An automated tissue preclassification approach for telepathology: implementation and performance analysis.

Telepathology is generally defined as the use of telecommunications technologies in the practice of anatomic or surgical pathology. In the usual telepathology scenario, a remotely located pathologist views images of tissues samples in order to render a diagnosis of the biopsy. Some telepathology systems involve interactive remote control of a microscope-based imaging system which delivers diagnostic quality imagery to the remote pathologist. The usefulness of such interactive systems depends on minimizing the end-to-end delays involved in controlling the robotic microscope, manipulating the tissue sample, and acquiring and transmitting the high-resolution image. An approach to minimizing end-to-end delay involves adding "intelligence" to the image acquisition system so that it can gather, classify, rank, and transmit diagnostically useful images in a semiautonomous fashion. In this research, we develop image analysis and ranking techniques which can improve the end-to-end performance of a robotic telepathology imaging system. Our semiautonomous image collection system uses morphological techniques to extract seed points for suspicious regions, a novel region growing algorithm to segment the regions of interest, and heuristically motivated expert system ranking techniques to select diagnostically relevant "next-step" image acquisitions. Diagnostic relevance of our segmentation and ranking algorithms is established via subjective and objective testing of the system. In subjective testing, pathologists Agree or Strongly Agree that all segmented regions are diagnostically relevant with probability greater than 0.75. In objective testing, 84% of "next-step" images acquired by our algorithms coincide with the areas most likely to be chosen by a pathologist.