Data-Centric Strategies for Overcoming PET/CT Heterogeneity: Insights from the AutoPET III Lesion Segmentation Challenge
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913501708025856 |
|---|---|
| author | Kovacs, Balint Xiao, Shuhan Rokuss, Maximilian Ulrich, Constantin Isensee, Fabian Maier-Hein, Klaus H. |
| author_facet | Kovacs, Balint Xiao, Shuhan Rokuss, Maximilian Ulrich, Constantin Isensee, Fabian Maier-Hein, Klaus H. |
| contents | The third autoPET challenge introduced a new data-centric task this year, shifting the focus from model development to improving metastatic lesion segmentation on PET/CT images through data quality and handling strategies. In response, we developed targeted methods to enhance segmentation performance tailored to the characteristics of PET/CT imaging. Our approach encompasses two key elements. First, to address potential alignment errors between CT and PET modalities as well as the prevalence of punctate lesions, we modified the baseline data augmentation scheme and extended it with misalignment augmentation. This adaptation aims to improve segmentation accuracy, particularly for tiny metastatic lesions. Second, to tackle the variability in image dimensions significantly affecting the prediction time, we implemented a dynamic ensembling and test-time augmentation (TTA) strategy. This method optimizes the use of ensembling and TTA within a 5-minute prediction time limit, effectively leveraging the generalization potential for both small and large images. Both of our solutions are designed to be robust across different tracers and institutional settings, offering a general, yet imaging-specific approach to the multi-tracer and multi-institutional challenges of the competition. We made the challenge repository with our modifications publicly available at \url{https://github.com/MIC-DKFZ/miccai2024_autopet3_datacentric}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10120 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Data-Centric Strategies for Overcoming PET/CT Heterogeneity: Insights from the AutoPET III Lesion Segmentation Challenge Kovacs, Balint Xiao, Shuhan Rokuss, Maximilian Ulrich, Constantin Isensee, Fabian Maier-Hein, Klaus H. Image and Video Processing Computer Vision and Pattern Recognition The third autoPET challenge introduced a new data-centric task this year, shifting the focus from model development to improving metastatic lesion segmentation on PET/CT images through data quality and handling strategies. In response, we developed targeted methods to enhance segmentation performance tailored to the characteristics of PET/CT imaging. Our approach encompasses two key elements. First, to address potential alignment errors between CT and PET modalities as well as the prevalence of punctate lesions, we modified the baseline data augmentation scheme and extended it with misalignment augmentation. This adaptation aims to improve segmentation accuracy, particularly for tiny metastatic lesions. Second, to tackle the variability in image dimensions significantly affecting the prediction time, we implemented a dynamic ensembling and test-time augmentation (TTA) strategy. This method optimizes the use of ensembling and TTA within a 5-minute prediction time limit, effectively leveraging the generalization potential for both small and large images. Both of our solutions are designed to be robust across different tracers and institutional settings, offering a general, yet imaging-specific approach to the multi-tracer and multi-institutional challenges of the competition. We made the challenge repository with our modifications publicly available at \url{https://github.com/MIC-DKFZ/miccai2024_autopet3_datacentric}. |
| title | Data-Centric Strategies for Overcoming PET/CT Heterogeneity: Insights from the AutoPET III Lesion Segmentation Challenge |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.10120 |