Development of prognostic models for advanced multiple hepatocellular carcinoma based on Cox regression, deep learning and machine learning algorithms DOI Creative Commons
Jie Shen, Yu Zhou,

Jun‐Peng Pei

и другие.

Frontiers in Medicine, Год журнала: 2024, Номер 11

Опубликована: Сен. 27, 2024

Background Most patients with multiple hepatocellular carcinoma (MHCC) are at advanced stage once diagnosed, so that clinical treatment and decision-making quite tricky. The AJCC-TNM system cannot accurately determine prognosis, our study aimed to identify prognostic factors for MHCC develop a model quantify the risk survival probability of patients. Methods Eligible HCC were obtained from Surveillance, Epidemiology, End Results (SEER) database, then models built using Cox regression, machine learning (ML), deep (DL) algorithms. model’s performance was evaluated C-index, receiver operating characteristic curve, Brier score decision curve analysis, respectively, best interpreted SHapley additive explanations (SHAP) interpretability technique. A total eight variables included in follow-up study, analysis identified gradient boosted (GBM) MHCC. In particular, GBM training cohort had C-index 0.73, 0.124, area under (AUC) values above 0.78 first, third, fifth year. Importantly, also performed well test cohort. Kaplan–Meier (K-M) demonstrated newly developed stratification could differentiate prognosis Conclusion Of ML models, predict most accurately.

Язык: Английский

Hepatocellular carcinoma: signaling pathways and therapeutic advances DOI Creative Commons

Jiaojiao Zheng,

Siying Wang, Lei Xia

и другие.

Signal Transduction and Targeted Therapy, Год журнала: 2025, Номер 10(1)

Опубликована: Фев. 6, 2025

Abstract Liver cancer represents a major global health concern, with projections indicating that the number of new cases could surpass 1 million annually by 2025. Hepatocellular carcinoma (HCC) constitutes around 90% liver and is primarily linked to factors incluidng aflatoxin, hepatitis B (HBV) C (HCV), metabolic disorders. There are no obvious symptoms in early stage HCC, which often leads delays diagnosis. Therefore, HCC patients usually present tumors advanced incurable stages. Several signaling pathways dis-regulated cause uncontrolled cell propagation, metastasis, recurrence HCC. Beyond frequently altered therapeutically targeted receptor tyrosine kinase (RTK) involved differentiation, telomere regulation, epigenetic modification stress response also provide therapeutic potential. Investigating key their inhibitors pivotal for achieving advancements management At present, primary approaches (TKI), immune checkpoint (ICI), combination regimens. New trials investigating therapies involving ICIs TKIs or anti-VEGF (endothelial growth factor) therapies, as well combinations two immunotherapy The outcomes these expected revolutionize across all Here, we here comprehensive review cellular pathways, potential, evidence derived from late-stage clinical discuss concepts underlying earlier trials, biomarker identification, development more effective therapeutics

Язык: Английский

Процитировано

7
The Diagnostic Classification of the Pathological Image Using Computer Vision DOI Creative Commons

Yasunari Matsuzaka,

Ryu Yashiro

Algorithms, Год журнала: 2025, Номер 18(2), С. 96 - 96

Опубликована: Фев. 8, 2025

Computer vision and artificial intelligence have revolutionized the field of pathological image analysis, enabling faster more accurate diagnostic classification. Deep learning architectures like convolutional neural networks (CNNs), shown superior performance in tasks such as classification, segmentation, object detection pathology. has significantly improved accuracy disease diagnosis healthcare. By leveraging advanced algorithms machine techniques, computer systems can analyze medical images with high precision, often matching or even surpassing human expert performance. In pathology, deep models been trained on large datasets annotated pathology to perform cancer diagnosis, grading, prognostication. While approaches show great promise challenges remain, including issues related model interpretability, reliability, generalization across diverse patient populations imaging settings.

Язык: Английский

Процитировано

0
HTRecNet: a deep learning study for efficient and accurate diagnosis of hepatocellular carcinoma and cholangiocarcinoma DOI Creative Commons
Jingze Li,

Yupeng Niu,

Jiang Du

и другие.

Frontiers in Cell and Developmental Biology, Год журнала: 2025, Номер 13

Опубликована: Март 24, 2025

Background Hepatocellular carcinoma (HCC) and cholangiocarcinoma (CCA) represent the primary liver cancer types. Traditional diagnostic techniques, reliant on radiologist interpretation, are both time-intensive often inadequate for detecting less prevalent CCA. There is an emergent need to explore automated methods using deep learning address these challenges. Methods This study introduces HTRecNet, a novel framework enhanced precision efficiency. The model incorporates sophisticated data augmentation strategies optimize feature extraction, ensuring robust performance even with constrained sample sizes. A comprehensive dataset of 5,432 histopathological images was divided into 5,096 training validation, 336 external testing. Evaluation conducted five-fold cross-validation applying metrics such as accuracy, area under receiver operating characteristic curve (AUC), Matthews correlation coefficient (MCC) against established clinical benchmarks. Results validation cohorts comprised 1,536 normal tissue, 3,380 HCC, 180 HTRecNet showed exceptional efficacy, consistently achieving AUC values over 0.99 across all categories. In testing, reached accuracy 0.97 MCC 0.95, affirming its reliability in distinguishing between normal, CCA tissues. Conclusion markedly enhances capability early accurate differentiation HCC from Its high efficiency position it invaluable tool settings, potentially transforming protocols. system offers substantial support refining workflows healthcare environments focused malignancies.

Язык: Английский

Процитировано

0
Evolving and Novel Applications of Artificial Intelligence in Abdominal Imaging DOI Creative Commons
Margaret L. Loper, Mina S. Makary

Tomography, Год журнала: 2024, Номер 10(11), С. 1814 - 1831

Опубликована: Ноя. 18, 2024

Advancements in artificial intelligence (AI) have significantly transformed the field of abdominal radiology, leading to an improvement diagnostic and disease management capabilities. This narrative review seeks evaluate current standing AI imaging, with a focus on recent literature contributions. work explores diagnosis characterization hepatobiliary, pancreatic, gastric, colonic, other pathologies. In addition, role has been observed help differentiate renal, adrenal, splenic disorders. Furthermore, workflow optimization strategies quantitative imaging techniques used for measurement tissue properties, including radiomics deep learning, are highlighted. An assessment how these advancements enable more precise diagnosis, tumor description, body composition evaluation is presented, which ultimately advances clinical effectiveness productivity radiology. Despite technical, ethical, legal challenges persist, challenges, as well opportunities future development,

Язык: Английский

Процитировано

2
Advancements in Artificial Intelligence-Enhanced Imaging Diagnostics for the Management of Liver Disease—Applications and Challenges in Personalized Care DOI Creative Commons
Naoshi Nishida

Bioengineering, Год журнала: 2024, Номер 11(12), С. 1243 - 1243

Опубликована: Дек. 9, 2024

Liver disease can significantly impact life expectancy, making early diagnosis and therapeutic intervention critical challenges in medical care. Imaging diagnostics play a crucial role diagnosing managing liver diseases. Recently, the application of artificial intelligence (AI) imaging analysis has become indispensable healthcare. AI, trained on vast datasets images, sometimes demonstrated diagnostic accuracy that surpasses human experts. AI-assisted are expected to contribute standardization quality. Furthermore, AI potential identify image features imperceptible humans, thereby playing an essential clinical decision-making. This capability enables physicians make more accurate diagnoses develop effective treatment strategies, ultimately improving patient outcomes. Additionally, is anticipated powerful tool personalized medicine. By integrating individual data with information, propose optimal plans for treatment, it component provision most appropriate care each patient. Current reports highlight advantages As technology continues evolve, advance treatments overall improvements healthcare

Язык: Английский

Процитировано

2
Development of prognostic models for advanced multiple hepatocellular carcinoma based on Cox regression, deep learning and machine learning algorithms DOI Creative Commons
Jie Shen, Yu Zhou,

Jun‐Peng Pei

и другие.

Frontiers in Medicine, Год журнала: 2024, Номер 11

Опубликована: Сен. 27, 2024

Background Most patients with multiple hepatocellular carcinoma (MHCC) are at advanced stage once diagnosed, so that clinical treatment and decision-making quite tricky. The AJCC-TNM system cannot accurately determine prognosis, our study aimed to identify prognostic factors for MHCC develop a model quantify the risk survival probability of patients. Methods Eligible HCC were obtained from Surveillance, Epidemiology, End Results (SEER) database, then models built using Cox regression, machine learning (ML), deep (DL) algorithms. model’s performance was evaluated C-index, receiver operating characteristic curve, Brier score decision curve analysis, respectively, best interpreted SHapley additive explanations (SHAP) interpretability technique. A total eight variables included in follow-up study, analysis identified gradient boosted (GBM) MHCC. In particular, GBM training cohort had C-index 0.73, 0.124, area under (AUC) values above 0.78 first, third, fifth year. Importantly, also performed well test cohort. Kaplan–Meier (K-M) demonstrated newly developed stratification could differentiate prognosis Conclusion Of ML models, predict most accurately.

Язык: Английский

Процитировано

0