Insights into radiomics: impact of feature selection and classification DOI Creative Commons
Alessandra Perniciano, Andrea Loddo, Cecilia Di Ruberto

и другие.

Multimedia Tools and Applications, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 15, 2024

Radiomics is an innovative discipline in medical imaging that uses advanced quantitative feature extraction from radiological images to provide a non-invasive method of interpreting the intricate biological panorama diseases. This takes advantage unique characteristics imaging, where radiation or ultrasound combines with tissues, reveal disease features and important biomarkers are invisible human eye. plays crucial role healthcare, spanning diagnosis, prognosis, recurrences, treatment response assessment, personalized medicine. systematic approach includes image preprocessing, segmentation, extraction, selection, classification, evaluation. survey attempts shed light on roles selection classification play discovering forecasting directions despite challenges posed by high dimensionality (i.e., when data contains huge number features). By analyzing 47 relevant research articles, this study has provided several insights into key techniques used across different stages radiology workflow. The findings indicate 27 articles utilized SVM classifier, while 23 surveyed studies LASSO approach. demonstrates how these particular methodologies have been widely research. assessment did, however, also point out areas require more research, such as evaluating stability algorithms adopting novel approaches like ensemble hybrid methods. Additionally, we examine some emerging subfields within field radiomics.

Язык: Английский

Artificial intelligence for the prevention and clinical management of hepatocellular carcinoma DOI Creative Commons
Julien Caldéraro, Tobias Paul Seraphin, Tom Luedde

и другие.

Journal of Hepatology, Год журнала: 2022, Номер 76(6), С. 1348 - 1361

Опубликована: Май 16, 2022

Hepatocellular carcinoma (HCC) currently represents the fifth most common malignancy and third-leading cause of cancer-related death worldwide, with incidence mortality rates that are increasing. Recently, artificial intelligence (AI) has emerged as a unique opportunity to improve full spectrum HCC clinical care, by improving risk prediction, diagnosis, prognostication. AI approaches include computational search algorithms, machine learning (ML) deep (DL) models. ML consists computer running repeated iterations models, in order progressively performance specific task, such classifying an outcome. DL models subtype ML, based on neural network structures inspired neuroanatomy human brain. A growing body recent data now apply diverse sources - including electronic health record data, imaging modalities, histopathology molecular biomarkers accuracy detection prediction treatment response. Despite promise these early results, future research is still needed standardise both generalisability interpretability results. If challenges can be overcome, potential profoundly change way which care provided patients or at HCC.

Язык: Английский

Процитировано

198
Artificial intelligence in liver diseases: Improving diagnostics, prognostics and response prediction DOI Creative Commons
David Nam, Julius Chapiro, Valérie Paradis

и другие.

JHEP Reports, Год журнала: 2022, Номер 4(4), С. 100443 - 100443

Опубликована: Фев. 2, 2022

Clinical routine in hepatology involves the diagnosis and treatment of a wide spectrum metabolic, infectious, autoimmune neoplastic diseases. Clinicians integrate qualitative quantitative information from multiple data sources to make diagnosis, prognosticate disease course, recommend treatment. In last 5 years, advances artificial intelligence (AI), particularly deep learning, have made it possible extract clinically relevant complex diverse clinical datasets. particular, histopathology radiology image contain diagnostic, prognostic predictive which AI can extract. Ultimately, such systems could be implemented as decision support tools. However, context hepatology, this requires further large-scale validation regulatory approval. Herein, we summarise state art with particular focus on data. We present roadmap for development novel biomarkers outline critical obstacles need overcome.

Язык: Английский

Процитировано

142
A predictive model integrating deep and radiomics features based on gadobenate dimeglumine-enhanced MRI for postoperative early recurrence of hepatocellular carcinoma DOI
Wenyu Gao, Wentao Wang,

Danjun Song

и другие.

La radiologia medica, Год журнала: 2022, Номер 127(3), С. 259 - 271

Опубликована: Фев. 7, 2022

Язык: Английский

Процитировано

43
Are deep models in radiomics performing better than generic models? A systematic review DOI Creative Commons
Aydın Demircioğlu

European Radiology Experimental, Год журнала: 2023, Номер 7(1)

Опубликована: Март 15, 2023

Application of radiomics proceeds by extracting and analysing imaging features based on generic morphological, textural, statistical defined formulas. Recently, deep learning methods were applied. It is unclear whether models (DMs) can outperform (GMs).

Язык: Английский

Процитировано

25
Role of microvascular invasion in early recurrence of hepatocellular carcinoma after liver resection: A literature review DOI Creative Commons
Zhihong Zhang, Chuang Jiang, Zeyuan Qiang

и другие.

Asian Journal of Surgery, Год журнала: 2024, Номер 47(5), С. 2138 - 2143

Опубликована: Март 5, 2024

Hepatectomy is widely considered a potential treatment for hepatocellular carcinoma (HCC). Unfortunately, one-third of HCC patients have tumor recurrence within 2 years after surgery (early recurrence), accounting more than 60% all patients. Early associated with worse prognosis. Previous studies shown that microvascular invasion (MVI) one the key factors early and poor prognosis in surgery. This paper reviews latest literature summarizes predictors MVI, correlation between MVI recurrence, identification suspicious nodules or subclinical lesions, strategies MVI-positive HCC. The aim to explore management

Язык: Английский

Процитировано

14
Artificial intelligence in liver imaging: methods and applications DOI

Peng Zhang,

Chaofei Gao,

Yifei Huang

и другие.

Hepatology International, Год журнала: 2024, Номер 18(2), С. 422 - 434

Опубликована: Фев. 20, 2024

Язык: Английский

Процитировано

10
Multitask deep learning for prediction of microvascular invasion and recurrence‐free survival in hepatocellular carcinoma based on MRI images DOI
Fang Wang, Gan Zhan, Qingqing Chen

и другие.

Liver International, Год журнала: 2024, Номер 44(6), С. 1351 - 1362

Опубликована: Март 4, 2024

Accurate preoperative prediction of microvascular invasion (MVI) and recurrence-free survival (RFS) is vital for personalised hepatocellular carcinoma (HCC) management. We developed a multitask deep learning model to predict MVI RFS using MRI scans.

Язык: Английский

Процитировано

10
Radiomics Models for Predicting Microvascular Invasion in Hepatocellular Carcinoma: A Systematic Review and Radiomics Quality Score Assessment DOI Open Access
Qiang Wang, Changfeng Li, Jiaxing Zhang

и другие.

Cancers, Год журнала: 2021, Номер 13(22), С. 5864 - 5864

Опубликована: Ноя. 22, 2021

Preoperative prediction of microvascular invasion (MVI) is importance in hepatocellular carcinoma (HCC) patient treatment management. Plenty radiomics models for MVI have been proposed. This study aimed to elucidate the role and evaluate their methodological quality. The quality was assessed by Radiomics Quality Score (RQS), risk bias evaluated Assessment Diagnostic Accuracy Studies (QUADAS-2). Twenty-two studies using CT, MRI, or PET/CT were included. All retrospective studies, only two had an external validation cohort. AUC values ranged from 0.69 0.94 test Substantial heterogeneity existed, low, with average RQS score 10 (28% total). Most demonstrated a low unclear domains QUADAS-2. In conclusion, model could be accurate effective tool HCC patients, although has so far insufficient. Future prospective cohort accordance standardized workflow are expected supply reliable that translates into clinical utilization.

Язык: Английский

Процитировано

45
Artificial intelligence: A review of current applications in hepatocellular carcinoma imaging DOI Creative Commons
Anna Pellat, Maxime Barat, Romain Coriat

и другие.

Diagnostic and Interventional Imaging, Год журнала: 2022, Номер 104(1), С. 24 - 36

Опубликована: Окт. 19, 2022

Язык: Английский

Процитировано

30
Application of a Convolutional Neural Network for Multitask Learning to Simultaneously Predict Microvascular Invasion and Vessels that Encapsulate Tumor Clusters in Hepatocellular Carcinoma DOI Creative Commons

Tongjia Chu,

Chen Zhao, Jian Zhang

и другие.

Annals of Surgical Oncology, Год журнала: 2022, Номер 29(11), С. 6774 - 6783

Опубликована: Июнь 26, 2022

Hepatocellular carcinoma (HCC) is the fourth most common cause of cancer death worldwide, and prognosis remains dismal. In this study, two pivotal factors, microvascular invasion (MVI) vessels encapsulating tumor clusters (VETC) were preoperatively predicted simultaneously to assess prognosis.A total 133 HCC patients who underwent surgical resection preoperative gadolinium ethoxybenzyl-diethylenetriaminepentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) included. The statuses MVI VETC obtained from pathological report CD34 immunohistochemistry, respectively. A three-dimensional convolutional neural network (3D CNN) for single-task learning aimed at prediction multitask simultaneous was established by using multiphase Gd-EOB-DTPA-enhanced MRI.The 3D CNN achieved an area under receiver operating characteristics curve (AUC) 0.896 (95% CI: 0.797-0.994). Multitask with extraction features improved performance prediction, AUC value 0.917 0.825-1.000), 0.860 0.728-0.993) prediction. framework could stratify high- low-risk groups regarding overall survival (p < 0.0001) recurrence-free 0.0001), revealing that MVI+/VETC+ associated poor deep based on predict improve while assessing status. This combined can enable individualized prognostication in before curative resection.

Язык: Английский

Процитировано

29