Multi-class classification algorithm for optical diagnosis of oral cancer

Majumder, Shovan K.; Gupta, Anand; Gupta, Sharad; Ghosh, Nirmalya; Gupta, Pradeep Kumar

doi:10.1016/j.jphotobiol.2006.05.004

Cited by 30 publications

(28 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optical spectroscopy is a noninvasive technique whose potential to facilitate diagnosis of oral lesions has been demonstrated by a number of groups [6][7][8][9][10][11][12]. Loss of autofluorescence in the blue-green region of the spectrum is thought to be diagnostically significant, and according to recent reports may be associated with subclinical genetic alterations in the cancer risk field [4]; but the nature of this association has not been explained.…”

Section: Introductionmentioning

confidence: 99%

Autofluorescence and diffuse reflectance spectroscopy of oral epithelial tissue using a depth-sensitive fiber-optic probe

et al. 2008

View full text Add to dashboard Cite

Optical spectroscopy can provide useful diagnostic information about the morphological and biochemical changes related to the progression of precancer in epithelial tissue. As precancerous lesions develop, the optical properties of both the superficial epithelium and underlying stroma are altered; measuring spectral data as a function of depth has the potential to improve diagnostic performance. We describe a clinical spectroscopy system with a depth-sensitive, ball lens coupled fiber-optic probe for noninvasive in vivo measurement of oral autofluorescence and diffuse reflectance spectra. We report results of spectroscopic measurements from oral sites in normal volunteers and in patients with neoplastic lesions of the oral mucosa; results indicate that the addition of depth selectivity can enhance the detection of optical changes associated with precancer.

show abstract

Section: Introductionmentioning

confidence: 99%

Autofluorescence and diffuse reflectance spectroscopy of oral epithelial tissue using a depth-sensitive fiber-optic probe

et al. 2008

View full text Add to dashboard Cite

show abstract

“…Consider two tasks T 1 and T 2 , and assume that the domain of the 3D ROC surface for T 1 is larger than and encloses the entire domain for T 2 . It is conceivable that the sensitivity of the ideal observer may be higher for T 1 than T 2 at all FPF values in the domain of T 2 , and despite this, the NVUS value for T 1 can be lower if the sensitivity for T 1 at FPF values outside the domain of T 2 is very low.…”

Section: Discussionmentioning

confidence: 99%

“…Let U ij (i ∈ {M, B, N}, j ∈ {M, B, N}), denote the utility of d i given t j , i.e., the utility of deciding that the observation belongs to class π i when the true class membership is π j . If the random vector w⃗ belongs to class π j , the expected utility conditioned on its class membership is (1) The expected utility of the decision rule is then given by averaging over all classes π j (2) where P(π j ) is the a-priori probability of class π j .…”

Section: A 3d Roc Surfacementioning

confidence: 99%

“…Many problems in pattern recognition involve multi-class classification, where the task can be defined as assigning a given observation vector to one of several classes. Some practical applications in the medical field in recent literature include: (1) diagnosis of oral cancer as high-grade squamous cell carcinoma, low-grade squamous cell carcinoma, leukoplakia, and normal squamous tissue [1]; (2) classification of the voxels in knee MRI volumes as tibial cartilage, femoral cartilage or the background [2]; (3) classification of ECG signals as normal, ventricular premature and supraventricular premature beats [3]; and (4) classification of pigmented skin lesions as benign, dysplastic nevi, or cutaneous melanoma [4]. In all of the applications above, the task of the designed classifier is to solve the multi-class discrimination task, as opposed to solving a number of binary decision tasks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance Analysis of Three-Class Classifiers: Properties of a 3-D ROC Surface and the Normalized Volume Under the Surface for the Ideal Observer

Sahiner

Chan

Hadjiiski

2008

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Classification of a given observation to one of three classes is an important task in many decision processes or pattern recognition applications. A general analysis of the performance of three-class classifiers results in a complex six-dimensional (6D) receiver operating characteristic (ROC) space, for which no simple analytical tool exists at present. We investigate the performance of an ideal observer under a specific set of assumptions that reduces the 6D ROC space to 3D by constraining the utilities of some of the decisions in the classification task. These assumptions lead to a 3D ROC space in which the true-positive fraction (TPF) can be expressed in terms of the two types of false-positive fractions (FPFs). We demonstrate that the TPF is uniquely determined by, and therefore is a function of, the two FPFs. The domain of this function is shown to be related to the decision boundaries in the likelihood ratio plane. Based on these properties of the 3D ROC space, we can define a summary measure, referred to as the normalized volume under the surface (NVUS), that is analogous to the area under the ROC curve (AUC) for a two-class classifier. We further investigate the properties of the 3D ROC surface and the NVUS for the ideal observer under the condition that the three class distributions are multivariate normal with equal covariance matrices. The probability density functions (pdfs) of the decision variables are shown to follow a bivariate log-normal distribution. By considering these pdfs, we express the TPF in terms of the FPFs, and integrate the TPF over its domain numerically to obtain the NVUS. In addition, we performed a Monte Carlo simulation study, in which the 3D ROC surface was generated by empirical "optimal" classification of case samples in the multi-dimensional feature space following the assumed distributions, to obtain an independent estimate of NVUS. The NVUS value obtained by using the analytical pdfs was found to be in good agreement with that obtained from the Monte Carlo simulation study. We also found that, under all conditions studied, the NVUS increased when the difficulty of the classification task was reduced by changing the parameters of the class distributions, thereby exhibiting the properties of a performance metric in analogous to AUC. Our results indicate that, under the conditions that lead to our 3D ROC analysis, the performance of a 3-class classifier may be analyzed by considering the ROC surface, and its accuracy characterized by the NVUS.

show abstract

“…Considerable success has been reported in distinguishing lesions from healthy oral mucosa, but the spectral variations among different anatomic sites within the oral cavity and the problem of discriminating benign lesions from precancerous/cancerous lesions continue to pose challenges [23,24]. Recent investigations reflect these complexities, including measurement techniques that target localized, superficial tissue regions where early premalignant changes are believed to occur [25,26]; algorithms that are explicitly based on specific anatomic sites within the oral cavity [27]; and multi-class algorithms that are designed to classify tissue into a range of diagnostic categories [28]. …”

Section: Introductionmentioning

confidence: 99%

Prospective evaluation of a portable depth-sensitive optical spectroscopy device to identify oral neoplasia

Schwarz

Gao

Stepanek

et al. 2010

Biomed. Opt. Express

View full text Add to dashboard Cite

A portable, depth-sensitive clinical spectroscopy device for noninvasive early diagnosis of oral cancer is described. We carried out a pilot study to evaluate the ability of the device to identify oral neoplasia using a previously developed diagnostic algorithm. A total of 79 oral sites in 33 subjects, including 28 patients with oral lesions and 5 healthy volunteers, were measured and analyzed. Measurements of 54 nonkeratinized oral sites yielded an area under the receiver operating characteristic curve of 0.90. Measurements of 25 keratinized oral sites yielded an area under the receiver operating characteristic curve of 0.83.

show abstract

Multi-class classification algorithm for optical diagnosis of oral cancer

Cited by 30 publications

References 30 publications

Autofluorescence and diffuse reflectance spectroscopy of oral epithelial tissue using a depth-sensitive fiber-optic probe

Autofluorescence and diffuse reflectance spectroscopy of oral epithelial tissue using a depth-sensitive fiber-optic probe

Performance Analysis of Three-Class Classifiers: Properties of a 3-D ROC Surface and the Normalized Volume Under the Surface for the Ideal Observer

Prospective evaluation of a portable depth-sensitive optical spectroscopy device to identify oral neoplasia

Contact Info

Product

Resources

About