Special Session MIAD 2010 Abstracts


Full Papers
Paper Nr: 4
Title:

A NEW SEMI-AUTOMATIC APPROACH FOR X-RAY CERVICAL IMAGES SEGMENTATION USING ACTIVE SHAPE MODEL

Authors:

Mohammed Benjelloun, Saïd Mahmoudi and Fabian Lecron

Abstract: This paper describes a new method for cervical vertebra segmentation in digitized X-ray images. We propose a segmentation approach based on Active Shape Model method whose main advantage is that it uses a statistical model. This model is created by training it with sample images on which the boundaries of the object of interest are annotated by an expert. The specialist knowledge is very useful in this context. This model represents the local statistics around each landmark. Our application allows the manipulation of a vertebra model. The results obtained are very promising.

Paper Nr: 5
Title:

A COMPARISON OF FOUR UNSUPERVISED CLUSTERING ALGORITHMS FOR SEGMENTING BRAIN TISSUE IN MULTI-SPECTRAL MR DATA

Authors:

Maria C. Valdés Hernández, J. M. Wardlaw and Sean Murphy

Abstract: The effects of atrophy and diffusion of the boundary between grey and white matter, common in elder individuals, represents a difficult problem for segmentation, not observed in healthy younger adults. The aim of this study is to evaluate four well-known unsupervised clustering algorithms in brain tissue segmentation using MR scans with atrophies and lesions. The brain is segmented into 3 different types: white matter, grey matter and CSF. We used four MR sequences: T1W, T2W, T2*W and FLAIR to classify each voxel in the image. No spatial information was used. The algorithms tested were k - means, EM (Gaussian mixture), MVQ (minimum variance quantisation) and Mean Shift. The datasets were acquired from an aged cohort (> 70 years). The resulting segmentations were quantitatively compared to expertly collected ground truth on 12 datasets, using the Dice coefficient as an overlap measure. The classification algorithms could be ranked in the following order: MVQ, k - means, EM and MeanShift from best to worst. The MVQ algorithm did best of all with over a .9 Dice overlap on CSF, and over .8 on white matter.

Posters
Paper Nr: 1
Title:

COMPUTER ASSISTED MICROSCOPY - The Era Small Size Slides & 4m Microscopes

Authors:

O. Ferrer-Roca and F. Marcano

Abstract: The present paper described the technique to evaluate digital resolution (DR), Visual Magnification (VM), onScreen Magnification (SM) and Useful magnification (US) in order to compare image quality and resolution for diagnostic purposes on computer assisted microscopes including Multi-Modal Miniature Microscopes-4M.The study was done on surgical pathology and cytological specimens comparing analog microscopic images versus digital Small Size Virtual Slides (SSVS) images. The SSVS were obtained with an 8 megapixel camera, in JPEG2000 format using a super-resolution algorithm of capture. The field of view-FOV images showed four times higher discrimination power, in spite of the low sampling density. The region of interest-ROI images, with a sampling density close to Shannon theory showed six times higher discrimination power. OnScreen magnification FOV achieved 640x and ROI 3200x augments that could never been reached using analog microscopy. The paper demonstrates that SSVS are ideal for hand-held microscopes or even mobile phones with ad-on capture systems.

Paper Nr: 2
Title:

MEDICAL VERIFICATION WATERMARKING FOR HEALTHCARE INFORMATION MANAGEMENT

Authors:

Ki-Ryong Kwon, Seung-Seob Park and Suk-Hwan Lee

Abstract: This paper presents a verification watermarking applied to healthcare information management. The proposed method uses the whole region based on the public-key cryptograph, which is transformed by the DWT transform to integrity verification. Furthermore, the public-key cryptograph algorithm is used for the embedded watermark image. We adaptively select the upper bit-plane including the LSB parts of each block when the watermark is inserted.