Digital hologram for data augmentation in learning-based pattern classification.

This study proposes a novel data augmentation method based on numerical focusing of digital holography to boost the performance of learning-based pattern classification. To conduct digital holographic data augmentation (DHDA), a complex pattern diffraction approach is used to provide the least separation of confusion in the effective diffraction regime to access the full-field wavefront information of a target sample. By using DHDA, the accessible amount of labeled data is increased to complement the data manifold and to provide various three-dimensional diffraction characteristics for improving the performance of learning-based pattern classification. Experimental results demonstrated that overall accuracy of pattern classification with DHDA (95.1%) was higher than that without DHDA (90.9%).

Rapid image stitching and computer-aided detection for multipass automated breast ultrasound.

PURPOSE: Breast ultrasound (US) is recently becoming more and more popular for detecting breast lesions. However, screening results in hundreds of US images for each subject. This magnitude of images can lead to fatigue in radiologist, causing failure in the detection of lesions of a subtle nature. In this study, an image stitching technique is proposed for combining multipass images of the whole breast into a series of full-view images, and a fully automatic screening system that works off these images is also presented. METHODS: Using the registration technique based on the simple sum of absolute block-mean difference (SBMD) measure, three-pass images were merged into full-view US images. An automatic screening system was then developed for detecting tumors from these full-view images. The preprocessing step was used to reduce the tumor detection time of the system and to improve image quality. The gray-level slicing method was then used to divide images into numerous regions. Finally, seven computerized features--darkness, uniformity, width-height ratio, area size, nonpersistence, coronal area size, and region continuity--were defined and used to determine whether or not each region was a part of a tumor. RESULTS: In the experiment, there was a total of 25 experimental cases with 26 lesions, and each case was composed of 252 images (three passes, 84 images/pass). The processing time of the proposed stitching procedure for each case was within 30 s with a Pentium IV 2.0 processor, and the detection sensitivity of the proposed CAD system was 92.3% with 1.76 false positives per case. CONCLUSIONS: The proposed automatic screening system can be applied to the whole breast images stitched together via SBMD-based registration in order to detect tumors.

Tamper detection and restoring system for medical images using wavelet-based reversible data embedding.

Over the past few years, the billows of the digital trends and the exploding growth of electronic networks, such as worldwide web, global mobility networks, etc., have drastically changed our daily lifestyle. In view of the widespread applications of digital images, medical images, which are produced by a wide variety of medical appliances, are stored in digital form gradually. These digital images are very easy to be modified imperceptively by malicious intruders for illegal purposes. The well-known adage that "seeing is believing" seems not always a changeless truth. Therefore, protecting images from being altered becomes an important issue. Based on the lossless data-embedding techniques, two detection and restoration systems are proposed to cope with forgery of medical images in this paper. One of them has the ability to recover the whole blocks of the image and the other enables to recover only a particular region where a physician will be interested in, with a better visual quality. Without the need of comparing with the original image, these systems have a great advantage of detecting and locating forged parts of the image with high possibility. And then it can also restore the counterfeited parts. Furthermore, once an image is announced authentic, the original image can be derived from the stego-image losslessly. The experimental results show that the restored version of a tampered image in the first method is extremely close to the original one. As to the second method, the region of interest selected by a physician can be recovered without any loss, when it is tampered.

Diffuse parenchymal lung diseases: 3D automated detection in MDCT.

Characterization and quantification of diffuse parenchymal lung disease (DPLD) severity using MDCT, mainly in interstitial lung diseases and emphysema, is an important issue in clinical research for the evaluation of new therapies. This paper develops a 3D automated approach for detection and diagnosis of DPLDs (emphysema, fibrosis, honeycombing, ground glass). The proposed methodology combines multi-resolution image decomposition based on 3D morphological filtering, and graph-based classification for a full characterization of the parenchymal tissue. The very promising results obtained on a small patient database are good premises for a near implementation and validation of the proposed approach in clinical routine.

Breast density analysis in 3-D whole breast ultrasound images.

The breast density information is one of important factors for estimating the risk in breast cancer detection and early prevention. In this paper, we present two methods, including threshold-based and proportion-based, to automatically analyze the breast density using whole breast ultrasound. The two algorithms are experimented with 32 cases which are scanned from 32 patients using the US machine SSD-5500 with a recent developed scanner ASU-1004 (Aloka, Japan). The experimental results are graded from 4 (extremely dense tissue) to 1 (almost entirely fat), and respectively compared with the majority grades of three radiologists. The accuracy of the threshold-based and proportion-based strategies is 88% and 84% respectively.

Three comparative approaches for breast density estimation in digital and screen film mammograms.

In general, several factors are used for risk estimation in breast cancer detection and early prevention, and one of the important factors in risk of breast cancer is breast density. The mammography is important and effective adjunct in diagnosing the breast cancer. The radiologists would analyze visually the breast density with the BI-RADS lexicon on mammograms. However, this usually causes a large inter-observer variability among the different experienced radiologists. In this paper, we individually adopt three methods, including pixel-based, region-based, and physics-based, to analyze the breast density on mammograms, and the results can offer radiologists a second quantification reading for predicting the risk of breast cancer. The three methods are tested on 208 digital and conventional film mammograms which are scanned from both breasts of 104 patients respectively. The experimental results show that the accuracy of the proposed region-based method, which is more consistent with the radiologists' viewpoint, is 88% more than other two conventional methods.