Journal for Immunotherapy of Cancer最新文献

{"title":"Spatial immune remodeling of the liver metastases: discovering the path to antimetastatic therapy.","authors":"Wenchao Xu, Yibo Wang, Nanzhou Wang, Jianzhou Liu, Li Zhou, Junchao Guo","doi":"10.1136/jitc-2024-011002","DOIUrl":"10.1136/jitc-2024-011002","url":null,"abstract":"<p><p>The intrinsic characteristics of metastatic tumors are of great importance in terms of the development of antimetastatic treatment strategies. Elucidation from a spatial immune perspective has the potential to provide a more comprehensive understanding of the mechanisms underlying immune escape, effectively addressing the limitations of relying solely on the analysis of immune cell subpopulation transcriptional profiles. Advances in spatial omics technology enable researchers to precisely analyze precious liver metastasis samples in a high-throughput manner, revealing spatial alterations in immune cell distribution induced by metastasis and exploring the molecular basis of the remodeling process. The aggregation of specific cell subpopulations in distinct regions not only modifies local immune characteristics but also concurrently affects global biological behaviors of liver metastatic tumors. Identifying specific spatial immune characteristics in pretreatment or early-stage treatment tissue samples may achieve accurate clinical predictions. Moreover, developing strategies that target spatial immune remodeling is a promising avenue for future antimetastatic therapy.</p>","PeriodicalId":14820,"journal":{"name":"Journal for Immunotherapy of Cancer","volume":"13 3","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11927485/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143663434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comprehensive immunophenotyping of gastric adenocarcinoma identifies an inflamed class of tumors amenable to immunotherapies.","authors":"Joel Veas Rodriguez, Miquel Piñol, Maria Alba Sorolla, Eva Parisi, Anabel Sorolla, Maria Santacana, Maria Ruiz, Genís Parra, Mario Bernabeu, Mar Iglesias, Carles Aracil, Alfredo Escartin, Felip Vilardell, Xavier Matias-Guiu, Antonieta Salud, Robert Montal","doi":"10.1136/jitc-2024-010024","DOIUrl":"10.1136/jitc-2024-010024","url":null,"abstract":"<p><strong>Background: </strong>Gastric adenocarcinoma (GAC) imposes a considerable global health burden. Molecular profiling of GAC from the tumor microenvironment perspective through a multi-omics approach is eagerly awaited in order to allow a more precise application of novel therapies in the near future.</p><p><strong>Methods: </strong>To better understand the tumor-immune interface of GAC, we identified an internal cohort of 82 patients that allowed an integrative molecular analysis including mutational profiling by whole-exome sequencing, RNA gene expression of 770 genes associated with immune response, and multiplex protein expression at spatial resolution of 34 immuno-oncology targets at different compartments (tumorous cells and immune cells). Molecular findings were validated in 595 GAC from the TCGA and ACRG external cohorts with available multiomics data. Prediction of response to immunotherapies of the discovered immunophenotypes was assessed in 1039 patients with cancer from external cohorts with available transcriptome data.</p><p><strong>Results: </strong>Unsupervised clustering by gene expression identified a subgroup of GAC that includes 52% of the tumors, the so-called Inflamed class, characterized by high tumor immunogenicity and cytotoxicity, particularly in the tumor center at protein level, with enrichment of <i>PIK3CA</i> and <i>ARID1A</i> mutations and increased presence of exhausted CD8+ T cells as well as co-inhibitory receptors such as <i>PD1</i>, <i>CTLA4</i>, <i>LAG3,</i> and <i>TIGIT</i>. The remaining 48% of tumors were called non-inflamed based on the observed exclusion of T cell infiltration, with an overexpression of <i>VEGFA</i> and higher presence of <i>TP53</i> mutations, resulting in a worse clinical outcome. A 10-gene RNA signature was developed for the identification of tumors belonging to these classes, demonstrating in evaluated datasets comparable clinical utility in predicting response to current immunotherapies when tested against other published gene signatures.</p><p><strong>Conclusions: </strong>Comprehensive immunophenotyping of GAC identifies an inflamed class of tumors that complements previously proposed tumor-based molecular clusters. Such findings may provide the rationale for exploring novel immunotherapeutic approaches for biomarker-enriched populations in order to improve GAC patient's survival.</p>","PeriodicalId":14820,"journal":{"name":"Journal for Immunotherapy of Cancer","volume":"13 3","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11927434/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143657210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Progesterone receptor-dependent downregulation of MHC class I promotes tumor immune evasion and growth in breast cancer.","authors":"Julio C Tinoco, Harmony I Saunders, Lauryn Rose Werner, Xiaopeng Sun, Eilidh I Chowanec, Amanda Heard, Prabhakar Chalise, Jeffery M Vahrenkamp, Andrea E Wilson, Cong-Xiao Liu, Gangjun Lei, Junping Wei, Hugo Cros, Hisham Mohammed, Melissa Troester, Charles Perou, Mary A Markiewicz, Jason Gertz, Justin M Balko, Zachary Conrad Hartman, Christy R Hagan","doi":"10.1136/jitc-2024-010179","DOIUrl":"10.1136/jitc-2024-010179","url":null,"abstract":"<p><strong>Background: </strong>Breast cancer (BC) continues to be a major health concern with 250,000 new cases diagnosed annually in the USA, 75% of which are hormone receptor positive (HR+), expressing estrogen receptor alpha (ER) and/or the progesterone receptor (PR). Although ER-targeted therapies are available, 30% of patients will develop resistance, underscoring the need for new non-ER/estrogen-based treatments. Notably, HR+BCs exhibit poor lymphocyte infiltration and contain an immunosuppressive microenvironment, which contributes to the limited efficacy of immunotherapies in HR+BC. In this study, we demonstrate that PR/progesterone signaling reduces major histocompatibility complex (MHC) Class I expression, facilitating immune evasion and escape from immune-based clearance of PR+tumors.</p><p><strong>Methods: </strong>To determine the effect of PR/progesterone on MHC Class I expression, we treated human and mouse mammary tumor cell lines with progesterone and/or interferon (IFN) and measured expression of genes involved in antigen processing and presentation (APP), as well as surface MHC Class I expression. We used the OT-I/SIINFEKL model antigen system to measure the impact of progesterone on immune cell-mediated killing of modified tumor cells. We also analyzed two large BC clinical cohorts to determine how PR expression correlates with APP gene expression and MHC Class I expression in ER-positive tumors.</p><p><strong>Results: </strong>In vitro, we show that PR/progesterone signaling reduces APP gene expression and MHC class I expression in human and breast mammary tumor cell lines. PR-mediated attenuation of APP/MHC Class I expression is more pronounced in the presence of IFN. In immune cell killing assays, PR-expressing mammary tumor cells treated with progesterone are protected from immune-mediated cytotoxicity. We demonstrate that PR expression in vivo prevents immune-mediated rejection of xenoantigen-modified mammary tumor cell lines through mechanisms involving MHC Class I expression and CD8 T cells. Data analysis of two large BC cohorts reveals lower APP gene expression and MHC Class I expression in ER/PR-positive tumors compared with ER-positive/PR-negative tumors. These findings show that HR+BCs, specifically PR+tumors, downregulate APP/MHC class I machinery through PR/progesterone signaling. Use of pharmacological PR/progesterone inhibitors may reverse these effects in patients with BC, thereby improving immunosurveillance and response to immunotherapies.</p>","PeriodicalId":14820,"journal":{"name":"Journal for Immunotherapy of Cancer","volume":"13 3","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11927445/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143657136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ICOS-expressing CAR-T cells mediate durable eradication of triple-negative breast cancer and metastasis.","authors":"Shelley Herbrich, Mehdi Chaib, Padmanee Sharma","doi":"10.1136/jitc-2025-011564","DOIUrl":"10.1136/jitc-2025-011564","url":null,"abstract":"<p><p>Triple-negative breast cancer (TNBC) remains one of the most aggressive and therapeutically challenging breast cancer subtypes. In their recent study, Cao <i>et al</i> introduced a B7H3-specific chimeric antigen receptor (CAR)-T cell with constitutive inducible co-stimulator (ICOS) expression (ICOS-B7H3-CAR-T), which demonstrated eradication of TNBC, including metastases, in preclinical models. These CAR-T cells exploit the expression of ICOS ligand on TNBC cells, enhancing antitumor cytotoxicity through ICOS signaling. Compared with conventional B7H3-CAR-T cells, the ICOS-B7H3-CAR-T cells exhibited superior antitumor efficacy, increased cytokine secretion, and prolonged survival in xenograft murine models. This study highlights ICOS as a promising co-stimulatory molecule for improving CAR-T therapy against solid tumors and underscores the critical role of ICOS signaling in enhancing therapeutic outcomes. Here, we discuss the implications of these findings for TNBC treatment, the importance of understanding and exploiting ICOS biology in immunotherapies, and future directions for optimizing ICOS CAR-T cell therapies in solid tumor immunotherapy.</p>","PeriodicalId":14820,"journal":{"name":"Journal for Immunotherapy of Cancer","volume":"13 3","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11927425/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143663413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"NK cells link immune-checkpoint blockade immunotherapy and response in melanoma brain metastases.","authors":"Gary Kohanbash, Stephen C Frederico, Itay Raphael","doi":"10.1136/jitc-2025-011581","DOIUrl":"10.1136/jitc-2025-011581","url":null,"abstract":"<p><p>Melanoma brain metastases (BMs) pose a significant clinical challenge. This commentary highlights the emerging understanding of the mechanisms behind immune-checkpoint blockade (ICB) efficacy in melanoma BMs. Specifically, we focus on a recent study by Fife <i>et al</i>, which revealed a non-canonical role for natural killer (NK) cells in shaping the tumor microenvironment following ICB therapy against melanoma BMs. Instead of direct tumor cell killing, this study demonstrates that ICB triggers NK cell chemokine release, CD8 T cell recruitment and enhanced antitumor immunity. The findings from this study highlight that the ICB mechanisms of action are complex and extend beyond the direct interference of inhibitor receptor-ligand interactions between cytotoxic CD8 T cells and tumor cells.</p>","PeriodicalId":14820,"journal":{"name":"Journal for Immunotherapy of Cancer","volume":"13 3","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11927483/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143663416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nivolumab adjuvant to chemo-radiation in localized muscle-invasive urothelial cancer: primary analysis of a multicenter, single-arm, phase II, investigator-initiated trial (NEXT).","authors":"Gliceida M Galarza Fortuna, Daniel Grass, Benjamin L Maughan, Rohit K Jain, Christopher Dechet, Julia Beck, Ekke Schuetz, Alejandro Sanchez, Brock O'Neil, Michael Poch, Roger Li, Shane Lloyd, Jonathan Tward, Tenzin Phunrab, Josiah Lyn Hawks, Umang Swami, Kenneth M Boucher, Neeraj Agarwal, Sumati Gupta","doi":"10.1136/jitc-2024-010572","DOIUrl":"10.1136/jitc-2024-010572","url":null,"abstract":"<p><strong>Background: </strong>Muscle-invasive urothelial cancer (UC) has a high risk of recurrence after definitive treatment. Nivolumab adjuvant to radical surgery improves disease-free survival in patients with UC with a high risk of recurrence; however, its role adjuvant to chemoradiation therapy (CRT) is unknown.</p><p><strong>Methods: </strong>The NEXT trial is a single-arm, phase-2 study evaluating the efficacy and tolerability of nivolumab adjuvant to CRT in patients with localized or locoregional UC. The primary endpoint is failure-free survival (FFS) at 2 years. Secondary endpoints include patterns of recurrence, toxicity and quality of life (QoL). Plasma cell-free DNA (cfDNA) was subjected to shallow whole-genome sequencing to correlate with outcomes.</p><p><strong>Results: </strong>28 patients were enrolled and received 480 mg of nivolumab intravenously every 4 weeks for up to 12 cycles adjuvant to CRT. The FFS at 2 years was 33.2% (95% CI 18.5% to 59.6%). Nine (32%) patients had localized progression, and eight (29%) had distant progression. 25 (89%) had one or more high-risk features (ie, plasmacytoid differentiation, T4, N+, multiple tumors, tumors >5 cm, residual disease before CRT, carcinoma in situ, and hydronephrosis). Patients with ≤2 high-risk features had a median FFS of 45.2 months (95% CI 14.56 to not reached (NR)) compared with 8.2 months (95% CI 7.1 to NR) in those with three or more risk features (p=0.0024). Nivolumab-associated treatment-related adverse events occurred in 18 (64.3%) patients, only 3 had grade 3 TRAEs, with significant changes in QoL. Plasma cfDNA copy number instability (CNI) scores ≤25 before the first dose of adjuvant nivolumab and at cycle 4 were associated with better overall survival compared with CNI scores ≥26 (49.6 months vs 20.5 months, p=0.0024). Genome copy number changes indicated chromatin remodeling and tyrosine kinase pathways, among others, as oncogenic drivers implicated in progression.</p><p><strong>Conclusion: </strong>Nivolumab adjuvant to CRT in localized or locally advanced UC is well tolerated. Stratification by risk factors and correlation with plasma cfDNA analyses generate hypotheses for potential patient selection and putative therapeutic targets for future study.</p><p><strong>Trial registration number: </strong>NCT03171025.</p>","PeriodicalId":14820,"journal":{"name":"Journal for Immunotherapy of Cancer","volume":"13 3","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11927433/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143657215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cyclin E1 overexpression triggers interferon signaling and is associated with antitumor immunity in breast cancer.","authors":"Shibo Yu, Chantal Stappenbelt, Mengting Chen, Mirte Dekker, Arkajyoti Bhattacharya, Tineke van der Sluis, Mieke C Zwager, Carolien P Schröder, Rudolf S N Fehrmann, Marcel A T M van Vugt, Bert van der Vegt","doi":"10.1136/jitc-2024-009239","DOIUrl":"10.1136/jitc-2024-009239","url":null,"abstract":"<p><strong>Background: </strong>Cyclin E1 overexpression drives oncogenesis in several cancers through deregulation of DNA replication and induction of genomic instability, which may potentially trigger immune signaling via cytoplasmic DNA. However, the effects of cyclin E1 overexpression on tumor immunity and its effects on the response to immune checkpoint inhibitors remain largely unclear.</p><p><strong>Methods: </strong>Tissue microarrays and clinical outcomes of 398 patients with breast cancer were analyzed to explore the correlation between cyclin E1 expression, patient survival, and immune cell infiltration using immunohistochemistry. Genomic data from publicly available data sets and three clinical trials evaluating immunotherapy were assessed to measure the impact of cyclin E1 expression on the immune cells in the tumor microenvironment and response to immunotherapy in patients with breast cancer. In addition, breast cancer cell lines with inducible cyclin E1 overexpression were employed to analyze the effects of cyclin E1 on inflammatory signaling.</p><p><strong>Results: </strong>Increased cyclin E1 expression in breast cancer was positively correlated with immune cell infiltration, including T cells, B cells, and natural killer cells, and activation of interferon-related pathways. Importantly, higher cyclin E1 expression or <i>CCNE1</i> amplification was associated with better response to immunotherapy in three clinical trials. Mechanistically, cyclin E1 overexpression resulted in micronuclei formation and activation of innate immune signaling, resulting in increased immune cell migration.</p><p><strong>Conclusions: </strong>Our data show that cyclin E1 overexpression associate with antitumor immunity through activation of innate inflammatory signaling and warrants investigation into amplification or overexpression of cyclin E1 in identifying patients with breast cancer eligible for immunotherapy.</p>","PeriodicalId":14820,"journal":{"name":"Journal for Immunotherapy of Cancer","volume":"13 3","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11927439/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143657211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"New soluble CSF-1R-dimeric mutein with enhanced trapping of both CSF-1 and IL-34 reduces suppressive tumor-associated macrophages in pleural mesothelioma.","authors":"Noémie Joalland, Agnès Quéméner, Sophie Deshayes, Romain Humeau, Mike Maillasson, Héloïse LeBihan, Apolline Salama, Judith Fresquet, Séverine Remy, Erwan Mortier, Christophe Blanquart, Carole Guillonneau, Ignacio Anegon","doi":"10.1136/jitc-2024-010112","DOIUrl":"10.1136/jitc-2024-010112","url":null,"abstract":"<p><strong>Background: </strong>Colony stimulating factor-1 receptor (CSF-1R) and its ligands CSF-1 and interleukin (IL)-34 have tumorigenic effects through both induction of suppressive macrophages, and survival/proliferation of tumor cells. In addition, the IL-34 tumorigenic effect can also be mediated by its other receptors, protein-tyrosine phosphatase zeta, Syndecan-1 (CD138) and triggering receptor expressed on myeloid cells 2. Small tyrosine kinase inhibitors are used to block CSF-1R signaling but lack specificity. Neutralizing anti-CSF-1 and/or IL-34 antibodies have been proposed, but their effects are limited. Thus, there is a need for a more specific and yet integrative approach.</p><p><strong>Methods: </strong>A human mutated form of the extracellular portion of CSF-1R was in silico modelized to trap both IL-34 and CSF-1 with higher affinity than the wild-type CSF-1R by replacing the methionine residue at position 149 with a Lysine (_M149K). The extracellular portion of the mutated CSF-1R M149K was dimerized using the immunoglobulin Fc sequence of a silenced human IgG1 (sCSF-1R_M149K-Fc). Signaling through CSF-1R, survival of monocytes and differentiation of suppressive macrophages were analyzed using pleural mesothelioma patient's samples and mesothelioma/macrophage spheroids in vitro and in vivo in the presence of sCSF-1R_M149K-Fc or sCSF-1R-Fc wild type control (sCSF-1R_WT-Fc).</p><p><strong>Results: </strong>We defined that the D1 to D5 domains of the extracellular portion of CSF-1R were required for efficient binding to IL-34 and CSF-1. The mutein sCSF-1R_M149K-Fc trapped with higher affinity than sCSF-1R_WT-Fc both CSF-1 and IL-34 added in culture and naturally produced in mesothelioma pleural effusions. sCSF-1R_M149K-Fc inhibited CSF-1R signaling, survival and differentiation of human suppressive macrophage in vitro and in vivo induced by pleural mesothelioma cells. Neutralization of IL-34 and CSF-1 by sCSF-1R_M149K-Fc also resulted in higher killing of pleural mesothelioma cells by a tumor-specific CD8⁺ T cell clone in mesothelioma/macrophage spheroids.</p><p><strong>Conclusions: </strong>sCSF-1R_M149K-Fc efficiently traps both CSF-1 and IL-34 and inhibits CSF-1R signaling, monocyte survival and suppressive macrophage differentiation induced by pleural mesothelioma cells producing CSF-1 and IL-34, as well as restores cytotoxic T-cell responses. sCSF-1R_M149K-Fc has therapeutic potential vs other therapies under development targeting single components of this complex cytokine pathway involved in cancer.</p>","PeriodicalId":14820,"journal":{"name":"Journal for Immunotherapy of Cancer","volume":"13 3","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11927444/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143657212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Addendum 1: <i>Society for Immunotherapy of Cancer (SITC) clinical practice guideline on immunotherapy for the treatment of melanoma, version 3.0</i>.","authors":"","doi":"10.1136/jitc-2023-006947add1","DOIUrl":"https://doi.org/10.1136/jitc-2023-006947add1","url":null,"abstract":"","PeriodicalId":14820,"journal":{"name":"Journal for Immunotherapy of Cancer","volume":"13 3","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143657207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Voxel-level radiomics and deep learning for predicting pathologic complete response in esophageal squamous cell carcinoma after neoadjuvant immunotherapy and chemotherapy.","authors":"Zhen Zhang, Tianchen Luo, Meng Yan, Haixia Shen, Kaiyi Tao, Jian Zeng, Jingping Yuan, Min Fang, Jian Zheng, Inigo Bermejo, Andre Dekker, Dirk De Ruysscher, Leonard Wee, Wencheng Zhang, Youhua Jiang, Yongling Ji","doi":"10.1136/jitc-2024-011149","DOIUrl":"10.1136/jitc-2024-011149","url":null,"abstract":"<p><strong>Background: </strong>Accurate prediction of pathologic complete response (pCR) following neoadjuvant immunotherapy combined with chemotherapy (nICT) is crucial for tailoring patient care in esophageal squamous cell carcinoma (ESCC). This study aimed to develop and validate a deep learning model using a novel voxel-level radiomics approach to predict pCR based on preoperative CT images.</p><p><strong>Methods: </strong>In this multicenter, retrospective study, 741 patients with ESCC who underwent nICT followed by radical esophagectomy were enrolled from three institutions. Patients from one center were divided into a training set (469 patients) and an internal validation set (118 patients) while the data from the other two centers was used as external validation sets (120 and 34 patients, respectively). The deep learning model, Vision-Mamba, integrated voxel-level radiomics feature maps and CT images for pCR prediction. Additionally, other commonly used deep learning models, including 3D-ResNet and Vision Transformer, as well as traditional radiomics methods, were developed for comparison. Model performance was evaluated using accuracy, area under the curve (AUC), sensitivity, specificity, and prognostic stratification capabilities. The SHapley Additive exPlanations analysis was employed to interpret the model's predictions.</p><p><strong>Results: </strong>The Vision-Mamba model demonstrated robust predictive performance in the training set (accuracy: 0.89, AUC: 0.91, sensitivity: 0.82, specificity: 0.92) and validation sets (accuracy: 0.83-0.91, AUC: 0.83-0.92, sensitivity: 0.73-0.94, specificity: 0.84-1.0). The model outperformed other deep learning models and traditional radiomics methods. The model's ability to stratify patients into high and low-risk groups was validated, showing superior prognostic stratification compared with traditional methods. SHAP provided quantitative and visual model interpretation.</p><p><strong>Conclusions: </strong>We present a voxel-level radiomics-based deep learning model to predict pCR to neoadjuvant immunotherapy combined with chemotherapy based on pretreatment diagnostic CT images with high accuracy and robustness. This model could provide a promising tool for individualized management of patients with ESCC.</p>","PeriodicalId":14820,"journal":{"name":"Journal for Immunotherapy of Cancer","volume":"13 3","pages":""},"PeriodicalIF":10.3,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11911808/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143639489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}