Marek Wodzinski

Marek Wodzinski

Associate Professor in Deep Learning

Publications

You can also find my articles on my Google Scholar profile.

Radiomics-based mapping of glioblastoma infiltration beyond contrast enhancement: diffusion–perfusion correlations and survival analysis in large public cohorts

Published in European Journal of Radiology, 2026

Contribution presenting a radiomics-based approach to map glioblastoma infiltration beyond regions of contrast enhancement, leveraging diffusion–perfusion MRI correlations and survival analysis across large public cohorts.

Recommended citation: S. Cepeda, O. Esteban-Sinovas, L. T. Luppino, S. Kuttner, M. Wodzinski, et al., Radiomics-based mapping of glioblastoma infiltration beyond contrast enhancement: diffusion–perfusion correlations and survival analysis in large public cohorts, European Journal of Radiology, vol. 201, p. 112888, 2026. https://www.sciencedirect.com/science/article/pii/S0720048X26002366

The TopCoW Challenge—Topology-Aware Circle of Willis Segmentation for CT and MR Angiography

Published in NEJM AI, 2026

Contribution presenting the TopCoW Challenge, establishing the first public benchmark and paired CT/MR angiography dataset for topology-aware anatomical segmentation of the Circle of Willis.

Recommended citation: K. Yang, F. Musio, Y. Ma, N. Juchler, et al., M. Wodzinski, et al., The TopCoW Challenge—Topology-Aware Circle of Willis Segmentation for CT and MR Angiography, NEJM AI, vol. 3, no. 8, AIdbp2500994, 2026. https://ai.nejm.org/doi/full/10.1056/AIdbp2500994

Multi-class segmentation of aortic branches and zones in computed tomography angiography: The AortaSeg24 challenge

Published in Medical Image Analysis, 2026

Contribution presenting the outcomes of the AortaSeg24 challenge, dedicated to multi-class segmentation of aortic branches and zones in computed tomography angiography, summarizing the participating methods and establishing a new benchmark for aortic anatomy analysis.

Recommended citation: M. Imran, J. R. Krebs, V. B. Sivaraman, T. Zhang, et al., M. Wodzinski, et al., Multi-class segmentation of aortic branches and zones in computed tomography angiography: The AortaSeg24 challenge, Medical Image Analysis, vol. 113, p. 104188, 2026. https://www.sciencedirect.com/science/article/pii/S1361841526002574

Spectral super-resolution for Parkinson’s voice via representation-level methods under mixed-reality acquisition

Published in Computer Methods and Programs in Biomedicine, 2026

Contribution presenting representation-level spectral super-resolution methods to improve Parkinsons voice analysis collected under mixed-reality acquisition conditions.

Recommended citation: M. Dudek, J. Sikora, J. Krzywdziak, M. Zbik, W. Szecowka, M. Wodzinski, M. Daniol, M. Wojcik-Pedziwiatr, D. Hemmerling, Spectral super-resolution for Parkinsons voice via representation-level methods under mixed-reality acquisition, Computer Methods and Programs in Biomedicine, vol. 285, p. 109522, 2026. https://www.sciencedirect.com/science/article/pii/S0169260726002713

Multi-structure segmentation in CBCT volumes: The ToothFairy2 challenge

Published in Medical Image Analysis, 2026

Contribution presenting the outcomes of the ToothFairy2 challenge, dedicated to multi-structure segmentation in CBCT volumes, summarizing the participating methods and establishing a new benchmark for dental image analysis.

Recommended citation: F. Bolelli, L. Lumetti, N. van Nistelrooij, S. Vinayahalingam, et al., M. Wodzinski, et al., Multi-structure segmentation in CBCT volumes: The ToothFairy2 challenge, Medical Image Analysis, p. 104095, 2026. https://www.sciencedirect.com/science/article/pii/S1361841526001647

Prospective biopsy-controlled validation of an AI model for predicting glioblastoma infiltration: Results from the SupraGlio trial

Published in Neuro-Oncology, 2026

Contribution presenting the SupraGlio trial - a prospective, biopsy-controlled validation of an AI model for predicting glioblastoma infiltration, confirming the clinical relevance of AI-based infiltration mapping for surgical planning.

Recommended citation: S. Cepeda, E. Hernando-Pérez, E. Pérez-Riesgo, I. Rodríguez-Valle, O. Esteban-Sinovas, et al., M. Wodzinski, et al., Prospective biopsy-controlled validation of an AI model for predicting glioblastoma infiltration: Results from the SupraGlio trial, Neuro-Oncology, noag088, 2026. https://academic.oup.com/neuro-oncology/advance-article-abstract/doi/10.1093/neuonc/noag088/8659548

Multimodal Analysis of Speech-Gaze Fusion in Mixed Reality for the Detection of Neurodegenerative Disorders

Published in 2026 IEEE Conference on Virtual Reality and 3D User Interfaces, 2026

Contribution presenting an MR-native gaze–speech fusion pipeline for Parkinsons disease characterization, showing that multimodal alignment of HoloLens 2 eye-tracking and linguistic features yields meaningful multivariate separability between PD patients and healthy controls even in small-cohort settings.

Recommended citation: M. Dudek, J. Sikora, D. Hemmerling, M. Daniol, M. Wodzinski, M. Wojcik-Pedziwiatr, Multimodal Analysis of Speech-Gaze Fusion in Mixed Reality for the Detection of Neurodegenerative Disorders, 2026 IEEE Conference on Virtual Reality and 3D User Interfaces, 2026 https://ieeexplore.ieee.org/abstract/document/11457492

Data-Centric Multiclass Aortic Segmentation: Revisiting Classical Architectures in Low-Data Regimes

Published in MICCAI 2024 Workshops, 2026

Contribution presenting a data‑centric 3D RUNet‑based pipeline for multiclass aorta segmentation, showing that robust preprocessing and targeted sampling can outperform baselines even in low‑data settings.

Recommended citation: M. Wodzinski, H. Müller, Data-Centric Multiclass Aortic Segmentation: Revisiting Classical Architectures in Low-Data Regimes, Multi-class Segmentation of the Aorta, 2026. https://link.springer.com/chapter/10.1007/978-3-032-14246-7_6

Development of an artificial intelligence-based algorithm for the detection of left atrial enlargement from feline thoracic radiographs

Published in Veterinary Quarterly, 2026

Contribution presenting AI heart‑CNN model developed to automatically detect left atrial enlargement in cats from radiographs, showing good performance especially for identifying more advanced disease.

Recommended citation: C. Valente, M.Wodzinski, C. Guglielmini, et al., Development of an artificial intelligence-based algorithm for the detection of left atrial enlargement from feline thoracic radiographs, Veterinary Quarterly, vol. 46, no. 1, 2026. https://www.tandfonline.com/doi/full/10.1080/01652176.2025.2611847

Automated Segmentation of Canine Pulmonary Masses in CT Imaging Using AI

Published in Veterinary Quarterly, 2025

Contribution to a veterinary imaging focused on AI-based segmentation of pulmonary masses in canine CT scans.

Recommended citation: A. Jurgas, S. Burti, M. Wodziński, C. Puccinelli, G.B. Cherubini, S. Citi, G. Poloni, N. Mastromattei, M. Bendazzoli, D. Wilson et al., Automated Segmentation of Canine Pulmonary Masses in CT Imaging Using AI, Veterinary Quarterly, vol. 45, no. 1, 2025. https://www.tandfonline.com/doi/pdf/10.1080/01652176.2025.2573449

Learn2Reg 2024: New Benchmark Datasets Driving Progress on New Challenges

Published in Machine Learning for Biomedical Imaging, 2025

The 2024 Learn2Reg challenge broadens medical image‑registration benchmarking with new multimodal, complex tasks and datasets that spur development of more advanced registration methods.

Recommended citation: L. Hansen, et al., Learn2Reg 2024: New Benchmark Datasets Driving Progress on New Challenges, Machine Learning for Biomedical Imaging, vol. 3, no. 12, 2025. https://www.melba-journal.org/papers/2025:034.html

Radiomics-based quantification of tumor infiltration in the non-enhancing peritumoral region on postoperative MRI is associated with survival in glioblastoma

Published in Scientific Reports, 2025

Study demonstrating that radiomics-based machine learning models can quantify tumor infiltration in non-enhancing peritumoral regions on postoperative MRI, providing an independent prognostic factor for glioblastoma survival.

Recommended citation: Santiago Cepeda, et al., Radiomics-based quantification of tumor infiltration in the non-enhancing peritumoral region on postoperative MRI is associated with survival in glioblastoma, Scientific Reports, 2025. https://www.nature.com/articles/s41598-025-27711-5

BONBID-HIE 2023: Lesion Segmentation Challenge in BOston Neonatal Brain Injury Data for Hypoxic Ischemic Encephalopathy

Published in IEEE Transactions on Medical Imaging, 2025

First BONBID-HIE challenge organized with diffusion MRI data (ADC maps) for lesion segmentation in neonatal Hypoxic Ischemic Encephalopathy. The study evaluates 14 submitted algorithms and provides insights into segmentation performance and clinical relevance.

Recommended citation: Rina Bao, et al., BONBID-HIE 2023: Lesion Segmentation Challenge in BOston Neonatal Brain Injury Data for Hypoxic Ischemic Encephalopathy, IEEE Transactions on Medical Imaging, 2025. https://ieeexplore.ieee.org/abstract/document/11297440

Mixed-Reality System for Neurodegenerative Disorders: Design, Implementation, and User Evaluation

Published in IEEE Pervasive Computing, 2025

The study presents a mixed‑reality, sensor‑based system that uses AR goggles and game‑like tasks to feasibly and comfortably assess motor and cognitive symptoms in neurodegenerative disorders.

Recommended citation: D. Hemmerling, et al., Mixed-Reality System for Neurodegenerative Disorders: Design, Implementation, and User Evaluation, IEEE Pervasive Computing, vol. 24, no. 4, 2025. https://ieeexplore.ieee.org/abstract/document/11264834

A Community Benchmark for the Automated Segmentation of Pediatric Neuroblastoma on Multi-Modal MRI: Design and Results of the SPPIN Challenge at MICCAI 2023

Published in Bioengineering, 2025

Description of the SPPIN Challenge outcomes - organzied at MICCAI 2023 focused on benchmarking automated segmentation methods for pediatric neuroblastoma using multi-modal MRI.

Recommended citation: M.A.D. Buser, D.C. Simons, M. Fitski, M.H.W.A. Wijnen, A.S. Littooij, A.H. ter Brugge, I.N. Vos, M.H.A. Janse, M. de Boer, R. ter Maat et al., A Community Benchmark for the Automated Segmentation of Pediatric Neuroblastoma on Multi-Modal MRI: Design and Results of the SPPIN Challenge at MICCAI 2023, Bioengineering, vol. 12, no. 11, 2025. https://www.mdpi.com/2306-5354/12/11/1157

Multi-step Segmentation of Pelvic Fractures: Handling Variable Fracture Counts Through Anatomical and Surface Analysis

Published in MICCAI Workshop on Deep Generative Models, 2025

Method to automatically segment variable pelvic fractures from CT volumes.

Recommended citation: Artur Jurgas, et al., Multi-step Segmentation of Pelvic Fractures: Handling Variable Fracture Counts Through Anatomical and Surface Analysis, MICCAI Workshop on Deep Generative Models, 2025. https://link.springer.com/chapter/10.1007/978-3-032-05825-6_10

Automated AI-based segmentation of canine hepatic focal lesions from CT studies

Published in Frontiers in Veterinary Science, 2025

A study introducing the first deep learning algorithm for automatic segmentation of hepatic masses in canine CT scans, achieving high accuracy with a Dice score of 0.86. This tool shows strong potential to support veterinary clinicians in treatment planning when surgical options are limited.

Recommended citation: Silvia Burti, et al., Automated AI-based segmentation of canine hepatic focal lesions from CT studies, Front. Vet. Sci. 12:1638142. doi: 10.3389/fvets.2025.1638142, 2025. https://www.frontiersin.org/journals/veterinary-science/articles/10.3389/fvets.2025.1638142/full

Automatic labels are as effective as manual labels in digital pathology images classification with deep learning

Published in Journal of Pathology Informatics, 2025

A study confirming that automatically generated labels are as effective as manually annotated ones in digital pathology, significantly reducing the time pathologists need to prepare the annotations.

Recommended citation: Niccolo Marini, et al., Automatic labels are as effective as manual labels in digital pathology images classification with deep learning, Journal of Pathology Informatics, 2025. https://www.sciencedirect.com/science/article/pii/S2153353925000483

Unsupervised skull segmentation in MR images utilizing modality translation and super-resolution

Published in Scientific Reports, 2025

Description of our contribution to automatic skull segmentation from MR volumes without using any ground-truth annotations

Recommended citation: Kamil Kwarciak, Mateusz Daniol, Daria Hemmerling, Marek Wodzinski, Unsupervised skull segmentation in MR images utilizing modality translation and super-resolution, Scientific Reports, 2025. https://www.nature.com/articles/s41598-025-05323-3

Automatic Multi-structure Segmentation in Cone Beam Computed Tomography Volumes Using Deep Encoder-Decoder Architectures

Published in MICCAI 2024 - ToothFairy, 2025

Description of the my contribution to the ToothFairy 2024 challenge related to automatic segmentation of dental structures.

Recommended citation: M. Wodzinski, H. Müller, Automatic Multi-structure Segmentation in Cone Beam Computed Tomography Volumes Using Deep Encoder-Decoder Architectures, MICCAI ToothFairy 2024, 2024. https://link.springer.com/chapter/10.1007/978-3-031-88977-6_7

3-D Image-to-Image Fusion in Lightsheet Microscopy by Two-Step Adversarial Network: Contribution to the FuseMyCells Challenge

Published in IEEE ISBI 2025, 2025

Description of my contribution to the FuseMyCells organized during the IEEE ISBI 2025 conference in Houston, Texas - the contribution scored the 1st place in the competition.

Recommended citation: M. Wodzinski, H. Muller, 3-D Image-to-Image Fusion in Lightsheet Microscopy by Two-Step Adversarial Network: Contribution to the FuseMyCells Challenge, IEEE ISBI 2025, 2025. https://arxiv.org/abs/2503.16075

Automated determination of hip arthrosis on the Kellgren–Lawrence scale in pelvic digital radiographs scans using machine learning

Published in Computer Methods and Programs in Biomedicine, 2025

Description of a deep learning-based method dedicated to automatic determination of hip arthrosis from radiographs.

Recommended citation: Karolina Nurzynska, Marek Wodzinski, Adam Piorkowski, et al., Automated determination of hip arthrosis on the Kellgren–Lawrence scale in pelvic digital radiographs scans using machine learning, Computer Methods and Programs in Biomedicine, 2025. https://www.sciencedirect.com/science/article/pii/S0169260725001592

Automatic Skull Reconstruction by Deep Learnable Symmetry Enforcement

Published in Computer Methods and Programs in Biomedicine, 2025

Description of a method for automatic skull reconstruction using dedicated symmetry loss that can be incorporated both during the training and inference phases. The method significantly improves the reconstruction outcomes for out-of-distribution cases.

Recommended citation: Marek Wodzinski, et al., Automatic Skull Reconstruction by Deep Learnable Symmetry Enforcement, Computer Methods and Programs in Biomedicine, 2025. https://www.sciencedirect.com/science/article/pii/S0169260725000872

MedShapeNet – a large-scale dataset of 3D medical shapes for computer vision

Published in Biomedical Engineering / Biomedizinische Technik, 2024

Introduction of MedShapeNet, a comprehensive dataset designed to bridge data-driven vision algorithms with medical applications.

Recommended citation: Jianning Li, et al., MedShapeNet – a large-scale dataset of 3D medical shapes for computer vision, Biomedical Engineering / Biomedizinische Technik, Vol. 69, 2024. https://www.degruyter.com/document/doi/10.1515/bmt-2024-0396/html

Automatic detection and multi-component segmentation of brain metastases in longitudinal MRI

Published in Scientific Reports, 2024

Study on automated detection and segmentation of brain metastases in longitudinal MRI, focusing on enhancing lesion, edema, and necrosis components.

Recommended citation: Vincent Andrearczyk, et al., Automatic detection and multi-component segmentation of brain metastases in longitudinal MRI, Scientific Reports, Vol. 14, 2024. https://www.nature.com/articles/s41598-024-78865-7

Segmenting the Inferior Alveolar Canal in CBCTs Volumes: the ToothFairy Challenge

Published in IEEE Transactions on Medical Imaging, 2024

The ToothFairy challenge, organized within MICCAI 2023, provided a public dataset of 443 CBCT scans to benchmark and encourage deep learning research for the segmentation of the Inferior Alveolar Canal (IAC), resulting in the first comprehensive comparative evaluation of IAC segmentation methods.

Recommended citation: Federico Bolelli, et al., Segmenting the Inferior Alveolar Canal in CBCTs Volumes: the ToothFairy Challenge, IEEE Transactions on Medical Imaging, 2024. https://ieeexplore.ieee.org/abstract/document/10816445

Automatic Registration of SHG and H&E Images with Feature-Based Initial Alignment and Intensity-Based Instance Optimization: Contribution to the COMULIS Challenge

Published in MICCAI 2024 - WBIR, 2024

Description of the method based on DeeperHistReg framework to the automatic registration of SHG and H&E slides.

Recommended citation: M. Wodzinski, H. Müller, Automatic Registration of SHG and H&E Images with Feature-based Initial Alignment and Intensity-based Instance Optimization: Contribution to the COMULIS Challenge, WBIR 2024, 2024. https://link.springer.com/chapter/10.1007/978-3-031-73480-9_27

Improving deep learning-based automatic cranial defect reconstruction by heavy data augmentation: From image registration to latent diffusion models

Published in Computers in Biology and Medicine, 2024

Contribution presenting the influence of various augmentation strategies to automatic cranial defect reconstruction with deep learning methods.

Recommended citation: Marek Wodzinski, et al., Improving deep learning-based automatic cranial defect reconstruction by heavy data augmentation: From image registration to latent diffusion models, Computers in Biology and Medicine, Vol. 182, 2024. https://www.sciencedirect.com/science/article/pii/S0010482524012149

Patch-Based Encoder-Decoder Architecture For Automatic Transmitted Light To Fluorescence Imaging Transition: Contribution To The Lightmycells Challenge

Published in IEEE ISBI, 2024

Description of the contribution to the LightMyCells challenge organized during IEEE ISBI 2024 - 3rd place.

Recommended citation: Marek Wodzinski; Henning Müller, Patch-Based Encoder-Decoder Architecture For Automatic Transmitted Light To Fluorescence Imaging Transition: Contribution To The Lightmycells Challenge, IEEE ISBI, 2024. https://ieeexplore.ieee.org/document/10635768

Multimodal representations of biomedical knowledge from limited training whole slide images and reports using deep learning

Published in Medical Image Analysis, 2024

Multimodal approach to classify WSIs using both visual and text data.

Recommended citation: Niccolò Marini, Stefano Marchesin, Marek Wodzinski, et al., Multimodal representations of biomedical knowledge from limited training whole slide images and reports using deep learning, Medical Image Analysis, 2024. https://www.sciencedirect.com/science/article/pii/S1361841524002287

Development of an artificial intelligence-based algorithm for predicting the severity of myxomatous mitral valve disease from thoracic radiographs by using two grading systems

Published in Research in Veterinary Science, 2024

Comparison of two grading systems to train and evaluate the severity of myxomatous mitral valve disease from thoracic radiographs.

Recommended citation: Carlotta Valente, Marek Wodzinski, Carlo Guglielmini, et al., Development of an artificial intelligence-based algorithm for predicting the severity of myxomatous mitral valve disease from thoracic radiographs by using two grading systems, Research in Veterinary Science, 2024. https://www.sciencedirect.com/science/article/pii/S0034528824002443

Improving quality control of whole slide images by explicit artifact augmentation

Published in Scientific Reports, 2024

Article presenting augmentation method to improve the generalizability of deep learning networks dedicated to quality control of WSIs.

Recommended citation: Artur Jurgas, Marek Wodzinski, Marina D’Amato, Jeroen van der Laak, Manfredo Atzori, Henning Müller, Improving quality control of whole slide images by explicit artifact augmentation, Scientific Reports, 2024. https://www.nature.com/articles/s41598-024-68667-2

EsmTemp-Transfer Learning Approach for Predicting Protein Thermostability

Published in International Conference on Computational Science, 2024

Description of a deep learning-based method to predict protein thermostability using text-dedicated transformers

Recommended citation: A. Sułek, J. Jończyk, P. Orzechowski, AA. Hamed, M. Wodzinski, EsmTemp-Transfer Learning Approach for Predicting Protein Thermostabilitye, International Conference on Computational Science, 2024. https://link.springer.com/chapter/10.1007/978-3-031-63759-9_23

RegWSI: Whole Slide Image Registration using Combined Deep Feature-and Intensity-Based Methods: Winner of the ACROBAT 2023 Challenge

Published in Computer Methods and Programs in Biomedicine, 2024

Article describing a novel WSI registration method that won the ACROBAT 2023 challenge.

Recommended citation: Marek Wodzinski et al. RegWSI: Whole slide image registration using combined deep feature- and intensity-based methods: Winner of the ACROBAT 2023 challenge, Computer Methods and Programs in Biomedicine, Vol. 250, 2024. https://www.sciencedirect.com/science/article/pii/S0169260724001834

AI-Based Automated Custom Cranial Implant Design–Challenges and Opportunities with Case Study

Published in Manufacturing Conference, 2024

This conference paper presents a case-study related to design challenges in automatic cranial implant modeling.

Recommended citation: Mateusz Daniol, Daria Hemmerling, Marek Wodzinski, AI-Based Automated Custom Cranial Implant Design – Challenges and Opportunities with Case Study, Advances in Manufacturing IV, 2024. https://link.springer.com/chapter/10.1007/978-3-031-56456-7_6

Automatic Aorta Segmentation with Heavily Augmented, High-Resolution 3-D ResUNet: Contribution to the SEG.A Challenge

Published in MICCAI 2023, 2024

Contribution to the SEG.A Challenge organized during MICCAI 2023 (1st in clinical evaluation).

Recommended citation: Marek Wodzinski, Henning Müller, Automatic Aorta Segmentation with Heavily Augmented, High-Resolution 3-D ResUNet: Contribution to the SEG.A Challenge, MICCAI Challenge on Segmentation of the Aorta, 2024. https://link.springer.com/chapter/10.1007/978-3-031-53241-2_4

Improving the classification of veterinary thoracic radiographs through inter-species and inter-pathology self-supervised pre-training of deep learning models

Published in Scientific Reports, 2023

Article describing a concept related inter-species and inter-pathology self-supervised pretraining.

Recommended citation: Weronika Celniak, Marek Wodzinski, Artur Jurgas, et. al., Improving the classification of veterinary thoracic radiographs through inter-species and inter-pathology self-supervised pre-training of deep learning models, Scientific Reports, Vol. 13, 2024. https://www.nature.com/articles/s41598-023-46345-z

Development of an artificial intelligence-based method for the diagnosis of the severity of myxomatous mitral valve disease from canine chest radiographs

Published in Frontiers in Veterinary Science, 2023

Article presenting AI-based method to access severity of myxomatous mitral valbe disease.

Recommended citation: Carlotta Valente, Marek Wodzinski, Carlo Guglielmini, et. al., Development of an artificial intelligence-based method for the diagnosis of the severity of myxomatous mitral valve disease from canine chest radiographs, Frontiers in Veterinary Science, 2023. https://www.frontiersin.org/articles/10.3389/fvets.2023.1227009/full

Vision Transformer for Parkinson’s Disease Classification using Multilingual Sustained Vowel Recordings

Published in IEEE EMBC 2023, 2023

Transformed-based method to classify Parkinson’s disease based on vowel recordings.

Recommended citation: Daria Hemmerling, Marek Wodzinski, Juan Rafael Orozco-Arroyave, et. al., Vision Transformer for Parkinson’s Disease Classification using Multilingual Sustained Vowel Recordings, IEEE EMBC 2023, 2023. https://ieeexplore.ieee.org/abstract/document/10340478

Unsupervised Method for Intra-patient Registration of Brain Magnetic Resonance Images Based on Objective Function Weighting by Inverse Consistency: Contribution to the BraTS-Reg Challenge

Published in MICCAI - BrainLes 2022, 2023

A successful algorithm to MR volumes registration acquired before and after brain tumor resection.

Recommended citation: Marek Wodzinski, et. al., Unsupervised Method for Intra-patient Registration of Brain Magnetic Resonance Images Based on Objective Function Weighting by Inverse Consistency: Contribution to the BraTS-Reg Challenge, MICCAI BrainLes 2022, 2023. https://link.springer.com/chapter/10.1007/978-3-031-33842-7_21

Towards clinical applicability and computational efficiency in automatic cranial implant design: An overview of the autoimplant 2021 cranial implant design challenge

Published in Medical Image Analysis, 2023

Benchmark of all the methods proposed for the AutoImplant challenge organized during MICCAI 2021

Recommended citation: Jianning Li, et al., Towards clinical applicability and computational efficiency in automatic cranial implant design: An overview of the autoimplant 2021 cranial implant design challenge, Medical Image Analysis, Vol. 88, 2023. https://www.sciencedirect.com/science/article/pii/S1361841523001251

Learn2Reg: Comprehensive Multi-Task Medical Image Registration Challenge, Dataset and Evaluation in the Era of Deep Learning

Published in IEEE Transactions on Medical Imaging, 2022

Article presenting the outcomes of the Learn2Reg challenge (medical image registration in radiology).

Recommended citation: Alessa Hering, et al., Learn2Reg: Comprehensive Multi-Task Medical Image Registration Challenge, Dataset and Evaluation in the Era of Deep Learning, IEEE Transactions on Medical Imaging, Vol. 42, 2023. https://ieeexplore.ieee.org/document/9925717

Deep Learning-based Framework for Automatic Cranial Defect Reconstruction and Implant Modeling

Published in Computer Methods and Programs in Biomedicine, 2022

Article presenting a pipeline dedicated to automatic cranial implant design and verification in mixed reality.

Recommended citation: Marek Wodzinski, et al., Deep Learning-based Framework for Automatic Cranial Defect Reconstruction and Implant Modeling, Computer Methods and Programs in Biomedicine, Vol. 226, 2022. https://www.sciencedirect.com/science/article/pii/S0169260722005545

Unleashing the potential of digital pathology data by training computer-aided diagnosis models without human annotations

Published in npj Digital Medicine, 2022

Article presenting a method how to train deep neural networks on digital pathology data without using human annotations.

Recommended citation: Niccolò Marini, et al., Unleashing the potential of digital pathology data by training computer-aided diagnosis models without human annotations, npj Digital Medicine, 2022. https://www.nature.com/articles/s41746-022-00635-4

Improving the Automatic Cranial Implant Design in Cranioplasty by Linking Different Datasets

Published in MICCAI 2021, 2021

Contribution to the AutoImplant challenge organized during MICCAI 2021 (1st place in all challenge tasks).

Recommended citation: Marek Wodzinski, Mateusz Daniol, Daria Hemmerling, Improving the Automatic Cranial Implant Design in Cranioplasty by Linking Different Datasets, MICCAI Cranial Implant Design Challenge, 2021. https://link.springer.com/chapter/10.1007/978-3-030-92652-6_4

An AI-based algorithm for the automatic classification of thoracic radiographs in cats

Published in Frontiers in Veterinary Science, 2021

Article presenting an AI-based methods to classify thoracic radiographs in cats.

Recommended citation: Tommaso Banzato, Marek Wodzinski, Federico Tauceri, et al., An AI-based algorithm for the automatic classification of thoracic radiographs in cats, Frontiers in Veterinary Science, Vol. 8, 2021. https://www.frontiersin.org/articles/10.3389/fvets.2021.731936/full

Adversarial Affine Registration for Real-Time Intraoperative Registration of 3-D US-US for Brain Shift Correction

Published in MICCAI-ASMUS 2021, 2021

Method presenting a 3-D US-US affine registration for brain shift correction using adversarial training.

Recommended citation: Marek Wodzinski, Andrzej Skalski, Adversarial Affine Registration for Real-Time Intraoperative Registration of 3-D US-US for Brain Shift Correction, MICCAI ASMUS, 2021. https://link.springer.com/chapter/10.1007/978-3-030-87583-1_8

Semi-Supervised Deep Learning-Based Image Registration Method with Volume Penalty for Real-Time Breast Tumor Bed Localization

Published in Sensors, 2021

Article introducing a volume-penalty method to handle missing data during breast tumor bed localization using image registration.

Recommended citation: Marek Wodzinski, et al., Semi-Supervised Deep Learning-Based Image Registration Method with Volume Penalty for Real-Time Breast Tumor Bed Localization, Sensors, 2021. https://www.mdpi.com/1424-8220/21/12/4085

Learning-based local quality assessment of reflectance confocal microscopy images for dermatology applications

Published in Biocybernetics and Biomedical Engineering, 2021

Article presenting a learning-based method for local quality assessment of RCM images.

Recommended citation: Miroslawa Sikorska, Andrzej Skalski, Marek Wodzinski, et al., Learning-based local quality assessment of reflectance confocal microscopy images for dermatology applications, Biocybernetics and Biomedical Engineering, Vol 41, 2021. https://www.sciencedirect.com/science/article/pii/S0208521621000632

Multistep, automatic and nonrigid image registration method for histology samples acquired using multiple stains

Published in Physics in Medicine & Biology, 2021

Article presenting an automatic algorithm for WSI registration that scored 3rd place during the ANHIR challenge.

Recommended citation: Marek Wodzinski, Andrzej Skalski, Multistep, automatic and nonrigid image registration method for histology samples acquired using multiple stains, Physics in Medicine & Biology, Vol 66., 2021. https://iopscience.iop.org/article/10.1088/1361-6560/abcad7

DeepHistReg: Unsupervised Deep Learning Registration Framework for Differently Stained Histology Samples

Published in Computer Methods and Programs in Biomedicine, 2021

Learning-based method for deformable registration of WSIs acquired using different stains.

Recommended citation: Marek Wodzinski, Henning Müller, DeepHistReg: Unsupervised Deep Learning Registration Framework for Differently Stained Histology Samples, Computer Methods and Programs in Biomedicine, Vol. 198, 2021. https://www.sciencedirect.com/science/article/pii/S0169260720316321

Deep Learning Approach to Parkinson’s Disease Detection Using Voice Recordings and Convolutional Neural Network Dedicated to Image Classification

Published in IEEE EMBC 2019, 2019

Deep learning-based method to classify Parkinson’s disease using CNNs dedicated to image classification.

Recommended citation: Marek Wodzinski, et al. Deep learning approach to Parkinson’s disease detection using voice recordings and convolutional neural network dedicated to image classification, IEEE EMBC 2019, 2019. https://ieeexplore.ieee.org/document/8856972

Improving oncoplastic breast tumor bed localization for radiotherapy planning using image registration algorithms

Published in Physics in Medicine & Biology, 2018

Article presenting usage of image registration method for improving oncoplastic breast tumor bed localization.

Recommended citation: Marek Wodzinski, et al., Improving oncoplastic breast tumor bed localization for radiotherapy planning using image registration algorithms, Physics in Medicine & Biology, Vol. 63, 2021. https://iopscience.iop.org/article/10.1088/1361-6560/aaa4b1