AI Article Synopsis

  • Machine learning (ML) in medical imaging, particularly for liver CT scans, is gaining traction, with studies exploring its applications, performance, and clinical uses.
  • A systematic review included 191 studies, revealing that while many ML applications analyze images without clinician input, recent trends indicate a shift towards integrating ML with clinical practices.
  • Overall, while ML shows promise for tasks like liver lesion classification and staging of liver conditions, further prospective validation is needed to enhance its clinical usability, necessitating collaboration between computer scientists and healthcare professionals.

Article Abstract

Objectives: Machine learning (ML) for medical imaging is emerging for several organs and image modalities. Our objectives were to provide clinicians with an overview of this field by answering the following questions: (1) How is ML applied in liver computed tomography (CT) imaging? (2) How well do ML systems perform in liver CT imaging? (3) What are the clinical applications of ML in liver CT imaging?

Methods: A systematic review was carried out according to the guidelines from the PRISMA-P statement. The search string focused on studies containing content relating to artificial intelligence, liver, and computed tomography.

Results: One hundred ninety-one studies were included in the study. ML was applied to CT liver imaging by image analysis without clinicians' intervention in majority of studies while in newer studies the fusion of ML method with clinical intervention have been identified. Several were documented to perform very accurately on reliable but small data. Most models identified were deep learning-based, mainly using convolutional neural networks. Potentially many clinical applications of ML to CT liver imaging have been identified through our review including liver and its lesion segmentation and classification, segmentation of vascular structure inside the liver, fibrosis and cirrhosis staging, metastasis prediction, and evaluation of chemotherapy.

Conclusion: Several studies attempted to provide transparent result of the model. To make the model convenient for a clinical application, prospective clinical validation studies are in urgent call. Computer scientists and engineers should seek to cooperate with health professionals to ensure this.

Key Points: • ML shows great potential for CT liver image tasks such as pixel-wise segmentation and classification of liver and liver lesions, fibrosis staging, metastasis prediction, and retrieval of relevant liver lesions from similar cases of other patients. • Despite presenting the result is not standardized, many studies have attempted to provide transparent results to interpret the machine learning method performance in the literature. • Prospective studies are in urgent call for clinical validation of ML method, preferably carried out by cooperation between clinicians and computer scientists.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10511359PMC
http://dx.doi.org/10.1007/s00330-023-09609-wDOI Listing

Publication Analysis

Top Keywords

liver
13
machine learning
12
liver computed
12
computed tomography
8
systematic review
8
applied liver
8
clinical applications
8
applications liver
8
studies
8
liver imaging
8

Similar Publications

Background: Lymph node metastasis is closely associated with the prognosis of patients with non-small cell lung cancer (NSCLC). This study aimed to evaluate the role of preoperative 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) parameters in mediastinal lymph node metastasis in NSCLC.

Methods: One hundred patients with NSCLC who underwent surgery, systematic lymph node dissection, who had undergone 18FFDG PET/CT for initial staging were divided into two groups: lymph node metastasis and non-metastasis.

View Article and Find Full Text PDF

The incidence of hyperuricemia has increased recently, posing a serious threat to public health. Hyperuricemia is associated with an increased risk of gout, chronic kidney disease (CKD), obesity, metabolic syndrome, type 2 diabetes mellitus, hypertension, hypertriglyceridaemia, metabolic dysfunction‑associated steatotic liver disease, acute kidney injury, coronary heart disease and cardiovascular disease (CVD). These diseases are commonly accompanied by varying degrees of kidney damage.

View Article and Find Full Text PDF

Five series of new 1,3,4-thiadiazole hybrids were designed and synthesized as promising EGFR inhibitors. Three human cancer cell lines were employed for testing each hybrid's in vitro antiproliferative efficacy; colon HCT-116, liver HepG-2 and breast MCF-7 using MTT assay. Comparing compound 9a to the reference doxorubicin, 9a shown superior activity to that of Dox with respect to MCF-7 (IC 3.

View Article and Find Full Text PDF

Research progress on the molecular mechanisms of Saikosaponin D in various diseases (Review).

Int J Mol Med

March 2025

Department of Gastroenterology, Shanghai Municipal Hospital of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai 200071, P.R. China.

Bupleurum, a Traditional Chinese Medicine (TCM) herb, is widely used in China and other Asian countries to manage chronic liver inflammation and viral hepatitis. Saikosaponin D (SSD), a triterpenoid saponin extracted from Bupleurum, exhibits extensive pharmacological properties, including anti‑inflammatory, antioxidant, anti‑apoptotic, anti‑fibrotic and anti‑cancer effects, making it a therapeutic candidate for numerous diseases. Clarifying the targets and molecular mechanisms underlying TCM compounds is essential for scientifically validating TCM's therapeutic roles in disease prevention and treatment, as well as for identifying novel therapeutic targets and lead compounds.

View Article and Find Full Text PDF

An effective drug-free hydrogel for accelerating the whole healing process of bacteria-infected wounds.

Biomater Sci

December 2024

Key Laboratory of Immune Microenvironment and Disease (Ministry of Education), The Province and Ministry Co-sponsored Collaborative Innovation Center for Medical Epigenetics, Tianjin Key Laboratory on Technologies Enabling Development of Clinical Therapeutics and Diagnostics (Theranostics), School of Pharmacy, Tianjin Medical University, Tianjin, 300070, China.

Wound healing is a dynamic and complex process involving hemostasis, inflammation, fibroblast proliferation, and tissue remodeling. This process is highly susceptible to bacterial infection, which often leads to impaired and delayed wound repair. While antibiotic therapy remains the primary clinical approach for treating bacteria-infected wounds, its widespread use poses a significant risk of developing bacterial resistance.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!

A PHP Error was encountered

Severity: Notice

Message: fwrite(): Write of 34 bytes failed with errno=28 No space left on device

Filename: drivers/Session_files_driver.php

Line Number: 272

Backtrace:

A PHP Error was encountered

Severity: Warning

Message: session_write_close(): Failed to write session data using user defined save handler. (session.save_path: /var/lib/php/sessions)

Filename: Unknown

Line Number: 0

Backtrace: