Search

Abstract The primary objective of the present study was to identify a subset of radiomic features extracted from primary tumor imaged by computed tomography of early-stage non-small cell lung cancer patients, which remain unaffected by variations in segmentation quality and in computed tomography image acquisition protocol. The robustness of these features to segmentation variations was assessed by analyzing the correlation of feature values extracted from lesion volumes delineated by two annotators. The robustness to variations in acquisition protocol was evaluated by examining the correlation of features extracted from high-dose and low-dose computed tomography scans, both of which were acquired for each patient as part of the stereotactic body radiotherapy planning process. Among 106 radiomic features considered, 21 were identified as robust. An analysis including univariate and multivariate assessments was subsequently conducted to estimate the predictive performance of these robust features on the outcome of early-stage non-small cell lung cancer patients treated with stereotactic body radiation therapy. The univariate predictive analysis revealed that robust features demonstrated superior predictive potential compared to non-robust features. The multivariate analysis indicated that linear regression models built with robust features displayed greater generalization capabilities by outperforming other models in predicting the outcomes of an external validation dataset.

Abstract This study aims to develop a robust pipeline for classifying invasive ductal carcinomas and benign tumors in histopathological images, addressing variability within and between centers. We specifically tackle the challenge of detecting atypical data and variability between common clusters within the same database. Our feature engineering-based pipeline comprises a feature extraction step, followed by multiple harmonization techniques to rectify intra- and inter-center batch effects resulting from image acquisition variability and diverse patient clinical characteristics. These harmonization steps facilitate the construction of more robust and efficient models. We assess the proposed pipeline’s performance on two public breast cancer databases, BreaKHIS and IDCDB, utilizing recall, precision, and accuracy metrics. Our pipeline outperforms recent models, achieving 90-95% accuracy in classifying benign and malignant tumors. We demonstrate the advantage of harmonization for classifying patches from different databases. Our top model scored 94.7% for IDCDB and 95.2% for BreaKHis, surpassing existing feature engineering-based models (92.1% for IDCDB and 87.7% for BreaKHIS) and attaining comparable performance to deep learning models. The proposed feature-engineering-based pipeline effectively classifies malignant and benign tumors while addressing variability within and between centers through the incorporation of various harmonization techniques. Our findings reveal that harmonizing variabilities between patches from different batches directly impacts the learning and testing performance of classification models. This pipeline has the potential to enhance breast cancer diagnosis and treatment and may be applicable to other diseases.

BackgroundThe aim of this work was to investigate the ability of building prognostic models in non-small cell lung cancer (NSCLC) using radiomic features from positron emission tomography and computed tomography with 2-deoxy-2-[fluorine-18]fluoro-d-glucose (18F-FDG PET/CT) images based on a “rough” volume of interest (VOI) containing the tumor instead of its accurate delineation, which is a significant time-consuming bottleneck of radiomics analyses.MethodsA cohort of 138 patients with stage II–III NSCLC treated with radiochemotherapy recruited retrospectively (n = 87) and prospectively (n = 51) was used. Two approaches were compared: firstly, the radiomic features were extracted from the delineated primary tumor volumes in both PET (using the automated fuzzy locally adaptive Bayesian, FLAB) and CT (using a semi-automated approach with 3D Slicer™) components. Both delineations were carried out within previously manually defined “rough” VOIs containing the tumor and the surrounding tissues, which were exploited for the second approach: the same features were extracted from this alternative VOI. Both sets for features were then combined with the clinical variables and processed through the same machine learning (ML) pipelines using the retrospectively recruited patients as the training set and the prospectively recruited patients as the testing set. Logistic regression (LR), random forest (RF), and support vector machine (SVM), as well as their consensus through averaging the output probabilities, were considered for feature selection and modeling for overall survival (OS) prediction as a binary classification (either median OS or 6 months OS). The resulting models were compared in terms of balanced accuracy, sensitivity, and specificity.ResultsOverall, better performance was achieved using the features from delineated tumor volumes. This was observed consistently across ML algorithms and for the two clinical endpoints. However, the loss of performance was not significant, especially when a consensus of the three ML algorithms was considered (0.89 vs. 0.88 and 0.78 vs. 0.77).ConclusionOur findings suggest that it is feasible to achieve similar levels of prognostic accuracy in radiomics-based modeling by relying on a faster and easier VOI definition, skipping a time-consuming tumor delineation step, thus facilitating automation of the whole radiomics workflow. The associated cost is a loss of performance in the resulting models, although this loss can be greatly mitigated when a consensus of several models is relied upon.

PurposeTo facilitate the demonstration of the prognostic value of radiomics, multicenter radiomics studies are needed. Pooling radiomic features of such data in a statistical analysis is however challenging, as they are sensitive to the variability in scanner models, acquisition protocols and reconstruction settings, which is often unavoidable in a multicentre retrospective analysis. A statistical harmonization strategy called ComBat was utilized in radiomics studies to deal with the "center-effect". The goal of the present work was to integrate a transfer learning (TL) technique within ComBat-and recently developed alternate versions of ComBat with improved flexibility (M-ComBat) and robustness (B-ComBat)-to allow the use of a previously determined harmonization transform to the radiomic feature values of new patients from an already known center.Material and methodsThe proposed TL approach were incorporated in the four versions of ComBat (standard, B, M, and B-M ComBat). The proposed approach was evaluated using a dataset of 189 locally advanced cervical cancer patients from 3 centers, with magnetic resonance imaging (MRI) and positron emission tomography (PET) images, with the clinical endpoint of predicting local failure. The impact performance of the TL approach was evaluated by comparing the harmonization achieved using only parts of the data to the reference (harmonization achieved using all the available data). It was performed through three different machine learning pipelines.ResultsThe proposed TL technique was successful in harmonizing features of new patients from a known center in all versions of ComBat, leading to predictive models reaching similar performance as the ones developed using the features harmonized with all the data available.ConclusionThe proposed TL approach enables applying a previously determined ComBat transform to new, previously unseen data.

Introduction: Locally advanced cervical cancer (CC) patients treated by chemoradiotherapy (CRT) have a significant local recurrence rate. The objective of this work was to assess the overlap between the initial high-uptake sub-volume (V1) on baseline 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) scans and the metabolic relapse (V2) sites after CRT in locally advanced CC.Methods: PET/CT performed before treatment and at relapse in 21 patients diagnosed with LACC and treated with CRT were retrospectively analyzed. CT images at the time of recurrence were registered to baseline CT using the 3D Slicer TM Expert Automated Registration module. The corresponding PET images were then registered using the corresponding transform. The fuzzy locally adaptive Bayesian (FLAB) algorithm was implemented using 3 classes (one for the background and the other two for tumor) in PET1 to simultaneously define an overall tumor volume and the sub-volume V1. In PET2, FLAB was implemented using 2 classes (one for background, one for tumor), in order to define V2. Four indices were used to determine the overlap between V1 and V2 (Dice coefficients, overlap fraction, X = (V1nV2)/V1 and Y = (V1nV2)/V2).Results: The mean (±standard deviation) follow-up was 26 ± 11 months. The measured overlaps between V1 and V2 were moderate to good according to the four metrics, with 0.62–0.81 (0.72 ± 0.05), 0.72–1.00 (0.85 ± 0.10), 0.55–1.00 (0.73 ± 0.16) and 0.50–1.00 (0.76 ± 0.12) for Dice, overlap fraction, X and Y, respectively.Conclusion: In our study, the overlaps between the initial high-uptake sub-volume and the recurrent metabolic volume showed moderate to good concordance. These results now need to be confirmed in a larger cohort using a more standardized patient repositioning procedure for sequential PET/CT imaging, as there is potential for RT dose escalation exploiting the pre-treatment PET high-uptake sub-volume.

Purpose: Prostatectomy is one of the main therapeutic options for prostate cancer (PCa). Studies proved the benefit of adjuvant radiotherapy (aRT) on clinical outcomes, with more toxicities when compared to salvage radiotherapy. A better assessment of the likelihood of biochemical recurrence (BCR) would rationalize performing aRT. Our goal was to assess the prognostic value of MRI-derived radiomics on BCR for PCa with high recurrence risk.Methods: We retrospectively selected patients with a high recurrence risk (T3a/b or T4 and/or R1 and/or Gleason score>7) and excluded patients with a post-operative PSA > 0.04 ng/mL or a lymph-node involvement. We extracted IBSI-compliant radiomic features (shape and first order intensity metrics, as well as second and third order textural features) from tumors delineated in T2 and ADC sequences. After random division (training and testing sets) and machine learning based feature reduction, a univariate and multivariate Cox regression analysis was performed to identify independent factors. The correlation with BCR was assessed using AUC and prediction of biochemical relapse free survival (bRFS) with a Kaplan-Meier analysis.Results: One hundred seven patients were included. With a median follow-up of 52.0 months, 17 experienced BCR. In the training set, no clinical feature was correlated with BCR. One feature from ADC (SZEGLSZM) outperformed with an AUC of 0.79 and a HR 17.9 (p = 0.0001). Lower values of SZEGLSZM are associated with more heterogeneous tumors. In the testing set, this feature remained predictive of BCR and bRFS (AUC 0.76, p = 0.0236).Conclusion: One radiomic feature was predictive of BCR and bRFS after prostatectomy helping to guide post-operative management.

Machine learning (ML) algorithms for selecting and combining radiomic features into multiparametric prediction models have become popular; however, it has been shown that large variations in performance can be obtained by relying on different approaches. The purpose of this study was to evaluate the potential benefit of combining different algorithms into an improved consensus for the final prediction, as it has been shown in other fields. Methods: The evaluation was carried out in the context of the use of radiomics from 18F-FDG PET/CT images for predicting outcome in stage II-III Non-Small Cell Lung Cancer. A cohort of 138 patients was exploited for the present analysis. Eighty-seven patients had been previously recruited retrospectively for another study and were used here for training and internal validation. We also used data from prospectively recruited patients (n = 51) for testing. Three different machine learning pipelines relying on embedded feature selection were trained to predict overall survival (OS) as a binary classification: Support Vector machines (SVMs), Random Forests (RFs), and Logistic Regression (LR). Two different clinical endpoints were investigated: median OS or OS shorter than 6 months. The fusion of the three approaches was implemented using two different strategies: majority voting on the binary outputs or averaging of the output probabilities. Results: Our results confirm previous findings, highlighting that different ML pipelines select different sets of features and reach different classification performances (accuracy in the testing set ranging between 63% and 67% for median OS, and between 75% and 80% for OS < 6 months). Generating a consensus improved the performance for both endpoints; with the probabilities averaging strategy outperforming the majority voting (accuracy of 78% vs. 71% for median OS and 89 vs. 84% for OS < 6 months). Overall, the performance of these radiomic-based models outperformed the standard clinical staging in both endpoints (accuracy of 58% and 53% accuracy in the testing set for each endpoint). Conclusion: Although obtained in a small cohort of patients, our results suggest that a consensus of machine learning algorithms can improve performance in the context of radiomics. The resulting prognostic stratification in the prospective testing cohort is higher than when relying on the clinical stage. This could be of interest for clinical practice as it could help to identify patients with higher risk amongst stage II and III patients, who could benefit from intensified treatment and/or more frequent follow-up after treatment.

MethodsThirty patients with proven colorectal cancer prospectively underwent integrated 18F-FDG PET/DCE-CT to assess the metabolic-flow phenotype. Both CT blood flow parametric maps and PET images were analyzed. Correlations between PET heterogeneity and perfusion CT were assessed by Spearman's rank correlation analysis.ResultsBlood flow visualization provided by DCE-CT images was significantly correlated with 18F-FDG PET metabolically active tumor volume as well as with uptake heterogeneity for patients with stage III/IV tumors (|ρ|:0.66 to 0.78; p-valueConclusionThe positive correlation found with tumor blood flow indicates that intra-tumor heterogeneity of 18F-FDG PET accumulation reflects to some extent tracer distribution and consequently indicates that 18F-FDG PET intra-tumor heterogeneity may be associated with physiological processes such as tumor vascularization.