Loading
Radiomics and Machine Learning in Medical Imaging / Lung Cancer Diagnosis and Treatment · Journal article
European Journal of Medical Research · September 7, 2026
Encouraging direction, but not yet definitive.
This is a retrospective multi-centre radiomics study developing and validating MRI-based deep learning models to predict radiological response of brain metastases to targeted therapy at 6 and 12 months. The models achieved external validation AUCs of 0.790 and 0.782 respectively and outperformed handcrafted and standalone deep learning signatures. However, the study uses a radiological surrogate endpoint and lacks prospective validation or evidence of clinical utility in altering treatment decisions.
Retrospective multi-centre cohort study with internal validation and external test set. Lung cancer patients with brain metastases who received targeted therapy, enrolled retrospectively from 7 centres.. Intervention: MRI-based deep learning radiomics models predicting response to targeted therapy.. Compared with: Handcrafted radiomics signatures and standalone deep learning signatures.. n = 765. Seven centres (specific locations not stated in abstract)..
6-month response prediction: external test AUC 0.790 (internal validation AUC 0.801, training AUC 0.848) 12-month response prediction: external test AUC 0.782 (internal validation AUC 0.818, training AUC 0.900) DLRMs outperformed handcrafted and DL signatures across all cohorts (all p < 0.05)
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
If externally validated prospectively, this model could help clinicians identify which brain metastases are likely to respond to targeted therapy before treatment initiation, potentially optimizing patient selection and avoiding ineffective therapy. However, the current evidence is insufficient to recommend clinical implementation; prospective validation and demonstration of impact on treatment decisions and patient outcomes are required.
A retrospective multi-centre radiomics study with internal and external validation showing moderate discriminatory performance (AUC 0.790–0.818 on external cohorts) for a clinically relevant surrogate endpoint, but lacking prospective design, hard clinical outcomes, or demonstration of impact on treatment decisions.
As stated by the source record.
Quoted from the source exactly as published.
If externally validated prospectively, this model could help clinicians identify which brain metastases are likely to respond to targeted therapy before treatment initiation, potentially optimizing patient selection and avoiding ineffective therapy. However, the current evidence is insufficient to recommend clinical implementation; prospective validation and demonstration of impact on treatment decisions and patient outcomes are required.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Abstract Background Brain metastases (BrMs) are the most common intracranial neoplasms, with lung cancer serving as the predominant primary source. Targeted therapy offers a powerful treatment option for patients with BrMs. It is critical to predict the response of BrMs to targeted therapy prior to treatment to screen out patients who may benefit from it. The purpose of this study is to develop and validate MRI-based deep learning radiomics models (DLRMs) for predicting BrMs responses to targeted therapy in lung cancer patients. Methods 765 BrMs from 151 lung cancer patients who received targeted therapy were retrospectively included from seven centers. 467 BrMs were assigned to the training cohort, 192 BrMs to the internal validation cohort, and 106 BrMs to the external test set. Follow-up brain MRIs were used to assess each BrM’s response status. Handcrafted and deep learning (DL) signatures were constructed from pretreatment BrM MR images using the LASSO method, respectively. Two DLRMs were established by integrating the handcrafted and DL signatures based on the LASSO logistic regression coefficients to predict the BrM 6-month and 12-month responses to targeted therapy, respectively. DLRMs’ performance was evaluated by the area under curves (AUCs) and compared with handcrafted or DL signatures by the DeLong test. Results The AUCs of DLRM in predicting BrM 6-month response to targeted therapy were 0.848, 0.801, and 0.790 in the training, internal validation, and external test cohorts, respectively. The AUCs of DLRM in predicting BrM 12-month response to targeted therapy were 0.900, 0.818, and 0.782 in the training, internal validation, and external test cohorts, respectively. DLRMs outperformed handcrafted and DL signatures in predicting targeted therapy responses across all cohorts (all p < 0.05). Decision curve analysis showed that the DLRMs could benefit lung cancer patients with BrMs. Conclusion MRI-based DLRMs could predict BrM responses to targeted therapy across 6- and 12-month periods, which can assist in optimizing treatment for lung cancer patients who suffer from BrM.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.