US Patent Application 17664702. DYNAMIC MULTIMODAL SEGMENTATION SELECTION AND FUSION simplified abstract
Contents
DYNAMIC MULTIMODAL SEGMENTATION SELECTION AND FUSION
Organization Name
Inventor(s)
Hongxiang Yi of Excelsior MN (US)
Rakesh Mullick of Bangalore (IN)
Lehel Mihály Ferenczi of Dunakeszi (HU)
Gopal Biligeri Avinash of Concord CA (US)
[[:Category:Borbála De�k-karancsi of Budapest (HU)|Borbála De�k-karancsi of Budapest (HU)]][[Category:Borbála De�k-karancsi of Budapest (HU)]]
Balázs Péter Cziria of Budapest (HU)
DYNAMIC MULTIMODAL SEGMENTATION SELECTION AND FUSION - A simplified explanation of the abstract
This abstract first appeared for US patent application 17664702 titled 'DYNAMIC MULTIMODAL SEGMENTATION SELECTION AND FUSION
Simplified Explanation
- This patent application describes techniques for selecting and combining different image segmentations in medical imaging. - The computer processing system receives a segmentation dataset that includes different image segmentations of an anatomical object, each segmented using different segmentation models from different medical images. - The different medical images and image segmentations vary in terms of capture modality, acquisition protocol, or acquisition parameters. - The system uses a dynamic ranking protocol to determine ranking scores for the different image segmentations. - The ranking scores control the relative contributions of the image segmentations in combining them into a fused segmentation for the anatomical object. - The system combines the image segmentations based on the ranking scores to generate the fused image segmentation.
Original Abstract Submitted
Techniques are described that facilitate dynamic multimodal segmentation selection and fusion in medical imaging. In one example embodiment, a computer processing system receives a segmentation dataset comprising a combination of different image segmentations of an anatomical object of interest respectively segmented via different segmentation models from different medical images captured of the (same) anatomical object, wherein the different medical images and the different image segmentations vary with respect to at least one of, capture modality, acquisition protocol, or acquisition parameters. The system employs a dynamic ranking protocol as opposed to a static ranking protocol to determine ranking scores for the different image segmentations that control relative contributions of the different image segmentations in association with combining the different image segmentations into a fused segmentation for the anatomical object. The system further combines the different image segmentations based on the ranking scores to generate the fused image segmentation.
