{"title":"使用Gabor滤波器集对小叶颈内腺增生进行判别分析:用Gabor滤波器特征对核不典型进行数值解释。","authors":"Fumikazu Kimura, Kengo Ohshima, Keiichiro Shirai, Ryo Kanai, Masaki Sonohara, Keiko Ishii","doi":"10.1159/000533255","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Lobular endocervical glandular hyperplasia (LEGH) is a benign lesion; however, it is considered to be the origin of gastric-type adenocarcinoma in the uterine cervix, and early diagnosis is important. At Shinshu University Hospital, screening of LEGH cells is based on the difference in color tone of cytoplasmic mucin on Papanicolaou staining and detection of gastric mucin using HIK1083-labeled latex agglutination assay. However, it is sometimes difficult to distinguish LEGH cells with subtle nuclear atypia from endocervical (EC) cells.</p><p><strong>Methods: </strong>We calculated the Gabor filter features (mean signal value, standard deviation, skewness, kurtosis) from the nuclei of cytological specimens in EC cells (37 cases) and LEGH cells (33 cases) using microscopic images, and we performed statistical analysis and discriminant analysis by linear support vector machine (LSVM) using these features. A Gabor filter is a linear filter defined as a mathematical representation of the mammalian visual system. Gabor filters with three wavelengths and eight angles were used for analysis.</p><p><strong>Results: </strong>Gabor filter features in EC cells were higher than in LEGH cells, demonstrating that the gradient of LEGH cell nuclei was milder than that of EC cell nuclei. The accuracy calculated using all Gabor filters was 91.0% and the accuracy of four Gabor filters (λ = 2/3π and θ = 0°, 45°, 90°, 135°) was 88.9%. High accuracy with low computation costs was achieved by reducing the number of features used for LSVM.</p><p><strong>Conclusion: </strong>The application of a Gabor filter with convolutional processing resulted in the edges of LEGH cells being slightly rough and thick, whereas those of EC cells were fine and thin. Thus, it is thought that the frequency of abrupt gradients of pixels was higher in EC cells than in LEGH cells, and the gradient of chromatin distribution in LEGH cell nuclei was milder than that in EC cell nuclei. It was possible to evaluate nuclear findings of EC and LEGH cells objectively by quantifying morphological features of nuclei using Gabor filters. It was possible to differentiate EC cells from LEGH cells using LSVM using Gabor filter features.</p>","PeriodicalId":6959,"journal":{"name":"Acta Cytologica","volume":" ","pages":"539-549"},"PeriodicalIF":1.6000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Discriminant Analysis Using Gabor Filter Sets for Lobular Endocervical Glandular Hyperplasia: Numerical Interpretation of Nuclear Atypia by Gabor Filter Features.\",\"authors\":\"Fumikazu Kimura, Kengo Ohshima, Keiichiro Shirai, Ryo Kanai, Masaki Sonohara, Keiko Ishii\",\"doi\":\"10.1159/000533255\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Introduction: </strong>Lobular endocervical glandular hyperplasia (LEGH) is a benign lesion; however, it is considered to be the origin of gastric-type adenocarcinoma in the uterine cervix, and early diagnosis is important. At Shinshu University Hospital, screening of LEGH cells is based on the difference in color tone of cytoplasmic mucin on Papanicolaou staining and detection of gastric mucin using HIK1083-labeled latex agglutination assay. However, it is sometimes difficult to distinguish LEGH cells with subtle nuclear atypia from endocervical (EC) cells.</p><p><strong>Methods: </strong>We calculated the Gabor filter features (mean signal value, standard deviation, skewness, kurtosis) from the nuclei of cytological specimens in EC cells (37 cases) and LEGH cells (33 cases) using microscopic images, and we performed statistical analysis and discriminant analysis by linear support vector machine (LSVM) using these features. A Gabor filter is a linear filter defined as a mathematical representation of the mammalian visual system. Gabor filters with three wavelengths and eight angles were used for analysis.</p><p><strong>Results: </strong>Gabor filter features in EC cells were higher than in LEGH cells, demonstrating that the gradient of LEGH cell nuclei was milder than that of EC cell nuclei. The accuracy calculated using all Gabor filters was 91.0% and the accuracy of four Gabor filters (λ = 2/3π and θ = 0°, 45°, 90°, 135°) was 88.9%. High accuracy with low computation costs was achieved by reducing the number of features used for LSVM.</p><p><strong>Conclusion: </strong>The application of a Gabor filter with convolutional processing resulted in the edges of LEGH cells being slightly rough and thick, whereas those of EC cells were fine and thin. Thus, it is thought that the frequency of abrupt gradients of pixels was higher in EC cells than in LEGH cells, and the gradient of chromatin distribution in LEGH cell nuclei was milder than that in EC cell nuclei. It was possible to evaluate nuclear findings of EC and LEGH cells objectively by quantifying morphological features of nuclei using Gabor filters. It was possible to differentiate EC cells from LEGH cells using LSVM using Gabor filter features.</p>\",\"PeriodicalId\":6959,\"journal\":{\"name\":\"Acta Cytologica\",\"volume\":\" \",\"pages\":\"539-549\"},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2023-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Acta Cytologica\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1159/000533255\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2023/7/27 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q3\",\"JCRName\":\"PATHOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Acta Cytologica","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1159/000533255","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/7/27 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"PATHOLOGY","Score":null,"Total":0}
Discriminant Analysis Using Gabor Filter Sets for Lobular Endocervical Glandular Hyperplasia: Numerical Interpretation of Nuclear Atypia by Gabor Filter Features.
Introduction: Lobular endocervical glandular hyperplasia (LEGH) is a benign lesion; however, it is considered to be the origin of gastric-type adenocarcinoma in the uterine cervix, and early diagnosis is important. At Shinshu University Hospital, screening of LEGH cells is based on the difference in color tone of cytoplasmic mucin on Papanicolaou staining and detection of gastric mucin using HIK1083-labeled latex agglutination assay. However, it is sometimes difficult to distinguish LEGH cells with subtle nuclear atypia from endocervical (EC) cells.
Methods: We calculated the Gabor filter features (mean signal value, standard deviation, skewness, kurtosis) from the nuclei of cytological specimens in EC cells (37 cases) and LEGH cells (33 cases) using microscopic images, and we performed statistical analysis and discriminant analysis by linear support vector machine (LSVM) using these features. A Gabor filter is a linear filter defined as a mathematical representation of the mammalian visual system. Gabor filters with three wavelengths and eight angles were used for analysis.
Results: Gabor filter features in EC cells were higher than in LEGH cells, demonstrating that the gradient of LEGH cell nuclei was milder than that of EC cell nuclei. The accuracy calculated using all Gabor filters was 91.0% and the accuracy of four Gabor filters (λ = 2/3π and θ = 0°, 45°, 90°, 135°) was 88.9%. High accuracy with low computation costs was achieved by reducing the number of features used for LSVM.
Conclusion: The application of a Gabor filter with convolutional processing resulted in the edges of LEGH cells being slightly rough and thick, whereas those of EC cells were fine and thin. Thus, it is thought that the frequency of abrupt gradients of pixels was higher in EC cells than in LEGH cells, and the gradient of chromatin distribution in LEGH cell nuclei was milder than that in EC cell nuclei. It was possible to evaluate nuclear findings of EC and LEGH cells objectively by quantifying morphological features of nuclei using Gabor filters. It was possible to differentiate EC cells from LEGH cells using LSVM using Gabor filter features.
期刊介绍:
With articles offering an excellent balance between clinical cytology and cytopathology, ''Acta Cytologica'' fosters the understanding of the pathogenetic mechanisms behind cytomorphology and thus facilitates the translation of frontline research into clinical practice. As the official journal of the International Academy of Cytology and affiliated to over 50 national cytology societies around the world, ''Acta Cytologica'' evaluates new and existing diagnostic applications of scientific advances as well as their clinical correlations. Original papers, review articles, meta-analyses, novel insights from clinical practice, and letters to the editor cover topics from diagnostic cytopathology, gynecologic and non-gynecologic cytopathology to fine needle aspiration, molecular techniques and their diagnostic applications. As the perfect reference for practical use, ''Acta Cytologica'' addresses a multidisciplinary audience practicing clinical cytopathology, cell biology, oncology, interventional radiology, otorhinolaryngology, gastroenterology, urology, pulmonology and preventive medicine.