A receiver operating characteristic partial area index for highly sensitive diagnostic tests.

Jiang, Yulei; Metz, Charles E.; Nishikawa, Robert M.

doi:10.1148/radiology.201.3.8939225

Cited by 254 publications

(177 citation statements)

References 0 publications

Supporting

Mentioning

174

Contrasting

Unclassified

Order By: Relevance

“…The differences in A z and 090 A z ' between the experienced mammographer and the computerized method were found to be not statistically significant (two-tailed P values of 0.38 and 0.30) based on the evaluation from the CLABROC program (35,36) and the modified version of the CLABROC program (30). Results of the Student t test for paired data showed that the differences in A and """A ' between the z 0.90 z average performance of the five radiologists and the computerized method were both statistically significant (twotailed P values of .0131 and .0015).…”

Section: Resultsmentioning

confidence: 88%

“…Clinically, the specificities at high sensitivity levels are most relevant because the "cost" of missing a cancer is greater than the cost of performing a biopsy to assess a benign lesion. Thus, the average performances in a high sensitivity range (true-positive fraction [TPF 0 ] above 0.90) were evaluated for both our classification schemes and the observers by using a partial area index, TPF A z ', from 0 to 1, which is the portion of the A that lies above a preselected sensitivity threshold (TPF 0 ) in a conventional ROC graph divided by the constant (1 -TPF 0 ) (30). These performances, in terms of specificity at a given sensitivity level, were also evaluated.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Advanced Methods for the Computer-Aided Diagnosis of Lesions in Digital Mammograms

Giger¹

1998

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 88%

Section: Methodsmentioning

confidence: 99%

Advanced Methods for the Computer-Aided Diagnosis of Lesions in Digital Mammograms

Giger¹

1998

View full text Add to dashboard Cite

“…The overall ROC area A z and the partial ROC area 0.90 A z were used as the reported performance indices. Although A z is the most common performance index for binary diagnostic tasks taking into account all possible decision thresholds, the partial ROC area index summarizes the detection performance for decision thresholds corresponding only to the high sensitivity portion (>90%) [46]. For our study, 0.90 A z is certainly a more appropriate performance index since any false-positive reduction scheme is expected to perform at a high cancer detection rate for a clinically effective cancer-screening CADe system.…”

Section: B Methodsmentioning

confidence: 99%

Evaluating the Effect of Image Preprocessing on an Information-Theoretic CAD System in Mammography

et al. 2008

View full text Add to dashboard Cite

Rationale and Objectives-In our earlier studies we reported an evidence-based Computer Assisted Decision (CAD) system for location-specific interrogation of mammograms. A contentbased image retrieval framework with information theoretic (IT) similarity measures serves as the foundation for this system. Specifically, the normalized mutual information (NMI) was shown to be the most effective similarity measure for reduction of false positive marks generated by other, prescreening mass detection schemes. The objective of this work was to investigate the importance of image filtering as a possible preprocessing step in our IT-CAD system. Materials and Methods-Different filters were applied, each one aiming to compensate for known limitations of the NMI similarity measure. The study was based on a region-of-interest database that included true masses and false positive regions from digitized mammograms. Results-ReceiverOperating Characteristics (ROC) analysis showed that IT-CAD is affected slightly by image filtering. Modest, yet statistically significant performance gain was observed with median filtering (overall ROC area index Az improved from 0.78 to 0.82). However, Gabor filtering improved performance for the high sensitivity portion of the ROC curve where a typical false positive reduction scheme should operate (partial ROC area index 0.90 A z improved from 0.33 to 0.37). Fusion of IT-CAD decisions from different filtering schemes markedly improved performance (A z =0.90 and 0.90 A z =0.55). At 95% sensitivity, the system's specificity improved by 36.6%.Conclusion-Additional improvement in false positive reduction can be achieved by incorporating image filtering as a preprocessing step in our information-theoretic CAD system.

show abstract

“…This measure corresponds to the probability of a drug-medical event pair known to be an ADR being assigned a higher confidence of being within the ADR class by the framework than a drug-medical event pair known to be a non-ADR [22]. In particular, we restrict out attention to a partial area, as we are only interested in the section of the curve where few drug-medical event pairs are classed as side effects [23]. When many drug-medical event pairs are classed as ADRs, there are likely to be many non-ADRs pairs incorrectly classed as ADRs and this is undesirable.…”

Section: Methodsmentioning

confidence: 99%

Tuning a Multiple Classifier System for Side Effect Discovery Using Genetic Algorithms

2014

View full text Add to dashboard Cite

Abstract-In previous work, a novel supervised framework implementing a binary classifier was presented that obtained excellent results for side effect discovery. Interestingly, unique side effects were identified when different binary classifiers were used within the framework, prompting the investigation of applying a multiple classifier system. In this paper we investigate tuning a side effect multiple classifying system using genetic algorithms. The results of this research show that the novel framework implementing a multiple classifying system trained using genetic algorithms can obtain a higher partial area under the receiver operating characteristic curve than implementing a single classifier. Furthermore, the framework is able to detect side effects efficiently and obtains a low false positive rate.

show abstract

A receiver operating characteristic partial area index for highly sensitive diagnostic tests.

Abstract: The partial area index can be used as a more meaningful alternative to the conventional Az index for highly sensitive diagnostic tests.

Cited by 254 publications

References 0 publications

Advanced Methods for the Computer-Aided Diagnosis of Lesions in Digital Mammograms

Advanced Methods for the Computer-Aided Diagnosis of Lesions in Digital Mammograms

Evaluating the Effect of Image Preprocessing on an Information-Theoretic CAD System in Mammography

Tuning a Multiple Classifier System for Side Effect Discovery Using Genetic Algorithms

Contact Info

Product

Resources

About