Domain-Specific Image Analysis for Cervical Neoplasia Detection Based on Conditional Random Fields

Abstract

This paper presents a domain-specific automated image analysis framework for the detection of pre-cancerous and cancerous lesions of the uterine cervix. Our proposed framework departs from previous methods in that we include domain-specific diagnostic features in a probabilistic manner using conditional random fields. Likewise, we provide a novel window-based performance assessment scheme for 2D image analysis which addresses the intrinsic problem of image misalignment. Image regions corresponding to different tissue types are indentified for the extraction of domain-specific anatomical features. The unique optical properties of each tissue type and the diagnostic relationships between neighboring regions are incorporated in the proposed conditional random field model. The validity of our method is examined using clinical data from 48 patients, and its diagnostic potential is demonstrated by a performance comparison with expert colposcopy annotations, using histopathology as the ground truth. The proposed automated diagnostic approach can support or potentially replace conventional colposcopy, allow tissue specimen sampling to be performed in a more objective manner, and lower the number of cervical cancer cases in developing countries by providing a cost effective screening solution in low-resource settings.

A system for detection of cervical precancerous in field emission scanning electron microscope images using texture features

“…The comparison performances of the cervical screening system and the several aforementioned approaches are tabulated in Table 3 in term of accuracy, sensitivity, and speci¯city. Four systems, namely system A, 25 B, 8 C, 26 and the proposed system are included for comparison.…”

“…Based on the results, the proposed system could be applied in clinical cervical cancer screening procedures. Note: System A, 25 B, 8 C, 26 and D (proposed system).…”

Scope of Improvement in Quality of Diagnostic Images for Pelvic region

“…It contributed for the classification of lesions however it suffers due to sticking with local optimal points to establish the relativity. Conditional random field, which is a member of the family of markov random field, has been exploited in [3] determine the lesions in the uterine cervix. Since the imaging systems often produce misalignment in the resultant image, a window based scheme has been used along with the conditional random field.…”

Intelligent Screening Systems for Cervical Cancer

“…Meanwhile, another feature to differentiate the abnormality of cervix using FISH image is the average intensity of each colored spot [60]. At the case of tissue level images, the changes in color and intensity correlate closely with changes in tissue type, severity of cervical neoplasia, and vessel patterns [61, 67, 86, 91, 93–97]. …”

“…Several techniques used for extracting the intensity features are as follows.Clustering technique [67, 86, 95, 97]. …”