MHMathieu Hatt

Mathieu Hatt

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Mathieu Hatt has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Robust automatic soft tissue flap segmentation using a challenging case-enriched nnU-Net in head and neck CT images

    by Abir Fathallah, Zacharia Mesbah, Alice Blache, Romain Mony, Arnaud Beddok, Jean Bourhis, Romain Modzelewski, Mathieu Hatt, Juliette Thariat

    Reconstructive surgery with a flap makes the definition of postoperative radiotherapy volumes challenging. It may also result in errors in automatic segmentation atlases of organ-at-risk and nodal volumes. Automating flap segmentation process could assist clinicians in planning radiotherapy and enable characterization of flap evolution over time and after radiotherapy. Flaps vary significantly in shape, volumes and associated artefacts. We therefore enriched a previously built training dataset with challenging cases to obtain a more robust real-world flap segmentation. Within the framework of the state-of-the-art nnU-Net deep learning architecture, we investigated whether constructing a training dataset with enhanced representation of challenging cases, often associated with poor segmentation performance or outright failures, could improve the overall accuracy and robustness of automated flap segmentation, based on Dice scores compared through paired Wilcoxon signed-rank tests. Clinical trial and real-world data were selected to increase the heterogeneity and enrich the training set with rare challenging cases (such as pedicled flaps, small flaps, unusual location including maxillary flaps, bone resection, presence of dental artefacts or bite block). This enriched training dataset led to improved performance of the nnU-Net model, increasing the mean Dice scores from 0.66 ± 0.29 to 0.74 ± 0.20 (p < 0.001), with median Dice scores rising from 0.76 to 0.80. Robust flap segmentation was achieved without modifying the neural network architecture, loss function, or algorithmic structure, through enrichment of the training set with anatomically and visually challenging cases. This model can be used for detailed analysis of geometrical and textural flap changes over time.


  • Open Access

    Accurate Tumor Delineation vs. Rough Volume of Interest Analysis for 18F-FDG PET/CT Radiomics-Based Prognostic Modeling inNon-Small Cell Lung Cancer

    by Shima Sepehri, Olena Tankyevych, Andrei Iantsen, Dimitris Visvikis, Mathieu Hatt, Catherine Cheze Le Rest

    Background: The 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.Methods: A 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.Results: Overall, 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).Conclusion: Our 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.


  • Open Access

    Comparison and Fusion of Machine Learning Algorithms for Prospective Validation of PET/CT Radiomic Features Prognostic Value in Stage II-III Non-Small Cell Lung Cancer

    by Shima Sepehri, Olena Tankyevych, Taman Upadhaya, Dimitris Visvikis, Mathieu Hatt, Catherine Cheze Le Rest

    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.


  • Open Access

    Responsible Radiomics Research for Faster Clinical Translation

    by Martin Vallières, Alex Zwanenburg, Bodgan Badic, Catherine Cheze Le Rest, Dimitris Visvikis, Mathieu Hatt


  • 18F-FDG PET/CT heterogeneity quantification through textural features in the era of harmonisation programs: a focus on lung cancer

    by Charline Lasnon, Mohamed Majdoub, Brice Lavigne, Pascal Do, Jeannick Madelaine, Dimitris Visvikis, Mathieu Hatt, Nicolas Aide

    Purpose Quantification of tumour heterogeneity in PET images has recently gained interest, but has been shown to be dependent on image reconstruction. This study aimed to evaluate the impact of the EANM/EARL accreditation program on selected 18F-FDG heterogeneity metrics. Methods To carry out our study, we prospectively analysed 71 tumours in 60 biopsy-proven lung cancer patient acquisitions reconstructed with unfiltered point spread function (PSF) positron emission tomography (PET) images (optimised for diagnostic purposes), PSF-reconstructed images with a 7-mm Gaussian filter (PSF7) chosen to meet European Association of Nuclear Medicine (EANM) 1.0 harmonising standards, and EANM Research Ltd. (EARL)-compliant ordered subset expectation maximisation (OSEM) images. Delineation was performed with fuzzy locally adaptive Bayesian (FLAB) algorithm on PSF images and reported on PSF7 and OSEM ones, and with a 50 % standardised uptake values (SUV)max threshold (SUVmax50%) applied independently to each image. Robust and repeatable heterogeneity metrics including 1st-order [area under the curve of the cumulative histogram (CHAUC)], 2nd-order (entropy, correlation, and dissimilarity), and 3rd-order [high-intensity larger area emphasis (HILAE) and zone percentage (ZP)] textural features (TF) were statistically compared. Results Volumes obtained with SUVmax50% were significantly smaller than FLAB-derived ones, and were significantly smaller in PSF images compared to OSEM and PSF7 images. PSF-reconstructed images showed significantly higher SUVmax and SUVmean values, as well as heterogeneity for CHAUC, dissimilarity, correlation, and HILAE, and a wider range of heterogeneity values than OSEM images for most of the metrics considered, especially when analysing larger tumours. Histological subtypes had no impact on TF distribution. No significant difference was observed between any of the considered metrics (SUV or heterogeneity features) that we extracted from OSEM and PSF7 reconstructions. Furthermore, the distributions of TF for OSEM and PSF7 reconstructions according to tumour volumes were similar for all ranges of volumes. Conclusion PSF reconstruction with Gaussian filtering chosen to meet harmonising standards resulted in similar SUV values and heterogeneity information as compared to OSEM images, which validates its use within the harmonisation strategy context. However, unfiltered PSF-reconstructed images also showed higher heterogeneity according to some metrics, as well as a wider range of heterogeneity values than OSEM images for most of the metrics considered, especially when analysing larger tumours. This suggests that, whenever available, unfiltered PSF images should also be exploited to obtain the most discriminative quantitative heterogeneity features.