Research progress on machine algorithm prediction of liver cancer prognosis after intervention therapy DOI
Feng Guo, Hao Hu, Hao Peng

и другие.

American Journal of Cancer Research, Год журнала: 2024, Номер 14(9), С. 4580 - 4596

Опубликована: Янв. 1, 2024

The treatment for liver cancer has transitioned from traditional surgical resection to interventional therapies, which have become increasingly popular among patients due their minimally invasive nature and significant local efficacy. However, with advancements in technologies, accurately assessing patient response predicting long-term survival a crucial research topic. Over the past decade, machine algorithms made remarkable progress medical field, particularly hepatology prognosis studies of hepatocellular carcinoma (HCC). Machine algorithms, including deep learning learning, can identify prognostic patterns trends by analyzing vast amounts clinical data. Despite advancements, several issues remain unresolved prediction using algorithms. Key challenges main controversies include effectively integrating multi-source data improve accuracy, addressing privacy ethical concerns, enhancing transparency interpretability algorithm decision-making processes. This paper aims systematically review analyze current applications potential undergoing therapy cancer, providing theoretical empirical support future practice.

Язык: Английский

Mapping the landscape of biliary tract cancer in Europe: challenges and controversies DOI Creative Commons
Lorenza Rimassa, Shahid A. Khan, Bas Groot Koerkamp

и другие.

The Lancet Regional Health - Europe, Год журнала: 2025, Номер 50, С. 101171 - 101171

Опубликована: Фев. 19, 2025

Biliary tract cancer (BTC) is becoming more common worldwide, with geographic differences in incidence and risk factors. In Europe, BTC may be associated primary sclerosing cholangitis, lithiasis, liver cirrhosis, but frequently observed as a sporadic disease. increasingly affects patients under 60 years, resulting significant social economic burden. Early diagnosis remains challenging due to vague symptoms 50% of BTC, lack specific biomarkers, late presentation poor prognosis. The identification at increased reliable biomarkers require collaborative efforts make faster progress. This Series paper highlights the disparities access diagnostic tools multidisciplinary care particularly economically disadvantaged regions, while identifying priority areas for improvement. Addressing these inequities requires harmonised guidelines, accelerated pathways curative treatments, improved awareness among healthcare professionals public. Multidisciplinary teams (MDTs) are crucial improving patient outcomes, yet inconsistencies exist their implementation not only between different countries, also centres within country. Collaboration standardisation treatment protocols across Europe essential effectively address management BTC.

Язык: Английский

Процитировано

1
Use of Artificial Intelligence for Liver Diseases: A Survey from the EASL Congress 2024 DOI Creative Commons
Laura Žigutytė, Thomas Sorz, Jan Clusmann

и другие.

JHEP Reports, Год журнала: 2024, Номер 6(12), С. 101209 - 101209

Опубликована: Сен. 6, 2024

Язык: Английский

Процитировано

4
Artificial intelligence in surgical medicine: a brief review DOI Open Access
Guo Chen,

Yutao He,

Zhitian Shi

и другие.

Annals of Medicine and Surgery, Год журнала: 2025, Номер 87(4), С. 2180 - 2186

Опубликована: Фев. 27, 2025

The application of artificial intelligence (AI) technology in the medical field, particularly surgical operations, has evolved from science fiction to a crucial tool. With continuous advancements computational power and algorithmic technology, AI is reshaping medicine landscape. From preoperative diagnosis planning intraoperative real-time navigation assistance postoperative rehabilitation follow-up management, significantly enhanced precision safety procedures. This paper systematically reviews development current applications surgery, focusing on specific case studies procedures, diagnostic assistance, navigation, highlighting its significant contributions improving safety. Despite obvious advantages success, reducing complications, accelerating patient recovery, use surgery still faces numerous challenges, including cost-effectiveness, dependency, data privacy security, clinical integration, physician training. review summarizes medicine, highlights benefits limitations, discusses challenges future directions integrating into practice.

Язык: Английский

Процитировано

0
Projected epidemiological trends and burden of liver cancer by 2040 based on GBD, CI5plus, and WHO data DOI Creative Commons
Qianqian Guo, Xiaorong Zhu, Narasimha M. Beeraka

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Ноя. 15, 2024

Incidence of liver cancer as one the most common cancers worldwide and become significant contributor for mortality among patients. The disease burden, risk factors, trends in incidence globally was described subsequently estimated projections or by 2040. Data regarding age-standardized rates obtained from multiple databases, including GLOBOCAN 2020, CI5 volumes I–XI, WHO database, Global Burden Disease (GBD)-2019. Concentrating on variations, this thorough analysis offers insights into patterns based gender age. Our findings encompass indicators, (ASRs), average annual percentage change (AAPC), future extending up to year Liver holds sixth position terms frequently diagnosed stands leading cause cancer-related deaths accounting 905,677 new cases 782,000 fatalities. Additionally, contributed 12,528,421 disability-adjusted life years (DALYs), with an DALYs rate 161.92 2019 worldwide. age-specific exhibited variations across different regions, showing a fivefold difference males females. A increase observed North Europe Asia, while African countries reported higher burden (ASR, 10 per 100,000) compared developed countries. Since last few years, have increased attained Annual Average Percentage Change (AAPC) 7.7 (95% CI 3.9–11.6) men highest AAPC 12.2 9.5–15.0) women. In 2019, Western emerged high-risk region related smoking alcohol consumption, high-income America carried high associated body-mass index. projected trend indicates surge incident cases, expected rise around 905,347 1,392,474 This study evidence pertinent cancer, particularly both young older adults, encompassing females, well those who are HIV-infected HBsAg positive. population poses public health concern that warrants attention healthcare professionals prioritize promotion awareness development effective prevention strategies, many developing

Язык: Английский

Процитировано

3
Preclinical Models of Hepatocellular Carcinoma: Current Utility, Limitations, and Challenges DOI Creative Commons
Antonio Cigliano, Weiting Liao, Giovanni Deiana

и другие.

Biomedicines, Год журнала: 2024, Номер 12(7), С. 1624 - 1624

Опубликована: Июль 22, 2024

Hepatocellular carcinoma (HCC), the predominant primary liver tumor, remains one of most lethal cancers worldwide, despite advances in therapy recent years. In addition to traditional chemically and dietary-induced HCC models, a broad spectrum novel preclinical tools have been generated following advent transgenic, transposon, organoid, silico technologies overcome this gloomy scenario. These models become rapidly robust instruments unravel molecular pathogenesis cancer establish new therapeutic approaches against deadly disease. The present review article aims summarize discuss commonly used for HCC, evaluating their strengths weaknesses.

Язык: Английский

Процитировано

2
Counterfactual Diffusion Models for Mechanistic Explainability of Artificial Intelligence Models in Pathology DOI Creative Commons
Laura Žigutytė, Tim Lenz, Tianyu Han

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Ноя. 3, 2024

Abstract Background Deep learning can extract predictive and prognostic biomarkers from histopathology whole slide images, but its interpretability remains elusive. Methods We develop validate MoPaDi (Morphing histoPathology Diffusion), which generates counterfactual mechanistic explanations. uses diffusion autoencoders to manipulate pathology image patches flip their biomarker status by changing the morphology. Importantly, includes multiple instance for weakly supervised problems. our method on four datasets classifying tissue types, cancer types within different organs, center of origin, a – microsatellite instability. Counterfactual transitions were evaluated through pathologists’ user studies quantitative cell analysis. Results achieves excellent reconstruction quality (multiscale structural similarity index measure 0.966–0.992) good classification performance (AUCs 0.76–0.98). In blinded study tissue-type counterfactuals, images realistic (63.3–73.3% original identified correctly). For other tasks, pathologists meaningful morphological features images. Conclusion explanations that reveal key driving deep model predictions in histopathology, improving interpretability.

Язык: Английский

Процитировано

2
Digital manufacturing of perovskite materials and solar cells DOI
Zixuan Wang, Zijian Chen, Boyuan Wang

и другие.

Applied Energy, Год журнала: 2024, Номер 377, С. 124120 - 124120

Опубликована: Сен. 17, 2024

Язык: Английский

Процитировано

1
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

1
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

1
Diagnosing Breast Cancer Using AI: A Comparison of Deep Learning and Traditional Machine Learning Methods DOI Open Access

Abisola Mercy Olowofeso,

Stanley T Akpunomu,

Olamide Shakirat Oni

и другие.

International Journal of Innovative Science and Research Technology (IJISRT), Год журнала: 2024, Номер unknown, С. 3606 - 3619

Опубликована: Июль 6, 2024

Breast cancer remains a significant health concern globally, with early detection being crucial for effective treatment. In this study, we explore the predictive power of various diagnostic features in breast using machine learning techniques. We analyzed dataset comprising clinical measurements mammograms from 569 patients, including mean radius, texture, perimeter, area, and smoothness, alongside diagnosis outcome. Our methodology involves preprocessing steps such as handling missing values removing duplicates, followed by correlation analysis to identify eliminate highly correlated features. Subsequently, train eight models, Logistic Regression (LR), K-Nearest Neighbors (K-NN), Linear Support Vector Machine (SVM), Kernel SVM, Naïve Bayes, Decision Trees Classifier (DTC), Random Forest (RFC), Artificial Neural Networks (ANN), predict based on selected Through comprehensive evaluation metrics accuracy confusion matrices, assess performance each model. findings reveal promising results, 6 out 8 models achieving high (>90%), ANN having highest diagnosing These results underscore potential algorithms aiding highlight importance feature selection improving performance.

Язык: Английский

Процитировано

0