Pub Date : 2024-07-31DOI: 10.1038/s41698-024-00659-x
Barbara Deschler-Baier, Markus Krebs, Matthias Kroiss, Manik Chatterjee, Daniel Gundel, Christian Kestler, Alexander Kerscher, Volker Kunzmann, Silke Appenzeller, Katja Maurus, Andreas Rosenwald, Ralf Bargou, Elena Gerhard-Hartmann, Vivek Venkataramani
This case report describes the efficacy of selpercatinib, a selective RET inhibitor, in an unusual case of large-cell neuroendocrine pancreatic carcinoma (LCNEPAC) harboring a CCDC6::RET fusion. A 56-year-old male with a history of multiple lines of systemic therapies exhibited marked clinical amelioration shortly after initiating selpercatinib within the LOXO-RET-17001 study (ClinicalTrials.gov ID: NCT03157128, first posted: 2017-05-17). Data from the patient’s smartwatch suggested early efficacy before conventional methods, such as serum tumor markers and CT imaging confirmed the antitumor activity. This case not only underscores the efficacy of selpercatinib in treating RET fusion-positive rare tumors but also highlights the potential of wearable technology in cancer care. In conclusion, the standard readings from commercially available wearable devices can be useful for the monitoring of treatment response to targeted therapy and may serve as digital biomarkers in clinical trials. This approach marks a significant advancement in patient-centric healthcare, leveraging technology to enhance the effectiveness and precision of treatment evaluation.
{"title":"Rapid response to selpercatinib in RET fusion positive pancreatic neuroendocrine carcinoma confirmed by smartwatch","authors":"Barbara Deschler-Baier, Markus Krebs, Matthias Kroiss, Manik Chatterjee, Daniel Gundel, Christian Kestler, Alexander Kerscher, Volker Kunzmann, Silke Appenzeller, Katja Maurus, Andreas Rosenwald, Ralf Bargou, Elena Gerhard-Hartmann, Vivek Venkataramani","doi":"10.1038/s41698-024-00659-x","DOIUrl":"10.1038/s41698-024-00659-x","url":null,"abstract":"This case report describes the efficacy of selpercatinib, a selective RET inhibitor, in an unusual case of large-cell neuroendocrine pancreatic carcinoma (LCNEPAC) harboring a CCDC6::RET fusion. A 56-year-old male with a history of multiple lines of systemic therapies exhibited marked clinical amelioration shortly after initiating selpercatinib within the LOXO-RET-17001 study (ClinicalTrials.gov ID: NCT03157128, first posted: 2017-05-17). Data from the patient’s smartwatch suggested early efficacy before conventional methods, such as serum tumor markers and CT imaging confirmed the antitumor activity. This case not only underscores the efficacy of selpercatinib in treating RET fusion-positive rare tumors but also highlights the potential of wearable technology in cancer care. In conclusion, the standard readings from commercially available wearable devices can be useful for the monitoring of treatment response to targeted therapy and may serve as digital biomarkers in clinical trials. This approach marks a significant advancement in patient-centric healthcare, leveraging technology to enhance the effectiveness and precision of treatment evaluation.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11291676/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141860486","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}
Pub Date : 2024-07-31DOI: 10.1038/s41698-024-00634-6
Sarina A. Piha-Paul, Chieh Tseng, Cheuk Hong Leung, Ying Yuan, Daniel D. Karp, Vivek Subbiah, David Hong, Siqing Fu, Aung Naing, Jordi Rodon, Milind Javle, Jaffer A. Ajani, Kanwal P. Raghav, Neeta Somaiah, Gordon B. Mills, Apostolia M. Tsimberidou, Xiaofeng Zheng, Ken Chen, Funda Meric-Bernstam
Cancer cells with BRCA1/2 deficiencies are sensitive to poly (ADP-ribose) polymerase (PARP) inhibitors. We evaluated the efficacy of talazoparib in DNA-Damage Repair (DDR)-altered patients. In this phase II trial, patients were enrolled onto one of four cohorts based on molecular alterations: (1) somatic BRCA1/2, (2) other homologous recombination repair pathway, (3) PTEN and (4) germline BRCA1/2. The primary endpoint was a clinical benefit rate (CBR): complete response, partial response or stable disease ≥24 weeks. 79 patients with a median of 4 lines of therapy were enrolled. CBR for cohorts 1–4 were: 32.5%, 19.7%, 9.4% and 30.6%, respectively. PTEN mutations correlated with reduced survival and a trend towards shorter time to progression.Talazoparib demonstrated clinical benefit in selected DDR-altered patients. PTEN mutations/loss patients derived limited clinical benefit. Further study is needed to determine whether PTEN is prognostic or predictive of response to PARP inhibitors.
{"title":"Phase II study of talazoparib in advanced cancers with BRCA1/2, DNA repair, and PTEN alterations","authors":"Sarina A. Piha-Paul, Chieh Tseng, Cheuk Hong Leung, Ying Yuan, Daniel D. Karp, Vivek Subbiah, David Hong, Siqing Fu, Aung Naing, Jordi Rodon, Milind Javle, Jaffer A. Ajani, Kanwal P. Raghav, Neeta Somaiah, Gordon B. Mills, Apostolia M. Tsimberidou, Xiaofeng Zheng, Ken Chen, Funda Meric-Bernstam","doi":"10.1038/s41698-024-00634-6","DOIUrl":"10.1038/s41698-024-00634-6","url":null,"abstract":"Cancer cells with BRCA1/2 deficiencies are sensitive to poly (ADP-ribose) polymerase (PARP) inhibitors. We evaluated the efficacy of talazoparib in DNA-Damage Repair (DDR)-altered patients. In this phase II trial, patients were enrolled onto one of four cohorts based on molecular alterations: (1) somatic BRCA1/2, (2) other homologous recombination repair pathway, (3) PTEN and (4) germline BRCA1/2. The primary endpoint was a clinical benefit rate (CBR): complete response, partial response or stable disease ≥24 weeks. 79 patients with a median of 4 lines of therapy were enrolled. CBR for cohorts 1–4 were: 32.5%, 19.7%, 9.4% and 30.6%, respectively. PTEN mutations correlated with reduced survival and a trend towards shorter time to progression.Talazoparib demonstrated clinical benefit in selected DDR-altered patients. PTEN mutations/loss patients derived limited clinical benefit. Further study is needed to determine whether PTEN is prognostic or predictive of response to PARP inhibitors.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11291882/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141860485","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}
Pub Date : 2024-07-31DOI: 10.1038/s41698-024-00662-2
Bruno Märkl, Nic G. Reitsam, Przemyslaw Grochowski, Johanna Waidhauser, Bianca Grosser
SARIFA was very recently introduced as a histomorphological biomarker with strong prognostic power for colorectal, gastric, prostate, and pancreatic cancer. It is characterized by the direct contact between tumor cells and adipocytes due to a lack of stromal reaction. This can be easily evaluated on routinely available H&E-slides with high interobserver agreement. SARIFA also reflects a specific tumor biology driven by metabolic reprogramming. Tumor cells in SARIFA-positive tumors benefit from direct interaction with adipocytes as an external source of lipids. Numerous studies have shown that lipid metabolism is crucial in carcinogenesis and cancer progression. We found that the interaction between tumor cells and adipocytes was not triggered by obesity, as previously assumed. Instead, we believe that this is due to an immunological mechanism. Knowledge about lipid metabolism in cancer from basic experiments can be transferred to develop strategies targeting this reprogramed metabolism.
{"title":"The SARIFA biomarker in the context of basic research of lipid-driven cancers","authors":"Bruno Märkl, Nic G. Reitsam, Przemyslaw Grochowski, Johanna Waidhauser, Bianca Grosser","doi":"10.1038/s41698-024-00662-2","DOIUrl":"10.1038/s41698-024-00662-2","url":null,"abstract":"SARIFA was very recently introduced as a histomorphological biomarker with strong prognostic power for colorectal, gastric, prostate, and pancreatic cancer. It is characterized by the direct contact between tumor cells and adipocytes due to a lack of stromal reaction. This can be easily evaluated on routinely available H&E-slides with high interobserver agreement. SARIFA also reflects a specific tumor biology driven by metabolic reprogramming. Tumor cells in SARIFA-positive tumors benefit from direct interaction with adipocytes as an external source of lipids. Numerous studies have shown that lipid metabolism is crucial in carcinogenesis and cancer progression. We found that the interaction between tumor cells and adipocytes was not triggered by obesity, as previously assumed. Instead, we believe that this is due to an immunological mechanism. Knowledge about lipid metabolism in cancer from basic experiments can be transferred to develop strategies targeting this reprogramed metabolism.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11291993/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141860487","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}
Tumor-draining lymph nodes (TDLNs) are usually the first station of tumor metastasis in lung cancer. TDLNs+ have distinct pathomorphologic and tumor microenvironment (TME)-compositional patterns, which still need to be thoroughly investigated in lung adenocarcinoma (LUAD). Here, we enrolled 312 LUAD patients with TDLNs+ from our institution between 2015 and 2019. 3DHISTECH was used to scan all of the TDLNs+. Based on morphologic features, TDLNs+ patterns were classified as polarized-type or scattered-type, and TME-compositional patterns were classified as colloid-type, necrosis-type, specific-type, and common-type. Multivariate analysis revealed an increased risk of early recurrence associated with scattered-type (HR 2.37, 95% CI: 1.06–5.28), colloid-type (HR 1.95, 95% CI: 1.03–3.67), and necrosis-type (HR 2.21, 95% CI: 1.13–4.89). NanoString transcriptional analysis revealed an immunosuppression and vascular invasion hallmark in scattered and necrosis patterns and an immunoactivated hallmark in polarized and common patterns. According to imaging mass cytometry (IMC), the scattered and necrosis patterns revealed that germinal centers (GC) were compromised, GCB cell and T cell proliferation were deficient, tumor cells had the potential for proliferation, and the immune attack may be weaker. In this study, we present evidence that LUAD patients have distinct patterns and immune hallmarks of TDLNs+ related to their prognosis.
{"title":"Prognostic patterns in invasion lymph nodes of lung adenocarcinoma reveal distinct tumor microenvironments","authors":"Shen Lao, Zisheng Chen, Wei Wang, Yongmei Zheng, Shan Xiong, Ping He, Huan Yi, Jianfu Li, Feng Li, Shuting Li, Miao He, Xiaoyan Liu, Chuang Qi, Jianxing He, Wenhua Liang","doi":"10.1038/s41698-024-00639-1","DOIUrl":"10.1038/s41698-024-00639-1","url":null,"abstract":"Tumor-draining lymph nodes (TDLNs) are usually the first station of tumor metastasis in lung cancer. TDLNs+ have distinct pathomorphologic and tumor microenvironment (TME)-compositional patterns, which still need to be thoroughly investigated in lung adenocarcinoma (LUAD). Here, we enrolled 312 LUAD patients with TDLNs+ from our institution between 2015 and 2019. 3DHISTECH was used to scan all of the TDLNs+. Based on morphologic features, TDLNs+ patterns were classified as polarized-type or scattered-type, and TME-compositional patterns were classified as colloid-type, necrosis-type, specific-type, and common-type. Multivariate analysis revealed an increased risk of early recurrence associated with scattered-type (HR 2.37, 95% CI: 1.06–5.28), colloid-type (HR 1.95, 95% CI: 1.03–3.67), and necrosis-type (HR 2.21, 95% CI: 1.13–4.89). NanoString transcriptional analysis revealed an immunosuppression and vascular invasion hallmark in scattered and necrosis patterns and an immunoactivated hallmark in polarized and common patterns. According to imaging mass cytometry (IMC), the scattered and necrosis patterns revealed that germinal centers (GC) were compromised, GCB cell and T cell proliferation were deficient, tumor cells had the potential for proliferation, and the immune attack may be weaker. In this study, we present evidence that LUAD patients have distinct patterns and immune hallmarks of TDLNs+ related to their prognosis.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11289302/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141856073","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}
Pub Date : 2024-07-29DOI: 10.1038/s41698-024-00645-3
Sandra Schwarz, Zhaoran Su, Mathias Krohn, Markus W. Löffler, Andreas Schlosser, Michael Linnebacher
Two hypermutated colon cancer cases with patient-derived cell lines, peripheral and tumor-infiltrating T cells available were selected for detailed investigation of immunological response. T cells co-cultured with autologous tumor cells showed only low levels of pro-inflammatory cytokines and failed at tumor recognition. Similarly, treatment of co-cultures with immune checkpoint inhibitors (ICI) did not boost antitumor immune responses. Since proteinase inhibitor 9 (PI-9) was detected in tumor cells, a specific inhibitor (PI-9i) was used in addition to ICI in T cell cytotoxicity testing. However, only pre-stimulation with tumor-specific peptides (cryptic and neoantigenic) significantly increased recognition and elimination of tumor cells by T cells independently of ICI or PI-9i. We showed, that ICI resistant tumor cells can be targeted by tumor-primed T cells and also demonstrated the superiority of tumor-naïve peripheral blood T cells compared to highly exhausted tumor-infiltrating T cells. Future precision immunotherapeutic approaches should include multimodal strategies to successfully induce durable anti-tumor immune responses.
我们选取了两例高突变结肠癌病例，这些病例有患者衍生细胞系、外周和肿瘤浸润 T 细胞，我们对它们的免疫反应进行了详细研究。同样，用免疫检查点抑制剂（ICI）处理共培养物也不能增强抗肿瘤免疫反应。由于在肿瘤细胞中检测到了蛋白酶抑制剂 9（PI-9），因此在 T 细胞细胞毒性测试中除了使用 ICI 外，还使用了一种特异性抑制剂（PI-9i）。我们的研究表明，ICI 耐药的肿瘤细胞可以被肿瘤刺激的 T 细胞靶向，同时也证明了与高度衰竭的肿瘤浸润 T 细胞相比，肿瘤免疫的外周血 T 细胞更具优势。未来的精准免疫治疗方法应包括多模式策略，以成功诱导持久的抗肿瘤免疫反应。
{"title":"Peptide-stimulated T cells bypass immune checkpoint inhibitor resistance and eliminate autologous microsatellite instable colorectal cancer cells","authors":"Sandra Schwarz, Zhaoran Su, Mathias Krohn, Markus W. Löffler, Andreas Schlosser, Michael Linnebacher","doi":"10.1038/s41698-024-00645-3","DOIUrl":"10.1038/s41698-024-00645-3","url":null,"abstract":"Two hypermutated colon cancer cases with patient-derived cell lines, peripheral and tumor-infiltrating T cells available were selected for detailed investigation of immunological response. T cells co-cultured with autologous tumor cells showed only low levels of pro-inflammatory cytokines and failed at tumor recognition. Similarly, treatment of co-cultures with immune checkpoint inhibitors (ICI) did not boost antitumor immune responses. Since proteinase inhibitor 9 (PI-9) was detected in tumor cells, a specific inhibitor (PI-9i) was used in addition to ICI in T cell cytotoxicity testing. However, only pre-stimulation with tumor-specific peptides (cryptic and neoantigenic) significantly increased recognition and elimination of tumor cells by T cells independently of ICI or PI-9i. We showed, that ICI resistant tumor cells can be targeted by tumor-primed T cells and also demonstrated the superiority of tumor-naïve peripheral blood T cells compared to highly exhausted tumor-infiltrating T cells. Future precision immunotherapeutic approaches should include multimodal strategies to successfully induce durable anti-tumor immune responses.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11286882/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141792923","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}
Pub Date : 2024-07-28DOI: 10.1038/s41698-024-00631-9
Nicholas Mai, Jie-Fu Chen, Satshil Rana, Mark Robson, Sarat Chandarlapaty, Ezra Y. Rosen
Simultaneous presentation of two separate primary breast cancers of differing histology at initial diagnosis is an uncommon phenomenon; it is even rarer to find these pathologically distinct populations within the same biopsy. Here we report the case of a patient diagnosed with clearly demarcated, pathologically heterogenous triple negative breast cancer (TNBC) and HER2+ breast cancer that was treated with a hybrid chemoimmunotherapy regimen combining elements of Keynote-522 and a standard HER2-directed neoadjuvant regimen, yielding apathologic complete response by the time of surgery with no notable adverse events. Molecular analysis of the histologically distinct tumor populations confirmed molecular evidence of differential HER2 expression but also suggested clonal relatedness of the two tumor populations based upon mutational profile, with phenotypic divergence potentially resulting from copy number alterations in NF1. Overall, this case highlights a rare histologic phenomenon that was successfully treated by combining both TNBC and HER2 directed neoadjuvant therapies.
{"title":"Pathologic complete response to KEYNOTE522 and HER2-directed therapy for synchronous TNBC and HER2+ breast cancer","authors":"Nicholas Mai, Jie-Fu Chen, Satshil Rana, Mark Robson, Sarat Chandarlapaty, Ezra Y. Rosen","doi":"10.1038/s41698-024-00631-9","DOIUrl":"10.1038/s41698-024-00631-9","url":null,"abstract":"Simultaneous presentation of two separate primary breast cancers of differing histology at initial diagnosis is an uncommon phenomenon; it is even rarer to find these pathologically distinct populations within the same biopsy. Here we report the case of a patient diagnosed with clearly demarcated, pathologically heterogenous triple negative breast cancer (TNBC) and HER2+ breast cancer that was treated with a hybrid chemoimmunotherapy regimen combining elements of Keynote-522 and a standard HER2-directed neoadjuvant regimen, yielding apathologic complete response by the time of surgery with no notable adverse events. Molecular analysis of the histologically distinct tumor populations confirmed molecular evidence of differential HER2 expression but also suggested clonal relatedness of the two tumor populations based upon mutational profile, with phenotypic divergence potentially resulting from copy number alterations in NF1. Overall, this case highlights a rare histologic phenomenon that was successfully treated by combining both TNBC and HER2 directed neoadjuvant therapies.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41698-024-00631-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141786109","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}
Accurate prediction of bone metastasis-free survival (BMFS) after complete surgical resection in patients with non-small cell lung cancer (NSCLC) may facilitate appropriate follow-up planning. The aim of this study was to establish and validate a preoperative CT-based deep learning (DL) signature to predict BMFS in NSCLC patients. We performed a retrospective analysis of 1547 NSCLC patients who underwent complete surgical resection, followed by at least 36 months of monitoring at two hospitals. We constructed a DL signature from multiparametric CT images using 3D convolutional neural networks, and we integrated this signature with clinical-imaging factors to establish a deep learning clinical-imaging signature (DLCS). We evaluated performance using Harrell’s concordance index (C-index) and the time-dependent receiver operating characteristic. We also assessed the risk of bone metastasis (BM) in NSCLC patients at different clinical stages using DLCS. The DL signature successfully predicted BM, with C-indexes of 0.799 and 0.818 for the validation cohorts. DLCS outperformed the DL signature with corresponding C-indexes of 0.806 and 0.834. Ranges for area under the curve at 1, 2, and 3 years were 0.820–0.865 for internal and 0.860–0.884 for external validation cohorts. Furthermore, DLCS successfully stratified patients with different clinical stages of NSCLC as high- and low-risk groups for BM (p < 0.05). CT-based DL can predict BMFS in NSCLC patients undergoing complete surgical resection, and may assist in the assessment of BM risk for patients at different clinical stages.
{"title":"Predicting bone metastasis-free survival in non-small cell lung cancer from preoperative CT via deep learning","authors":"Jia Guo, Jianguo Miao, Weikai Sun, Yanlei Li, Pei Nie, Wenjian Xu","doi":"10.1038/s41698-024-00649-z","DOIUrl":"10.1038/s41698-024-00649-z","url":null,"abstract":"Accurate prediction of bone metastasis-free survival (BMFS) after complete surgical resection in patients with non-small cell lung cancer (NSCLC) may facilitate appropriate follow-up planning. The aim of this study was to establish and validate a preoperative CT-based deep learning (DL) signature to predict BMFS in NSCLC patients. We performed a retrospective analysis of 1547 NSCLC patients who underwent complete surgical resection, followed by at least 36 months of monitoring at two hospitals. We constructed a DL signature from multiparametric CT images using 3D convolutional neural networks, and we integrated this signature with clinical-imaging factors to establish a deep learning clinical-imaging signature (DLCS). We evaluated performance using Harrell’s concordance index (C-index) and the time-dependent receiver operating characteristic. We also assessed the risk of bone metastasis (BM) in NSCLC patients at different clinical stages using DLCS. The DL signature successfully predicted BM, with C-indexes of 0.799 and 0.818 for the validation cohorts. DLCS outperformed the DL signature with corresponding C-indexes of 0.806 and 0.834. Ranges for area under the curve at 1, 2, and 3 years were 0.820–0.865 for internal and 0.860–0.884 for external validation cohorts. Furthermore, DLCS successfully stratified patients with different clinical stages of NSCLC as high- and low-risk groups for BM (p < 0.05). CT-based DL can predict BMFS in NSCLC patients undergoing complete surgical resection, and may assist in the assessment of BM risk for patients at different clinical stages.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41698-024-00649-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141786110","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}
Pub Date : 2024-07-27DOI: 10.1038/s41698-024-00635-5
Hongru Shen, Meng Yang, Jilei Liu, Kexin Chen, Xiangchun Li
Accurate discrimination between patients with and without cancer from cfDNA is crucial for early cancer diagnosis. Herein, we develop and validate a deep-learning-based model entitled end-motif inspection via transformer (EMIT) for discriminating individuals with and without cancer by learning feature representations from cfDNA end-motifs. EMIT is a self-supervised learning approach that models rankings of cfDNA end-motifs. We include 4606 samples subjected to different types of cfDNA sequencing to develop EIMIT, and subsequently evaluate classification performance of linear projections of EMIT on six datasets and an additional inhouse testing set encopassing whole-genome, whole-genome bisulfite and 5-hydroxymethylcytosine sequencing. The linear projection of representations from EMIT achieved area under the receiver operating curve (AUROC) values ranged from 0.895 (0.835–0.955) to 0.996 (0.994–0.997) across these six datasets, outperforming its baseline by significant margins. Additionally, we showed that linear projection of EMIT representations can achieve an AUROC of 0.962 (0.914–1.0) in identification of lung cancer on an independent testing set subjected to whole-exome sequencing. The findings of this study indicate that a transformer-based deep learning model can learn cancer-discrimative representations from cfDNA end-motifs. The representations of this deep learning model can be exploited for discriminating patients with and without cancer.
{"title":"Development of a deep learning model for cancer diagnosis by inspecting cell-free DNA end-motifs","authors":"Hongru Shen, Meng Yang, Jilei Liu, Kexin Chen, Xiangchun Li","doi":"10.1038/s41698-024-00635-5","DOIUrl":"10.1038/s41698-024-00635-5","url":null,"abstract":"Accurate discrimination between patients with and without cancer from cfDNA is crucial for early cancer diagnosis. Herein, we develop and validate a deep-learning-based model entitled end-motif inspection via transformer (EMIT) for discriminating individuals with and without cancer by learning feature representations from cfDNA end-motifs. EMIT is a self-supervised learning approach that models rankings of cfDNA end-motifs. We include 4606 samples subjected to different types of cfDNA sequencing to develop EIMIT, and subsequently evaluate classification performance of linear projections of EMIT on six datasets and an additional inhouse testing set encopassing whole-genome, whole-genome bisulfite and 5-hydroxymethylcytosine sequencing. The linear projection of representations from EMIT achieved area under the receiver operating curve (AUROC) values ranged from 0.895 (0.835–0.955) to 0.996 (0.994–0.997) across these six datasets, outperforming its baseline by significant margins. Additionally, we showed that linear projection of EMIT representations can achieve an AUROC of 0.962 (0.914–1.0) in identification of lung cancer on an independent testing set subjected to whole-exome sequencing. The findings of this study indicate that a transformer-based deep learning model can learn cancer-discrimative representations from cfDNA end-motifs. The representations of this deep learning model can be exploited for discriminating patients with and without cancer.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41698-024-00635-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141786357","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}
Pub Date : 2024-07-26DOI: 10.1038/s41698-024-00656-0
Hania Paverd, Konstantinos Zormpas-Petridis, Hannah Clayton, Sarah Burge, Mireia Crispin-Ortuzar
In this Perspective paper we explore the potential of integrating radiological imaging with other data types, a critical yet underdeveloped area in comparison to the fusion of other multi-omic data. Radiological images provide a comprehensive, three-dimensional view of cancer, capturing features that would be missed by biopsies or other data modalities. This paper explores the complexities and challenges of incorporating medical imaging into data integration models, in the context of precision oncology. We present the different categories of imaging-omics integration and discuss recent progress, highlighting the opportunities that arise from bringing together spatial data on different scales.
{"title":"Radiology and multi-scale data integration for precision oncology","authors":"Hania Paverd, Konstantinos Zormpas-Petridis, Hannah Clayton, Sarah Burge, Mireia Crispin-Ortuzar","doi":"10.1038/s41698-024-00656-0","DOIUrl":"10.1038/s41698-024-00656-0","url":null,"abstract":"In this Perspective paper we explore the potential of integrating radiological imaging with other data types, a critical yet underdeveloped area in comparison to the fusion of other multi-omic data. Radiological images provide a comprehensive, three-dimensional view of cancer, capturing features that would be missed by biopsies or other data modalities. This paper explores the complexities and challenges of incorporating medical imaging into data integration models, in the context of precision oncology. We present the different categories of imaging-omics integration and discuss recent progress, highlighting the opportunities that arise from bringing together spatial data on different scales.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11282284/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141766901","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}
Gastrointestinal stromal tumor (GIST) is the most common mesenchymal original tumor in gastrointestinal (GI) tract and is considered to have varying malignant potential. With the advancement of computer science, radiomics technology and deep learning had been applied in medical researches. It’s vital to construct a more accurate and reliable multimodal predictive model for recurrence-free survival (RFS) aiding for clinical decision-making. A total of 254 patients underwent surgery and pathologically diagnosed with GIST in The First Hospital of China Medical University from 2019 to 2022 were included in the study. Preoperative contrast enhanced computerized tomography (CE-CT) and hematoxylin/eosin (H&E) stained whole slide images (WSI) were acquired for analysis. In the present study, we constructed a sum of 11 models while the multimodal model (average C-index of 0.917 on validation set in 10-fold cross validation) performed the best on external validation cohort with an average C-index of 0.864. The multimodal model also reached statistical significance when validated in the external validation cohort (n = 42) with a p-value of 0.0088 which pertained to the recurrence-free survival (RFS) comparison between the high and low groups using the optimal threshold on the predictive score. We also explored the biological significance of radiomics and pathomics features by visualization and quantitative analysis. In the present study, we constructed a multimodal model predicting RFS of GIST which was prior over unimodal models. We also proposed hypothesis on the correlation between morphology of tumor cell and prognosis.
胃肠道间质瘤（GIST）是胃肠道中最常见的间质原发肿瘤，被认为具有不同的恶性潜能。随着计算机科学的发展，放射组学技术和深度学习已被应用于医学研究。构建一个更准确、更可靠的无复发生存率（RFS）多模态预测模型，帮助临床决策至关重要。该研究共纳入2019年至2022年在中国医科大学附属第一医院接受手术并病理诊断为GIST的254例患者。研究人员采集了术前造影剂增强计算机断层扫描（CE-CT）和苏木精/伊红（H&E）染色的全切片图像（WSI）进行分析。在本研究中，我们构建了 11 个模型的总和，而多模态模型（10 倍交叉验证中验证集的平均 C 指数为 0.917）在外部验证队列中表现最佳，平均 C 指数为 0.864。在外部验证队列（n = 42）中验证时，多模态模型也达到了统计学意义，p 值为 0.0088，这与使用预测评分最佳阈值的高组和低组的无复发生存率（RFS）比较有关。我们还通过可视化和定量分析探讨了放射组学和病理组学特征的生物学意义。在本研究中，我们构建了一个预测 GIST RFS 的多模态模型，该模型优于单模态模型。我们还提出了肿瘤细胞形态与预后相关性的假设。
{"title":"Development and interpretation of a multimodal predictive model for prognosis of gastrointestinal stromal tumor","authors":"He Song, XianHao Xiao, Xu Han, YeFei Sun, GuoLiang Zheng, Qi Miao, YuLong Zhang, JiaYing Tan, Gang Liu, QianRu He, JianPing Zhou, ZhiChao Zheng, GuiYang Jiang","doi":"10.1038/s41698-024-00636-4","DOIUrl":"10.1038/s41698-024-00636-4","url":null,"abstract":"Gastrointestinal stromal tumor (GIST) is the most common mesenchymal original tumor in gastrointestinal (GI) tract and is considered to have varying malignant potential. With the advancement of computer science, radiomics technology and deep learning had been applied in medical researches. It’s vital to construct a more accurate and reliable multimodal predictive model for recurrence-free survival (RFS) aiding for clinical decision-making. A total of 254 patients underwent surgery and pathologically diagnosed with GIST in The First Hospital of China Medical University from 2019 to 2022 were included in the study. Preoperative contrast enhanced computerized tomography (CE-CT) and hematoxylin/eosin (H&E) stained whole slide images (WSI) were acquired for analysis. In the present study, we constructed a sum of 11 models while the multimodal model (average C-index of 0.917 on validation set in 10-fold cross validation) performed the best on external validation cohort with an average C-index of 0.864. The multimodal model also reached statistical significance when validated in the external validation cohort (n = 42) with a p-value of 0.0088 which pertained to the recurrence-free survival (RFS) comparison between the high and low groups using the optimal threshold on the predictive score. We also explored the biological significance of radiomics and pathomics features by visualization and quantitative analysis. In the present study, we constructed a multimodal model predicting RFS of GIST which was prior over unimodal models. We also proposed hypothesis on the correlation between morphology of tumor cell and prognosis.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11282065/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141766899","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：