lymph node invasion.
Conclusions
Radiomic features can discriminate histopathology of panNET, suggesting a role of radiomics as a non-invasive tool for tumor characterization.
Trial registration number
: NCT03967951, 30/05/2019
Radiomics may aid in predicting prognosis in patients with colorectal liver metastases (CLM). Consistent data is available on CT, yet limited data is available on MRI. This study assesses the ...capability of MRI-derived radiomic features (RFs) to predict local tumor progression-free survival (LTPFS) in patients with CLMs treated with microwave ablation (MWA).
All CLM patients with pre-operative Gadoxetic acid-MRI treated with MWA in a single institution between September 2015 and February 2022 were evaluated. Pre-procedural information was retrieved retrospectively. Two observers manually segmented CLMs on T2 and T1-Hepatobiliary phase (T1-HBP) scans. After inter-observer variability testing, 148/182 RFs showed robustness on T1-HBP, and 141/182 on T2 (ICC > 0.7).Cox multivariate analysis was run to establish clinical (CLIN-mod), radiomic (RAD-T1, RAD-T2), and combined (COMB-T1, COMB-T2) models for LTPFS prediction.
Seventy-six CLMs (43 patients) were assessed. Median follow-up was 14 months. LTP occurred in 19 lesions (25%).CLIN-mod was composed of minimal ablation margins (MAMs), intra-segment progression and primary tumor grade and exhibited moderately high discriminatory power in predicting LTPFS (AUC = 0.89,
= 0.0001). Both RAD-T1 and RAD-T2 were able to predict LTPFS: (RAD-T1: AUC = 0.83,
= 0.0003; RAD-T2: AUC = 0.79,
= 0.001). Combined models yielded the strongest performance (COMB-T1: AUC = 0.98,
= 0.0001; COMB-T2: AUC = 0.95,
= 0.0003). Both combined models included MAMs and tumor regression grade; COMB-T1 also featured 10
percentile of signal intensity, while tumor flatness was present in COMB-T2.
MRI-based radiomic evaluation of CLMs is feasible and potentially useful for LTP prediction. Combined models outperformed clinical or radiomic models alone for LTPFS prediction.
Purpose
To explore the variation of the discriminative power of CT (Computed Tomography) radiomic features (RF) against image discretization/interpolation in predicting early distant relapses (EDR) ...after upfront surgery.
Materials and methods
Data of 144 patients with pre-surgical high contrast CT were processed consistently with IBSI (Image Biomarker Standardization Initiative) guidelines. Image interpolation/discretization parameters were intentionally changed, including cubic voxel size (0.21–27 mm
3
) and binning (32–128 grey levels) in a 15 parameter’s sets. After excluding RF with poor inter-observer delineation agreement (ICC < 0.80) and not negligible inter-scanner variability, the variation of 80 RF against discretization/interpolation was first quantified. Then, their ability in classifying patients with early distant relapses (EDR, < 10 months, previously assessed at the first quartile value of time-to-relapse) was investigated in terms of AUC (Area Under Curve) variation for those RF significantly associated to EDR.
Results
Despite RF variability against discretization/interpolation parameters was large and only 30/80 RF showed %COV < 20 (%COV = 100*STDEV/MEAN), AUC changes were relatively limited: for 30 RF significantly associated with EDR (AUC values around 0.60–0.70), the mean values of SD of AUC variability and AUC range were 0.02 and 0.05 respectively. AUC ranges were between 0.00 and 0.11, with values ≤ 0.05 in 16/30 RF. These variations were further reduced when excluding the extreme values of 32 and 128 for grey levels (Average AUC range 0.04, with values between 0.00 and 0.08).
Conclusions
The discriminative power of CT RF in the prediction of EDR after upfront surgery for pancreatic cancer is relatively invariant against image interpolation/discretization within a large range of voxel sizes and binning.
Different ML models were compared to predict toxicity in RT on a large cohort (n = 1314).
The endpoint was RTOG G2/G3 acute toxicity, resulting in 204/1314 patients with the event. The dataset, ...including 25 clinical, anatomical, and dosimetric features, was split into 984 for training and 330 for internal tests. The dataset was standardized; features with a high
-value at univariate LR and with Spearman ρ>0.8 were excluded; synthesized data of the minority were generated to compensate for class imbalance. Twelve ML methods were considered. Model optimization and sequential backward selection were run to choose the best models with a parsimonious feature number. Finally, feature importance was derived for every model.
The model's performance was compared on a training-test dataset over different metrics: the best performance model was LightGBM. Logistic regression with three variables (LR3) selected via bootstrapping showed performances similar to the best-performing models. The AUC of test data is slightly above 0.65 for the best models (highest value: 0.662 with LightGBM).
No model performed the best for all metrics: more complex ML models had better performances; however, models with just three features showed performances comparable to the best models using many (n = 13-19) features.
Despite careful selection, the recurrence rate after upfront surgery for pancreatic adenocarcinoma can be very high. We aimed to construct and validate a model for the prediction of early distant ...recurrence (<12 months from index surgery) after upfront pancreaticoduodenectomy. After exclusions, 147 patients were retrospectively enrolled. Preoperative clinical and radiological (CT-based) data were systematically evaluated; moreover, 182 radiomics features (RFs) were extracted. Most significant RFs were selected using minimum redundancy, robustness against delineation uncertainty and an original machine learning bootstrap-based method. Patients were split into training (n = 94) and validation cohort (n = 53). Multivariable Cox regression analysis was first applied on the training cohort; the resulting prognostic index was then tested in the validation cohort. Clinical (serum level of CA19.9), radiological (necrosis), and radiomic (SurfAreaToVolumeRatio) features were significantly associated with the early resurge of distant recurrence. The model combining these three variables performed well in the training cohort (p = 0.0015, HR = 3.58, 95%CI = 1.98–6.71) and was then confirmed in the validation cohort (p = 0.0178, HR = 5.06, 95%CI = 1.75–14.58). The comparison of survival curves between low and high-risk patients showed a p-value <0.0001. Our model may help to better define resectability status, thus providing an actual aid for pancreatic adenocarcinoma patients’ management (upfront surgery vs. neoadjuvant chemotherapy). Independent validations are warranted.
To assess dosimetry predictors of gastric and duodenal toxicities for locally advanced pancreatic cancer (LAPC) patients treated with chemo-radiotherapy in 15 fractions.
Data from 204 LAPC patients ...treated with induction+concurrent chemotherapy and radiotherapy (44.25 Gy in 15 fractions) were available. Forty-three patients received a simultaneous integrated boost of 48-58 Gy. Gastric/duodenal Common Terminology Criteria for Adverse Events v. 5 (CTCAEv5) Grade ≥2 toxicities were analyzed. Absolute/% duodenal and stomach dose-volume histograms (DVHs) of patients with/without toxicities were compared: the most predictive DVH points were identified, and their association with toxicity was tested in univariate and multivariate logistic regressions together with near-maximum dose (D
) and selected clinical variables.
Toxicity occurred in 18 patients: 3 duodenal (ulcer and duodenitis) and 10 gastric (ulcer and stomatitis); 5/18 experienced both. At univariate analysis, V44cc (duodenum: p = 0.02, OR = 1.07; stomach: p = 0.01, OR = 1.12) and D
(p = 0.07, OR = 1.19; p = 0.008, OR = 1.12) were found to be the most predictive parameters. Stomach/duodenum V44Gy and stomach D
were confirmed at multivariate analysis and found to be sufficiently robust at internal, bootstrap-based validation; the results regarding duodenum D
were less robust. No clinical variables or %DVH was significantly associated with toxicity. The best duodenum cutoff values were V44Gy < 9.1 cc (and D
< 47.6 Gy); concerning the stomach, they were V44Gy < 2 cc and D
< 45 Gy. The identified predictors showed a high negative predictive value (>94%).
In a large cohort treated with hypofractionated radiotherapy for LAPC, the risk of duodenal/gastric toxicities was associated with duodenum/stomach DVH. Constraining duodenum V44Gy < 9.1 cc, stomach V44Gy < 2 cc, and stomach D
< 45 Gy should keep the toxicity rate at approximately or below 5%. The association with duodenum D
was not sufficiently robust due to the limited number of events, although results suggest that a limit of 45-46 Gy should be safe.
Purpose
An increase of skin dose during head and neck cancer (HNC) radiotherapy is potentially dangerous. Aim of this study was to quantify skin dose variation and to assess the need of planning ...adaptation (ART) to counteract it.
Methods
Planning CTs of 32 patients treated with helical tomotherapy (HT) according to a Simultaneous Integrated Boost (SIB) technique delivering 54/66 Gy in 30 fractions were deformably co-registered to MVCTs taken at fractions 15 and 30; in addition, the first fraction was also considered. The delivered dose-of-the-day was calculated on the corresponding deformed images. Superficial body layers (SL) were considered as a surrogate for skin, considering a layer thickness of 2 mm. Variations of SL DVH (∆SL) during therapy were quantified, focusing on ∆SL95% (i.e., 62.7 Gy).
Results
Small changes (within ± 1 cc for ∆SL95%) were seen in 15/32 patients. Only 2 patients experienced ∆SL95% > 1 cc in at least one of the two monitored fractions. Negative ∆SL95% > 1 cc (up to 17 cc) were much more common (15/32 patients). The trend of skin dose changes was mostly detected at the first fraction. Negative changes were correlated with the presence of any overlap between PTV and SL at planning and were explained in terms of how the planning system optimizes the PTV dose coverage near the skin. Acute toxicity was associated with planning DVH and this association was not improved if considering DVHs referring to fractions 15/30.
Conclusion
About half of the patients treated with SIB with HT for HNC experienced a skin-sparing effect during therapy; only 6% experienced an increase. Our findings do not support skin-sparing ART, while suggesting the introduction of improved skin-sparing planning techniques.
•The impact of delineation uncertainty on CT features (RF) was quantified for panNEN.•Data of 31 patients and 3 radiologists referred to 69 RF were analyzed.•Volume agreement was good (DICE: 0.78) ...despite the small values (median: 1.3 cc).•Intra-Class Correlation (ICC) showed very high agreement (ICC > 0.8) for 65/69 RF.•CT radiomics of panNEN is very robust with respect to delineation uncertainty.
The aim of this study was to quantify the impact of CT delineation uncertainty of pancreatic neuroendocrine neoplasms (panNEN) on Radiomic features (RF).
Thirty-one previously operated patients were considered. Three expert radiologists contoured panNEN lesions on pre-surgical high-resolution contrast-enhanced CT images and contours were transferred onto pre-contrast CT. Volume agreement was quantified by the DICE index. After images resampling and re-binning, 69 RF were extracted and the impact of inter-observer variability was assessed by Intra-Class Correlation (ICC): ICC > 0.80 was considered as a threshold for “very high” inter-observer agreement.
The median volume was 1.3 cc (range: 0.2–110 cc); a satisfactory inter-observer volume agreement was found (mean DICE = 0.78). Only 4 RF showed ICC < 0.80 (0.48–0.73), including asphericity and three RFs (of five) of the neighborhood intensity difference matrix (NID).
The impact of inter-observer variability in delineating panNEN on RF was minimum, with the exception of the NID family and asphericity, showing a moderate agreement. These results support the feasibility of studies aiming to assess CT radiomic biomarkers for panNEN.
The ongoing COVID-19 pandemic currently involves millions of people worldwide. Radiology plays an important role in the diagnosis and management of patients, and chest computed tomography (CT) is the ...most widely used imaging modality. An automatic method to characterize the lungs of COVID-19 patients based on individually optimized Hounsfield unit (HU) thresholds was developed and implemented. Lungs were considered as composed of three components—aerated, intermediate, and consolidated. Three methods based on analytic fit (Gaussian) and maximum gradient search (using polynomial and original data fits) were implemented. The methods were applied to a population of 166 patients scanned during the first wave of the pandemic. Preliminarily, the impact of the inter-scanner variability of the HU-density calibration curve was investigated. Results showed that inter-scanner variability was negligible. The median values of individual thresholds th1 (between aerated and intermediate components) were −768, −780, and −798 HU for the three methods, respectively. A significantly lower median value for th2 (between intermediate and consolidated components) was found for the maximum gradient on the data (−34 HU) compared to the other two methods (−114 and −87 HU). The maximum gradient on the data method was applied to quantify the three components in our population—the aerated, intermediate, and consolidation components showed median values of 793 ± 499 cc, 914 ± 291 cc, and 126 ± 111 cc, respectively, while the median value of the first peak was −853 ± 56 HU.