Fine-Tuning Approach for Segmentation of Gliomas in Brain Magnetic Resonance Images with a Machine Learning Method to Normalize Image Differences among Facilities

Abstract

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.

Integrated Analysis of Whole Genome and Epigenome Data Using Machine Learning Technology: Toward the Establishment of Precision Oncology

“…Currently, there are high expectations for the development of medical AI, and it is expected that AI technology will be actively introduced in actual clinical practice in the future. On the other hand, medical AI research for clinical applications is currently focused on medical image analysis (137)(138)(139)(140)(141)(142)(143)(144), and research on the introduction of AI to omics analysis such as whole genome analysis and epigenome analysis, as well as its clinical application, has not progressed sufficiently yet. In this regard, one of the problems associated with the widespread adoption of AI-based methodologies in omics analysis is that even though sequencing technology and other advanced analytics are increasingly being used in research and clinical practice, there is still a lot of confusion about the best protocols to adopt for analysis.…”

Reverse Engineering Glioma Radiomics to Conventional Neuroimaging

“…4 ). 28 , 38 , 89) Extensive variability of FLAIR could be problematic when detecting a qualitative imaging feature such as the T2-FLAIR mismatch sign. This observation motivated us to “reverse engineer” our findings from radiomic research to conventional neuroimaging, such as the T2-FLAIR mismatch sign.…”

Towards Clinical Application of Artificial Intelligence in Ultrasound Imaging

“…In recent years, artificial intelligence (AI), which includes machine learning and deep learning, has been developing rapidly, and AI is increasingly being adopted in medical research and applications [6][7][8][9][10][11][12][13][14][15][16]. Deep learning is a leading subset of machine learning, which is defined by non-programmed learning from a large amount of data with convolutional neural networks (CNNs) [17].…”