Oldřich Kodym
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Oldřich Kodym has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
Adam Herout
Graph@FIT, Brno University of Technology
5 shared publicationsMichal Španěl
Graph@FIT, Brno University of Technology
4 shared publications- Adriaan Lambrechts
Materialise NV, Leuven, Belgium
2 shared publications - Alexander Hermans
Lab for Artificial Intelligence in Medicine, Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, 52074 Aachen, Germany
2 shared publications - André Ferreira
University of Minho
2 shared publications Antoine Coppens
2 shared publications
Latest Publications
- Open Access
- 17 October 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 299
Beyond benchmarks: Towards robust artificial intelligence bone segmentation in socio-technical systems
- 17 October 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 299
Open AccessBeyond benchmarks: Towards robust artificial intelligence bone segmentation in socio-technical systems
- Open Access
Beyond Benchmarks: Towards Robust Artificial Intelligence Bone Segmentation in Socio-Technical Systems
Despite the advances in automated medical image segmentation, AI models still underperform in various clinical settings, challenging real-world integration. In this multicenter evaluation, we analyzed 20 state-of-the-art mandibular segmentation models across 19,218 segmentations of 1,000 clinically resampled CT/CBCT scans. We show that segmentation accuracy varies by up to 25% depending on socio-technical factors such as voxel size, bone orientation, and patient conditions such as osteosynthesis or pathology. Higher sharpness, isotropic smaller voxels, and neutral orientation significantly improved results, while metallic osteosynthesis and anatomical complexity led to significant degradation. Our findings challenge the common view of AI models as “plug-and-play” tools and suggest evidence-based optimization recommendations for both clinicians and developers. This will in turn boost the integration of AI segmentation tools in routine healthcare.
Open AccessBeyond Benchmarks: Towards Robust Artificial Intelligence Bone Segmentation in Socio-Technical Systems
Despite the advances in automated medical image segmentation, AI models still underperform in various clinical settings, challenging real-world integration. In this multicenter evaluation, we analyzed 20 state-of-the-art mandibular segmentation models across 19,218 segmentations of 1,000 clinically resampled CT/CBCT scans. We show that segmentation accuracy varies by up to 25% depending on socio-technical factors such as voxel size, bone orientation, and patient conditions such as osteosynthesis or pathology. Higher sharpness, isotropic smaller voxels, and neutral orientation significantly improved results, while metallic osteosynthesis and anatomical complexity led to significant degradation. Our findings challenge the common view of AI models as “plug-and-play” tools and suggest evidence-based optimization recommendations for both clinicians and developers. This will in turn boost the integration of AI segmentation tools in routine healthcare.
- 3 December 2021
- Published by Springer Nature
- p. 19-28
Segmentation of Defective Skulls from CT Data for Tissue Modelling
- 3 December 2021
- Published by Springer Nature
- p. 19-28
Segmentation of Defective Skulls from CT Data for Tissue Modelling
- 1 October 2021
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 137, 104766
Deep learning for cranioplasty in clinical practice: Going from synthetic to real patient data
- 1 October 2021
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 137, 104766
Deep learning for cranioplasty in clinical practice: Going from synthetic to real patient data
- 22 September 2021
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 25 (1) , 15-28
$\hbox {TG}^2$: text-guided transformer GAN for restoring document readability and perceived quality- 22 September 2021
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 25 (1) , 15-28
$\hbox {TG}^2$: text-guided transformer GAN for restoring document readability and perceived quality- 2 September 2021
- Published by Springer Nature
- p. 492-506
Page Layout Analysis System for Unconstrained Historic Documents
- 2 September 2021
- Published by Springer Nature
- p. 492-506
Page Layout Analysis System for Unconstrained Historic Documents
- 4 December 2020
- Published by Springer Nature
- p. 56-64
Cranial Defect Reconstruction Using Cascaded CNN with Alignment
- 4 December 2020
- Published by Springer Nature
- p. 56-64
Cranial Defect Reconstruction Using Cascaded CNN with Alignment
- Open Access
Segmentation of Defective Skulls from CT Data for Tissue Modelling
In this work we present a method of automatic segmentation of defective skulls for custom cranial implant design and 3D printing purposes. Since such tissue models are usually required in patient cases with complex anatomical defects and variety of external objects present in the acquired data, most deep learning-based approaches fall short because it is not possible to create a sufficient training dataset that would encompass the spectrum of all possible structures. Because CNN segmentation experiments in this application domain have been so far limited to simple patch-based CNN architectures, we first show how the usage of the encoder-decoder architecture can substantially improve the segmentation accuracy. Then, we show how the number of segmentation artifacts, which usually require manual corrections, can be further reduced by adding a boundary term to CNN training and by globally optimizing the segmentation with graph-cut. Finally, we show that using the proposed method, 3D segmentation accurate enough for clinical application can be achieved with 2D CNN architectures as well as their 3D counterparts.
Open AccessSegmentation of Defective Skulls from CT Data for Tissue Modelling
In this work we present a method of automatic segmentation of defective skulls for custom cranial implant design and 3D printing purposes. Since such tissue models are usually required in patient cases with complex anatomical defects and variety of external objects present in the acquired data, most deep learning-based approaches fall short because it is not possible to create a sufficient training dataset that would encompass the spectrum of all possible structures. Because CNN segmentation experiments in this application domain have been so far limited to simple patch-based CNN architectures, we first show how the usage of the encoder-decoder architecture can substantially improve the segmentation accuracy. Then, we show how the number of segmentation artifacts, which usually require manual corrections, can be further reduced by adding a boundary term to CNN training and by globally optimizing the segmentation with graph-cut. Finally, we show that using the proposed method, 3D segmentation accurate enough for clinical application can be achieved with 2D CNN architectures as well as their 3D counterparts.
- 1 August 2020
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 123, 103886
Skull shape reconstruction using cascaded convolutional networks
- 1 August 2020
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 123, 103886
Skull shape reconstruction using cascaded convolutional networks
- 14 February 2019
- Published by Springer Nature
- p. 105-114
Segmentation of Head and Neck Organs at Risk Using CNN with Batch Dice Loss
- 14 February 2019
- Published by Springer Nature
- p. 105-114
Segmentation of Head and Neck Organs at Risk Using CNN with Batch Dice Loss