Detecting Collagen by Machine Learning Improved Photoacoustic Spectral Analysis for Breast Cancer Diagnostics: Feasibility Studies With Murine Models DOI Creative Commons
Jiayan Li,

Lu Bai,

Yingna Chen

и другие.

Journal of Biophotonics, Год журнала: 2024, Номер 18(1)

Опубликована: Ноя. 26, 2024

Collagen, a key structural component of the extracellular matrix, undergoes significant remodeling during carcinogenesis. However, important role collagen levels in breast cancer diagnostics still lacks effective vivo detection techniques to provide deeper understanding. This study presents photoacoustic spectral analysis improved by machine learning as promising non-invasive diagnostic method, focusing on exploring salient biomarker. Murine model experiments revealed more profound associations with other components than normal tissues. Moreover, an optimal set feature wavelengths was identified genetic algorithm for enhanced performance, among which 75% were from collagen-dominated absorption wavebands. Using spectra, achieved 72% accuracy, 66% sensitivity, and 78% specificity, surpassing full-range spectra 6%, 4%, 8%, respectively. The proposed methods examine feasibility offering valuable biochemical insights into existing techniques, showing great potential early-stage detection.

Язык: Английский

Dehydrodiisoeugenol targets the PLK1-p53 axis to inhibit breast cancer cell cycle DOI Creative Commons
Dan Li, Yifan Zheng, Yongxia Yang

и другие.

Frontiers in Pharmacology, Год журнала: 2025, Номер 16

Опубликована: Фев. 28, 2025

Introduction There are about 2,300,000 new cases of breast cancer worldwide each year. Breast has become the first most common in world and leading cause death among women. At same time, chemotherapy resistance patients with advanced is still a serious challenge. Alpinia Katsumadai Hayata (AKH), as traditional Chinese herbal medicine, wide range pharmacological activities. Related studies have found that many compounds AKH anti-breast activity. However, it worth exploring which component main active inhibiting its mechanism action. Methods In this study, dehydrodiisoeugenol (DHIE) was screened ingredient against based on LC-MS combined drug similarity disease enrichment analysis. WGCNA, network pharmacology, molecular docking, transcriptome sequencing analysis, immune infiltration analysis single-cell were used to explore DHIE cancer. CCK-8, flow cytometry Western blot verify results vitro . The efficacy drugs verified vivo by constructing subcutaneous tumor-bearing mouse model. Results Our research showed enriched core gene targets mainly act epithelial cells tissues significantly inhibit growth affecting PLK1-p53 signaling axis arrest cell cycle at G0/G1 phase. Further although had opposite regulatory effects different isoforms p53 types cells, they eventually caused arrest. addition, reduced tumor burden, level proliferation-related marker Ki-67, inhibited expression PLK1 model, further enhanced when DOX. Discussion Collectively, our study suggests AHK may induce regulating axis, provide therapeutic strategy for specific mechanisms regulates subtypes advantages chemotherapeutic combinations compared other exploring.

Язык: Английский

Процитировано

0

Prediction of Prostate Cancer Biochemical Recurrence After Radical Prostatectomy by Collagen Models Using Multiomic Profiles DOI Creative Commons

Maria Frantzi,

Piotr Tymoszuk, Stefan Salcher

и другие.

European Urology Oncology, Год журнала: 2025, Номер unknown

Опубликована: Май 1, 2025

The interplay between prostate cancer and the tumor microenvironment is well documented of primary importance in disease evolution. Herein, we investigated prognostic value tissue urinary collagen-related molecular signatures predicting biochemical recurrence (BCR) after radical prostatectomy (RP). A comprehensive analysis 55 features was conducted using transcriptomic datasets (n = 1393), with further validation at proteomic level 69). Additionally, a distinct cohort 73) underwent urine-based peptidomic analysis, culminating urine-derived model. Independent significance assessed Cox proportional hazards modeling, while model's predictive performance benchmarked against established clinical metrics. An expression transcripts identified 11 significantly associated BCR (C-index: 0.55-0.72, p < 0.002). Multivariable models incorporating these enhanced accuracy, surpassing variables 0.66-0.89, Proteomic confirmed five key collagen proteins, model 0.73, 95% confidence interval: 0.62-0.85) demonstrated strong potential, although limited by small patient numbers. collagen-based predicted overall survival significant 0.59-0.70, 0.01). Collagen-based both urine emerge as robust biomarkers for following RP.

Язык: Английский

Процитировано

0

Machine Learning Empowered a Graphical User Interface on Native Fluorescence to Predict Breast Cancer DOI Creative Commons
Ashwini Amin,

Mallika Priya,

Jackson Rodrigues

и другие.

ACS Omega, Год журнала: 2025, Номер 10(20), С. 20315 - 20325

Опубликована: Май 14, 2025

Breast cancer poses a significant global health challenge, requiring improved diagnostic solutions for its timely intervention and treatment. Real-time approaches in current practice offer promising avenues early detection. However, these techniques often lack specificity, necessitating the development of robust tools real-time applications. In study, fluorescence spectroscopy is integrated with machine learning algorithms, graphical user interface (GUI) developed rapid breast prediction. This study records 206 native spectra, 103 spectra each from 31 normal malignant tissues using 325 nm excitation, followed by discrimination analysis different including backpropagation artificial neural network (BP-ANN), support vector (SVM), Naïve Bayes (NB). Comparative reveals that SVM combination polynomial kernel demonstrated superior performance accuracy (98.78%), sensitivity (100%), specificity (97.56%), precision (97.62%), among others. Furthermore, in-house GUI applied to data showed possibility prediction pathological tissues, facilitating standalone

Язык: Английский

Процитировано

0

Functional gold nanoparticles in diagnosis and treatment of cancer: A systematic review DOI Creative Commons

B. Li,

Maihemuti Yakufu, Ru Xie

и другие.

APL Materials, Год журнала: 2025, Номер 13(5)

Опубликована: Май 1, 2025

Early diagnosis and prompt treatment of cancer are critical to reducing mortality rates enhancing patient quality life. Nanotechnology-driven emerging approaches widely adopted in early treatment, effectively addressing the high costs, potential radiation risks, sensitivity limitations traditional methods. Among diverse range nanomaterials, gold nanoparticles (Au NPs) have demonstrated remarkable for owing their exceptional physicochemical stability distinctive localized surface plasmon resonance effect. Moreover, small size enables Au NPs target malignant tumor tissues passively through enhanced permeation retention This review begins with a concise overview optical properties NPs, followed by an examination detection mechanism NP-based biosensors markers systematic summary related studies. The latest advances NPs-based therapeutic technology research, including photothermal therapy, photodynamic combination therapy field highlighted. Finally, this provides outlook further applications diagnostic integration.

Язык: Английский

Процитировано

0

Review: Comparison of traditional and modern diagnostic methods in breast cancer DOI

Hussein Kareem Elaibi,

Farah Fakhir Mutlag,

Ebru Halvacı

и другие.

Measurement, Год журнала: 2024, Номер unknown, С. 116258 - 116258

Опубликована: Ноя. 1, 2024

Язык: Английский

Процитировано

2

Detecting Collagen by Machine Learning Improved Photoacoustic Spectral Analysis for Breast Cancer Diagnostics: Feasibility Studies With Murine Models DOI Creative Commons
Jiayan Li,

Lu Bai,

Yingna Chen

и другие.

Journal of Biophotonics, Год журнала: 2024, Номер 18(1)

Опубликована: Ноя. 26, 2024

Collagen, a key structural component of the extracellular matrix, undergoes significant remodeling during carcinogenesis. However, important role collagen levels in breast cancer diagnostics still lacks effective vivo detection techniques to provide deeper understanding. This study presents photoacoustic spectral analysis improved by machine learning as promising non-invasive diagnostic method, focusing on exploring salient biomarker. Murine model experiments revealed more profound associations with other components than normal tissues. Moreover, an optimal set feature wavelengths was identified genetic algorithm for enhanced performance, among which 75% were from collagen-dominated absorption wavebands. Using spectra, achieved 72% accuracy, 66% sensitivity, and 78% specificity, surpassing full-range spectra 6%, 4%, 8%, respectively. The proposed methods examine feasibility offering valuable biochemical insights into existing techniques, showing great potential early-stage detection.

Язык: Английский

Процитировано

0