Molecular typing of lung adenocarcinoma with computed tomography and CT image-based radiomics: a narrative review of research progress and prospects

Accuracy of machine learning in preoperative identification of genetic mutation status in lung cancer: A systematic review and meta-analysis

BACKGROUND AND PURPOSE

We performed this systematic review and meta-analysis to investigate the performance of ML in detecting genetic mutation status in NSCLC patients.

MATERIALS AND METHODS

We conducted a systematic search of PubMed, Cochrane, Embase, and Web of Science up until July 2023. We discussed the genetic mutation status of EGFR, ALK, KRAS, and BRAF, as well as the mutation status at different sites of EGFR.

RESULTS

We included a total of 128 original studies, of which 114 constructed ML models based on radiomic features mainly extracted from CT, MRI, and PET-CT data. From a genetic mutation perspective, 121 studies focused on EGFR mutation status analysis. In the validation set, for the detection of EGFR mutation status, the aggregated c-index was 0.760 (95%CI: 0.706-0.814) for clinical feature-based models, 0.772 (95%CI: 0.753-0.791) for CT-based radiomics models, 0.816 (95%CI: 0.776-0.856) for MRI-based radiomics models, and 0.750 (95%CI: 0.712-0.789) for PET-CT-based radiomics models. When combined with clinical features, the aggregated c-index was 0.807 (95%CI: 0.781-0.832) for CT-based radiomics models, 0.806 (95%CI: 0.773-0.839) for MRI-based radiomics models, and 0.822 (95%CI: 0.789-0.854) for PET-CT-based radiomics models. In the validation set, the aggregated c-indexes for radiomics-based models to detect mutation status of ALK and KRAS, as well as the mutation status at different sites of EGFR were all greater than 0.7.

CONCLUSION

The use of radiomics-based methods for early discrimination of EGFR mutation status in NSCLC demonstrates relatively high accuracy. However, the influence of clinical variables cannot be overlooked in this process. In addition, future studies should also pay attention to the accuracy of radiomics in identifying mutation status of other genes in EGFR.

Novel prognostic signature for lung adenocarcinoma based on immune-related mRNA pairs

Lung adenocarcinoma (LUAD) is a highly lethal malignant tumor. While the involvement of multiple mRNAs in the progression of LUAD is well established, the potential diagnostic value of immune-related mRNAs (irmRNAs) in LUAD remains largely unexplored. In this study, we utilized RNA-seq, clinical data, and immune-related gene information from LUAD patients to identify differentially expressed immune-related mRNAs (DEirmRNAs) and developed a predictive risk model based on specific DEirmRNA pairs closely linked with patient prognosis. We classified patients into high-risk and low-risk groups and analyzed factors such as survival rate, clinical characteristics, gene enrichment, immune cell infiltration, tumor mutation load, and drug susceptibility. We confirmed the expression levels of these DEirmRNAs in tumor tissues using qRT-PCR assay. Our results showed that the low-risk group had a longer survival time and lower tumor mutation burden (TMB) and microsatellite instability (MSI) compared to the high-risk group. The high-risk group also had a significant reduction in the number of certain immune cells and a lower half-maximum inhibitor concentration (IC50). We identified specific DEirmRNA pairs that were up-regulated or down-regulated in tumor tissues compared to adjacent tissues. Our prognostic risk model based on DEirmRNA pairs could be used to predict the prognosis of LUAD patients and provide reference for better treatment.

Radiomics Signature to Predict Prognosis in Early-Stage Lung Adenocarcinoma (≤3 cm) Patients with No Lymph Node Metastasis

Objectives: To investigate the predictive ability of radiomics signature to predict the prognosis of early-stage primary lung adenocarcinoma (≤3 cm) with no lymph node metastasis (pathological stage I). Materials and Methods: This study included consecutive patients with lung adenocarcinoma (≤3 cm) with no lymph node metastasis (pathological stage I) and divided them into two groups: good prognosis group and poor prognosis group. The association between the radiomics signature and prognosis was explored. An integrative radiomics model was constructed to demonstrate the value of the radiomics signature for individualized prognostic prediction. Results: Six radiomics features were significantly different between the two prognosis groups and were used to construct a radiomics model. On the training and test sets, the area under the receiver operating characteristic curve value of the radiomics model in discriminating between the two groups were 0.946 and 0.888, respectively, and those of the pathological model were 0.761 and 0.798, respectively. A radiomics nomogram combining sex, tumor size and rad-score was built. Conclusion: The radiomics signature has potential utility in estimating the prognosis of patients with pathological stage I lung adenocarcinoma (≤3 cm), potentially enabling a step forward in precision medicine.