Lung cancer & nodules
Study compares two algorithms and interactions with radiologists of varying experiences
2024_09
Impact of artificial intelligence assistance on pulmonary nodule detection and localization in chest CT: a comparative study among radiologists of varying experience levels
Peters et al.
https://pubmed.ncbi.nlm.nih.gov/39341945/
Highlights
The study evaluated the performance of radiology residents and senior radiologists with and without AI assistance. The nodule detection rate and localization improved for the residents but there was no effect on the performance of the senior radiologists. The authors also compared the nodule detection rates and LungRads classifications of two algorithms below.
Software 1: ClearRead CT by Riverain.
Software 2: AI-Rad Companion by Siemens.
Tumor microenvironment assessed using radiomics
2023_01
Tumor-infiltrating lymphocyte enrichment predicted by CT radiomics analysis is associated with clinical outcomes of non-small cell lung cancer patients receiving immune checkpoint inhibitors
Park et al.
https://pubmed.ncbi.nlm.nih.gov/36660547/
Highlights
The authors demonstrated that a radiomics system can predict the tumor-infiltrating lymphocyte characteristics in the tumor microenvironment (TME) using only CT scan features. The radiomic system was developed using information from H & E slides about the TME. In this CT radiomics model, predicted TIL enrichment score was significantly associated with immune checkpoint inhibitor outcomes in NSCLC patients
Review article: AI in lung cancer & lung nodules
2023_01
Artificial intelligence: A critical review of applications for lung nodule and lung cancer
C de Margerie-Mellon, G Chassagnon.
https://pubmed.ncbi.nlm.nih.gov/36513593/
Highlights
A review article coveraing basic concepts and exploring relevant literature that discusses AI in lung cancer and lung nodule care.
AI judges nodule malignancy risk
2022_09
Clinical Impact and Generalizability of a Computer-Assisted Diagnostic Tool to Risk-Stratify Lung Nodules With CT
Adams et al.
https://pubmed.ncbi.nlm.nih.gov/36064040/
Highlights
A computer-assisted diagnosis software improved risk classification from chest CTs of screening and incidentally detected lung nodules compared with Lung-RADS. mSI (malignancy Similarity Index) added predictive value independent of existing radiological and clinical variables.