Search

1.1 Knowledge representation The most essential part of building an expert system is the acquirement and representation of domain knowledge. In the seventies, Feigenbaum indicated the important concept of knowledge engineering. He emphasized that to utilize knowledge in problem-solving process is equally important with knowing how to solve a problem. Knowledge, according to how it is stored, can be classified to tacit knowledge and explicit knowledge. The tacit knowledge, existing in the brain of experts, can only be acquired through interviewing the domain experts. On the other hand, the explicit knowledge can be expressed clearly. Since explicit knowledge is easier to be handled, it was used in most expert systems. Knowledge representation affects how problems are solved. Human knowledge can be expressed in the form of mathematic formulas, speech, text and figures. In artificial intelligence domain, especially in expert system research, several knowledge representation forms had been proposed (Negnevitsky, 2002). They are: 1. Semantic networks (Quillian, 1965, 1968): Using directed graph to represent knwolege objects and their relationship. Each object in the network is linked to other objects by their semantic relationships. 2. Case-based format (Watson, 1997; Kolodner 1993): Knowledge is stored in the form of cases-solutions. 3. Rule-based format (Triantaphyllou & Felici, 2006): If-Then rules are stored as the knowledge source. 4. Frame-based format (Minsky, 1975): Objects are divided into several frames, and each frame contains its corresponding attribute to describe the characteristics of the objects. 5. Ontology (Munn, 2009 ; Uschold & Gruninger, 1996): It is a representation of some pre-existing domain of reality which reflects the properties of the objects within its domain in such a way that there obtains a systematic correlation between reality and the representation itself. It is formalized in a way that allows it to support automatic information processing. 22

Purpose To assess the effect of the previously reported optical coherence tomography (OCT) signal normalization method on reducing the discrepancies in image appearance among spectral-domain OCT (SD-OCT) devices. Methods Healthy eyes and eyes with various retinal pathologies were scanned at the macular region using similar volumetric scan patterns with at least two out of three SD-OCT devices at the same visit (Cirrus HD-OCT, Zeiss, Dublin, CA; RTVue, Optovue, Fremont, CA; and Spectralis, Heidelberg Engineering, Heidelberg, Germany). All the images were processed with the signal normalization. A set of images formed a questionnaire with 24 pairs of cross-sectional images from each eye with any combination of the three SD-OCT devices either both pre- or postsignal normalization. Observers were asked to evaluate the similarity of the two displayed images based on the image appearance. The effects on reducing the differences in image appearance before and after processing were analyzed. Results Twenty-nine researchers familiar with OCT images participated in the survey. Image similarity was significantly improved after signal normalization for all three combinations (P ≤ 0.009) as Cirrus and RTVue combination became the most similar pair, followed by Cirrus and Spectralis, and RTVue and Spectralis. Conclusions The signal normalization successfully minimized the disparities in the image appearance among multiple SD-OCT devices, allowing clinical interpretation and comparison of OCT images regardless of the device differences. Translational Relevance The signal normalization would enable direct OCT images comparisons without concerning about device differences and broaden OCT usage by enabling long-term follow-ups and data sharing.

To determine whether angiography with swept-source (SS) optical coherence tomography (OCT) identifies subclinical type 1 neovascularization in asymptomatic eyes with intermediate age-related macular degeneration (iAMD).Prospective, observational, consecutive case series.Patients with asymptomatic iAMD in one eye and neovascular age-related macular degeneration (AMD) in their fellow eye.The patients underwent SS OCT angiography (OCTA), fluorescein angiography (FA), and indocyanine green angiography (ICGA), and the images from these 3 angiographic techniques were compared.Identification of subclinical type 1 neovascularization with SS OCTA in asymptomatic eyes with iAMD.Eleven consecutive patients with iAMD in one eye and neovascular AMD in their fellow eye were imaged with FA, ICGA, and SS OCTA between August 2014 and September 2015. Clinical examination of the 11 eyes revealed drusen and pigmentary abnormalities in the central macula and no evidence of macular fluid on routine OCT imaging. Ten of the 11 eyes had no evidence of leakage on FA and 1 eye had questionable fluorescein leakage. Indocyanine green angiography revealed the presence of central macular plaques in 3 of the 11 asymptomatic eyes with iAMD, and SS OCTA revealed unambiguous type 1 neovascularization corresponding to the plaques in all 3 eyes. Optical coherence tomography angiography did not identify neovascularization in the remaining 8 eyes.Swept-source OCTA identified type 1 neovascularization corresponding to ICGA plaques in asymptomatic eyes with iAMD. The ability of OCTA to provide noninvasive, fast, detailed, depth-resolved identification of nonexudative neovascular lesions in eyes with iAMD suggests the need for a new classification system that distinguishes between neovascular and nonneovascular iAMD.

To image subretinal neovascularization in proliferative macular telangiectasia Type 2 (MacTel2) using swept source optical coherence tomography based microangiography (OMAG).Patients with macular telangiectasia Type 2 were enrolled in a prospective, observational study known as the MacTel Project and evaluated using a high-speed 1,050 nm swept-source OCT prototype system. The OMAG algorithm generated en face flow images from three retinal layers, and the region bounded by the outer retina and Bruch membrane, the choriocapillaris, and the remaining choroidal vasculature. The en face OMAG images were compared with images from fluorescein angiography and indocyanine green angiography.Three eyes with neovascular macular telangiectasia Type 2 were imaged. The neovascularization was best identified from the en face OMAG images that included a layer between the outer retinal boundary and Bruch membrane. Optical coherence tomography based microangiography images identified these abnormal vessels better than fluorescein angiography and were comparable to the images obtained using indocyanine green angiography. In all 3 cases, OMAG identified choroidal vessels communicating with the neovascularization, and these choroidal vessels were evident in the 2 cases with indocyanine green angiography imaging. In 1 case, monthly injections of bevacizumab reduced the microvascular complexity of the neovascularization, and the telangiectatic changes within the retinal microvasculature. In another case, less frequent bevacizumab therapy was associated with growth of the subretinal neovascular complex.Optical coherence tomography based microangiography imaging provided detailed, depth-resolved information about subretinal neovascularization in macular telangiectasia Type 2 eyes demonstrating superiority to fluorescein angiography imaging, and similarities to indocyanine green angiography imaging for documenting the retinal microvascular changes, the size and extent of the neovascular complex, the communications between the neovascular complex and the choroidal circulation, and the response to monthly bevacizumab therapy.