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

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.