AI Article Synopsis

  • - The study aimed to see if machine learning could predict early recurrence of intrahepatic cholangiocarcinoma (IHC) after surgery by analyzing radiomics and tumor size.
  • - Researchers looked at 138 patients' CT images and found that larger tumors and higher lymph node metastasis rates were linked to early recurrence, while texture features from the tumor and surrounding liver helped make predictions.
  • - The predictive model showed a strong accuracy (AUC of 0.84) in identifying patients at risk for recurrence within one year, highlighting the potential of combining radiomics and machine learning in oncology.

Article Abstract

Background: Most patients recur after resection of intrahepatic cholangiocarcinoma (IHC). We studied whether machine-learning incorporating radiomics and tumor size could predict intrahepatic recurrence within 1-year.

Methods: This was a retrospective analysis of patients with IHC resected between 2000 and 2017 who had evaluable computed tomography imaging. Texture features (TFs) were extracted from the liver, tumor, and future liver remnant (FLR). Random forest classification using training (70.3%) and validation cohorts (29.7%) was used to design a predictive model.

Results: 138 patients were included for analysis. Patients with early recurrence had a larger tumor size (7.25 cm [IQR 5.2-8.9] vs. 5.3 cm [IQR 4.0-7.2], P = 0.011) and a higher rate of lymph node metastasis (28.6% vs. 11.6%, P = 0.041), but were not more likely to have multifocal disease (21.4% vs. 17.4%, P = 0.643). Three TFs from the tumor, FD1, FD30, and IH4 and one from the FLR, ACM15, were identified by feature selection. Incorporation of TFs and tumor size achieved the highest AUC of 0.84 (95% CI 0.73-0.95) in predicting recurrence in the validation cohort.

Conclusion: This study demonstrates that radiomics and machine-learning can reliably predict patients at risk for early intrahepatic recurrence with good discrimination accuracy.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9355916PMC
http://dx.doi.org/10.1016/j.hpb.2022.02.004DOI Listing

Publication Analysis

Top Keywords

tumor size
12
resection intrahepatic
8
intrahepatic cholangiocarcinoma
8
intrahepatic recurrence
8
analysis patients
8
tfs tumor
8
recurrence
5
patients
5
tumor
5
machine learning
4

Similar Publications

Colon lipomas are rare benign, nonepithelial tumors that are often asymptomatic. However, when symptoms do occur, they vary depending on the size and location of the lipoma and are generally nonspecific. Diagnosis is confirmed through histopathological analysis.

View Article and Find Full Text PDF

Functionalized aluminum hydroxide-based self-adjuvanted nanovaccine orchestrates antitumor immune responses via Dectin-1 signaling.

J Control Release

December 2024

Key Laboratory of Drug-Targeting and Drug Delivery System of the Education Ministry and Sichuan Province, Sichuan Engineering Laboratory for Plant-Sourced Drug and Sichuan Research Centre for Drug Precision Industrial Technology, West China School of Pharmacy, Sichuan University, Chengdu 610041, People's Republic of China. Electronic address:

Self-adjuvanted vaccine delivery platforms possess potential for targeted delivery of antigens and initiation of potent immune responses. Although aluminum-containing adjuvants have been approved and widely used in human vaccines, their effectiveness in inducing Th1-type immune responses is far from satisfactory. To facilitate antigen delivery and activate potent antitumor immune responses, a self-adjuvanted nanovaccine (CPBG-Al@OVA) is constructed by functionalizing aluminum hydroxide with β-1,3-glucan, which recognizes pattern recognition receptors via Dectin-1.

View Article and Find Full Text PDF

The morphologic diagnosis of colorectal carcinoma (CRC) is typically straight forward. However, there are certain subtypes of CRC that pose diagnostic challenges for daily practice due to sometimes overlapping morphologic and immunohistochemical features. These subtypes include poorly differentiated adenocarcinoma NOS, in the absence of conventional morphology (PDA-NOS), large cell neuroendocrine carcinoma (LCNEC), medullary carcinoma (MC), undifferentiated carcinoma (UC) and lymphoepithelioma-like carcinoma (LELC).

View Article and Find Full Text PDF

The efficacy of targeted therapy and/or immunotherapy with or without chemotherapy in patients with Colorectal Cancer: A Network Meta-Analysis.

Eur J Pharmacol

December 2024

Nanhai Hospital of Traditional Chinese Medicine, Jinan University, No.16, Guicheng South Fifth Road, China, Foshan Guangdong 528200; Jinan University, Guangzhou 510632, China; Guangzhou University of Chinese Medicine, Guangzhou, China 510006. Electronic address:

Background: The use of targeted drugs and immunotherapy has significantly impacted the treatment of Colorectal Cancer. However, horizontal comparison among various regimens is extremely rare. Therefore, we evaluated the survival efficacy of multiple treatment regimens of targeted therapy and/or immunotherapy with or without chemotherapy in patients with Colorectal Cancer.

View Article and Find Full Text PDF

Objective. T: O determine whether tumor size, categorized as >5 cm or ≤5 cm, influences overall survival in patients with primary breast sarcoma.

Material And Methods: The study population consisted of patients diagnosed with primary breast sarcoma between January 1, 2010, and December 31, 2020.

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: