State-of-the-Art Segmentation Techniques and Future Directions for Multiple Sclerosis Brain Lesions

Manual segmentation of multiple sclerosis (MS) in brain imaging is a challenging task due to intra and inter-observer variability resulting in poor reproducibility. To overcome the limitations of manual assessment various automatic segmentation techniques has been proposed in the literature. This paper presents the systematic review of the literature in automated multiple sclerosis lesion segmentation, the lesions complexity and classification of various existing automated methods. A comparative analysis of the various MS segmentation techniques is also presented and future directions are identified to carry out research work further in this field.

Automated summary

This paper provides a systematic review of automated multiple sclerosis lesion segmentation in the literature, analyzing the complexity of lesions and classification of existing automatic methods. It also presents a comparative analysis of various MS segmentation techniques, identifying future directions for further research in this field.