Fractal Analysis Method for the Complexity of Cell Cluster Staining on Breast FNAB

Alzheimer's disease: new insight in assessing of amyloid plaques morphologies using multifractal geometry based on Naive Bayes optimized by random forest algorithm

Alzheimer's disease (AD) is a physical illness, which damages a person's brain; it is the most common cause of dementia. AD can be characterized by the formation of amyloid-beta (Aβ) deposits. They exhibit diverse morphologies that range from diffuse to dense-core plaques. Most of the histological images cannot be described precisely by traditional geometry or methods. Therefore, this study aims to employ multifractal geometry in assessing and classifying amyloid plaque morphologies. The classification process is based on extracting the most descriptive features related to the amyloid-beta (Aβ) deposits using the Naive Bayes classifier. To eliminate the less important features, the Random Forest algorithm has been used. The proposed methodology has achieved an accuracy of 99%, sensitivity of 100%, and specificity of 98.5%. This study employed a new dataset that had not been widely used before.

Usefulness of Fractal Analysis of Kirsch Edge Images for the Tissue Fragment Inner Structure in Breast FNAB

OBJECTIVE

Recent advances in high-precision mammography and ultrasound screening have led to an increase in the detection of early lesions (ductal carcinoma in situ and small cancers) appearing as microcalcified lesions or microcystic images, and there needs to be an improvement in the accuracy of breast fine-needle aspiration biopsy (FNAB) assessing these lesions. The objective of this study was to investigate whether fractal analysis of Kirsch edge images for the tissue fragment inner structure (FKT) is useful in breast FNAB. FKT measures tissue fragment chromasia of hyperchromatic crowded tissue fragments (HCG), tissue fragment shape unevenness, and tissue fragment inner structure complexity. Study Design Materials: Nineteen epithelial tissue fragments of fibroadenoma (FA) from 7 patients and 52 tissue fragments of invasive breast carcinoma of no special type (IBC-NST) (grade 1-2) from 11 patients were assessed. First, tissue fragments were classified into small (smaller than 60 × 102 μm2), medium, and large (100 × 102 μm2 or larger), and the appearance rate of each size was determined. Second, for FKT, the luminance value of tissue fragment chromasia, the unevenness and fractal value, and the tissue fragment inner structure complexity were determined. In statistical analysis, the Steel-Dwass test, nonlinear discriminant analysis, and receiver operating characteristic analysis were performed, setting the significance level at p < 0.05.

RESULTS

"Unevenness of the tissue fragment shape," "fractal value of the tissue fragment shape," and "fractal value of the tissue fragment inner structure" were significantly higher in small and large tissue fragments in IBC-NST compared with those in FA. The specificity and sensitivity were the highest (100%) in small tissue fragments in multivariate analysis using 4 variables ("luminance value of tissue fragment chromasia," "unevenness of tissue fragment shape," "fractal value of the tissue fragment shape," and "fractal value of the tissue fragment inner structure").

CONCLUSION

FKT, which evaluates "tissue fragment darkness," "tissue fragment shape unevenness," and "tissue fragment inner structure complexity" focusing on small tissue fragments of HCG in breast FNAB, is useful as a system that assists cytopathological assessment of breast FNAB.