A Digital Workflow for Automated Assessment of Tumor-Infiltrating Lymphocytes in Oral Squamous Cell Carcinoma Using QuPath and a StarDist-Based Model DOI Open Access

Angela Crispino,

Silvia Varricchio, Gennaro Ilardi

et al.

Pathologica, Journal Year: 2024, Volume and Issue: 116(6), P. 390 - 403

Published: Dec. 1, 2024

The search for reliable prognostic markers in oral squamous cell carcinoma (OSCC) remains a critical need. Tumor-infiltrating lymphocytes (TILs), particularly T lymphocytes, play pivotal role the immune response against tumors and are strongly correlated with favorable prognoses. Computational pathology has proven highly effective histopathological image analysis, automating tasks such as detection, classification, segmentation.

Language: Английский

Computer-assisted diagnosis to improve diagnostic pathology: A review DOI Creative Commons
Alessandro Caputo,

Elisabetta Maffei,

Nalini Gupta

et al.

Indian Journal of Pathology and Microbiology, Journal Year: 2025, Volume and Issue: 68(1), P. 3 - 10

Published: Jan. 1, 2025

ABSTRACT With an increasing demand for accuracy and efficiency in diagnostic pathology, computer-assisted diagnosis (CAD) emerges as a prominent transformative solution. This review aims to explore the practical applications, implications, strengths, weaknesses of CAD applied pathology. A comprehensive literature search was conducted include English-language studies focusing on tools, digital Artificial intelligence (AI) applications The underscores potential tools particularly streamlining processes, reducing turnaround times, augmenting accuracy. It emphasizes strides made integration AI, promising prospects prognostic biomarker discovery using computational methods. Additionally, ethical considerations regarding data privacy, equity, trust AI deployment are examined. has revolutionize insights gleaned from this offer panoramic view recent advancements. Ultimately, guide future research, influence clinical practice, inform policy-making by elucidating horizons pitfalls integrating

Language: Английский

Citations

0
Leveraging deep learning for identification and segmentation of “CAF-1/p60-positive” nuclei in oral squamous cell carcinoma tissue samples DOI Creative Commons
Silvia Varricchio, Gennaro Ilardi, Daniela Russo

et al.

Journal of Pathology Informatics, Journal Year: 2024, Volume and Issue: 15, P. 100407 - 100407

Published: Nov. 9, 2024

In the current study, we introduced a unique method for identifying and segmenting oral squamous cell carcinoma (OSCC) nuclei, concentrating on those predicted to have significant CAF-1/p60 protein expression. Our suggested model uses StarDist architecture, deep-learning framework designed biomedical image segmentation tasks. The training dataset comprises painstakingly annotated masks created from tissue sections previously stained with hematoxylin eosin (H&E) then restained immunohistochemistry (IHC) p60 protein. algorithm subtle morphological colorimetric H&E cellular characteristics predict IHC expression in OSCC nuclei. StarDist-based architecture performs exceptionally well localizing identified by IHC-based ground truth. summary, our innovative approach harnesses deep learning multimodal information advance automated analysis of nuclei exhibiting specific patterns. This methodology holds promise expediting accurate pathological assessment gaining deeper insights into role within context cancer progression.

Language: Английский

Citations

2
Ki-67 expression and its correlation with clinicopathological parameters in Iraqi breast cancer patients DOI Open Access

Ammar Ahmed Hussein,

Rayah Baban,

Qahtan A. Mahdi

et al.

International Journal of Health Sciences, Journal Year: 2024, Volume and Issue: 8(2), P. 158 - 169

Published: July 27, 2024

Breast cancer is the most common worldwide and major cause of cancer-related death among women in both developed developing countries. In Iraq, breast accounted for 37.9% all malignant cases 2020 15.3% fatalities. Relevant biomarkers play an important role predicting prognosis deciding effective therapy each patient to delay metastases reduce mortality. Objective: This study aimed assess significance Ki-67 expression as a prognostic biomarker patients well investigate correlations between their clinicopathological features. Methods: The case-control comprised sixty newly diagnosed ten with benign tumors who served controls. We assessed tissue level protein using immunohistochemistry technique. Results: Our results showed that median immunohistochemical scores group were higher than those control group; difference was significant (p < 0.001). score cells increases tumor size grade. substantial negative correlation estrogen receptor positive HER2 expression.

Language: Английский

Citations

1
Regulating the ctDNA binding interactions and in vitro antitumor activities by chiral amide-bonded H2Porphyrins containing zero- to three- L-alanine units DOI
Wei Tang, Ting Tang, Ting Yang

et al.

Journal of Porphyrins and Phthalocyanines, Journal Year: 2024, Volume and Issue: 28(05), P. 282 - 290

Published: May 1, 2024

Herein, a series of four chiral amide-bonded H 2 porphyrins containing zero- to three- L-alanine units have been prepared and characterized. Also, the spectroscopic investigations biocompatibility evaluations these amphiphilic were carried out illustrate relationship between number alanine antitumor behaviors. Interestingly, Porphyrin 3 with two has stronger DNA interaction cell membrane penetration ability that significantly enhances

Language: Английский

Citations

0
Oral Cancer Using Deep Learning and Auto-Fluorescence Image Analysis DOI

Muhammed Yaseer P,

Arul Xavier V M,

S S Shyni

et al.

Published: May 16, 2024

Language: Английский

Citations

0
Transformation from hematoxylin-and-eosin staining to Ki-67 immunohistochemistry digital staining images using deep learning: experimental validation on the labeling index DOI Creative Commons

C.-Y. Ji,

Kengo Oshima,

Takumi Urata

et al.

Journal of Medical Imaging, Journal Year: 2024, Volume and Issue: 11(04)

Published: July 30, 2024

PurposeEndometrial cancer (EC) is one of the most common types affecting women. While hematoxylin-and-eosin (H&E) staining remains standard for histological analysis, immunohistochemistry (IHC) method provides molecular-level visualizations. Our study proposes a digital to generate hematoxylin-3,3′-diaminobenzidine (H-DAB) IHC stain Ki-67 whole slide image EC tumor from its H&E counterpart.ApproachWe employed color unmixing technique yield density maps optical (OD) stains and utilized U-Net end-to-end inference. The effectiveness proposed was evaluated using Pearson correlation between physical stain's labeling index (LI), key metric indicating proliferation. Two different cross-validation schemes were designed in our study: intraslide validation cross-case (CCV). In widely used scheme, training sets might include regions same slide. rigorous CCV scheme strictly prohibited any contributing training.ResultsThe yielded high-resolution with preserved features, reliable terms LI. patches resulted biased accuracy (e.g., R=0.98) significantly higher than that CCV. retained fair R=0.66) LIs calculated counterpart. Inferring OD enhanced metric, outperforming baseline model RGB space.ConclusionsOur revealed molecule-level insights could be obtained images deep learning. Furthermore, improvement brought via inference indicated possible creating more generalizable models per-stain analysis.

Language: Английский

Citations

0
A Digital Workflow for Automated Assessment of Tumor-Infiltrating Lymphocytes in Oral Squamous Cell Carcinoma Using QuPath and a StarDist-Based Model DOI Open Access

Angela Crispino,

Silvia Varricchio, Gennaro Ilardi

et al.

Pathologica, Journal Year: 2024, Volume and Issue: 116(6), P. 390 - 403

Published: Dec. 1, 2024

The search for reliable prognostic markers in oral squamous cell carcinoma (OSCC) remains a critical need. Tumor-infiltrating lymphocytes (TILs), particularly T lymphocytes, play pivotal role the immune response against tumors and are strongly correlated with favorable prognoses. Computational pathology has proven highly effective histopathological image analysis, automating tasks such as detection, classification, segmentation.

Language: Английский

Citations

0