A fusion method based on Deep Learning and Case-Based Reasoning which improves the resulting medical image segmentations. (1st June 2020)

• Record Type: Journal Article
• Authors: Corbat, Lisa; Nauval, Mohammad; Henriet, Julien; Lapayre, Jean-Christophe
• Is Part Of: Expert systems with applications. Volume 147(2020)
• Publication Date: 2020-06-01
• Subjects: Fusion -- Conflict management -- Segmentation -- Cancer tumour -- Deep learning -- Case-based reasoning; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2020.113200
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: This paper proposes a DL-CBR method for the fusion of segmentations. This method has been applied to 9 children with an average of 109 slices per patient. Tumours and kidneys were segmented separately and merged through our method. Results obtained resolved all the conflicts and improved the overall segmentations. Abstract: The fusion of multiple segmentations of different biological structures is inevitable in the case where each structure has been segmented individually for performance reasons. However, when aggregating these structures for a final segmentation, conflicting pixels may appear. These conflicts can be solved by artificial intelligence techniques. Our system, integrated into the SAIAD project, carries out the fusion of deformed kidneys and nephroblastoma segmentations using the combination of Deep Learning and Case-Based Reasoning. The performances of our method were evaluated on 9 patients affected by nephroblastoma, and compared with other AI and non-AI methods adapted from the literature. The results demonstrate its effectiveness in resolving the conflicting pixels and its ability to improve the resulting segmentations.