#PredictingEGFRmutationwithRadiomicsandDeepLearningFusion #CancerResearch

Habitat radiomics and deep learning fusion nomogram to predict EGFR mutation status in stage I non-small cell lung cancer: a multicenter study

The study design introduced four radiomic models incorporating intratumoral, peritumoral, and habitat region radiomics, along with deep learning models. The workflow of the study is illustrated in Figure 1. Patients with stage I NSCLC who underwent curative surgery were retrospectively enrolled from four academic medical centers. Preoperative non-enhanced CT images and clinical data were collected, with inclusion and exclusion criteria specified. A total of 438 patients were included, divided into training, validation, and external test sets. Image acquisition, segmentation, and preprocessing were performed using ITK-SNAP software. Peritumoral regions were dilated, and habitat generation was detailed. Feature extraction, selection, and development of radiomic models and deep learning models were conducted. Clinical signature and nomogram construction were also part of the study. Statistical analysis included tests for comparing clinical characteristics, cross-validation, ROC curves, calibration curves, and DCA. The study was approved by the Ethics Committee of the General Hospital of Northern Theater Command, with informed consent waived due to the retrospective nature of the study. The study aimed to develop and evaluate radiomic and deep learning models for predicting EGFR mutations in NSCLC patients undergoing surgery, with a focus on model interpretability and clinical utility.

Source link

Source link:

What do you think?

Leave a Reply

GIPHY App Key not set. Please check settings

AI on Ice - Episode 2

AI on Ice – Episode 2: The Frozen Frontier #ArtificialIntelligence

An Alternative to Conventional Neural Networks Could Help Reveal What AI Is Doing behind the Scenes

Chinese AI apps revolutionizing US education system with #AIEdTransformation