Y Jiang

University of Chicago, Chicago, Illinois, United States

Are you Y Jiang?

Claim your profile

Publications (9)33.92 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: Receiver Operating Characteristic (ROC) analysis has been a mainstay of many research developments as well as various clinical studies/trials. It has provided medical physicists with a way to objectively measure how data are presented in an image, how people perceive those images, and how one can compare different observers or different imaging modalities with each other. ROC analysis plays an important role in both technology assessment and clinical decision‐making, especially as various aspects of imaging biomarkers and personalized medicine are evaluated. Over the past five years, on average, almost 40 papers/year that were published in MEDICAL PHYSICS utilized ROC analysis. The challenges and opportunities in ROC analysis research and in its application in various tasks are active areas, including expanding the mathematical formulation for multiple lesions per image, location‐based sensitivity, and evaluation without ground truth, as well as expanding its role in imaging biomarker validation, assessing response to therapy, theranostics, and image‐based phenotyping with genomics (image‐omics). Learning Objectives: 1. Review the mathematical foundations and implementation of ROC analysis in basic research and clinical trials; and understand the role and limitations of ROC analysis in large scale clinical studies/trials 2. Recognize advances in ROC analysis in order to incorporate multiple lesions per image, location‐based sensitivity, evaluation without ground truth, theranostics, and others 3. Appreciate the evolving role of ROC analysis in the evaluation of imaging biomarkers and image‐based phenotyping Research supported by NIH, DOE, and DOD. COI: Stockholder, Hologic, Inc Shareholder, Quantitative Insights, Inc Royalties, Hologic, Inc Royalties, General Electric Company Royalties, MEDIAN Technologies Royalties, Riverain Technologies, LLC Royalties, Mitsubishi Corporation Royalties, Toshiba Maryellen Giger Corporation Researcher, Koninklijke Philips Electronics NV Researcher, U‐Systems, Inc
    Medical Physics 06/2013; 40(6):494. DOI:10.1118/1.4815603 · 3.01 Impact Factor
  • Annals of the Rheumatic Diseases 02/2013; 72(Suppl 1):A23-A23. DOI:10.1136/annrheumdis-2013-203216.26 · 9.27 Impact Factor
  • Arthritis Research & Therapy 09/2012; 14(3). DOI:10.1186/ar3959 · 4.12 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Several of the authors have previously published an analysis of multiple sources of uncertainty in the receiver operating characteristic (ROC) assessment and comparison of diagnostic modalities. The analysis assumed that the components of variance were the same for the modalities under comparison. The purpose of the present work is to obtain a generalization that does not require that assumption. The generalization is achieved by splitting three of the six components of variance in the previous model into modality-dependent contributions. Two distinct formulations of this approach can be obtained from alternative choices of the three components to be split; however, a one-to-one relationship exists between the magnitudes of the components estimated from these two formulations. The method is applied to a study of multiple readers, with and without the aid of a computer-assist modality. performing the task of discriminating between benign and malignant clusters of microcalcifications. Analysis according to the first method of splitting shows large decreases in the reader and reader-by-case components of variance when the computer assist is used by the readers. Analysis in terms of the alternative splitting shows large decreases in the corresponding modality-interaction components. A solution to the problem of multivariate ROC analysis without the assumption of equal variance structure across modalities has been provided. Alternative formulations lead to consistent results related by a one-to-one mapping. A surprising result is that estimates of confidence intervals and numbers of cases and readers required for a specified confidence interval remain the same in the more general model as in the restricted model.
    Academic Radiology 08/2001; 8(7):605-15. · 2.08 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Area under a receiver operating characteristic (ROC) curve (Az) is widely used as an index of diagnostic performance. However, Az is not a meaningful summary of clinical diagnostic performance when high sensitivity must be maintained clinically. The authors developed a new ROC partial area index, which measures clinical diagnostic performance more meaningfully in such situations, to summarize an ROC curve in only a high-sensitivity region. The mathematical formation of the partial area index was derived from the conventional binormal model. Statistical tests of apparent differences in this index were formulated analogous to that of Az. One common statistical test involving the partial area index was validated by computer simulations under realistic conditions. An example in mammography illustrates a situation in which the partial area index is more meaningful than Az in measuring clinical diagnostic performance. The partial area index can be used as a more meaningful alternative to the conventional Az index for highly sensitive diagnostic tests.
    Radiology 01/1997; 201(3):745-50. DOI:10.1148/radiology.201.3.8939225 · 6.21 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: To develop a method for differentiating malignant from benign clustered microcalcifications in which image features are both extracted and analyzed by a computer. One hundred mammograms from 53 patients who had undergone biopsy for suspicious clustered microcalcifications were analyzed by a computer. Eight computer-extracted features of clustered microcalcifications were merged by an artificial neural network. Human input was limited to initial identification of the microcalcifications. Computer analysis allowed identification of 100% of the patients with breast cancer and 82% of the patients with benign conditions. The accuracy of computer analysis was statistically significantly better than that of five radiologists (P = .03). Quantitative features can be extracted and analyzed by a computer to distinguish malignant from benign clustered microcalcifications. This technique may help radiologists reduce the number of false-positive biopsy findings.
    Radiology 04/1996; 198(3):671-8. DOI:10.1148/radiology.198.3.8628853 · 6.21 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: To improve the performance of a computerized scheme for detection of clustered microcalcifications in digitized mammograms, causes of detected false-positive microcalcification signals were analyzed. The false positives were grouped into four categories, namely, microcalcification like noise patterns, artifacts, linear patterns, and others. In an edge-gradient analysis, local edge-gradient values at signal-perimeter pixels of detected microcalcification signals were determined to eliminate false positives that look like subtle microcalcifications or are due to artifacts. In a linear-pattern analysis, the degree of linearity for linear patterns was determined from local gradient values from a set of linear templates oriented in 16 different directions. Threshold values for the edge-gradient analysis and the linear-pattern analysis were determined using a training database of 39 mammograms. It was possible to eliminate 59% and 25%, respectively, of 91 detected false-positive clusters with loss of only 3% of true-positive clusters. The combination of the two methods further improved the scheme in eliminating a total of 73% of the false-positive clusters with loss of 3% of true-positive clusters. Using these thresholds, the two methods were evaluated on another database of 50 mammograms. 62%, 31%, and 80% of the false-positive clusters were eliminated with loss of 3% of true-positive clusters or less, in the edge-gradient analysis, the linear-pattern analysis, and the combination of the two methods, respectively. The edge-gradient analysis and the linear-pattern analysis can reduce the false-positive detection rate, while maintaining a high level of the sensitivity.
    Medical Physics 03/1995; 22(2):161-9. DOI:10.1118/1.597465 · 3.01 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: A computerized technique is being developed to automatically detect clustered microcalcifications on digital mammograms. The method consists of three steps. First the signal-to-noise ratio of microcalcifications is enhanced by filtering the image to reduce the normal background structure of the mammogram. Second, signals (potential microcalcifications) are identified by means of global grey-level thresholding, morphological erosion, and a local adaptive grey-level thresholding. Third, the number of falsely detected signals is reduced by examining the power spectrum of individual signals, determining the spatial distribution of the signals, and examining the relationship between size, shape, and background pixel value of microcalcifications. Using this approach, the computer scheme was tested using 78 mammograms, half containing subtle clusters of microcalcifications and half containing no clusters. The scheme was capable of detecting 87% of true clusters with, on average, two false clusters detected per image
    Systems, Man and Cybernetics, 1992., IEEE International Conference on; 11/1992