Parameter-efficient Fine-tuning for improved Convolutional Baseline for Brain Tumor Segmentation in Sub-Saharan Africa Adult Glioma Dataset
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_ | 1866929638096240640 |
|---|---|
| author | Adhikari, Bijay Kulung, Pratibha Bohaju, Jakesh Poudel, Laxmi Kanta Raymond, Confidence Zhang, Dong Anazodo, Udunna C Khanal, Bishesh Shakya, Mahesh |
| author_facet | Adhikari, Bijay Kulung, Pratibha Bohaju, Jakesh Poudel, Laxmi Kanta Raymond, Confidence Zhang, Dong Anazodo, Udunna C Khanal, Bishesh Shakya, Mahesh |
| contents | Automating brain tumor segmentation using deep learning methods is an ongoing challenge in medical imaging. Multiple lingering issues exist including domain-shift and applications in low-resource settings which brings a unique set of challenges including scarcity of data. As a step towards solving these specific problems, we propose Convolutional adapter-inspired Parameter-efficient Fine-tuning (PEFT) of MedNeXt architecture. To validate our idea, we show our method performs comparable to full fine-tuning with the added benefit of reduced training compute using BraTS-2021 as pre-training dataset and BraTS-Africa as the fine-tuning dataset. BraTS-Africa consists of a small dataset (60 train / 35 validation) from the Sub-Saharan African population with marked shift in the MRI quality compared to BraTS-2021 (1251 train samples). We first show that models trained on BraTS-2021 dataset do not generalize well to BraTS-Africa as shown by 20% reduction in mean dice on BraTS-Africa validation samples. Then, we show that PEFT can leverage both the BraTS-2021 and BraTS-Africa dataset to obtain mean dice of 0.8 compared to 0.72 when trained only on BraTS-Africa. Finally, We show that PEFT (0.80 mean dice) results in comparable performance to full fine-tuning (0.77 mean dice) which may show PEFT to be better on average but the boxplots show that full finetuning results is much lesser variance in performance. Nevertheless, on disaggregation of the dice metrics, we find that the model has tendency to oversegment as shown by high specificity (0.99) compared to relatively low sensitivity(0.75). The source code is available at https://github.com/CAMERA-MRI/SPARK2024/tree/main/PEFT_MedNeXt |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_14100 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Parameter-efficient Fine-tuning for improved Convolutional Baseline for Brain Tumor Segmentation in Sub-Saharan Africa Adult Glioma Dataset Adhikari, Bijay Kulung, Pratibha Bohaju, Jakesh Poudel, Laxmi Kanta Raymond, Confidence Zhang, Dong Anazodo, Udunna C Khanal, Bishesh Shakya, Mahesh Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Automating brain tumor segmentation using deep learning methods is an ongoing challenge in medical imaging. Multiple lingering issues exist including domain-shift and applications in low-resource settings which brings a unique set of challenges including scarcity of data. As a step towards solving these specific problems, we propose Convolutional adapter-inspired Parameter-efficient Fine-tuning (PEFT) of MedNeXt architecture. To validate our idea, we show our method performs comparable to full fine-tuning with the added benefit of reduced training compute using BraTS-2021 as pre-training dataset and BraTS-Africa as the fine-tuning dataset. BraTS-Africa consists of a small dataset (60 train / 35 validation) from the Sub-Saharan African population with marked shift in the MRI quality compared to BraTS-2021 (1251 train samples). We first show that models trained on BraTS-2021 dataset do not generalize well to BraTS-Africa as shown by 20% reduction in mean dice on BraTS-Africa validation samples. Then, we show that PEFT can leverage both the BraTS-2021 and BraTS-Africa dataset to obtain mean dice of 0.8 compared to 0.72 when trained only on BraTS-Africa. Finally, We show that PEFT (0.80 mean dice) results in comparable performance to full fine-tuning (0.77 mean dice) which may show PEFT to be better on average but the boxplots show that full finetuning results is much lesser variance in performance. Nevertheless, on disaggregation of the dice metrics, we find that the model has tendency to oversegment as shown by high specificity (0.99) compared to relatively low sensitivity(0.75). The source code is available at https://github.com/CAMERA-MRI/SPARK2024/tree/main/PEFT_MedNeXt |
| title | Parameter-efficient Fine-tuning for improved Convolutional Baseline for Brain Tumor Segmentation in Sub-Saharan Africa Adult Glioma Dataset |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2412.14100 |