yvan gomez

Dr. yvan gomez


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 January 2026 in Medical Image Analysis
Verified
Journal Article
Open access
VZVladyslav Zalevskyi
Vladyslav Zalevskyi
TSThomas Sanchez
Thomas Sanchez
MKMisha Kaandorp
Misha Kaandorp
MRMargaux Roulet
Margaux Roulet
DFDiego Fajardo-Rojas
Diego Fajardo-Rojas
MCMeritxell Bach Cuadra
Meritxell Bach Cuadra
Accurate fetal brain tissue segmentation and biometric measurement are essential for monitoring neurodevelopment and detecting abnormalities in utero. The Fetal Tissue Annotation (FeTA) Challenges have established robust multi-center benchmarks for evaluating state-of-the-art segmentation methods. This paper presents the results of the 2024 challenge edition, which introduced three key innovations. First, we introduced a topology-aware metric based on the Euler characteristic difference (ED) to overcome the performance plateau observed with traditional metrics like Dice or Hausdorff distance (HD), as the performance of the best models in segmentation surpassed the inter-rater variability. While the best teams reached similar scores in Dice (0.81-0.82) and HD95 (2.1-2.3 mm), ED provided greater discriminative power: the winning method achieved an ED of 20.9, representing roughly a 50% improvement over the second- and third-ranked teams despite comparable Dice scores. Second, we introduced a new 0.55T low-field MRI test set, which, when paired with high-quality super-resolution reconstruction, achieved the highest segmentation performance across all test cohorts (Dice=0.86, HD95=1.69, ED=6.26). This provides the first quantitative evidence that low-cost, low-field MRI can match or surpass high-field systems in automated fetal brain segmentation. Third, the new biometry estimation task exposed a clear performance gap: although the best model reached a mean average percentage error (MAPE) of 7.72%, most submissions failed to outperform a simple gestational-age-based linear regression model (MAPE=9.56%), and all remained above inter-rater variability with a MAPE of 5.38%. Finally, by analyzing the top-performing models from FeTA 2024 alongside those from previous challenge editions, we identify ensembles of 3D nnU-Net trained on both real and synthetic data with both image- and anatomy-level augmentations as the most effective approaches for fetal brain segmentation. Our quantitative analysis reveals that acquisition site, super-resolution strategy, and image quality are the primary sources of domain shift, informing recommendations to enhance the robustness and generalizability of automated fetal brain analysis methods.

15 November 2021 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
YGyvan gomez
yvan gomez
Vincent BALAYAVincent BALAYA
Vincent BALAYA
KLKarine Lepigeon
Karine Lepigeon
PMPatrice Mathevet
Patrice Mathevet
MJMartine Jacot-Guillarmod
Martine Jacot-Guillarmod
Objective: The aim of this study was to describe the evolution of high-grade cervical dysplasia during pregnancy and the postpartum period and to determine factors associated with dysplasia regression. Methods: Pregnant patients diagnosed with high-grade lesions were identified in our tertiary hospital center. High-grade lesions were defined either cytologically, by high squamous intraepithelial lesion/atypical squamous cells being unable to exclude HSIL (HSIL/ASC-H), or histologically, with cervical intraepithelial neoplasia (CIN) 2+ (all CIN 2 and CIN 3) during pregnancy. Postpartum regression was defined cytologically or histologically by at least a one-degree reduction in severity from the antepartum diagnosis. A logistic regression model was applied to determine independent predictive factors for high-grade cervical dysplasia regression after delivery. Results: Between January 2000 and October 2017, 79 patients fulfilled the inclusion criteria and were analyzed. High-grade cervical lesions were diagnosed by cytology in 87% of cases (69/79) and confirmed by histology in 45% of those (31/69). The overall regression rate in our cohort was 43% (34/79). Univariate analysis revealed that parity (p = 0.04), diabetes (p = 0.04) and third trimester cytology (p = 0.009) were associated with dysplasia regression. Nulliparity (OR = 4.35; 95%CI = (1.03–18.42); p= 0.046) was identified by multivariate analysis as an independent predictive factor of high-grade dysplasia regression. The presence of HSIL on third-trimester cervical cytology (OR = 0.17; 95%CI = (0.04–0.72); p = 0.016) was identified as an independent predictive factor of high-grade dysplasia persistence at postpartum. Conclusion: Our regression rate was high, at 43%, for high-grade cervical lesions postpartum. Parity status may have an impact on dysplasia regression during pregnancy. A cervical cytology should be performed at the third trimester to identify patients at risk of CIN persistence after delivery. However, larger cohorts are required to confirm these results.

1 August 2025 in Molecular Neurobiology
Verified
Journal Article
Open access
PDF file
Laia Guardia-EscoteLaia Guardia-Escote
Laia Guardia-Escote
YGyvan gomez
yvan gomez
MFMercè Fuentes-Amell
Mercè Fuentes-Amell
CRCarlota Rovira
Carlota Rovira
EGEduard Gratacos
Eduard Gratacos
MIMiriam Illa
Miriam Illa
Intrauterine growth restriction (IUGR) is a condition in which the fetus fails to reach its genetic growth potential, often resulting in neurodevelopmental alterations. This study investigates the neuroprotective potential of gestational melatonin (MEL) treatment using an IUGR rabbit model. IUGR was induced by ligating the uteroplacental vessels of one uterine horn in pregnant rabbits, using the other horn as the control (CNT). Dams received either placebo (PLA) or MEL from gestational day 25 to 30, when pups were delivered by cesarean section. We performed a functional evaluation, followed by placental histopathology, oligodendrocyte quantification, neuronal arborization, and DAB (3, 3'-diaminobenzidine) staining of MEL receptors in the brain. IUGR groups exhibited significantly lower body weights and survival rates than CNTs, confirming successful model induction. Placental analysis indicated higher phase 2 ischemia in IUGR than CNTs, and reduced calcifications in MEL-treated groups. Brain analysis showed fewer oligodendrocytes and MEL receptors in PLA-treated IUGR groups compared to CNTs, partially reversed by MEL treatment. A dual response to MEL was observed in several endpoints, with beneficial effects on IUGR and detrimental effects on CNT groups. In conclusion, MEL demonstrates beneficial effects on the IUGR brain, particularly by increasing oligodendrocyte numbers, but its detrimental effects in CNT groups warrant caution in healthy pregnancies. These results indicate that substances can act as both therapeutic and toxic agents depending on physiological context, underscoring the need for further research to understand MEL’s mechanisms and optimize treatment strategies.