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.

Identifying distinct heterochromatin regions using combinatorial epigenetic probes in live cells

The 3D spatial organization of the genome controls gene expression and cell functionality. Heterochromatin (HC), which is the densely compacted and largely silenced part of the chromatin, is the driver for the formation and maintenance of nuclear organization in the mammalian nucleus. It is functionally divided into highly compact constitutive heterochromatin (cHC) and transcriptionally poised facultative heterochromatin (fHC). Long regarded as a static structure, the highly dynamic nature of the heterochromatin is being slowly understood and studied. These changes in HC occur on various temporal scales during the cell cycle and differentiation processes. Most methods that capture information about the heterochromatin are static techniques that cannot provide a readout of how the HC organization evolves with time. The delineation of specific areas such as fHC are also rendered difficult due to its diffusive nature and lack of specific features. Another degree of complexity in characterizing changes in heterochromatin occurs due to the heterogeneity in the HC organization of individual cells, necessitating single cell studies. Overall, there is a need for live cell compatible tools that can stably track the heterochromatin as it undergoes re-organization. In this work, we present an approach to track cHC and fHC based on the epigenetic hallmarks associated with them. Unlike conventional immunostaining approaches, we use small recombinant protein probes that allow us to dynamically monitor the HC by binding to modifications specific to the cHC and fHC, such as H3K9me3, DNA methylation and H3K27me3. We demonstrate the use of the probes to follow the changes in HC induced by drug perturbations at the single cell level. We also use the probe sets combinatorically to simultaneously track chromatin regions enriched in two selected epigenetic modifications using a FRET based approach that enabled us tracking distinctive chromatin features in situ.

Limited frequency of malignant change in lobular endocervical glandular hyperplasia

Introduction

Although lobular endocervical glandular hyperplasia is a benign disorder of the uterine cervix, its potential as a precursor of minimal deviation adenocarcinoma has been reported. However, the natural history of the disease and the frequency of malignant change are not fully understood. We evaluated the frequency of malignant change of clinical lobular endocervical glandular hyperplasia and explored useful parameters indicating malignant change.

Methods

The clinical courses of 175 patients with cervical multi-cystic lesions who visited Shinshu University Hospital between June 1995 and June 2019 were retrospectively analyzed. We examined the results of follow-up and outcomes of the patients diagnosed with lobular endocervical glandular hyperplasia and investigated the frequency of malignant transformation.

Results

Of the 175 patients, 15, 84, and 76 were clinically diagnosed with suspected malignancy, suspected lobular endocervical glandular hyperplasia, and suspected nabothian cyst, respectively. Of these patients, 69 patients with suspected lobular endocervical glandular hyperplasia were followed, and 12 underwent hysterectomy after a mean follow-up of 57.1 (range: 3–154) months due to lesion enlargement (increase in tumor diameter of >20%) and/or worsening cytology. Of these 12 patients, two had lobular endocervical glandular hyperplasia with atypia and one had minimal deviation adenocarcinoma. Of 69 patients, the rate of malignant change was 1.4% (1/69). The growth rates of the lesions for these three patients during follow-up were significantly higher than those of nine patients who underwent surgery with lobular endocervical glandular hyperplasia without atypia and 48 follow-up cases of suspected lobular endocervical glandular hyperplasia. The cut-off value of the growth rate suggesting malignant transformation was 38.1% (84.6% sensitivity and 100% specificity). Tumor size and cytology did not change in the remaining 57 cases continuing follow-up.

Conclusion

An increase in tumor size and worsening cytology are important parameters for detecting malignant transformation of lobular endocervical glandular hyperplasia during follow-up. However, the frequency of malignant change of this disease may be limited. These results suggest that conservative management may be an option for clinical lobular endocervical glandular hyperplasia.

Discriminant analysis and interpretation of nuclear chromatin distribution and coarseness using gray-level co-occurrence matrix features for lobular endocervical glandular hyperplasia

BACKGROUND

Lobular endocervical glandular hyperplasia (LEGH) is a disease considered to be the origin of tumorigenesis of minimal deviation adenocarcinoma, which has characteristic expression in the gastric pyloric mucosa. It is difficult to diagnose by nuclear findings because of lower nuclear atypia. In this study, nuclei of endocervical (EC) and LEGH cells were digitized, and nuclear information was quantified from nuclear images and objectively evaluated using a computer. We examined whether it is possible to distinguish between EC and LEGH cells, which is difficult by human eyes.

METHODS

Signal intensity, morphological features, Otsu thresholding technique and gray-level co-occurrence matrix (GLCM) features were calculated from nuclei of EC and LEGH cells on cytology microscopic images. Then, discriminant analysis was performed using the significant difference test and linear support vector machine (LSVM).

RESULTS

GLCM features in LEGH cells were higher than those in EC cells. The nuclei of LEGH cells had a higher frequency of signal value pairs with a larger signal value difference than that of EC cells. Therefore, LEGH cell nuclei are thought to have more chromatin granules, and the chromatin is coarse and granular. Moreover, in the LSVM discriminant analysis, the accuracy of GLCM calculated using these features was 85.4%.

CONCLUSION

In this study, GLCM accurately demonstrated the nuclear chromatin distribution and coarseness. Discriminant analysis of EC and LEGH cells using GLCM features is useful.