Preoperative MRI radiomic analysis for predicting local tumor progression in colorectal liver metastases before microwave ablation.

PURPOSE: 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). METHODS: 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. RESULTS: 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, p = 0.0001). Both RAD-T1 and RAD-T2 were able to predict LTPFS: (RAD-T1: AUC = 0.83, p = 0.0003; RAD-T2: AUC = 0.79, p = 0.001). Combined models yielded the strongest performance (COMB-T1: AUC = 0.98, p = 0.0001; COMB-T2: AUC = 0.95, p = 0.0003). Both combined models included MAMs and tumor regression grade; COMB-T1 also featured 10th percentile of signal intensity, while tumor flatness was present in COMB-T2. CONCLUSION: 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.

Comparing Performances of Predictive Models of Toxicity after Radiotherapy for Breast Cancer Using Different Machine Learning Approaches.

PURPOSE: Different ML models were compared to predict toxicity in RT on a large cohort (n = 1314). METHODS: 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 p-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. RESULTS: 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). CONCLUSIONS: 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.

Skin dose-volume predictors of moderate-severe late side effects after whole breast radiotherapy.

BACKGROUND: Toxicity after whole breast Radiotherapy is a relevant issue, impacting the quality-of-life of a not negligible number of patients. We aimed to develop a Normal Tissue Complication Probability (NTCP) model predicting late toxicities by combining dosimetric parameters of the breast dermis and clinical factors. METHODS: The skin structure was defined as the outer CT body contour's 5 mm inner isotropic expansion. It was retrospectively segmented on a large mono-institutional cohort of early-stage breast cancer patients enrolled between 2009 and 2017 (n = 1066). Patients were treated with tangential-field RT, delivering 40 Gy in 15 fractions to the whole breast. Toxicity was reported during Follow-Up (FU) using SOMA/LENT scoring. The study endpoint was moderate-severe late side effects consisting of Fibrosis-Atrophy-Telangiectasia-Pain (FATP G ≥ 2) developed within 42 months after RT completion. A machine learning pipeline was designed with a logistic model combining clinical factors and absolute skin DVH (cc) parameters as output. RESULTS: The FATP G2 + rate was 3.8 %, with 40/1066 patients experiencing side effects. After the preprocessing of variables, a cross-validation was applied to define the best-performing model. We selected a 4-variable model with Post-Surgery Cosmetic alterations (Odds Ratio, OR = 7.3), Aromatase Inhibitors (as a protective factor with OR = 0.45), V20 Gy (50 % of the prescribed dose, OR = 1.02), and V42 Gy (105 %, OR = 1.09). Factors were also converted into an adjusted V20Gy. CONCLUSIONS: The association between late reactions and skin DVH when delivering 40 Gy/15 fr was quantified, suggesting an independent role of V20 and V42. Few clinical factors heavily modulate the risk.

Real-world validation of Artificial Intelligence-based Computed Tomography auto-contouring for prostate cancer radiotherapy planning.

Background and purpose: Artificial Intelligence (AI)-based auto-contouring for treatment planning in radiotherapy needs extensive clinical validation, including the impact of editing after automatic segmentation. The aims of this study were to assess the performance of a commercial system for Clinical Target Volumes (CTVs) (prostate/seminal vesicles) and selected Organs at Risk (OARs) (rectum/bladder/femoral heads + femurs), evaluating also inter-observer variability (manual vs automatic + editing) and the reduction of contouring time. Materials and methods: Two expert observers contoured CTVs/OARs of 20 patients in our Treatment Planning System (TPS). Computed Tomography (CT) images were sent to the automatic contouring workstation: automatic contours were generated and sent back to TPS, where observers could edit them if necessary. Inter- and intra-observer consistency was estimated using Dice Similarity Coefficients (DSC). Radiation oncologists were also asked to score the quality of automatic contours, ranging from 1 (complete re-contouring) to 5 (no editing). Contouring times (manual vs automatic + edit) were compared. Results: DSCs (manual vs automatic only) were consistent with inter-observer variability (between 0.65 for seminal vesicles and 0.94 for bladder); editing further improved performances (range: 0.76-0.94). The median clinical score was 4 (little editing) and it was <4 in 3/2 patients for the two observers respectively. Inter-observer variability of automatic + editing contours improved significantly, being lower than manual contouring (e.g.: seminal vesicles: 0.83vs0.73; prostate: 0.86vs0.83; rectum: 0.96vs0.81). Oncologist contouring time reduced from 17 to 24 min of manual contouring time to 3-7 min of editing time for the two observers (p < 0.01). Conclusion: Automatic contouring with a commercial AI-based system followed by editing can replace manual contouring, resulting in significantly reduced time for segmentation and better consistency between operators.

Limited impact of discretization/interpolation parameters on the predictive power of CT radiomic features in a surgical cohort of pancreatic cancer patients.

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 mm3) 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.

Prediction of the characteristics of aggressiveness of pancreatic neuroendocrine neoplasms (PanNENs) based on CT radiomic features.

OBJECTIVES: To predict tumor grade (G1 vs. G2/3), presence of distant metastasis (M+), metastatic lymph nodes (N+), and microvascular invasion (VI) of pancreatic neuroendocrine neoplasms (PanNEN) based on preoperative CT radiomic features (RFs), by applying a machine learning approach aimed to limit overfit. METHODS: This retrospective study included 101 patients who underwent surgery for PanNEN; the entire population was split into training (n = 70) and validation cohort (n = 31). Based on a previously validated methodology, after tumor segmentation on contrast-enhanced CT, RFs were extracted from unenhanced CT images. In addition, conventional radiological and clinical features were combined with RFs into multivariate logistic regression models using minimum redundancy and a bootstrap-based machine learning approach. For each endpoint, models were trained and validated including only RFs (RF_model), and both (radiomic and clinicoradiological) features (COMB_model). RESULTS: Twenty-five patients had G2/G3 tumor, 37 N+, and 14 M+ and 38 were shown to have VI. From a total of 182 RFs initially extracted, few independent radiomic and clinicoradiological features were identified. For M+ and G, the resulting models showed moderate to high performances: areas under the curve (AUC) for training/validation cohorts were 0.85/0.77 (RF_model) and 0.81/0.81 (COMB_model) for M+ and 0.67/0.72 and 0.68/0.70 for G. Concerning N+ and VI, only the COMB_model could be built, with poorer performance for N+ (AUC = 0.72/0.61) compared to VI (0.82/0.75). For all endpoints, the negative predictive value was good (≥ 0.75). CONCLUSIONS: Combining few radiomic and clinicoradiological features resulted in presurgical prediction of histological characteristics of PanNENs. Despite the limited risk of overfit, external validations are warranted. KEY POINTS: • Histology is the only tool currently available allowing characterization of PanNEN biological characteristics important for prognostic assessment; significant limitations to this approach exist. • Based upon preoperative contrast-enhanced CT images, a machine learning approach optimized to favor models' generalizability was successfully applied to train predictive models for tumor grading (G1 vs. G2/3), microvascular invasion, metastatic lymph nodes, and distant metastatic spread. • Moderate to high discriminative models (AUC: 0.67-0.85) based on few parameters (≤ 3) showing high negative predictive value (0.75-0.98) were generated and then successfully validated.

Measurement of leaf lamina moisture with a low-cost electrical humidity sensor: case study on a wheat water-mutant.

BACKGROUND: The presence and persistence of water on the leaf can affect crop performance and thus might be a relevant trait to select for or against in breeding programmes. Low-cost, rapid and relatively simple methods are of significant importance for screening of large populations of plants for moisture analysis of detached leaves. Leaf moisture can be detected using an electric circuit, where the resistance changes are proportional to the moisture of the measured surface. In this study, we present a protocol to analyse genotypic differences through the electrical properties of living or stored tissues, performed using a commercial device. Expanded and non-expanded leaves were compared to determine the effects of leaf maturity on these data. Two wheat genotypes that differ in tissue affinity for bound water were used to define the influence of water status. RESULTS: The device indirectly estimates leaf moisture content using two electrodes applied to the leaf lamina of fresh and stored samples. Single moisture readings using this moisture meter had mean execution time of ~ 1.0 min. Exponential associations provided good fits for relationships between the moisture meter reading (MMR) and the electrical resistance applied to the electrodes. MMR normalised for the water/ dry matter ratio (MMRnorm) was lower for mature leaves of the water-mutant than those of wild-type, for the fully hydrated fresh leaves. MMR of fully mature leaves when partially dehydrated and measured after 10 min at 27 °C and 40% relative humidity was greater for the water-mutant than the wild-type. CONCLUSIONS: This case study provides a low-cost tool to compare electrical-resistance estimates of leaf moisture content, together with a promising and rapid phenotyping protocol for genotypic screening of wheat under standard environmental conditions. Measurement of changes in MMR with time, of fresh and partially dehydrated leaves, or of MMR normalised to tissue water content allowed for differentiation between the genotypes. Furthermore, the differences observed between genotypes that here relate particular to tissue affinity for bound water suggest that not only the free-water fraction, but also other water fractions, can affect these electrically estimated leaf moisture measures.