Publications by authors named "R Augulis"
Article Synopsis
- The management of kidney transplant patients heavily relies on biopsy diagnoses, which currently lack consistency and reproducibility in assessing rejection features and tissue changes.
- This study introduces a computational method that uses deep learning to automate the assessment of kidney biopsy histopathology, specifically focusing on the tubulointerstitial area.
- By analyzing a large dataset of biopsy images, the researchers were able to identify distinct patterns of acute and chronic injury, offering a more precise approach for classifying and understanding kidney allograft conditions.
Intratumoral heterogeneity of Ki67 proliferation index outperforms conventional immunohistochemistry prognostic factors in estrogen receptor-positive HER2-negative breast cancer.
Dovile Zilenaite-Petrulaitiene Allan Rasmusson Justinas Besusparis Ruta Barbora Valkiuniene Renaldas Augulis
Virchows Arch
January 2024
Article Synopsis
- * This study applied digital image analysis (DIA) to analyze whole slide images from 254 ER-positive HER2-negative BC patients, focusing on the prognostic value of ITH indicators, particularly using Haralick's texture metrics for Ki67.
- * The findings revealed that Ki67 entropy, which assesses the spatial arrangement of tumor cells, is a significant predictor of BC-specific survival, surpassing the traditional proliferation rate evaluations and highlighting the importance of ITH in prognosis.
Despite advances in diagnostic and treatment technologies, predicting outcomes of patients with hepatocellular carcinoma (HCC) remains a challenge. Prognostic models are further obscured by the variable impact of the tumor properties and the remaining liver parenchyma, often affected by cirrhosis or non-alcoholic fatty liver disease that tend to precede HCC. This study investigated the prognostic value of reticulin and collagen microarchitecture in liver resection samples.
View Article and Find Full Text PDFArticle Synopsis
- Ki67 is a key biomarker in breast cancer but struggles with consistent measurement between labs, prompting research into automated digital image analysis (DIA).
- The study assessed Ki67 levels using specially prepared slides from 30 breast cancer patients, with analysis conducted by 17 labs to evaluate consistency in scoring.
- Results showed a strong correlation between consecutive sections, but core biopsy samples had notably higher Ki67 scores than whole sections, indicating that core biopsies may provide a more accurate biological status of the tumor.
Article Synopsis
- The extracellular matrix (ECM) collagen changes significantly during cancer development, but these changes are often overlooked in traditional cancer diagnostics, which typically use H&E staining.
- A new technique called polarimetric second-harmonic generation (P-SHG) microscopy allows for detailed imaging and analysis of collagen structures without the need for staining, providing more information about tissue characteristics.
- The study demonstrates that P-SHG microscopy can effectively differentiate between tumor and normal breast tissue, achieving high accuracy rates (94.2% accuracy) and suggesting it could be a valuable tool in cancer diagnostics and prognosis.