Jiangling Guo

A Probabilistic Approach to Segmentation and Classification of Neoplasia in Uterine Cervix Images Using Color and Geometric Features

Automated segmentation and classification of diagnostic markers in medical imagery are challenging tasks. Numerous algorithms for segmentation and classification based on statistical approaches of varying complexity are found in the literature. However, the design of an efficient and automated algorithm for precise classification of desired diagnostic markers is extremely image-specific. The National Library of Medicine (NLM), in collaboration with the National Cancer Institute (NCI), is creating an archive of 60,000 digitized color images of the uterine cervix. NLM is developing tools for the analysis and dissemination of these images over the Web for the study of visual features correlated with precancerous neoplasia and cancer. To enable indexing of images of the cervix, it is essential to develop algorithms for the segmentation of regions of interest, such as acetowhitened regions, and automatic identification and classification of regions exhibiting mosaicism and punctation. Success of such algorithms depends, primarily, on the selection of relevant features representing the region of interest. We present color and geometric features based statistical classification and segmentation algorithms yielding excellent identification of the regions of interest. The distinct classification of the mosaic regions from the non-mosaic ones has been obtained by clustering multiple geometric and color features of the segmented sections using various morphological and statistical approaches. Such automated classification methodologies will facilitate content-based image retrieval from the digital archive of uterine cervix and have the potential of developing an image based screening tool for cervical cancer.

A multispectral digital Cervigram analyzer in the wavelet domain for early detection of cervical cancer

The significance and need for expert interpretation of cervigrams (images of the cervix) in the study of the uterine cervix changes and pre-neoplasic lesions preceding cervical cancer are being investigated. The National Cancer Institute has collected a unique dataset taken from patients with normal cervixes and at various stages of cervical pre-cancer and cancer. This dataset allows us the opportunity for studying the uterine cervix changes for validating the potential of automated classification and recognition algorithms in discriminating cervical neoplasia and normal tissue. Pilot studies have been designed (1) to evaluate the effect of image transformation and optimal color mapping on the accepted levels of compression needed for effective dissemination of cervical image data over a network and (2) for automated detection of lesions from feature extraction, registration, and segmentation of lesions in cervix image sequences. In this paper, we present the results of the effectiveness of a novel, wavelet based, multi-spectral analyzer in retaining diagnostic features in encoded cervical images, thus allowing investigation on the potential of automated detection of lesions in cervix image sequences using automated registration, color transformation and bit-rate control, and a statistical segmentation approach.

Memory-Efficient Image Codec Using Line-based Backward Coding of Wavelet Trees

Wavelet tree-based image compression algorithms have excellent rate distortion performance. However, they have a major drawback in their memory consumption. A new approach based on backward coding of wavelet trees (BCWT) has been recently developed. Although the BCWT algorithm itself uses much less memory than the SPIHT algorithm, the total system memory usage in BCWT coding is still high due to the large memory consumption of the wavelet transform. In this paper, the line-based BCWT algorithm is presented, which utilizes the line-based wavelet transform to achieve BCWT coding. Due to the backward coding feature of the BCWT algorithm, the line-based BCWT algorithm can significantly reduce the overall system memory usage. Depending upon the image size, the memory usage of the line-based BCWT algorithm can be less than 1% of the memory usage of the SPIHT algorithm. Compared with the original BCWT algorithm, the line-based BCWT algorithm can use less than 2% of the memory that the BCWT algorithm consumes, thus making this algorithm extremely suitable for implementation on resource-limited platforms

Backward Coding of Wavelet Trees with Fine-grained Bitrate Control

Backward Coding of Wavelet Trees (BCWT) is an extremely fast wavelet-tree-based image coding algorithm. Utilizing a unique backward coding algorithm, BCWT also provides a rich set of features such as resolution- scalability, extremely low memory usage, and extremely low complexity. However, BCWT in its original form inherits one drawback also existing in most non-bitplane codecs, namely coarse bitrate control. In this paper, two solutions for improving the bitrate controllability of BCWT are presented. The first solution is based on dual minimum quantization levels, allowing BCWT to achieve fine-grained bitrates with quality-index as a controlling parameter; the second solution is based on both dual minimum quantization levels and a coding histogram, providing the ability to use target bitrate as the controlling parameter with only a small speed penalty.

Preparing digitized cervigrams for colposcopy research and education: determination of optimal resolution and compression parameters.

Objective Visual assessment of digitized cervigrams through the Internet needs to be optimized. The National Cancer Institute and National Library of Medicine are involved in a large effort to improve colposcopic assessment and, in preparation, are conducting methodologic research. Materials and Methods We selected 50 cervigrams with diagnoses ranging from normal to cervical intraepithelial neoplasia 3 or invasive cancer. Those pictures were scanned at 5 resolution levels from 1,550 to 4,000 dots per inch (dpi) and were presented to 4 expert colposcopists to assess image quality. After the ideal resolution level was determined, pictures were compressed at 7 compression ratios from 20:1 to 80:1 to determine the optimal level of compression that permitted full assessment of key visual details. Results There were no statistically significant differences between the 3,000 and 4,000 dpi pictures. At 2,000 dpi resolution, only one colposcopist found a slightly statistically significant difference (p = 0.02) compared with the gold standard. There was a clear loss of quality of the pictures at 1,660 dpi. At compression ratio 60:1, 3 of 4 evaluators found statistically significant differences when comparing against the gold standard. Conclusions Our results suggest that 2,000 dpi is the optimal level for digitizing cervigrams, and the optimal compression ratio is 50:1 using a novel wavelet-based technology. At these parameters, pictures have no significant differences with the gold standard.

Bit-rate allocation control and quality improvement for color channels in HMVQ image compression

Medical images usually require higher fidelity than commonly used natural images, especially with respect to detail preservation. Color medical images also require a higher degree of color preservation. In this paper, we present the extension of the novel gray-scale image compression technique, hybrid multi-scale vector quantization (HMVQ) to color image compression. Limitations of common color image compression methods in controlling bit-rate allocation for color channels are discussed, and the ability of HMVQ in overcoming such limitations while improving the color quality is demonstrated.

Low-memory-usage image coding with line-based wavelet transform

When compared to the traditional row-column wavelet transform, the line-based wavelet transform can achieve significant memory savings. However, the design of an image codec using the line-based wavelet transform is an intricate task because of the irregular order in which the wavelet coefficients are generated. The independent block coding feature of JPEG2000 makes it work effectively with the line-based wavelet transform. However, with wavelet tree-based image codecs, such as set partitioning in hierarchical trees, the memory usage of the codecs does not realize significant advantage with the line-based wavelet transform because many wavelet coefficients must be buffered before the coding starts. In this paper, the line-based wavelet transform was utilized to facilitate backward coding of wavelet trees (BCWT). Although the BCWT algorithm is a wavelet tree-based algorithm, its coding order differs from that of the traditional wavelet tree-based algorithms, which allows the proposed line-based image codec to become more memory efficient than other line-based image codecs, including line-based JPEG2000, while still offering comparable rate distortion performance and much lower system complexity.

Ultra high resolution image coding and ROI viewing using line-based backward coding of wavelet trees (L-BCWT)

Viewing high quality regions of interest (ROI) from compressed bit streams of high resolution images is a desirable but extremely challenging goal. Current image formats used for such viewing commonly use tile based compression and suffer from tile-boundary artifacts. They also have a larger memory requirement because they maintain redundant scaled-down versions of the original image to provide progressive-of-resolution capabilities. We present here a novel codec based on line-based backward coding of wavelet trees (L-BCWT) that has been specifically designed to address these difficulties. With L-BCWT, only a fraction of the compressed image data is in memory at any given time while providing ROI and progressive-of-resolution capabilities. The performance of LBCWT is demonstrated with histology images on the order of billions of pixels or multi-gigabytes of raw data.

A Resolution- and Rate- Scalable Image Subband Coding Scheme with Backward Coding of Wavelet Trees

A new multirate image subband coding scheme for backward coding of wavelet trees (BCWT) is presented. Fully utilizing the multirate characteristic of wavelet subband decomposition, BCWT inherently provides resolution-scalability for resolution-progressive decoding. With the proposed coding scheme, BCWT can also be adjusted to provide rate-scalability for quality-progressive decoding. More importantly, resolution-scalability is retained. Compared with current state-of-the-art JPEG2000 image coding, BCWT has much lower complexity and performs more than 6 times faster

Random Access Region of Interest in Backward Coding of Wavelet Trees

Random access to high quality regions of interest (ROI) from compressed bit streams of large images is becoming a necessary feature in many applications, particularly in viewing important areas within larger images. We have developed a completely new multi-rate image subband coding scheme using backward coding of wavelet trees (BCWT), which is fast, memory-efficient and resolution-scalable, while offering much less complexity than many other codecs, including block-based ones, e.g. JPEG2000. Although the focus of this paper is the inclusion of random access ROI decoding capabilities in BCWT, the method can also be modified in order to accommodate conventional ROI schemes in which the selected region is decoded with higher fidelity than the rest of the image. Experimental results compare the original BCWT bitstream size against that of the resulting ROI.