Fast JPEG 2000 decoder and its use in medical imaging

Acceptable compression ratio of full-field digital mammography using JPEG 2000

AIM

To estimate the acceptable compression ratio of full-field digital mammography (FFDM) using the Joint Photographic Experts Group (JPEG) 2000 compression algorithm.

MATERIALS AND METHODS

Eighty cases that included images of 40 masses (20 benign, 20 malignant) and 40 microcalcifications (20 benign, 20 malignant) were collected. The images were compressed to five different lossy ratios: 20:1, 40:1, 60:1, 80:1, and 100:1, and four radiologists independently determined whether the compressed group was distinguishable from the control group. The ratio of the compressed group that was rated indistinguishable from the control group was compared for each reviewer, and the results were analysed for agreements of three or more reviewers.

RESULTS

The ability to distinguish the compressed image from the control group is given as a range across the four reviewers: 0-1.3% (0/80 to 1/80) of the 20:1, 0-2.5% (0/80 to 2/80) of the 40:1, 5-7.5% (4/80 to 6/80) of the 60:1, 10-37.5% (8/80 to 30/80) of the 80:1, and 30-87.5% (24/80 to 70/80) of the 100:1. For three compression groups (20:1, 40:1, and 60:1), three or more reviewers agreed that there was a distinguishable difference for 0/80, 0/80, and 3/80 images, respectively. Thus, the compressed images do not differ significantly from the control group (p>0.05). However, the 80:1 and 100:1 compressed images were different for 9/80 and 29/80 images, respectively, which is significantly different from the control group (p<0.05).

CONCLUSION

The lossy 60:1 compression ratio for FFDM is visually identical to the control image and, therefore, potentially acceptable for primary interpretation.

Impact of JPEG 2000 compression on lesion detection in MR imaging

PURPOSE

Lossy compression algorithms enable the efficient transmission of large medical image datasets over bandwidth-limited digital networks or facilitate the long-term storage of the daily image production. Although JPEG 2000 has been adopted by DICOM as the standard for lossy-to-lossless compression, still a set of guidelines needs to be derived that allows for the usage of the lossy mode, potentially jeopardizing the accuracy of lesion detection and characterization, and so, of the resulting diagnosis task effectiveness in the medical diagnosis process. In this article the authors present and evaluate a generic methodology for the determination of the minimal bit rate that still ensures an accurate detection in magnetic resonance images of specific lesions. In this article, they demonstrate the methodology for two particular pathologies, i.e., multiple sclerosis and Virchow-Robin space enlargements.

METHODS

Involving qualified personnel, the minimal bit rate is estimated from ROC experiments initially simulated through mathematical observers that are designed with several objective metrics. The mathematical observer models included three variants of the Hotelling observer plus the non-prewhitening matched filter with eye model, while the objective measures are based on distance, correlation, singular value decomposition, and structural similarity.

RESULTS

The results indicate that the highest compression without seriously affecting the detection of the studied lesions is achieved at a bit rate of 0.125 bpp. At this value, the detection effectiveness exceeded 95% with less than 5% standard deviation, while only 4.4% of the outcomes were classified as false negatives by the experts and 11.6% as false positives.

CONCLUSIONS

The optimal bit rate found assures that important information on the small investigated structures is still preserved for their accurate detection and their a posteriori characterization.

Detection of simulated lesions on data-compressed digital mammograms

PURPOSE

To evaluate retrospectively the effect of a wavelet-based compression method on the detection of simulated masses of various sizes and clustered microcalcifications on data-compressed digital mammograms.

MATERIALS AND METHODS

The images used in this study were acquired with institutional review board approval and patient informed consent, both of which allowed subsequent image data analysis. Patient identification was removed from images, and the study complied with requirements of the Health Insurance Portability and Accountability Act. Masses 3, 6, and 8 mm in diameter were analytically simulated and added to clinical mammographic backgrounds. In addition, microcalcifications were extracted from a clinical mammogram and hybridized with simulated microcalcifications for use in this study. Image compression conditions of 1:1, 15:1, and 30:1 were investigated. Observer responses were recorded with a six-point rating scale, and receiver operating characteristic (ROC) analysis was performed. In addition, two well-established numeric observer models were used to study the effect of image compression under the same compression conditions as were used with human observers. Analysis of variance was performed after observer adjustment to compare the mean values for area under the ROC curve (A(z)) across the three compression levels for the masses and microcalcification clusters.

RESULTS

The results of the study indicated no significant differences in the A(z) values for masses with the compression conditions investigated. For images of microcalcifications, there were significant differences in A(z) values between compression ratios of 1:1 and 30:1 (P = .0005) and of 15:1 and 30:1 (P = .004); the difference between compression ratios of 1:1 and 15:1 was nonsignificant (P = .053). The observer models and human observers exhibited similar trends in detection of the masses investigated in this study.

CONCLUSION

Detection of simulated masses was not affected by the compression method with the conditions used in this study, while the detection of microcalcifications was significantly reduced with a compression ratio of more than 15:1.

Interactive image enhancement of CR and DR images

There is continual pressure on the radiology department to increase its productivity. Two important links to productivity in the computed/digital radiography (CR/DR) workflow chain are the postprocessing step by technologists and the primary diagnosis step by radiologists, who may apply additional image enhancements to aid them in diagnosis. With the large matrix size of CR and DR images and the computational complexity of these algorithms, it has been challenging to provide interactive image enhancement, particularly on full-resolution images. We have used a new programmable processor as the main computing engine of enhancement algorithms for CR or DR images. We have mapped these algorithms to the processor, maximally utilizing its architecture. On a 12-bit 2688 x 2688 image, we have achieved the execution time of 465A ms for adaptive unsharp masking, window/level, image rotate, and lookup table operations using a single processor, which represents at least an order of magnitude improvement compared to the response time of current systems. This kind of performance facilitates rapid computation with preset parameter values and/or enables truly interactive QA processing on radiographs by technologists. The fast response time of these algorithms would be especially useful in a real-time radiology setting, where the radiologist's waiting time in performing image enhancements before making diagnosis can be greatly reduced. We believe that the use of these processors for fast CR/DR image computing coupled with the seamless flow of images and patient data will enable the radiology department to achieve higher productivity.