Dr. Mina Rezaei Profile

Dr. Mina Rezaei

Post-doctoral Researcher

SPIE Involvement:

Author

Publications (6)

SPIE Journal Paper | 9 October 2023 Open Access

Bayesian uncertainty estimation for detection of long-tailed and unseen conditions in medical images

Mina Rezaei, Janne Näppi, Bernd Bischl, Hiroyuki Yoshida

JMI, Vol. 10, Issue 05, 054501, (October 2023) https://doi.org/10.1117/12.10.1117/1.JMI.10.5.054501

KEYWORDS: Gallium nitride, Education and training, Image segmentation, Data modeling, Semantics, Machine learning, Performance modeling, Medical imaging, Deep learning, Statistical modeling

Read Abstract +

PurposeDeep supervised learning provides an effective approach for developing robust models for various computer-aided diagnosis tasks. However, there is often an underlying assumption that the frequencies of the samples between the different classes of the training dataset are either similar or balanced. In real-world medical data, the samples of positive classes often occur too infrequently to satisfy this assumption. Thus, there is an unmet need for deep-learning systems that can automatically identify and adapt to the real-world conditions of imbalanced data.ApproachWe propose a deep Bayesian ensemble learning framework to address the representation learning problem of long-tailed and out-of-distribution (OOD) samples when training from medical images. By estimating the relative uncertainties of the input data, our framework can adapt to imbalanced data for learning generalizable classifiers. We trained and tested our framework on four public medical imaging datasets with various imbalance ratios and imaging modalities across three different learning tasks: semantic medical image segmentation, OOD detection, and in-domain generalization. We compared the performance of our framework with those of state-of-the-art comparator methods.ResultsOur proposed framework outperformed the comparator models significantly across all performance metrics (pairwise t-test: p < 0.01) in the semantic segmentation of high-resolution CT and MR images as well as in the detection of OOD samples (p < 0.01), thereby showing significant improvement in handling the associated long-tailed data distribution. The results of the in-domain generalization also indicated that our framework can enhance the prediction of retinal glaucoma, contributing to clinical decision-making processes.ConclusionsTraining of the proposed deep Bayesian ensemble learning framework with dynamic Monte-Carlo dropout and a combination of losses yielded the best generalization to unseen samples from imbalanced medical imaging datasets across different learning tasks.

DOWNLOAD PAPER

Proceedings Article | 4 April 2022 Poster + Presentation + Paper

Deep mutual GANs: representation learning from multiple experts

Mina Rezaei, Janne Näppi, Bernd Bischl, Hiroyuki Yoshida

Proceedings Volume 12037, 120370U (2022) https://doi.org/10.1117/12.2612968

KEYWORDS: Gallium nitride, Data modeling, Performance modeling, Tumor growth modeling, Medical imaging, Liver, Image segmentation, Head, Skin, Instrument modeling

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Deep variational clustering framework for self-labeling large-scale medical images

Farzin Soleymani, Mohammad Eslami, Tobias Elze, Bernd Bischl, Mina Rezaei

Proceedings Volume 12032, 120320B (2022) https://doi.org/10.1117/12.2613331

KEYWORDS: Medical imaging, Computer programming, Data modeling, Convolutional neural networks, Reconstruction algorithms, Neural networks, Machine learning, Feature extraction, Process modeling, Image processing

Read Abstract +

One of the most promising approaches for unsupervised learning is combining deep representation learning and deep clustering. Recent studies propose to simultaneously learn representation using deep neural networks and perform clustering by defining a clustering loss on top of embedded features. Unsupervised image clustering naturally requires good feature representations to capture the distribution of the data and subsequently differentiate data points from one another. Among existing deep learning models, the generative variational autoencoder explicitly learns data generating distribution in a latent space. We propose a Deep Variational Clustering (DVC) framework for unsupervised representation learning and clustering of large-scale medical images. DVC simultaneously learns the multivariate Gaussian posterior through the probabilistic convolutional encoder, and the likelihood distribution with the probabilistic convolutional decoder; and optimizes cluster labels assignment. Here, the learned multivariate Gaussian posterior captures the latent distribution of a large set of unlabeled images. Then, we perform unsupervised clustering on top of the variational latent space using a clustering loss. In this approach, the probabilistic decoder helps to prevent the distortion of data points in the latent space, and to preserve local structure of data generating distribution. The training process can be considered as a self-training process to refine the latent space and simultaneously optimizing cluster assignments iteratively. We evaluated our proposed framework on three public datasets that represented different medical imaging modalities. Our experimental results show that our proposed framework generalizes better across different datasets. It achieves compelling results on several medical imaging benchmarks. Thus, our approach offers potential advantages over conventional deep unsupervised learning in real-world applications. The source code of the method and of all the experiments are available publicly at: https://github.com/csfarzin/DVC

Proceedings Article | 4 April 2022 Presentation + Paper

Bayesian uncertainty estimation for detection of long-tail and unseen conditions in abdominal images

Mina Rezaei, Janne Näppi, Bernd Bischl, Hiroyuki Yoshida

Proceedings Volume 12033, 1203311 (2022) https://doi.org/10.1117/12.2612955

KEYWORDS: Image segmentation, Data modeling, Medical imaging, Statistical modeling, Liver, Computed tomography, Network architectures, Magnetic resonance imaging, Statistical analysis

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Generative synthetic adversarial network for internal bias correction and handling class imbalance problem in medical image diagnosis

Mina Rezaei, Tomoki Uemura, Janne Näppi, Hiroyuki Yoshida, Christoph Lippert, Christoph Meinel

Proceedings Volume 11314, 113140E (2020) https://doi.org/10.1117/12.2551166

KEYWORDS: Medical imaging, Image classification

Read Abstract +

Proceedings Article | 13 March 2019 Paper

Learning imbalanced semantic segmentation through cross-domain relations of multi-agent generative adversarial networks

Mina Rezaei, Haojin Yang, Christoph Meinel

Proceedings Volume 10950, 1095027 (2019) https://doi.org/10.1117/12.2512215

KEYWORDS: Image segmentation, Tumors, 3D image processing, Brain, Computed tomography, Magnetic resonance imaging, Medical imaging, 3D modeling, Machine learning

Read Abstract +

Showing 5 of 6 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years