Signaling local non-credibility in an automatic segmentation pipeline

@inproceedings{citeulike:2790910, abstract = {The advancing technology for automatic segmentation of medical images should be accompanied by techniques to inform the user of the local credibility of results. To the extent that this technology produces clinically acceptable segmentations for a significant fraction of cases, there is a risk that the clinician will assume every result is acceptable. In the less frequent case where segmentation fails, we are concerned that unless the user is alerted by the computer, she would still put the result to clinical use. By alerting the user to the location of a likely segmentation failure, we allow her to apply limited validation and editing resources where they are most needed. We propose an automated method to signal suspected non-credible regions of the segmentation, triggered by statistical outliers of the local image match function. We apply this test to m-rep segmentations of the bladder and prostate in CT images using a local image match computed by PCA on regional intensity quantile functions. We validate these results by correlating the non-credible regions with regions that have surface distance greater than 5.5mm to a reference segmentation for the bladder. A 6mm surface distance was used to validate the prostate results. Varying the outlier threshold level produced a receiver operating characteristic with area under the curve of 0.89 for the bladder and 0.92 for the prostate. Based on this preliminary result, our method has been able to predict local segmentation failures and shows potential for validation in an automatic segmentation pipeline.}, author = {Levy, J. H. and Broadhurst, R. E. and Ray, S. and Chaney, E. L. and Pizer, S. M. }, booktitle = {Medical Imaging 2007: Image Processing. Edited by Pluim, Josien P. W.; Reinhardt, Joseph M.. Proceedings of the SPIE, Volume 6512, pp. 65123Q (2007).}, citeulike-article-id = {2790910}, doi = {10.1117/12.709015}, keywords = {image, medical, midag, segmentation, self}, month = {March}, posted-at = {2008-05-12 22:47:29}, priority = {2}, series = {Presented at the Society of Photo-Optical Instrumentation Engineers (SPIE) Conference}, title = {Signaling local non-credibility in an automatic segmentation pipeline}, url = {http://dx.doi.org/10.1117/12.709015}, volume = {6512}, year = {2007} }

TY - CONF ID - citeulike:2790910 L3 - citeulike-article-id:2790910 TI - Signaling local non-credibility in an automatic segmentation pipeline T2 - Medical Imaging 2007: Image Processing. Edited by Pluim, Josien P. W.; Reinhardt, Joseph M.. Proceedings of the SPIE, Volume 6512, pp. 65123Q (2007). SE - Presented at the Society of Photo-Optical Instrumentation Engineers (SPIE) Conference VL - 6512 N2 - The advancing technology for automatic segmentation of medical images should be accompanied by techniques to inform the user of the local credibility of results. To the extent that this technology produces clinically acceptable segmentations for a significant fraction of cases, there is a risk that the clinician will assume every result is acceptable. In the less frequent case where segmentation fails, we are concerned that unless the user is alerted by the computer, she would still put the result to clinical use. By alerting the user to the location of a likely segmentation failure, we allow her to apply limited validation and editing resources where they are most needed. We propose an automated method to signal suspected non-credible regions of the segmentation, triggered by statistical outliers of the local image match function. We apply this test to m-rep segmentations of the bladder and prostate in CT images using a local image match computed by PCA on regional intensity quantile functions. We validate these results by correlating the non-credible regions with regions that have surface distance greater than 5.5mm to a reference segmentation for the bladder. A 6mm surface distance was used to validate the prostate results. Varying the outlier threshold level produced a receiver operating characteristic with area under the curve of 0.89 for the bladder and 0.92 for the prostate. Based on this preliminary result, our method has been able to predict local segmentation failures and shows potential for validation in an automatic segmentation pipeline. KW - image KW - medical KW - midag KW - segmentation KW - self AU - Levy, JH AU - Broadhurst, RE AU - Ray, S AU - Chaney, EL AU - Pizer, SM PY - 2007/March// UR - http://dx.doi.org/10.1117/12.709015 ER -