We intend to construct a system to automatically diagnose malignant potential of colon biopsies. First, we classified biopsies components (nuclei, cytoplasm and interstitium) by discriminant analysis method with Mahalanobis's generalized distance and Otsu method twice. Furthermore, only ductal nuclei were sorted out from the other nuclei by using differences of areas and densities of edges, that is high in lymphoid follicles. We proposed a method for quantifying pseudostratified nuclei by a measure of thickness of ductal nuclei and methods for quantifying structural atypia by fractal dimension analysis with Box-counting method and HLAC features. Moreover, poorly and moderately differentiated carcinoma in Group5 was able to be discriminated with high accuracy by density of labeled ranges. With these features, biopsies' images were classified into 4 Groups by support vector machine.
|出版ステータス||Published - 2013 1月 1|
|イベント||2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013 - Nagoya, Japan|
継続期間: 2013 9月 14 → 2013 9月 17
|Other||2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013|
|Period||13/9/14 → 13/9/17|
ASJC Scopus subject areas
- コンピュータ サイエンスの応用