Ivan Ezhov

Ivan Ezhov

Auto-generated profile, based on publicly available information

Ivan Ezhov

Department of Informatics, Technical University of Munich, Munich, Germany

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
5 December 2022 in Nature Communications
Verified
Journal Article
Open access
PDF file
SPSarthak Pati
Sarthak Pati
Ujjwal BaidUjjwal Baid
Ujjwal Baid
BEBrandon Edwards
Brandon Edwards
MSMicah Sheller
Micah Sheller
SWShih-Han Wang
Shih-Han Wang
Spyridon BakasSpyridon Bakas
Spyridon Bakas
Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.

1 May 2023 in Machine Learning for Biomedical Imaging
Verified
Journal Article
Open access
PDF file
FKFlorian Kofler
Florian Kofler
IEIvan Ezhov
Ivan Ezhov
FIFabian Isensee
Fabian Isensee
FBFabian Balsiger
Fabian Balsiger
CBChristoph Berger
Christoph Berger
BMBjoern Menze
Bjoern Menze
Metrics optimized in complex machine learning tasks are often selected in an ad-hoc manner. It is unknown how they align with human expert perception. We explore the correlations between established quantitative segmentation quality metrics and qualitative evaluations by professionally trained human raters. Therefore, we conduct psychophysical experiments for two complex biomedical semantic segmentation problems. We discover that current standard metrics and loss functions correlate only moderately with the segmentation quality assessment of experts. Importantly, this effect is particularly pronounced for clinically relevant structures, such as the enhancing tumor compartment of glioma in brain magnetic resonance and grey matter in ultrasound imaging. It is often unclear how to optimize abstract metrics, such as human expert perception, in convolutional neural network (CNN) training. To cope with this challenge, we propose a novel strategy employing techniques of classical statistics to create complementary compound loss functions to better approximate human expert perception. Across all rating experiments, human experts consistently scored computer-generated segmentations better than the human-curated reference labels. Our results, therefore, strongly question many current practices in medical image segmentation and provide meaningful cues for future research.

8 July 2025 in Nature Communications
Verified
Journal Article
Open access
PDF file
MZMaximilian Zenk
Maximilian Zenk
Ujjwal BaidUjjwal Baid
Ujjwal Baid
SPSarthak Pati
Sarthak Pati
ALAkis Linardos
Akis Linardos
BEBrandon Edwards
Brandon Edwards
Spyridon BakasSpyridon Bakas
Spyridon Bakas
Computational competitions are the standard for benchmarking medical image analysis algorithms, but they typically use small curated test datasets acquired at a few centers, leaving a gap to the reality of diverse multicentric patient data. To this end, the Federated Tumor Segmentation (FeTS) Challenge represents the paradigm for real-world algorithmic performance evaluation. The FeTS challenge is a competition to benchmark (i) federated learning aggregation algorithms and (ii) state-of-the-art segmentation algorithms, across multiple international sites. Weight aggregation and client selection techniques were compared using a multicentric brain tumor dataset in realistic federated learning simulations, yielding benefits for adaptive weight aggregation, and efficiency gains through client sampling. Quantitative performance evaluation of state-of-the-art segmentation algorithms on data distributed internationally across 32 institutions yielded good generalization on average, albeit the worst-case performance revealed data-specific modes of failure. Similar multi-site setups can help validate the real-world utility of healthcare AI algorithms in the future.

4 November 2022 in Medical Image Analysis
Verified
Journal Article
Closed access
IEIvan Ezhov
Ivan Ezhov
KSKevin Scibilia
Kevin Scibilia
KFKatharina Franitza
Katharina Franitza
FSFelix Steinbauer
Felix Steinbauer
SSSuprosanna Shit
Suprosanna Shit
BMBjoern Menze
Bjoern Menze

12 December 2024 in Medical Image Analysis
Verified
Journal Article
Closed access
RZRay Zirui Zhang
Ray Zirui Zhang
IEIvan Ezhov
Ivan Ezhov
MBMichal Balcerak
Michal Balcerak
AZAndy Zhu
Andy Zhu
BWBenedikt Wiestler
Benedikt Wiestler
JLJohn S. Lowengrub
John S. Lowengrub

20 December 2021 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
IEIvan Ezhov
Ivan Ezhov
TMTudor Mot
Tudor Mot
SSSuprosanna Shit
Suprosanna Shit
JLJana Lipkova
Jana Lipkova
JPJohannes C. Paetzold
Johannes C. Paetzold
BMBjoern Menze
Bjoern Menze
Modeling of brain tumor dynamics has the potential to advance therapeutic planning. Current modeling approaches resort to numerical solvers that simulate the tumor progression according to a given differential equation. Using highly-efficient numerical solvers, a single forward simulation takes up to a few minutes of compute. At the same time, clinical applications of tumor modeling often imply solving an inverse problem, requiring up to tens of thousands of forward model evaluations when used for a Bayesian model personalization via sampling. This results in a total inference time prohibitively expensive for clinical translation. While recent data-driven approaches become capable of emulating physics simulation, they tend to fail in generalizing over the variability of the boundary conditions imposed by the patient-specific anatomy. In this paper, we propose a learnable surrogate for simulating tumor growth which maps the biophysical model parameters directly to simulation outputs, i.e. the local tumor cell densities, whilst respecting patient geometry. We test the neural solver in a Bayesian model personalization task for a cohort of glioma patients. Bayesian inference using the proposed surrogate yields estimates analogous to those obtained by solving the forward model with a regular numerical solver. The near real-time computation cost renders the proposed method suitable for clinical settings. The code is available at https://github.com/IvanEz/tumor-surrogate .