by Mu, Tingting; Nandi, Asoke K.; Rangayyan, Rangaraj M.

Breast masses due to benign disease and malignant tumors related to breast cancer differ in terms of shape, edge-sharpness, and texture characteristics. In this study, we evaluate a set of 22 features including 5 shape factors, 3 edge-sharpness measures, and 14 texture features computed from 111 regions in mammograms, with 46 regions related to malignant tumors and 65 to benign masses. Feature selection is performed by a genetic algorithm based on several criteria, such as alignment of the kernel with the target function, class separability, and normalized distance. Fisher’s linear discriminant analysis, the support vector machine (SVM), and our strict two-surface proximal (S2SP) classifier, as well as their corresponding kernel-based nonlinear versions, are used in the classification task with the selected features. The nonlinear classification performance of kernel Fisher’s discriminant analysis, SVM, and S2SP, with the Gaussian kernel, reached 0.95 in terms of the area under the receiver operating characteristics curve. The results indicate that improvement in classification accuracy may be gained by using selected combinations of shape, edge-sharpness, and texture features.

DOI: 10.1007/s10278-007-9102-z
Online Date: 2/28/2008
Print publication date: 6/1/2008
View article on SpringerLink

by Buccoliero, Luca; Calciolari, Stefano; Marsilio, Marta; Mattavelli, Elisa

This contribution focuses on picture archiving and communication systems (PACS) in the Italian National Healthcare System (NHS). It finally aims to test the Chiefs Radiology Department’s perceptions about PACS along the main evaluation dimensions emerging from the literature. First, a brief review of the main literature concerning PACS evaluation leads the authors to classify the different approaches undertaken and highlight the main variables of investigation. Second, the evidence emerging from a survey is presented and discussed in the light of the literature review. The survey aims to: (a) map out the degree of PACSs diffusion and their main features in the Italian NHS; (b) verify whether and how PACS impact the dimensions analyzed in many evaluation studies carried out to date; (c) test the relationship between some measured impacts and specific PACS features.

DOI: 10.1007/s10278-007-9101-0
Online Date: 2/22/2008
Print publication date: 2/1/2009
View article on SpringerLink

by Minnigh, Todd R.; Gallet, Jacqueline

Repeats are indicators for the quality-imaging manager to schedule additional training and to be used as a basis for dialog with the reading radiologists to improve the service and quality to patients and referring physicians. Through the thoughtful application of software and networking, dose management, X-ray usage, and repeat analysis data can be made available centrally. This provides clinically useful technologist-centric results greatly benefiting an enterprise. This study tracked a radiology department’s use of a digital X-ray dashboard software application. It was discovered that 80% of the exams were performed by only 21% of the technologists and that the technologist with the highest throughput had a personal repeat rate of 6.5% compared to the department average of 7.6%. This study indicated that useful information could be derived and used as a basis for improving the radiology department’s operations and in maintaining high quality standards.

DOI: 10.1007/s10278-007-9098-4
Online Date: 2/13/2008
Print publication date: 2/1/2009
View article on SpringerLink

by Kobayashi, Luiz O. M.; Furuie, Sergio S.

This paper presents a novel algorithm to successfully achieve viable integrity and authenticity addition and verification of n-frame DICOM medical images using cryptographic mechanisms. The aim of this work is the enhancement of DICOM security measures, especially for multiframe images. Current approaches have limitations that should be properly addressed for improved security. The algorithm proposed in this work uses data encryption to provide integrity and authenticity, along with digital signature. Relevant header data and digital signature are used as inputs to cipher the image. Therefore, one can only retrieve the original data if and only if the images and the inputs are correct. The encryption process itself is a cascading scheme, where a frame is ciphered with data related to the previous frames, generating also additional data on image integrity and authenticity. Decryption is similar to encryption, featuring also the standard security verification of the image. The implementation was done in JAVA, and a performance evaluation was carried out comparing the speed of the algorithm with other existing approaches. The evaluation showed a good performance of the algorithm, which is an encouraging result to use it in a real environment.

DOI: 10.1007/s10278-008-9103-6
Online Date: 2/12/2008
Print publication date: 2/1/2009
View article on SpringerLink

by Asbach, Patrick; Canda, Valer; Hermann, Kay-Geert A.; Krug, Lasse; Hahn, Horst K.; Hamm, Bernd; Klessen, Christian

The study investigates the performance of a dedicated whole-body magnetic resonance imaging (MRI) interpretation software with regard to diagnostic efficiency using quantitative and qualitative parameters. Forty-eight oncologic patients underwent whole-body computed tomography (WB-CT) and whole-body magnetic resonance imaging (WB-MRI). In a quantitative analysis, the times needed for interpretation of the CT and MRI datasets were measured. The MRI studies were read using a standard workstation and the whole-body MRI interpretation software, respectively. In the qualitative analysis, the numbers of metastases were separately recorded for 13 organ systems, again interpreting the MRI images on the standard workstation and with the dedicated software. Moreover, user friendliness and system usability were evaluated using a standardized questionnaire. Use of the whole-body MRI interpretation software significantly reduced the MRI interpretation time compared with the standard workstation. There was no significant difference between interpretation time of WB-CT and interpretation time of WB-MRI using the dedicated software. Comparison with WB-CT as the reference method demonstrated no significant difference between the whole-body MRI interpretation software prototype and the standard interpretation software in the number of metastases detected. In conclusion, the use of the dedicated whole-body reading software improves the interpretation process of WB-MRI studies with respect to time efficiency and system usability.

DOI: 10.1007/s10278-008-9107-2
Online Date: 2/12/2008
Print publication date: 10/1/2008
View article on SpringerLink

by Veldkamp, Wouter J.H.; Kroft, Lucia J.M.; Delft, Jan Pieter A.; Geleijns, Jacob

The purpose of this study is to provide a pragmatic tool for studying the relationship between dose and image quality in clinical chest images. To achieve this, we developed a technique for simulating the effect of dose reduction on image quality of digital chest images. The technique was developed for a digital charge-coupled-device (CCD) chest unit with slot-scan acquisition. Raw pixel values were scaled to a lower dose level, and a random number representing noise to each specific pixel value was added. After adding noise, raw images were post processed in the standard way. Validation was performed by comparing pixel standard deviation, as a measure of noise, in simulated images with images acquired at actual lower doses. To achieve this, a uniform test object and an anthropomorphic phantom were used. Additionally, noise power spectra of simulated and actual images were compared. Also, detectability of simulated lesions was investigated using a model observer. The mean difference in noise values between simulated and real lower-dose phantom images was smaller than 5% for relevant clinical settings. Noise power spectra appeared to be comparable on average but simulated images showed slightly higher noise levels for higher spatial frequencies and slightly lower noise levels for lower spatial frequencies. Comparable detection performance was shown in simulated and actual images with slightly worse detectability for simulated lower dose images. We have developed and validated a method for simulating dose reduction. Our method seems an acceptable pragmatic tool for studying the relationship between dose and image quality.

DOI: 10.1007/s10278-008-9104-5
Online Date: 2/8/2008
Print publication date: 4/1/2009
View article on SpringerLink

by Wang, X.; Chao, L.; Chen, L.; Tian, B.; Ma, G.; Zang, Y.; Hua, M.; Sun, J.

HER-2/neu is a valuable therapeutic and prognostic marker in primary breast carcinomas. The aim of this study was to evaluate the association between mammographic calcifications and HER-2/neu overexpression in primary breast carcinomas and assess its clinical perspective. A retrospective study of 152 preoperative mammograms in patients with breast carcinoma was performed. Expression of HER-2/neu was determined by immunohistochemical staining on 152 tissues that comprised specimens of 11 ductal carcinoma in situ (DCIS) and 141 primary invasive carcinomas. Mammographic calcifications were evaluated according to the Breast Imaging Reporting and Data System (BI-RADS), fourth edition. Calcifications were found in 73 (48.0%) out of 152 patients by mammography finding. Calcifications were more common in carcinomas with HER-2/neu overexpression (45:73, 61.6%) than in those without HER-2/neu overexpression (28:79, 35.4%; P = 0.001). Of the 73 carcinomas with calcifications on mammography, mass with spiculated margin as an associated finding of calcifications was more significantly frequent in carcinomas with HER-2/neu overexpression (15 of 45, 33.3%) than in those without HER-2/neu overexpression (2 of 28, 7.1%; P = 0.036). Fine linear morphology was more common in carcinomas with HER-2/neu overexpression (15:45, 33.3%) when compared with those without HER-2/neu overexpression (2:28, 7.1%; P = 0.036). Clustered distribution of calcifications was more common in carcinomas with HER-2/neu overexpression (26:45, 57.8%) compared with carcinomas without HER-2/neu overexpression (6:28, 21.4%; P = 0.048). Mammographic calcifications are correlated with HER-2/neu overexpression in primary breast carcinomas. Calcifications detected during screening mammography are not only of diagnostic value but of use in determining therapeutic options and prognosis.

DOI: 10.1007/s10278-008-9105-4
Online Date: 2/7/2008
Print publication date: 6/1/2008
View article on SpringerLink

by Deserno, Thomas M.; Antani, Sameer; Long, Rodney

Content-based image retrieval (CBIR) is a promising technology to enrich the core functionality of picture archiving and communication systems (PACS). CBIR has a potential for making a strong impact in diagnostics, research, and education. Research as reported in the scientific literature, however, has not made significant inroads as medical CBIR applications incorporated into routine clinical medicine or medical research. The cause is often attributed (without supporting analysis) to the inability of these applications in overcoming the “semantic gap.” The semantic gap divides the high-level scene understanding and interpretation available with human cognitive capabilities from the low-level pixel analysis of computers, based on mathematical processing and artificial intelligence methods. In this paper, we suggest a more systematic and comprehensive view of the concept of “gaps” in medical CBIR research. In particular, we define an ontology of 14 gaps that addresses the image content and features, as well as system performance and usability. In addition to these gaps, we identify seven system characteristics that impact CBIR applicability and performance. The framework we have created can be used a posteriori to compare medical CBIR systems and approaches for specific biomedical image domains and goals and a priori during the design phase of a medical CBIR application, as the systematic analysis of gaps provides detailed insight in system comparison and helps to direct future research.

DOI: 10.1007/s10278-007-9092-x
Online Date: 2/1/2008
Print publication date: 4/1/2009
View article on SpringerLink

by He, Qian; He, Wen; Wang, Keyang; Ma, Daqing

The aim of this study is to evaluate the effect of multiscale processing in digital chest radiography on automated detection of lung nodule with a computer-aided diagnosis (CAD) system. The study involved 58 small-nodule patient cases and 58 normal cases. The 58 patient cases included a total of 64 noncalcified lung nodules up to 15 mm in diameter. Each case underwent an examination with a digital radiography system (Digital Diagnost, Philips Medical Systems), and the acquired image was processed by the following three types of multiscale processing (Unique Image Processing Package, Philips Medical Systems) respectively: (1) standard image from the default processing parameter (structure preference, 0.0), (2) high-pass image with structure preference of 0.4, (3) low-pass image with structure preference of −0.4. The CAD output images were produced with a real-time computer assistance system (IQQA™-Chest, EDDA Technology). Two experienced chest radiologists established the nodule gold standard by consensus reading according to computed tomography results, and analyzed and recorded the detection of lung nodules and false-positive detections of these CAD output images. For the entire cases involved (each case with three types of different processing), a total of 348 observations were evaluated by the receiver operating characteristic (ROC) analysis. The mean area under the ROC curve (

) value was 0.700 for the standard images, 0.587 for the high-pass images, and 0.783 for the low-pass images. There were statistically significant
_z values among these three types of processed images ( < 0.01). Multiscale processing in digital chest radiography can affect the automated detection of lung nodule by CAD, which is consistent with effects from visual inspection.

DOI: 10.1007/s10278-007-9094-8
Online Date: 2/1/2008
Print publication date: 10/1/2008
View article on SpringerLink