The Future Processing Healthcare team consists of researchers and software engineers. Their accomplishments include numerous academic publications and presentations at key sector conferences such as

RSNA, ECR, MICCAI.

They are actively involved in advancing progress in the field of deep learning at the international level. And they apply their extensive knowledge in building AI technologies for healthcare guided by a rigorous evidence-based approach.

Listed below are selected research publications.

Fully-automated deep learning-powered system for DCE-MRI analysis of brain tumors

Authors: Jakub Nalepa, Pablo Ribalta Lorenzo, Michal Marcinkiewicz, Barbara Bobek-Billewicz, Pawel Wawrzyniak, Maksym Walczak, Michal Kawulok, Wojciech Dudzik, Krzysztof Kotowski, Izabela Burda, Bartosz Machura, Grzegorz Mrukwa, Pawel Ulrych, Michael P Hayball

Publication date: 2020/1/1

Journal: Artificial intelligence in medicine

DESCRIPTION

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays an important role in diagnosis and grading of brain tumors. Although manual DCE biomarker extraction algorithms boost the diagnostic yield of DCE-MRI by providing quantitative information on tumor prognosis and prediction, they are time-consuming and prone to human errors. In this paper, we propose a fully-automated, end-to-end system for DCE-MRI analysis of brain tumors. Our deep learning-powered technique does not require any user interaction, it yields reproducible results, and it is rigorously validated against benchmark and clinical data. Also, we introduce a cubic model of the vascular input function used for pharmacokinetic modeling which significantly decreases the fitting error when compared with the state of the art, alongside a real-time algorithm for determination of the vascular input region. An extensive experimental …

Segmenting Brain Tumors from MRI Using Cascaded 3D U-Nets

Authors: Krzysztof Kotowski, Szymon Adamski, Wojciech Malara, Bartosz Machura, Lukasz Zarudzki, Jakub Nalepa

Publication data: 26 March 2021

Conference paper: International MICCAI Brainlesion Workshop

DESCRIPTION

In this paper, we exploit a cascaded 3D U-Net architecture to perform detection and segmentation of brain tumors (low- and high-grade gliomas) from multi-modal magnetic resonance scans. First, we detect tumors in a binary-classification setting, and they later undergo multi-class segmentation. To provide high-quality generalization, we investigate several regularization techniques that help improve the segmentation performance obtained for the unseen scans, and benefit from the expert knowledge of a senior radiologist captured in a form of several post-processing routines. Our preliminary experiments elaborated over the BraTS’20 validation set revealed that our approach delivers high-quality tumor delineation.

Data augmentation for brain-tumor segmentation: a review

Authors: Jakub Nalepa, Michal Marcinkiewicz, Michal Kawulok

Publication date: 2019/12/11

Source: Frontiers in computational neuroscience

DESCRIPTION

Data augmentation is a popular technique which helps improve generalization capabilities of deep neural networks, and can be perceived as implicit regularization. It plays a pivotal role in scenarios in which the amount of high-quality ground-truth data is limited, and acquiring new examples is costly and time-consuming. This is a very common problem in medical image analysis, especially tumor delineation. In this paper, we review the current advances in data-augmentation techniques applied to magnetic resonance images of brain tumors. To better understand the practical aspects of such algorithms, we investigate the papers submitted to the Multimodal Brain Tumor Segmentation Challenge (BraTS 2018 edition), as the BraTS dataset became a standard benchmark for validating existent and emerging brain-tumor detection and segmentation techniques. We verify which data augmentation approaches were exploited and what was their impact on the abilities of underlying supervised learners. Finally, we highlight the most promising research directions to follow in order to synthesize high-quality artificial brain-tumor examples which can boost the generalization abilities of deep models.

Detection and segmentation of brain tumors from MRI using U-Nets

Authors: Krzysztof Kotowski, Jakub Nalepa, Wojciech Dudzik

Publication date: 2019/10/17

Conference: International MICCAI Brainlesion Workshop

DESCRIPTION

In this paper, we exploit a cascaded U-Net architecture to perform detection and segmentation of brain tumors (low- and high-grade gliomas) from magnetic resonance scans. First, we detect tumors in a binary-classification setting, and they later undergo multi-class segmentation. The total processing time of a single input volume amounts to around 15  s using a single GPU. The preliminary experiments over the BraTS’19 validation set revealed that our approach delivers high-quality tumor delineation and offers instant segmentation.

Data augmentation via image registration

Authors: Jakub Nalepa, Grzegorz Mrukwa, Szymon Piechaczek, Pablo Ribalta Lorenzo, Michal Marcinkiewicz, Barbara Bobek-Billewicz, Pawel Wawrzyniak, Pawel Ulrych, Janusz Szymanek, Marcin Cwiek, Wojciech Dudzik, Michal Kawulok, Michael P Hayball

Publication date: 2019/9/22

Conference: 2019 IEEE International Conference on Image Processing (ICIP)

DESCRIPTION

Data augmentation helps improve generalization of deep neural networks, and can be perceived as implicit regularization. It is pivotal in scenarios in which the amount of ground-truth data is limited, and acquiring new examples is costly and time-consuming. This is a common problem in medical image analysis, especially tumor delineation-in this paper, we focus on brain-tumor segmentation from magnetic resonance imaging (MRI), and propose a novel augmentation technique which exploits image registration to benefit from subtle spatial and/or tissue characteristics captured within the training set. We used a set of MRI scans of 44 low-grade glioma patients, augmented it using the proposed technique, and exploited it to train U-Net-based deep networks. The results show that our augmentation delivers statistically important boost of performance without sacrificing inference speed.

Segmenting brain tumors from FLAIR MRI using fully convolutional neural networks

Authors: Pablo Ribalta Lorenzo, Jakub Nalepa, Barbara Bobek-Billewicz, Pawel Wawrzyniak, Grzegorz Mrukwa, Michal Kawulok, Pawel Ulrych, Michael P Hayball

Publication date: 2019/7/1

Journal: Computer methods and programs in biomedicine

DESCRIPTION

Background and Objective. Magnetic resonance imaging (MRI) is an indispensable tool in diagnosing brain-tumor patients. Automated tumor segmentation is being widely researched to accelerate the MRI analysis and allow clinicians to precisely plan treatment—accurate delineation of brain tumors is a critical step in assessing their volume, shape, boundaries, and other characteristics. However, it is still a very challenging task due to inherent MR data characteristics and high variability, e.g., in tumor sizes or shapes. We present a new deep learning approach for accurate brain tumor segmentation which can be trained from small and heterogeneous datasets annotated by a human reader (providing high-quality ground-truth segmentation is very costly in practice).

Methods. In this paper, we present a new deep learning technique for segmenting brain tumors from fluid attenuation inversion recovery MRI. Our …