Combined deep learning and radiomics in pretreatment radiation esophagitis prediction for patients with esophageal cancer underwent volumetric modulated arc therapy.

PURPOSE: To develop a combined radiomics and deep learning (DL) model in predicting radiation esophagitis (RE) of a grade ≥ 2 for patients with esophageal cancer (EC) underwent volumetric modulated arc therapy (VMAT) based on computed tomography (CT) and radiation dose (RD) distribution images. MATERIALS AND METHODS: A total of 273 EC patients underwent VMAT were retrospectively reviewed and enrolled from two centers and divided into training (n = 152), internal validation (n = 66), and external validation (n = 55) cohorts, respectively. Radiomic and dosiomic features along with DL features using convolutional neural networks were extracted and screened from CT and RD images to predict RE. The performance of these models was evaluated and compared using the area under curve (AUC) of the receiver operating characteristic curves (ROC). RESULTS: There were 5 and 10 radiomic and dosiomic features were screened, respectively. XGBoost achieved a best AUC of 0.703, 0.694 and 0.801, 0.729 with radiomic and dosiomic features in the internal and external validation cohorts, respectively. ResNet34 achieved a best prediction AUC of 0.642, 0.657 and 0.762, 0.737 for radiomics based DL model (DLR) and RD based DL model (DLD) in the internal and external validation cohorts, respectively. Combined model of DLD + Dosiomics + clinical factors achieved a best AUC of 0.913, 0.821 and 0.805 in the training, internal, and external validation cohorts, respectively. CONCLUSION: Although the dose was not responsible for the prediction accuracy, the combination of various feature extraction methods was a factor in improving the RE prediction accuracy. Combining DLD with dosiomic features was promising in the pretreatment prediction of RE for EC patients underwent VMAT.

Radiation pneumonitis prediction with dual-radiomics for esophageal cancer underwent radiotherapy.

BACKGROUND: To integrate radiomics and dosiomics features from multiple regions in the radiation pneumonia (RP grade ≥ 2) prediction for esophageal cancer (EC) patients underwent radiotherapy (RT). METHODS: Total of 143 EC patients in the authors' hospital (training and internal validation: 70%:30%) and 32 EC patients from another hospital (external validation) underwent RT from 2015 to 2022 were retrospectively reviewed and analyzed. Patients were dichotomized as positive (RP+) or negative (RP-) according to CTCAE V5.0. Models with radiomics and dosiomics features extracted from single region of interest (ROI), multiple ROIs and combined models were constructed and evaluated. A nomogram integrating radiomics score (Rad_score), dosiomics score (Dos_score), clinical factors, dose-volume histogram (DVH) factors, and mean lung dose (MLD) was also constructed and validated. RESULTS: Models with Rad_score_Lung&Overlap and Dos_score_Lung&Overlap achieved a better area under curve (AUC) of 0.818 and 0.844 in the external validation in comparison with radiomics and dosiomics models with features extracted from single ROI. Combining four radiomics and dosiomics models using support vector machine (SVM) improved the AUC to 0.854 in the external validation. Nomogram integrating Rad_score, and Dos_score with clinical factors, DVH factors, and MLD further improved the RP prediction AUC to 0.937 and 0.912 in the internal and external validation, respectively. CONCLUSION: CT-based RP prediction model integrating radiomics and dosiomics features from multiple ROIs outperformed those with features from a single ROI with increased reliability for EC patients who underwent RT.

Depletion of SASP senescent cardiomyocytes with senolytic drugs confers therapeutic effects in doxorubicin-related cardiotoxicity.

Doxorubicin (Dox), an anthracycline antibiotic, is widely used in cancer treatment. Although its antitumor efficacy appears significant, its clinical use is greatly restricted by its induction of cardiotoxicity. Cardiac senescence drives the Dox-induced cardiotoxicity, but whether diminishing these senescent cardiomyocytes could alleviate the cardiotoxicity remains unclear. Here, we assessed whether senescent cardiomyocytes have a senescence-associated secretory phenotype (SASP) that affects healthy non-senescent cardiomyocytes, rendering them senescent via the delivery of exosomes. Additionally, we explored whether targeting SASP senescent cardiomyocytes using a Bcl-2 inhibitor could alleviate cardiotoxicity. Cardiac damage was induced in a mouse model of continuous Dox treatment in vivo, and cardiomyocytes in vitro. Immunofluorescence of the senescence markers of Cdkn2a, Cdkn1a and γ-H2A.X was used to assess the SASP in the Dox-treated heart. To explore the molecular mechanisms involved, the Bcl-2 inhibitor ABT-199 was employed to eliminate SASP senescent cardiomyocytes. We show that the cardiomyocytes acquire a SASP during Dox treatment. The senescent cardiomyocytes upregulated Bcl-2, although treatment of mice with ABT-199 selectively eliminated SASP senescent cardiomyocytes involved in Dox-induced cardiotoxicity, thus leading to partial alleviation of Dox-induced cardiotoxicity. Moreover, we concluded that SASP factors secreted by senescent cardiomyocytes induced by Dox renders otherwise healthy cardiomyocytes senescent through exosome delivery. Our findings suggest that SASP senescent cardiomyocytes are a significant component of the pathogenesis of Dox-dependent cardiotoxicity and indicate that targeting the clearance of SASP senescent cardiomyocytes could be a new therapeutic approach for Dox-induced cardiac injury.

Multi-omics deep learning for radiation pneumonitis prediction in lung cancer patients underwent volumetric modulated arc therapy.

BACKGROUND AND OBJECTIVE: To evaluate the feasibility and accuracy of radiomics, dosiomics, and deep learning (DL) in predicting Radiation Pneumonitis (RP) in lung cancer patients underwent volumetric modulated arc therapy (VMAT) to improve radiotherapy safety and management. METHODS: Total of 318 and 31 lung cancer patients underwent VMAT from First Affiliated Hospital of Wenzhou Medical University (WMU) and Quzhou Affiliated Hospital of WMU were enrolled for training and external validation, respectively. Models based on radiomics (R), dosiomics (D), and combined radiomics and dosiomics features (R+D) were constructed and validated using three machine learning (ML) methods. DL models trained with CT (DLR), dose distribution (DLD), and combined CT and dose distribution (DL(R+D)) images were constructed. DL features were then extracted from the fully connected layers of the best-performing DL model to combine with features of the ML model with the best performance to construct models of R+DLR, D+DLD, R+D+DL(R+D)) for RP prediction. RESULTS: The R+D model achieved a best area under curve (AUC) of 0.84, 0.73, and 0.73 in the internal validation cohorts with Support Vector Machine (SVM), XGBoost, and Logistic Regression (LR), respectively. The DL(R+D) model achieved a best AUC of 0.89 and 0.86 using ResNet-34 in training and internal validation cohorts, respectively. The R+D+DL(R+D) model achieved a best performance in the external validation cohorts with an AUC, accuracy, sensitivity, and specificity of 0.81(0.62-0.99), 0.81, 0.84, and 0.67, respectively. CONCLUSIONS: The integration of radiomics, dosiomics, and DL features is feasible and accurate for the RP prediction to improve the management of lung cancer patients underwent VMAT.

Mitochondria-Targeted Nanoadjuvants Induced Multi-Functional Immune-Microenvironment Remodeling to Sensitize Tumor Radio-Immunotherapy.

It is newly revealed that collagen works as a physical barrier to tumor immune infiltration, oxygen perfusion, and immune depressor in solid tumors. Meanwhile, after radiotherapy (RT), the programmed death ligand-1 (PD-L1) overexpression and transforming growth factor-ß (TGF-ß) excessive secretion would accelerate DNA damage repair and trigger T cell exclusion to limit RT efficacy. However, existing drugs or nanoparticles can hardly address these obstacles of highly effective RT simultaneously, effectively, and easily. In this study, it is revealed that inducing mitochondria dysfunction by using oxidative phosphorylation inhibitors like Lonidamine (LND) can serve as a highly effective multi-immune pathway regulation strategy through PD-L1, collagen, and TGF-ß co-depression. Then, IR-LND is prepared by combining the mitochondria-targeted molecule IR-68 with LND, which then is loaded with liposomes (Lip) to create IR-LND@Lip nanoadjuvants. By doing this, IR-LND@Lip more effectively sensitizes RT by generating more DNA damage and transforming cold tumors into hot ones through immune activation by PD-L1, collagen, and TGF-ß co-inhibition. In conclusion, the combined treatment of RT and IR-LND@Lip ultimately almost completely suppressed the growth of bladder tumors and breast tumors.

MRI radiomics nomogram integrating postoperative adjuvant treatments in recurrence risk prediction for patients with early-stage cervical cancer.

BACKGROUND AND PURPOSE: Adjuvant treatments are valuable to decrease the recurrence rate and improve survival for early-stage cervical cancer patients (ESCC), Therefore, recurrence risk evaluation is critical for the choice of postoperative treatment. A magnetic resonance imaging (MRI) based radiomics nomogram integrating postoperative adjuvant treatments was constructed and validated externally to improve the recurrence risk prediction for ESCC. MATERIAL AND METHODS: 212 ESCC patients underwent surgery and adjuvant treatments from three centers were enrolled and divided into the training, internal validation, and external validation cohorts. Their clinical data, pretreatment T2-weighted images (T2WI) were retrieved and analyzed. Radiomics models were constructed using machine learning methods with features extracted and screen from sagittal and axial T2WI. A nomogram for recurrence prediction was build and evaluated using multivariable logistic regression analysis integrating radiomic signature and adjuvant treatments. RESULTS: A total of 8 radiomic features were screened out of 1020 extracted features. The extreme gradient boosting (XGboost) model based on MRI radiomic features performed best in recurrence prediction with an area under curve (AUC) of 0.833, 0.822 in the internal and external validation cohorts, respectively. The nomogram integrating radiomic signature and clinical factors achieved an AUC of 0.806, 0.718 in the internal and external validation cohorts, respectively, for recurrence risk prediction for ESCC. CONCLUSION: In this study, the nomogram integrating T2WI radiomic signature and clinical factors is valuable to predict the recurrence risk, thereby allowing timely planning for effective treatments for ESCC with high risk of recurrence.

Multifunctional iron-apigenin nanocomplex conducting photothermal therapy and triggering augmented immune response for triple negative breast cancer.

Triple negative breast cancer (TNBC) presents a formidable challenge due to its low sensitivity to many chemotherapeutic drugs and a relatively low overall survival rate in clinical practice. Photothermal therapy has recently garnered substantial interest in cancer treatment, owing to its swift therapeutic effectiveness and minimal impact on normal cells. Metal-polyphenol nanostructures have recently garnered significant attention as photothermal transduction agents due to their facile preparation and favorable photothermal properties. In this study, we employed a coordinated approach involving Fe3+ and apigenin, a polyphenol compound, to construct the nanostructure (nFeAPG), with the assistance of ß-CD and DSPE-PEG facilitating the formation of the complex nanostructure. In vitro research demonstrated that the formed nFeAPG could induce cell death by elevating intracellular oxidative stress, inhibiting antioxidative system, and promoting apoptosis and ferroptosis, and near infrared spectrum irradiation further strengthen the therapeutic outcome. In 4T1 tumor bearing mice, nFeAPG could effectively accumulate into tumor site and exhibit commendable control over tumor growth. Futher analysis demonstrated that nFeAPG ameliorated the suppressed immune microenvironment by augmenting the response of DC cells and T cells. This study underscores that nFeAPG encompasses a multifaceted capacity to combat TNBC, holding promise as a compelling therapeutic strategy for TNBC treatment.

A T-Cell Inspired Sonoporation System Enhances Low-Dose X-Ray-Mediated Pyroptosis and Radioimmunotherapy Efficacy by Restoring Gasdermin-E Expression.

Genome editing has the potential to improve the unsatisfactory therapeutic effect of antitumor immunotherapy. However, the cell plasma membrane prevents the entry of almost all free genome-manipulation agents. Therefore, a system can be spatiotemporally controlled and can instantly open the cellular membrane to allow the entry of genome-editing agents into target cells is needed. Here, inspired by the ability of T cells to deliver cytotoxins to cancer cells by perforation, an ultrasound (US)-controlled perforation system (UPS) is established to enhance the delivery of free genome-manipulating agents. The UPS can perforate the tumor cell membrane while maintaining cell viability via a controllable lipid peroxidation reaction. In vitro, transmembrane-incapable plasmids can enter cells and perform genome editing with the assistance of UPS, achieving an efficiency of up to 90%. In vivo, the UPS is biodegradable, nonimmunogenic, and tumor-targeting, enabling the puncturing of tumor cells under US. With the application of UPS-assisted genome editing, gasdermin-E expression in 4T1 tumor-bearing mice is successfully restored, which leads to pyroptosis-mediated antitumor immunotherapy via low-dose X-ray irradiation. This study provides new insights for designing a sonoporation system for genome editing. Moreover, the results demonstrate that restoring gasdermin expression by genome editing significantly improves the efficacy of radioimmunotherapy.

A CTL-Inspired Killing System Using Ultralow-Dose Chemical-Drugs to Induce a Pyroptosis-Mediated Antitumor Immune Function.

A Cytotoxic T lymphocyte-inspired system capable of using ultralow-dose chemical drugs to manipulate cell death is needed to investigate the antitumor immunotherapy. Recent studies reveal pyroptosis promotes antitumor immune function. However, high-dose chemotherapy leads to cytokine release syndrome by pyroptosis. Therefore, pyroptosis-inducing ultralow-dose chemotherapy is potential in preclinical and clinical research, but its efficacy, safety, and the antitumor immune responses are not clear. Here, a near-infrared light controllable killing system (BIK system) is established by which ultralow-dose doxorubicin can be spatiotemporally transported to tumor cells and mediate efficient pyroptosis. This BIK system reduces total drug consumption to less than one-thirtieth the common dose in vitro. Moreover, this BIK system exhibited good tumor targeting and tumor penetration. This system is applied for pyroptosis-induced antitumor therapies, which shows less than ≈25 µg kg-1 doxorubicin is sufficient for tumor regression with negligible injuries to major organs. The antitumor immune function are proven to correlate with the impressive efficacy of pyroptosis-inducing ultralow-dose chemotherapy. This study provides new insights into the design of nanoassisted systems for activating the antitumor immunity by microstimulation; the application of the BIK system suggests that ultralow-dose chemotherapy is sufficient for inducing a robust pyroptosis-mediated antitumor immunity.

Mutual communication between radiosensitive and radioresistant esophageal cancer cells modulates their radiosensitivity.

Radiotherapy is an important treatment modality for patients with esophageal cancer; however, the response to radiation varies among different tumor subpopulations due to tumor heterogeneity. Cancer cells that survive radiotherapy (i.e., radioresistant) may proliferate, ultimately resulting in cancer relapse. However, the interaction between radiosensitive and radioresistant cancer cells remains to be elucidated. In this study, we found that the mutual communication between radiosensitive and radioresistant esophageal cancer cells modulated their radiosensitivity. Radiosensitive cells secreted more exosomal let-7a and less interleukin-6 (IL-6) than radioresistant cells. Exosomal let-7a secreted by radiosensitive cells increased the radiosensitivity of radioresistant cells, whereas IL-6 secreted by radioresistant cells decreased the radiosensitivity of radiosensitive cells. Although the serum levels of let-7a and IL-6 before radiotherapy did not vary significantly between patients with radioresistant and radiosensitive diseases, radiotherapy induced a more pronounced decrease in serum let-7a levels and a greater increase in serum IL-6 levels in patients with radioresistant cancer compared to those with radiosensitive cancer. The percentage decrease in serum let-7a and the percentage increase in serum IL-6 levels at the early stage of radiotherapy were inversely associated with tumor regression after radiotherapy. Our findings suggest that early changes in serum let-7a and IL-6 levels may be used as a biomarker to predict the response to radiotherapy in patients with esophageal cancer and provide new insights into subsequent treatments.