BMC Cancer最新文献

{"title":"Long-term outcomes of salvage high-dose-rate brachytherapy for localized recurrence of prostate cancer following definitive radiation therapy: a retrospective analysis.","authors":"Kenta Watanabe, Nobuhiko Kamitani, Naoki Ikeda, Yujiro Kawata, Ryoji Tokiya, Takafumi Hayashi, Yoshiyuki Miyaji, Tsutomu Tamada, Kuniaki Katsui","doi":"10.1186/s12885-025-13918-2","DOIUrl":"10.1186/s12885-025-13918-2","url":null,"abstract":"<p><strong>Background: </strong>Salvage high-dose-rate brachytherapy (HDR-BT) is a potential treatment for localized recurrence of prostate cancer following definitive radiation therapy. This study aimed to evaluate the long-term safety and efficacy of HDR-BT alone, without androgen deprivation therapy (ADT), in this patient population.</p><p><strong>Methods: </strong>We conducted a retrospective analysis of patients with prostate cancer who developed pathologically confirmed local recurrence after definitive radiation therapy and were treated with salvage HDR-BT alone at Kawasaki Medical School Hospital between 2007 and 2021. The prescribed HDR-BT dose was 22 Gy in 2 fractions. Biochemical relapse-free survival (bRFS), cause-specific survival (CSS), and overall survival (OS) were assessed using the Kaplan-Meier method. Adverse events were evaluated based on the Common Terminology Criteria for Adverse Events.</p><p><strong>Results: </strong>Thirty-five patients were included, with a median follow-up of 66.0 months (range, 8.1-169.1). The 5-year bRFS, CSS, and OS rates were 29.7%, 100%, and 89.3%, respectively. Biochemical recurrence occurred in 21 patients (60.0%). Grade 2 adverse events were reported in eight patients (22.9%), while two (5.7%) experienced grade 3 adverse events. All grade 3 adverse events occurred in patients who had HDR-BT as their initial definitive radiation therapy.</p><p><strong>Conclusions: </strong>Salvage HDR-BT without ADT is a safe and effective treatment option for localized prostate cancer recurrence after definitive radiation therapy. It provides excellent CSS rates with acceptable toxicity while potentially reducing the need for ADT. Further prospective studies are warranted to confirm these findings.</p>","PeriodicalId":9131,"journal":{"name":"BMC Cancer","volume":"25 1","pages":"524"},"PeriodicalIF":3.4,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11930011/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143691055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Updated results of 3,050 non-melanoma skin cancer (NMSC) lesions in 1725 patients treated with high resolution dermal ultrasound-guided superficial radiotherapy, a multi-institutional study.","authors":"Mairead Moloney, Peyton M Harris, Peter Kaczmarski, Songzhu Zheng, Daniel Ladd, Donna Serure, Ariana Malik, Lio Yu","doi":"10.1186/s12885-025-13864-z","DOIUrl":"10.1186/s12885-025-13864-z","url":null,"abstract":"<p><strong>Background: </strong>Image-guided superficial radiation therapy (IGSRT) using a high resolution dermal ultrasound, is becoming a non-surgical highly effective treatment option for non-melanoma skin cancer (NMSC). In a previous study, we reported results from a multi-institutional study of 1616 patients with 2917 NMSC lesions treated with IGSRT showing a 99.3% rate of local control (LC) with mean follow-up of 16.06 months.</p><p><strong>Methods: </strong>In this study, we analyze 133 additional lesions from 93 patients, as well as update previous findings with a longer follow-up duration, and perform subgroup analysis and Kaplan-Meier statistics. A retrospective analysis of 1709 patients with 3,050 Stage 0, I, and II NMSC lesions treated from 2017 to 2020 was performed.</p><p><strong>Results: </strong>With image guidance, lesions received a median of 20 fractions of 50, 70, or 100 kilovoltage(kV) IGSRT. Average follow-up was 25.1 months with a maximum follow up of 65.6 months for the entire cohort. Sixty-eight patients expired, with deaths due to unrelated causes, who had no-evidence of disease (NED) at last follow-up prior to death, leading to Disease-Specific-Survival of 100% (Overall survival was 96%). Absolute LC of 99.2% was achieved in 3,027 of 3,050 lesions with overall absolute LC for BCC, SCC, and SCC-is being 99.0%, 99.2%, and 99.8%, respectively. As of January 2022, no other late complications were found.</p><p><strong>Discussion: </strong>These updated results demonstrates that IGSRT should be considered a first-line option for the non-surgical treatment of NMSC as it continues to achieve low complication rates while maintaining a high level of LC.</p>","PeriodicalId":9131,"journal":{"name":"BMC Cancer","volume":"25 1","pages":"526"},"PeriodicalIF":3.4,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11930008/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143691073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"NDRG1 alleviates Erastin-induced ferroptosis of hepatocellular carcinoma.","authors":"Liuzheng Li, Tong Wu, Guocha Gong, Bo Li, Jiawei Feng, Leisheng Xu, Hairong Zhao, Xuechang Gao","doi":"10.1186/s12885-025-13954-y","DOIUrl":"10.1186/s12885-025-13954-y","url":null,"abstract":"<p><strong>Background: </strong>NDRG1, a cell differentiation-associated factor, has recently emerged as a regulator ferroptosis. Nevertheless, its role in modulating ferroptosis within hepatocellular carcinoma (HCC) remains uncharacterized.</p><p><strong>Methods: </strong>The differential expression of NDRG1 and its prognostic value were analyzed in HCC using data from TCGA and GEO. Ferroptosis in HepG2 and Huh7 cells was assessed using flow cytometry, transmission electron microscopy, and propidium iodide staining following NDRG1 knockdown using shRNA. RNA-seq was performed to characterize the mRNA expression profiles in HepG2 cells, identifying differentially expressed mRNAs (DE-mRNAs) and NDRG1-related hub genes.</p><p><strong>Results: </strong>NDRG1 was overexpressed in multiple malignant tumors, including HCC, and was associated with a significantly poor prognosis in HCC patients. A nomogram model integrating NDRG1 expression and clinical parameters demonstrated robust prognostic accuracy. NDRG1 knockdown potentiated erastin-induced alterations in Fe²⁺, total ROS, lipid ROS, and ferroptosis markers (PTGS2, ACSL4, GPX4, SLC7A11, GSH, GSSG), while exacerbating mitochondrial ultrastructural damage in HepG2 and Huh7 cells. Erastin induction elicited 1,056 DE-mRNAs, while subsequent NDRG1 knockdown revealed 1,323 DE-mRNAs in HepG2 cells. These DE-mRNAs are mainly involved in metastasis, immunity, growth, ferroptosis, and are associated with AMPK, MAPK, and PI3K/AKT pathways. Moreover, NDRG1 potentially interacted with HSPA8, CDH1, ALDOC, ANGPTL4, ANKRD37, CA9, ERBB3, FOS. qRT-PCR confirmed their expression changes consistent with RNA-seq.</p><p><strong>Conclusion: </strong>NDRG1 exhibits strong predictive value for HCC, and accelerates tumor progression by suppressing ferroptosis.</p>","PeriodicalId":9131,"journal":{"name":"BMC Cancer","volume":"25 1","pages":"522"},"PeriodicalIF":3.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11929176/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical course and prognostic factors of patients with dedifferentiated liposarcoma: a retrospective analysis.","authors":"Jelena Casier, Iris Timmermans, Annouschka Laenen, Daphne Hompes, Thomas Douchy, Raf Sciot, Melissa Christiaens, Hazem Wafa, Patrick Schöffski","doi":"10.1186/s12885-025-13813-w","DOIUrl":"10.1186/s12885-025-13813-w","url":null,"abstract":"<p><strong>Introduction: </strong>Dedifferentiated liposarcoma (DDLPS) is a fairly common subtype of soft tissue sarcoma, but relatively little is known about the clinical course and prognostic factors of this mesenchymal malignancy.</p><p><strong>Methods: </strong>We performed a retrospective analysis of patients diagnosed with DDLPS at the University Hospital Leuven, Belgium between 1991 and 2022 based on an established clinical database and patient records.</p><p><strong>Results: </strong>We identified 259 patients with DDLPS, with the retroperitoneum as most common location of the primary tumor (47.5%). 204/259 patients (78.8%) patients had primary surgery. Radiotherapy was administered in the pre- (46/259, 17.8%) or postoperative setting (51/259, 19.7%). At diagnosis 28/259 (10.8%) patients presented with locally inoperable disease and 26/259 (10.0%) with synchronous metastasis. In patients who had primary surgery, local relapses were seen in 114/259 (44.0%) patients and 80/259 (30.9%) patients developed metachronous metastasis. A total of 48/259 (18.5%) patients developed both local relapse and metastasis. Patients with inoperable or metastatic disease were often treated with systemic therapy. The most common first-line systemic therapies were doxorubicin (51/98, 52.0%), doxorubicin combined with ifosfamide (12/98, 12.2%) and different types of experimental treatments (18/98, 18.4%). The median overall survival from first diagnosis of DDLPS to death of all causes was 70.5 months (95% confidence interval [CI] 56.6-98.6) for all patients, 10.9 months (95% CI 3.6-29.2) in patients with inoperable disease, 28.4 months (95% CI 1.3-199.3) for patients with local relapse and only 9.4 months (95% CI 1.2-25.9) for patients with metastatic disease. We identified lower age, primary surgery, absence of synchronous metastasis, absence of local relapse and treatment with experimental therapy as statistically significant favorable prognostic factors.</p><p><strong>Conclusions: </strong>DDLPS is a subtype of soft tissue sarcoma with an aggressive clinical course and very poor prognosis, especially in patients with inoperable or metastatic disease. The results with classic chemotherapy are poor, and experimental treatments may be a preferred choice for individual patients. Data from this retrospective series can inform the design of future prospective and ongoing trials in this setting.</p>","PeriodicalId":9131,"journal":{"name":"BMC Cancer","volume":"25 1","pages":"517"},"PeriodicalIF":3.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11927263/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A risk prediction model for gastric cancer based on endoscopic atrophy classification.","authors":"Yadi Lan, Weijia Sun, Shen Zhong, Qianqian Xu, Yining Xue, Zhaoyu Liu, Lei Shi, Bing Han, Tianyu Zhai, Mingyue Liu, Yujing Sun, Hongwei Xu","doi":"10.1186/s12885-025-13860-3","DOIUrl":"10.1186/s12885-025-13860-3","url":null,"abstract":"<p><strong>Backgrounds: </strong>Gastric cancer (GC) is a prevalent malignancy affecting the digestive system. We aimed to develop a risk prediction model based on endoscopic atrophy classification for GC.</p><p><strong>Methods: </strong>We retrospectively collected the data from January 2020 to October 2021 in our hospital and randomly divided the patients into training and validation sets in an 8:2 ratio. We used multiple machine learning algorithms such as logistic regression (LR), Decision tree, Support Vector Machine, Random forest, and so on to establish the models. We employed the Least absolute shrinkage and selection operator (LASSO) to screen variables for the LR model. However, we chose all the variables to construct the models for other machine learning algorithms. All models were evaluated using the receiver operating characteristic curve (ROC), predictive histograms, and decision curve analysis (DCA).</p><p><strong>Results: </strong>A total of 1156 patients were selected for the analysis. Five variables, including age, sex, family history of GC, HP infection status, and Kimura-Takemoto Classification (KTC), were screened using LASSO analysis. The area under the curve (AUC) of all the machine learning models ranged from 0.762 to 0.974 in the training set and from 0.608 to 0.812 in the validation set. Among them, the LR model exhibited the highest AUC value (0.812, 95%CI: 0.737-0.887) in the validation set with good calibration and clinical applicability. Finally, we constructed a nomogram to demonstrate the LR model.</p><p><strong>Conclusions: </strong>We established a nomogram based on endoscopic atrophy classification for GC, which might be valuable in predicting GC risk and assisting clinical decision-making.</p>","PeriodicalId":9131,"journal":{"name":"BMC Cancer","volume":"25 1","pages":"518"},"PeriodicalIF":3.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11927292/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of pathological complete response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer using ¹⁸F-FDG PET radiomics features of primary tumour and lymph nodes.","authors":"Xingbiao Liu, Zhilin Ji, Libo Zhang, Linlin Li, Wengui Xu, Qian Su","doi":"10.1186/s12885-025-13905-7","DOIUrl":"10.1186/s12885-025-13905-7","url":null,"abstract":"<p><strong>Background: </strong>Predicting the response to neoadjuvant chemoimmunotherapy in patients with resectable non-small cell lung cancer (NSCLC) facilitates clinical treatment decisions. Our study aimed to establish a machine learning model that accurately predicts the pathological complete response (pCR) using ¹⁸F-FDG PET radiomics features.</p><p><strong>Methods: </strong>We retrospectively included 210 patients with NSCLC who completed neoadjuvant chemoimmunotherapy and subsequently underwent surgery with pathological results, categorising them into a training set of 147 patients and a test set of 63 patients. Radiomic features were extracted from the primary tumour and lymph nodes. Using 10-fold cross-validation with the least absolute shrinkage and selection operator method, we identified the most impactful radiomic features. The clinical features were screened using univariate and multivariate analyses. Machine learning models were developed using the random forest method, leading to the establishment of one clinical feature model, one primary tumour radiomics model, and two fusion radiomics models. The performance of these models was evaluated based on the area under the curve (AUC).</p><p><strong>Results: </strong>In the training set, the three radiomic models showed comparable AUC values, ranging from 0.901 to 0.925. The clinical model underperformed, with an AUC of 0.677. In the test set, the Fusion_LN1LN2 model achieved the highest AUC (0.823), closely followed by the Fusion_Lnall model with an AUC of 0.729. The primary tumour model achieved a moderate AUC of 0.666, whereas the clinical model had the lowest AUC at 0.631. Additionally, the Fusion_LN1LN2 model demonstrated positive net reclassification improvement and integrated discrimination improvement values compared with the other models, and we employed the SHapley Additive exPlanations methodology to interpret the results of our optimal model.</p><p><strong>Conclusions: </strong>Our fusion radiomics model, based on ¹⁸F-FDG-PET, will assist clinicians in predicting pCR before neoadjuvant chemoimmunotherapy for patients with resectable NSCLC.</p>","PeriodicalId":9131,"journal":{"name":"BMC Cancer","volume":"25 1","pages":"520"},"PeriodicalIF":3.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11929329/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using machine learning for predicting cancer-specific mortality in bladder cancer patients undergoing radical cystectomy: a SEER-based study.","authors":"Lei Dai, Kun Ye, Gaosheng Yao, Juan Lin, Zhiping Tan, Jinhuan Wei, Yanchang Hu, Junhang Luo, Yong Fang, Wei Chen","doi":"10.1186/s12885-025-13942-2","DOIUrl":"10.1186/s12885-025-13942-2","url":null,"abstract":"<p><strong>Background: </strong>Accurately assessing the prognosis of bladder cancer patients after radical cystectomy has important clinical and research implications. Current models, based on traditional statistical approaches and complex variables, have limited performance. We aimed to develop a machine learning (ML)-based prognostic model to predict 5-year cancer-specific mortality (CSM) in bladder cancer patients undergoing radical cystectomy, and compare its performance with current validated models.</p><p><strong>Methods: </strong>Patients were selected from the Surveillance, Epidemiology, and End Results database and the First Affiliated Hospital of Sun Yat-sen University for model construction and validation. We used univariate and multivariate Cox regression to select variables with independent prognostic significance for inclusion in the model's construction. Six ML algorithms and Cox proportional hazards regression were used to construct prediction models. Concordance index (C-index) and Brier scores were used to compare the discrimination and calibration of these models. The Shapley additive explanation method was used to explain the best-performing model. Finally, we compared this model with three existing prognostic models in urothelial carcinoma patients using C-index, area under the receiver operating characteristic curve (AUC), Brier scores, calibration curves, and decision curve analysis (DCA).</p><p><strong>Results: </strong>This study included 8,380 patients, with 6,656 in the training set, 1,664 in the internal validation set, and 60 in the external validation set. Eight features were ultimately identified to build models. The Light Gradient Boosting Machine (LightGBM) model showed the best performance in predicting 5-year CSM in bladder cancer patients undergoing radical cystectomy (internal validation: C-index = 0.723, Brier score = 0.191; external validation: C-index = 0.791, Brier score = 0.134). The lymph node density and tumor stage have the most significant impact on the prediction. In comparison with current validated models, our model also demonstrated the best discrimination and calibration (internal validation: C-index = 0.718, AUC = 0.779, Brier score = 0.191; external validation: C-index = 0.789, AUC = 0.884, Brier score = 0.137). Finally, calibration curves and DCA exhibited better predictive performance as well.</p><p><strong>Conclusions: </strong>We successfully developed an explainable ML model for predicting 5-year CSM after radical cystectomy in bladder cancer patients, and it demonstrated better performance compared to existing models.</p>","PeriodicalId":9131,"journal":{"name":"BMC Cancer","volume":"25 1","pages":"523"},"PeriodicalIF":3.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11929216/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The combination of poly(ADP-ribose) polymerase inhibitor and statin inhibits the proliferation of human castration-resistant and taxane-resistant prostate cancer cells in vitro and in vivo.","authors":"Yoshitaka Sekine, Daisuke Oka, Akira Ohtsu, Hiroshi Nakayama, Takeshi Miyao, Yoshiyuki Miyazawa, Seiji Arai, Hidekazu Koike, Hiroshi Matsui, Yasuhiro Shibata, Kazuhiro Suzuki","doi":"10.1186/s12885-025-13895-6","DOIUrl":"10.1186/s12885-025-13895-6","url":null,"abstract":"<p><strong>Background: </strong>Olaparib exhibits antitumor effects in castration-resistant prostate cancer patients with germline mutations in DNA repair genes. We previously reported that simvastatin reduced the expression of DNA repair genes in PC-3 cells. The efficacy of combination therapy using olaparib and simvastatin as \"BRCAness\" in castration-resistant and taxane-resistant prostate cancers was evaluated in this study.</p><p><strong>Methods: </strong>PC-3, LNCaP, and 22Rv1 human prostate cancer cell lines were used to develop androgen-independent LNCaP cells (LNCaP-LA). mRNA and protein expression levels were evaluated by quantitative real-time polymerase chain reaction and western blot analysis, respectively. Cell viability was determined using the MTS assay and cell counts. All evaluations were performed on cells treated with simvastatin with or without olaparib.</p><p><strong>Results: </strong>The mRNA levels of BRCA1, BRCA2, RAD51, FANCD2, FANCG, FANCA, BARD1, RFC3, RFC4, and RFC5, which are known DNA repair genes, were downregulated by simvastatin in androgen-independent prostate cancer cells, such as PC-3, LNCaP-LA, and 22Rv1 cells. In contrast, the expression of all these genes remained unchanged in androgen-dependent LNCaP cells following treatment with simvastatin. Furthermore, simvastatin increased the expression of above stated genes in normal prostate stromal cells (PrSC). The reduction in BRCA1 and BRCA2 expression following siRNA transfection increased the cytocidal effects of Olaparib in PC-3 and LNCaP-LA cells. The combination of olaparib and simvastatin further inhibited cell proliferation compared to monotherapy with either drug in PC-3, 22Rv1, and LNCaP-LA cells but not in PrSC cells. In a 22Rv1-derived mouse xenograft model, the combination of olaparib and simvastatin enhanced the inhibition of cell proliferation. Moreover, we established a 22Rv1 cell line with acquired resistance to Cabazitaxel (22Rv1-CR). In 22Rv1-CR cells, simvastatin also decreased the expression of BRCA1, BRCA2, and FANCA, and the combination of olaparib and simvastatin further enhanced the inhibition of cell proliferation compared with treatment with either of the drugs alone.</p><p><strong>Conclusions: </strong>Simvastatin altered the expression of several genes associated with DNA repair in castration-resistant and taxane-resistant prostate cancer cells. The combination of poly (ADP-ribose) polymerase inhibitors and drugs that decrease DNA repair gene expression can potentially affect castration-resistant and taxane-resistant prostate cancer growth.</p>","PeriodicalId":9131,"journal":{"name":"BMC Cancer","volume":"25 1","pages":"521"},"PeriodicalIF":3.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11929194/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Early prediction of progression-free survival of patients with locally advanced nasopharyngeal carcinoma using multi-parametric MRI radiomics.","authors":"Lian Jian, Cai Sheng, Huaping Liu, Handong Li, Pingsheng Hu, Zhaodong Ai, Xiaoping Yu, Huai Liu","doi":"10.1186/s12885-025-13899-2","DOIUrl":"10.1186/s12885-025-13899-2","url":null,"abstract":"<p><strong>Purpose: </strong>Prognostic prediction plays a pivotal role in guiding personalized treatment for patients with locoregionally advanced nasopharyngeal carcinoma (LANPC). However, few studies have investigated the incremental value of functional MRI to the conventional MRI-based radiomic models. Here, we aimed to develop a radiomic model including functional MRI to predict the prognosis of LANPC patients.</p><p><strong>Methods: </strong>One hundred and twenty-six patients (training dataset, n = 88; validation dataset, n = 38) with LANPC were retrospectively included. Radiomic features were extracted from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), contrast-enhanced T1WI (cT1WI), and diffusion-weighted imaging (DWI). Pearson correlation analysis and recursive feature elimination or Relief were used for identifying features associated with progression-free survival (PFS). Five machine learning algorithms with cross-validation were compared to develop the optimal single-layer and fusion radiomic models. Clinical and combined models were developed via multivariate Cox regression model.</p><p><strong>Results: </strong>The clinical model based on TNM stage achieved a C-index of 0.544 in the validation dataset. The fusion radiomic model, incorporating DWI-, T1WI-, and cT1WI-derived imaging features, yielded the highest C-index of 0.788, outperforming DWI-based (C-index = 0.739), T1WI-based (C-index = 0.734), cT1WI-based (C-index = 0.722), and T1WI plus cT1WI-based models (C-index = 0.747) in predicting PFS. The fusion radiomic model yielded the C-index of 0.786 and 0.690 in predicting distant metastasis-free survival and overall survival, respectively. However, the addition of TNM stage to the fusion radiomic model could not improve the predictive power.</p><p><strong>Conclusion: </strong>The fusion radiomic model demonstrates favorable performance in predicting survival outcomes in LANPC patients, surpassing TNM staging alone. Integration of DWI-derived features into conventional MRI radiomic models could enhance predictive accuracy.</p>","PeriodicalId":9131,"journal":{"name":"BMC Cancer","volume":"25 1","pages":"519"},"PeriodicalIF":3.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11929181/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of PDAC diagnosis and prognosis evaluation models based on machine learning.","authors":"Yingqi Xiao, Shixin Sun, Naxin Zheng, Jing Zhao, Xiaohan Li, Jianmin Xu, Haolian Li, Chenran Du, Lijun Zeng, Juling Zhang, Xiuyun Yin, Yuan Huang, Xuemei Yang, Fang Yuan, Xingwang Jia, Boan Li, Bo Li","doi":"10.1186/s12885-025-13929-z","DOIUrl":"10.1186/s12885-025-13929-z","url":null,"abstract":"<p><strong>Background: </strong>Pancreatic ductal adenocarcinoma (PDAC) is difficult to detect early and highly aggressive, often leading to poor patient prognosis. Existing serum biomarkers like CA19-9 are limited in early diagnosis, failing to meet clinical needs. Machine learning (ML)/deep learning (DL) technologies have shown great potential in biomedicine. This study aims to establish PDAC differential diagnosis and prognosis assessment models using ML combined with serum biomarkers for early diagnosis, risk stratification, and personalized treatment recommendations, improving early diagnosis rates and patient survival.</p><p><strong>Methods: </strong>The study included serum biomarker data and prognosis information from 117 PDAC patients. ML models (Random Forest (RF), Neural Network (NNET), Support Vector Machine (SVM), and Gradient Boosting Machine (GBM)) were used for differential diagnosis, evaluated by accuracy, Kappa test, ROC curve, sensitivity, and specificity. COX proportional hazards model and DeepSurv DL model predicted survival risk, compared by C-index and Log-rank test. Based on DeepSurv's risk predictions, personalized treatment recommendations were made and their effectiveness assessed.</p><p><strong>Results: </strong>Effective PDAC diagnosis and prognosis models were built using ML. The validation set data shows that the accuracy of the RF, NNET, SVM, and GBM models are 84.21%, 84.21%, 76.97%, and 83.55%; the sensitivity are 91.26%, 90.29%, 89.32%, and 88.35%; and the specificity are 69.39%, 71.43%, 51.02%, and 73.47%. The Kappa values are 0.6266, 0.6307, 0.4336, and 0.6215; and the AUC are 0.889, 0.8488, 0.8488, and 0.8704, respectively. BCAT1, AMY, and CA12-5 were selected as modeling parameters for the prognosis model using COX regression. DeepSurv outperformed the COX model on both training and validation sets, with C-indexes of 0.738 and 0.724, respectively. The Kaplan-Meier survival curves indicate that personalized treatment recommendations based on DeepSurv can help patients achieve survival benefits.</p><p><strong>Conclusion: </strong>This study built efficient PDAC diagnosis and prognosis models using ML, improving early diagnosis rates and prognosis accuracy. The DeepSurv model excelled in prognosis prediction and successfully guided personalized treatment recommendations and supporting PDAC clinical management.</p>","PeriodicalId":9131,"journal":{"name":"BMC Cancer","volume":"25 1","pages":"512"},"PeriodicalIF":3.4,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11924714/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143669042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}