Daisuke Kawahara

Imaging-defined high-risk phenotypes may capture biologically aggressive disease states, but translating them into therapeutic hypotheses remains challenging. We developed ParetoRx, a radiogenomic imaging-informatics framework integrating computed tomography radiomics, pathway-level transcriptomic analysis, multiobjective Pareto optimization, and model-free Q-learning for non-small cell lung cancer (NSCLC). Pretreatment CT data from 402 patients were used for model development and internal validation, with 110 patients forming a held-out external cohort. The final radiomics model achieved an external C-index of 0.707 (95% CI 0.627–0.783); high-risk patients had worse overall survival (HR 3.461, 95% CI 1.674–7.153), with minimal change after adjustment for histology (HR 3.444, 95% CI 1.662–7.137). Gene set enrichment and single-sample pathway analyses identified exploratory associations involving E2F targets, MYC targets V1, inflammatory response, and hypoxia, although no pathway met FDR < 0.05. LINCS L1000 perturbational profiles were evaluated using transcriptomic reversal, pathway specificity, and a feasibility-related proxy, with 4188 compounds retained in the common complete-case analysis. Multiobjective Pareto optimization was combined with three-split consensus ranking and sequential policy evaluation. TWS-119 showed consistent prioritization across all three splits (ranks 1, 3, and 4) and was Pareto-optimal in each split. In simulation-based evaluation, model-free Q-learning achieved higher terminal-goal attainment than myopic and static policies across all three splits, with improvements of approximately 6.2–13.3 percentage points over the myopic comparator. These findings support ParetoRx as an exploratory framework for biologically informed compound prioritization and computational sequential decision-making, while independent drug response and clinical validation remain necessary.

Brain malignant tumor needs accurate and fast segmentation for clinical diagnostics and radiation treatment planning. However, multi-contrast magnetic resonance images (MRI) are used to segment the necrotic, enhancing, and non-enhancing tumor (non-ET) regions. The current study improved an auto-segmentation model using a generative adversarial network (GAN) incorporated dual-attention (DAtGAN) on MRI images of glioma. A dataset used was that from the brain tumor segmentation (BraTS) challenge 2017 on Medical Image Computing and Computer Assisted Intervention Society (MICCAI). The DAtGAN introduced an attention module that helps to exploit the global information effectively for both the generator and discriminator of the GAN. The segmentation performance of the DAtGAN was compared with the conventional GAN. The average Dice similarity coefficient (DSC) of the GAN model was 0.85 for the ET, 0.89 for the core tumor region (CT), and 0.87 for the whole tumor (WT) region. The average DSC of the DAtGAN model was 0.88 for the ET, 0.92 for the CT, and 0.91 for the WT. The Intersection Over the Union was higher and the maximum Hausdorff distance (HD) was smaller for the DAtGAN than for the GAN model. The current study evaluated the auto-segmentation of glioma patients using the DAtGAN model. The proposed DAtGAN model is potentially valuable for improving the segmentation performance compared with other deep learning and atlas-based segmentation models. These results suggest that DAtGAN could be a valuable tool in clinical settings, providing more accurate and efficient segmentation for glioma patients, and ultimately enhancing treatment planning and outcomes.

Oligometastasis is a concept that refers to the condition between localized cancer and widespread distant metastases; however, a consensus on the definition has yet to be reached. Metastasis-directed therapy (MDT) has recently been established to incorporate local therapy, such as radiotherapy and surgery, for distant metastases. Previous trials have proposed the possibility of long-term survival with the administration of MDT for patients with oligometastases. However, the efficacy and safety of MDT have not been sufficiently validated. We are conducting this clinical trial to confirm the superiority of MDT combined with subtype-specific systemic drug therapy over systemic drug therapy alone in patients with oligometastatic breast cancer. Here, “oligometastases” are defined as tumors with a maximum diameter ≤ 3 cm and total number ≤ 3. The primary endpoint is overall survival. We intend to enroll 340 patients from 62 institutions over a 3-year period. This trial has been registered in the Japan Registry of Clinical Trials (jRCTs031230439).

Introduction: Pneumonitis represents one of the clinically significant adverse events observed in patients with non-small-cell lung cancer (NSCLC) who receive durvalumab as consolidation therapy after chemoradiotherapy (CRT). Although clinical factors such as radiation dose (e.g., V20) and interstitial lung abnormalities (ILAs) have been reported as risk predictors, accurate and objective prognostication remains difficult. This study aimed to develop a radiomics-based machine learning model to predict grade ≥ 2 pneumonitis. Methods: This retrospective study included patients with unresectable NSCLC who received CRT followed by durvalumab. Radiomic features, including first-order and texture and shape-based features with wavelet transformation were extracted from whole-lung regions on pre-durvalumab computed tomography (CT) images. Machine learning models, support vector machines, k-nearest neighbor, neural networks, and naïve Bayes classifiers were developed and evaluated using a testing cohort. Model performance was assessed using five-fold cross-validation. Conventional predictors, including V20 and ILAs, were also assessed using logistic regression and receiver operating characteristic analysis. Results: Among 123 patients, 44 (35.8%) developed grade ≥ 2 pneumonitis. The best-performing model, a support vector machine, achieved an AUC of 0.88 and accuracy of 0.81, the conventional model showed lower performance with an AUC of 0.71 and accuracy of 0.64. Conclusions: Radiomics-based machine learning demonstrated superior performance over clinical parameters in predicting pneumonitis. This approach may enable individualized risk stratification and support early intervention in patients with NSCLC.

Purpose: This study aimed to establish a framework for optimizing planning target volume (PTV) margins in liver SBRT using virtual 4DCT (v4DCT), by introducing the concept of the Dosimetric Coverage Amplitude (DCA) to quantify motion tolerance and deriving an Optimal Margin (OM) that balances tumor coverage with normal‐tissue sparing. Methods: VMAT plans were developed using a whole‐body phantom with a virtual tumor, ensuring that the prescription dose corresponded to D _95% of the PTV. The 60%–80% isodose levels were defined relative to the maximum dose to represent alternative prescription surfaces. v4DCT simulated free‐breathing conditions across 10 respiratory phases to generate virtual four‐dimensional radiotherapy (v4DRT) dose distributions. The DCA was defined as the maximum respiratory amplitude at which GTV dose coverage (D100% or D99%) was maintained. Based on DCA analysis, the OM was determined as the clinically applicable margin derived from the isodose plan that satisfied the DCA condition and minimized normal tissue dose. Results: DCA analysis revealed that GTV dose coverage was maintained for respiratory motion amplitudes up to 1.9–2.2 times larger than the conventional PTV margin of 10 mm. Taking into account GTV dose coverage, average GTV dose relative to the 80%‐static reference, and normal‐tissue dose, the 60% isodose plan was identified as the optimal prescription level. From this plan, the OM was calculated as 5.6 mm, representing a 44% reduction compared with the conventional 10‐mm PTV, while maintaining GTV coverage and minimizing liver dose. This margin reduction was attributed to the steeper dose gradient associated with prescribing to a lower isodose level. The v4DCT approach enabled the generation of multiple respiratory phase images, allowing quantitative evaluation of motion‐induced dose distribution and optimization of margins based on respiratory variability. Conclusion: The proposed v4DCT‐based framework demonstrated that the 60% isodose plan provided the optimal balance between tumor coverage and normal‐tissue sparing, yielding an OM of 5.6 mm (44% reduction compared with the conventional 10‐mm PTV). This approach offers a clinically applicable strategy for margin reduction in liver SBRT while maintaining robust dosimetric coverage.