کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
445199 | 693154 | 2011 | 17 صفحه PDF | دانلود رایگان |
To support the challenging task of early epithelial cancer diagnosis from in vivo endomicroscopy, we propose a content-based video retrieval method that uses an expert-annotated database. Motivated by the recent successes of non-medical content-based image retrieval, we first adjust the standard Bag-of-Visual-Words method to handle single endomicroscopic images. A local dense multi-scale description is proposed to keep the proper level of invariance, in our case to translations, in-plane rotations and affine transformations of the intensities. Since single images may have an insufficient field-of-view to make a robust diagnosis, we introduce a video-mosaicing technique that provides large field-of-view mosaic images. To remove outliers, retrieval is followed by a geometrical approach that captures a statistical description of the spatial relationships between the local features. Building on image retrieval, we then focus on efficient video retrieval. Our approach avoids the time-consuming parts of the video-mosaicing by relying on coarse registration results only to account for spatial overlap between images taken at different times. To evaluate the retrieval, we perform a simple nearest neighbors classification with leave-one-patient-out cross-validation. From the results of binary and multi-class classification, we show that our approach outperforms, with statistical significance, several state-of-the art methods. We obtain a binary classification accuracy of 94.2%, which is quite close to clinical expectations.
To support the challenging task of early epithelial cancer diagnosis from in vivo endomicroscopy, we propose a content-based video retrieval method that uses an expert-annotated database. We adjust the standard Bag-of-Visual-Words method to handle endomicroscopic image retrieval. The proper level of invariance is ensured by a local dense multi-scale description. To remove outliers, retrieval is followed by a geometrical approach that captures a statistical description of the spatial relationships between the local features. Video retrieval is performed using the coarse registration results of video-mosaicing to account for spatial overlap between images taken at different times. Retrieval evaluation consists of a simple nearest neighbors classification with leave-one-patient-out cross-validation. Results of binary and multi-class classification show that our method outperforms, with statistical significance, several state-of-the art methods.Figure optionsDownload high-quality image (200 K)Download as PowerPoint slideResearch highlights
► Content-based video retrieval is applied to endomicroscopy for diagnosis support.
► Adjusted Bag-of-Visual-Words method is combined with video-mosaicing technique.
► Retrieval is objectively evaluated using leave-one-patient-out kNN classification.
► Binary classification evaluates retrieval with accuracy 94.2%.
► The method outperforms state-of-the-art in terms of multi-class classification.
Journal: Medical Image Analysis - Volume 15, Issue 4, August 2011, Pages 460–476