Fine-Tuning Approach for Segmentation of Gliomas in Brain Magnetic Resonance Images with a Machine Learning Method to Normalize Image Differences among Facilities
| Autor: | Nobuhiro Hata, Shota Tanaka, Akitake Mukasa, Masahiro Nonaka, Ryohei Otani, Kensuke Tateishi, Kazuma Kobayashi, Junya Fukai, Yoshiko Okita, Naohiro Tsuyuguchi, Masamichi Takahashi, Jun Sese, Yoshitaka Narita, Ryo Nishikawa, Takehiro Uda, Naoki Shinojima, Risa Kawaguchi, Mototaka Miyake, Hideyuki Arita, Kaoru Tamura, Manabu Kinoshita, Ryuji Hamamoto, Fumi Higuchi, Kuniaki Saito, Koichi Ichimura, Motoo Nagane, Satoshi Takahashi, Yonehiro Kanemura |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
0301 basic medicine
Cancer Research Computer science Machine learning computer.software_genre lcsh:RC254-282 Article Image (mathematics) 03 medical and health sciences 0302 clinical medicine Sørensen–Dice coefficient glioma Segmentation Brain magnetic resonance imaging MR images business.industry Deep learning Significant difference deep learning Image segmentation lcsh:Neoplasms. Tumors. Oncology. Including cancer and carcinogens 030104 developmental biology machine learning Oncology 030220 oncology & carcinogenesis Artificial intelligence business computer fine-tuning Tumor segmentation |
| Zdroj: | Cancers, Vol 13, Iss 1415, p 1415 (2021) Cancers Volume 13 Issue 6 |
| ISSN: | 2072-6694 |
| Popis: | Machine learning models for automated magnetic resonance image segmentation may be useful in aiding glioma detection. However, the image differences among facilities cause performance degradation and impede detection. This study proposes a method to solve this issue. We used the data from the Multimodal Brain Tumor Image Segmentation Benchmark (BraTS) and the Japanese cohort (JC) datasets. Three models for tumor segmentation are developed. In our methodology, the BraTS and JC models are trained on the BraTS and JC datasets, respectively, whereas the fine-tuning models are developed from the BraTS model and fine-tuned using the JC dataset. Our results show that the Dice coefficient score of the JC model for the test portion of the JC dataset was 0.779 ± 0.137, whereas that of the BraTS model was lower (0.717 ± 0.207). The mean Dice coefficient score of the fine-tuning model was 0.769 ± 0.138. There was a significant difference between the BraTS and JC models (p < 0.0001) and the BraTS and fine-tuning models (p = 0.002) however, no significant difference between the JC and fine-tuning models (p = 0.673). As our fine-tuning method requires fewer than 20 cases, this method is useful even in a facility where the number of glioma cases is small. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|