Hamidreza Ashayeri, Navid Sobhi, Paweł Pławiak, Siamak Pedrammehr, R. Alizadehsani, Ali Jafarizadeh
Artificial intelligence (AI), encompassing machine learning (ML) and deep learning (DL), has revolutionized medical research, facilitating advancements in drug discovery and cancer diagnosis. ML identifies patterns in data, while DL employs neural networks for intricate processing. Predictive modeling challenges, such as data labeling, are addressed by transfer learning (TL), leveraging pre-existing models for faster training. TL shows potential in genetic research, improving tasks like gene expression analysis, mutation detection, genetic syndrome recognition, and genotype–phenotype association. This review explores the role of TL in overcoming challenges in mutation detection, genetic syndrome detection, gene expression, or phenotype–genotype association. TL has shown effectiveness in various aspects of genetic research. TL enhances the accuracy and efficiency of mutation detection, aiding in the identification of genetic abnormalities. TL can improve the diagnostic accuracy of syndrome-related genetic patterns. Moreover, TL plays a crucial role in gene expression analysis in order to accurately predict gene expression levels and their interactions. Additionally, TL enhances phenotype–genotype association studies by leveraging pre-trained models. In conclusion, TL enhances AI efficiency by improving mutation prediction, gene expression analysis, and genetic syndrome detection. Future studies should focus on increasing domain similarities, expanding databases, and incorporating clinical data for better predictions.
{"title":"Transfer Learning in Cancer Genetics, Mutation Detection, Gene Expression Analysis, and Syndrome Recognition","authors":"Hamidreza Ashayeri, Navid Sobhi, Paweł Pławiak, Siamak Pedrammehr, R. Alizadehsani, Ali Jafarizadeh","doi":"10.3390/cancers16112138","DOIUrl":"https://doi.org/10.3390/cancers16112138","url":null,"abstract":"Artificial intelligence (AI), encompassing machine learning (ML) and deep learning (DL), has revolutionized medical research, facilitating advancements in drug discovery and cancer diagnosis. ML identifies patterns in data, while DL employs neural networks for intricate processing. Predictive modeling challenges, such as data labeling, are addressed by transfer learning (TL), leveraging pre-existing models for faster training. TL shows potential in genetic research, improving tasks like gene expression analysis, mutation detection, genetic syndrome recognition, and genotype–phenotype association. This review explores the role of TL in overcoming challenges in mutation detection, genetic syndrome detection, gene expression, or phenotype–genotype association. TL has shown effectiveness in various aspects of genetic research. TL enhances the accuracy and efficiency of mutation detection, aiding in the identification of genetic abnormalities. TL can improve the diagnostic accuracy of syndrome-related genetic patterns. Moreover, TL plays a crucial role in gene expression analysis in order to accurately predict gene expression levels and their interactions. Additionally, TL enhances phenotype–genotype association studies by leveraging pre-trained models. In conclusion, TL enhances AI efficiency by improving mutation prediction, gene expression analysis, and genetic syndrome detection. Future studies should focus on increasing domain similarities, expanding databases, and incorporating clinical data for better predictions.","PeriodicalId":504676,"journal":{"name":"Cancers","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141265658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jeong Ha Lee, Jeong Yun Jang, J. Noh, Kyungmi Yang, Hongryull Pyo
Primary tracheobronchial adenoid cystic carcinoma (ACC) is a rare malignancy, so the optimal radiotherapy (RT) dose remains unestablished. We aimed to evaluate the effectiveness of dose-escalated RT for primary tracheobronchial ACC. We retrospectively reviewed 48 patients who had undergone definitive or postoperative RT. Patients classified into the low- and high-dose groups received RT doses <70.0 and ≥70.0 Gy in EQD2, respectively. The primary endpoint was freedom from local progression (FFLP) and overall survival (OS). Throughout the follow-up period, seven patients (14.6%) experienced local progression, while 31 (64.6%) exhibited distant metastasis, most commonly in the lungs. In total, the 5-year FFLP and OS rates were 85.7 and 84.7%, respectively. Multivariate analysis revealed that regional lymph node metastasis at diagnosis and receipt of definitive RT were associated with poorer OS. In the subgroup analysis, the definitive RT group had a 5-year FFLP rate of 33.3 and 78.2% in the low- and high-dose groups (p = 0.065), whereas 5-year OS rates were 66.7 and 79.0%, respectively (p = 0.022). Four patients (8.3%) experienced Grade 3 toxicity with tracheal or main bronchus stenosis. Dose-escalated RT with conventional fractionation may be effective in patients with tracheobronchial ACC, especially for a definitive aim.
{"title":"Dose-Escalated Radiotherapy for Primary Tracheobronchial Adenoid Cystic Carcinoma","authors":"Jeong Ha Lee, Jeong Yun Jang, J. Noh, Kyungmi Yang, Hongryull Pyo","doi":"10.3390/cancers16112127","DOIUrl":"https://doi.org/10.3390/cancers16112127","url":null,"abstract":"Primary tracheobronchial adenoid cystic carcinoma (ACC) is a rare malignancy, so the optimal radiotherapy (RT) dose remains unestablished. We aimed to evaluate the effectiveness of dose-escalated RT for primary tracheobronchial ACC. We retrospectively reviewed 48 patients who had undergone definitive or postoperative RT. Patients classified into the low- and high-dose groups received RT doses <70.0 and ≥70.0 Gy in EQD2, respectively. The primary endpoint was freedom from local progression (FFLP) and overall survival (OS). Throughout the follow-up period, seven patients (14.6%) experienced local progression, while 31 (64.6%) exhibited distant metastasis, most commonly in the lungs. In total, the 5-year FFLP and OS rates were 85.7 and 84.7%, respectively. Multivariate analysis revealed that regional lymph node metastasis at diagnosis and receipt of definitive RT were associated with poorer OS. In the subgroup analysis, the definitive RT group had a 5-year FFLP rate of 33.3 and 78.2% in the low- and high-dose groups (p = 0.065), whereas 5-year OS rates were 66.7 and 79.0%, respectively (p = 0.022). Four patients (8.3%) experienced Grade 3 toxicity with tracheal or main bronchus stenosis. Dose-escalated RT with conventional fractionation may be effective in patients with tracheobronchial ACC, especially for a definitive aim.","PeriodicalId":504676,"journal":{"name":"Cancers","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141272244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Schnaiter, E. Schamschula, Juliane Laschtowiczka, H. Fiegl, Johannes Zschocke, A. Zeimet, Katharina Wimmer, Daniel Reimer
Background: Homologous recombination deficiency (HRD) has evolved into a major diagnostic marker in high-grade ovarian cancer (HGOC), predicting the response to poly (adenosine diphosphate-ribose) polymerase inhibitors (PARPi) and also platinum-based therapy. In addition to HRD, the type of peritoneal tumor spread influences the treatment response and patient survival; miliary type tumor spread has a poorer predicted outcome than non-miliary type tumor spread. Methods: Known methods for HRD assessment were adapted for our technical requirements and the predictive-value integrated genomic instability score (PIGIS) for HRD assessment evolved as an outcome. PIGIS was validated in HGOC samples from 122 patients. We used PIGIS to analyze whether the type of tumor spread correlated with HRD status and whether this had an impact on survival. Results: We demonstrated that PIGIS can discriminate HRD-positive from HRD-negative samples. Tumors with a miliary tumor spread are HRD-negative and have a very bad prognosis with a progression-free survival (PFS) of 15.6 months and an overall survival (OS) of 3.9 years. However, HRD-negative non-miliary spreading tumors in our cohort had a much better prognosis (PFS 35.4 months, OS 8.9 years); similar to HRD-positive tumors (PFS 34.7 months, OS 8.9 years). Conclusions: Our results indicate that in a predominantly PARPi naïve cohort, the type of tumor spread and concomitant cytoreduction efficiency is a better predictor of survival than HRD and that HRD may be an accidental surrogate marker for tumor spread and concomitant cytoreduction efficiency. It remains to be determined whether this also applies for sensitivity to PARPi.
{"title":"Stratification of Homologous Recombination Deficiency-Negative High-Grade Ovarian Cancer by the Type of Peritoneal Spread into Two Groups with Distinct Survival Outcomes","authors":"S. Schnaiter, E. Schamschula, Juliane Laschtowiczka, H. Fiegl, Johannes Zschocke, A. Zeimet, Katharina Wimmer, Daniel Reimer","doi":"10.3390/cancers16112129","DOIUrl":"https://doi.org/10.3390/cancers16112129","url":null,"abstract":"Background: Homologous recombination deficiency (HRD) has evolved into a major diagnostic marker in high-grade ovarian cancer (HGOC), predicting the response to poly (adenosine diphosphate-ribose) polymerase inhibitors (PARPi) and also platinum-based therapy. In addition to HRD, the type of peritoneal tumor spread influences the treatment response and patient survival; miliary type tumor spread has a poorer predicted outcome than non-miliary type tumor spread. Methods: Known methods for HRD assessment were adapted for our technical requirements and the predictive-value integrated genomic instability score (PIGIS) for HRD assessment evolved as an outcome. PIGIS was validated in HGOC samples from 122 patients. We used PIGIS to analyze whether the type of tumor spread correlated with HRD status and whether this had an impact on survival. Results: We demonstrated that PIGIS can discriminate HRD-positive from HRD-negative samples. Tumors with a miliary tumor spread are HRD-negative and have a very bad prognosis with a progression-free survival (PFS) of 15.6 months and an overall survival (OS) of 3.9 years. However, HRD-negative non-miliary spreading tumors in our cohort had a much better prognosis (PFS 35.4 months, OS 8.9 years); similar to HRD-positive tumors (PFS 34.7 months, OS 8.9 years). Conclusions: Our results indicate that in a predominantly PARPi naïve cohort, the type of tumor spread and concomitant cytoreduction efficiency is a better predictor of survival than HRD and that HRD may be an accidental surrogate marker for tumor spread and concomitant cytoreduction efficiency. It remains to be determined whether this also applies for sensitivity to PARPi.","PeriodicalId":504676,"journal":{"name":"Cancers","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141270346","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
P. Jasielski, Izabela Zawlik, Anna Bogaczyk, N. Potocka, Sylwia Paszek, Michał Maźniak, Aleksandra Witkoś, Adrianna Korzystka, Aleksandra Kmieć, Tomasz Kluz
Endometrial cancer is one of the most common malignant tumours in women. The development of this tumour is associated with several genetic disorders, many of which are still unknown. One type of RNA molecules currently being intensively studied in many types of cancer are long non-coding RNAs (lncRNAs). LncRNA-coding genes occupy a large fraction of the human genome. LncRNAs regulate many aspects of cell development, metabolism, and other physiological processes. Diverse types of lncRNA can function as a tumour suppressor or an oncogene that can alter migration, invasion, cell proliferation, apoptosis, and immune system response. Recent studies suggest that selected lncRNAs are important in an endometrial cancer course. Our article describes over 70 lncRNAs involved in the development of endometrial cancer, which were studied via in vivo and in vitro research. It was proved that lncRNAs could both promote and inhibit the development of endometrial cancer. In the future, lncRNAs may become an important therapeutic target. The aim of this study is to review the role of lncRNAs in the development of carcinoma of uterine body.
{"title":"The Promotive and Inhibitory Role of Long Non-Coding RNAs in Endometrial Cancer Course—A Review","authors":"P. Jasielski, Izabela Zawlik, Anna Bogaczyk, N. Potocka, Sylwia Paszek, Michał Maźniak, Aleksandra Witkoś, Adrianna Korzystka, Aleksandra Kmieć, Tomasz Kluz","doi":"10.3390/cancers16112125","DOIUrl":"https://doi.org/10.3390/cancers16112125","url":null,"abstract":"Endometrial cancer is one of the most common malignant tumours in women. The development of this tumour is associated with several genetic disorders, many of which are still unknown. One type of RNA molecules currently being intensively studied in many types of cancer are long non-coding RNAs (lncRNAs). LncRNA-coding genes occupy a large fraction of the human genome. LncRNAs regulate many aspects of cell development, metabolism, and other physiological processes. Diverse types of lncRNA can function as a tumour suppressor or an oncogene that can alter migration, invasion, cell proliferation, apoptosis, and immune system response. Recent studies suggest that selected lncRNAs are important in an endometrial cancer course. Our article describes over 70 lncRNAs involved in the development of endometrial cancer, which were studied via in vivo and in vitro research. It was proved that lncRNAs could both promote and inhibit the development of endometrial cancer. In the future, lncRNAs may become an important therapeutic target. The aim of this study is to review the role of lncRNAs in the development of carcinoma of uterine body.","PeriodicalId":504676,"journal":{"name":"Cancers","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141271483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Clare M. Adams, Amanda McBride, Peter Michener, Irina Shkundina, R. Mitra, Hyun Hwan An, Pierluigi Porcu, Christine M. Eischen
Clinical trials with single-agent venetoclax/ABT-199 (anti-apoptotic BCL2 inhibitor) revealed that diffuse large B-cell lymphoma (DLBCL) is not solely dependent on BCL2 for survival. Gaining insight into pathways/proteins that increase venetoclax sensitivity or unique vulnerabilities in venetoclax-resistant DLBCL would provide new potential treatment avenues. Therefore, we generated acquired venetoclax-resistant DLBCL cells and evaluated these together with intrinsically venetoclax-resistant and -sensitive DLBCL lines. We identified resistance mechanisms, including alterations in BCL2 family members that differed between intrinsic and acquired venetoclax resistance and increased dependencies on specific pathways. Although combination treatments with BCL2 family member inhibitors may overcome venetoclax resistance, RNA-sequencing and drug/compound screens revealed that venetoclax-resistant DLBCL cells, including those with TP53 mutation, had a preferential dependency on oxidative phosphorylation. Mitochondrial electron transport chain complex I inhibition induced venetoclax-resistant, but not venetoclax-sensitive, DLBCL cell death. Inhibition of IDH2 (mitochondrial redox regulator) synergistically overcame venetoclax resistance. Additionally, both acquired and intrinsic venetoclax-resistant DLBCL cells were similarly sensitive to inhibitors of transcription, B-cell receptor signaling, and class I histone deacetylases. These approaches were also effective in DLBCL, follicular, and marginal zone lymphoma patient samples. Our results reveal there are multiple ways to circumvent or overcome the diverse venetoclax resistance mechanisms in DLBCL and other B-cell lymphomas and identify critical targetable pathways for future clinical investigations.
{"title":"Identifying Targetable Vulnerabilities to Circumvent or Overcome Venetoclax Resistance in Diffuse Large B-Cell Lymphoma","authors":"Clare M. Adams, Amanda McBride, Peter Michener, Irina Shkundina, R. Mitra, Hyun Hwan An, Pierluigi Porcu, Christine M. Eischen","doi":"10.3390/cancers16112130","DOIUrl":"https://doi.org/10.3390/cancers16112130","url":null,"abstract":"Clinical trials with single-agent venetoclax/ABT-199 (anti-apoptotic BCL2 inhibitor) revealed that diffuse large B-cell lymphoma (DLBCL) is not solely dependent on BCL2 for survival. Gaining insight into pathways/proteins that increase venetoclax sensitivity or unique vulnerabilities in venetoclax-resistant DLBCL would provide new potential treatment avenues. Therefore, we generated acquired venetoclax-resistant DLBCL cells and evaluated these together with intrinsically venetoclax-resistant and -sensitive DLBCL lines. We identified resistance mechanisms, including alterations in BCL2 family members that differed between intrinsic and acquired venetoclax resistance and increased dependencies on specific pathways. Although combination treatments with BCL2 family member inhibitors may overcome venetoclax resistance, RNA-sequencing and drug/compound screens revealed that venetoclax-resistant DLBCL cells, including those with TP53 mutation, had a preferential dependency on oxidative phosphorylation. Mitochondrial electron transport chain complex I inhibition induced venetoclax-resistant, but not venetoclax-sensitive, DLBCL cell death. Inhibition of IDH2 (mitochondrial redox regulator) synergistically overcame venetoclax resistance. Additionally, both acquired and intrinsic venetoclax-resistant DLBCL cells were similarly sensitive to inhibitors of transcription, B-cell receptor signaling, and class I histone deacetylases. These approaches were also effective in DLBCL, follicular, and marginal zone lymphoma patient samples. Our results reveal there are multiple ways to circumvent or overcome the diverse venetoclax resistance mechanisms in DLBCL and other B-cell lymphomas and identify critical targetable pathways for future clinical investigations.","PeriodicalId":504676,"journal":{"name":"Cancers","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141271737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Aryan Pandey, Anubha Chandla, Mahlet Mekonnen, Gabrielle Hovis, Zoe E. Teton, Kunal S. Patel, Richard G. Everson, Madhuri Wadehra, Isaac Yang
Although primary studies have reported the safety and efficacy of LITT as a primary treatment in glioma, they are limited by sample sizes and institutional variation in stereotactic parameters such as temperature and laser power. The current literature has yet to provide pooled statistics on outcomes solely for primary brain tumors according to the 2021 WHO Classification of Tumors of the Central Nervous System (WHO CNS5). In the present study, we identify recent articles on primary CNS neoplasms treated with LITT without prior intervention, focusing on relationships with molecular profile, PFS, and OS. This meta-analysis includes the extraction of data from primary sources across four databases using the Covidence systematic review manager. The pooled data suggest LITT may be a safe primary management option with tumor ablation rates of 94.8% and 84.6% in IDH-wildtype glioblastoma multiforme (GBM) and IDH-mutant astrocytoma, respectively. For IDH-wildtype GBM, the pooled PFS and OS were 5.0 and 9.0 months, respectively. Similar to rates reported in the prior literature, the neurologic and non-neurologic complication rates for IDH-wildtype GBM were 10.3% and 4.8%, respectively. The neurologic and non-neurologic complication rates were somewhat higher in the IDH-mutant astrocytoma cohort at 33% and 8.3%, likely due to a smaller cohort size.
虽然已有初步研究报告了 LITT 作为胶质瘤主要治疗方法的安全性和有效性，但这些研究受到样本量和立体定向参数（如温度和激光功率）机构差异的限制。目前的文献尚未根据 2021 年世界卫生组织中枢神经系统肿瘤分类（WHO CNS5）提供仅针对原发性脑肿瘤的疗效汇总统计数据。在本研究中，我们找出了近期关于未经事先干预而使用 LITT 治疗原发性中枢神经系统肿瘤的文章，重点关注与分子特征、PFS 和 OS 的关系。这项荟萃分析包括使用 Covidence 系统综述管理器从四个数据库的原始资料中提取数据。汇总数据表明，LITT可能是一种安全的主要治疗方案，IDH-野生型多形性胶质母细胞瘤（GBM）和IDH-突变型星形细胞瘤的肿瘤消融率分别为94.8%和84.6%。对于IDH-野生型GBM，汇总的PFS和OS分别为5.0个月和9.0个月。与之前文献报道的发生率相似，IDH-野生型GBM的神经系统和非神经系统并发症发生率分别为10.3%和4.8%。IDH突变型星形细胞瘤队列中的神经系统和非神经系统并发症发生率略高，分别为33%和8.3%，这可能是由于队列规模较小所致。
{"title":"Safety and Efficacy of Laser Interstitial Thermal Therapy as Upfront Therapy in Primary Glioblastoma and IDH-Mutant Astrocytoma: A Meta-Analysis","authors":"Aryan Pandey, Anubha Chandla, Mahlet Mekonnen, Gabrielle Hovis, Zoe E. Teton, Kunal S. Patel, Richard G. Everson, Madhuri Wadehra, Isaac Yang","doi":"10.3390/cancers16112131","DOIUrl":"https://doi.org/10.3390/cancers16112131","url":null,"abstract":"Although primary studies have reported the safety and efficacy of LITT as a primary treatment in glioma, they are limited by sample sizes and institutional variation in stereotactic parameters such as temperature and laser power. The current literature has yet to provide pooled statistics on outcomes solely for primary brain tumors according to the 2021 WHO Classification of Tumors of the Central Nervous System (WHO CNS5). In the present study, we identify recent articles on primary CNS neoplasms treated with LITT without prior intervention, focusing on relationships with molecular profile, PFS, and OS. This meta-analysis includes the extraction of data from primary sources across four databases using the Covidence systematic review manager. The pooled data suggest LITT may be a safe primary management option with tumor ablation rates of 94.8% and 84.6% in IDH-wildtype glioblastoma multiforme (GBM) and IDH-mutant astrocytoma, respectively. For IDH-wildtype GBM, the pooled PFS and OS were 5.0 and 9.0 months, respectively. Similar to rates reported in the prior literature, the neurologic and non-neurologic complication rates for IDH-wildtype GBM were 10.3% and 4.8%, respectively. The neurologic and non-neurologic complication rates were somewhat higher in the IDH-mutant astrocytoma cohort at 33% and 8.3%, likely due to a smaller cohort size.","PeriodicalId":504676,"journal":{"name":"Cancers","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141272541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The presence of spread through air spaces (STASs) in early-stage lung adenocarcinoma is a significant prognostic factor associated with disease recurrence and poor outcomes. Although current STAS detection methods rely on pathological examinations, the advent of artificial intelligence (AI) offers opportunities for automated histopathological image analysis. This study developed a deep learning (DL) model for STAS prediction and investigated the correlation between the prediction results and patient outcomes. To develop the DL-based STAS prediction model, 1053 digital pathology whole-slide images (WSIs) from the competition dataset were enrolled in the training set, and 227 WSIs from the National Taiwan University Hospital were enrolled for external validation. A YOLOv5-based framework comprising preprocessing, candidate detection, false-positive reduction, and patient-based prediction was proposed for STAS prediction. The model achieved an area under the curve (AUC) of 0.83 in predicting STAS presence, with 72% accuracy, 81% sensitivity, and 63% specificity. Additionally, the DL model demonstrated a prognostic value in disease-free survival compared to that of pathological evaluation. These findings suggest that DL-based STAS prediction could serve as an adjunctive screening tool and facilitate clinical decision-making in patients with early-stage lung adenocarcinoma.
{"title":"Deep Learning Analysis for Predicting Tumor Spread through Air Space in Early-Stage Lung Adenocarcinoma Pathology Images","authors":"De-Xiang Ou, Chao-Wen Lu, Li-Wei Chen, Wen-Yao Lee, Hsiang-Wei Hu, Jen-Hao Chuang, Mong-Wei Lin, Kuan-Yu Chen, Ling-Ying Chiu, Jin-Shing Chen, Chung-Ming Chen, Min-Shu Hsieh","doi":"10.3390/cancers16112132","DOIUrl":"https://doi.org/10.3390/cancers16112132","url":null,"abstract":"The presence of spread through air spaces (STASs) in early-stage lung adenocarcinoma is a significant prognostic factor associated with disease recurrence and poor outcomes. Although current STAS detection methods rely on pathological examinations, the advent of artificial intelligence (AI) offers opportunities for automated histopathological image analysis. This study developed a deep learning (DL) model for STAS prediction and investigated the correlation between the prediction results and patient outcomes. To develop the DL-based STAS prediction model, 1053 digital pathology whole-slide images (WSIs) from the competition dataset were enrolled in the training set, and 227 WSIs from the National Taiwan University Hospital were enrolled for external validation. A YOLOv5-based framework comprising preprocessing, candidate detection, false-positive reduction, and patient-based prediction was proposed for STAS prediction. The model achieved an area under the curve (AUC) of 0.83 in predicting STAS presence, with 72% accuracy, 81% sensitivity, and 63% specificity. Additionally, the DL model demonstrated a prognostic value in disease-free survival compared to that of pathological evaluation. These findings suggest that DL-based STAS prediction could serve as an adjunctive screening tool and facilitate clinical decision-making in patients with early-stage lung adenocarcinoma.","PeriodicalId":504676,"journal":{"name":"Cancers","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141268791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tumors that spontaneously shrink from unknown causes in tumor regression, and that return to normal cells in tumor reversion, are phenomena with the potential to contribute new knowledge and novel therapies for cancer patient survival. Tumorigenesis is associated with dysregulated phosphate metabolism and an increased transport of phosphate into tumor cells, potentially mediated by phosphate overload from excessive dietary phosphate intake, a significant problem in Western societies. This paper proposes that reduced dietary phosphate overload and reregulated phosphate metabolism may reverse an imbalance of kinases and phosphatases in cell signaling and cellular proliferation, thereby activating autophagy in tumor regression and reversion. Dietary phosphate can also be reduced by sickness-associated anorexia, fasting-mimicking diets, and other diets low in phosphate, all of which have been associated with tumor regression. Tumor reversion has also been demonstrated by transplanting cancer cells into a healthy microenvironment, plausibly associated with normal cellular phosphate concentrations. Evidence also suggests that the sequestration and containment of excessive phosphate within encapsulated tumors is protective in cancer patients, preventing the release of potentially lethal amounts of phosphate into the general circulation. Reducing dietary phosphate overload has the potential to provide a novel, safe, and effective reversion therapy for cancer patients, and further research is warranted.
{"title":"Spontaneous Tumor Regression and Reversion: Insights and Associations with Reduced Dietary Phosphate","authors":"Ronald B. Brown","doi":"10.3390/cancers16112126","DOIUrl":"https://doi.org/10.3390/cancers16112126","url":null,"abstract":"Tumors that spontaneously shrink from unknown causes in tumor regression, and that return to normal cells in tumor reversion, are phenomena with the potential to contribute new knowledge and novel therapies for cancer patient survival. Tumorigenesis is associated with dysregulated phosphate metabolism and an increased transport of phosphate into tumor cells, potentially mediated by phosphate overload from excessive dietary phosphate intake, a significant problem in Western societies. This paper proposes that reduced dietary phosphate overload and reregulated phosphate metabolism may reverse an imbalance of kinases and phosphatases in cell signaling and cellular proliferation, thereby activating autophagy in tumor regression and reversion. Dietary phosphate can also be reduced by sickness-associated anorexia, fasting-mimicking diets, and other diets low in phosphate, all of which have been associated with tumor regression. Tumor reversion has also been demonstrated by transplanting cancer cells into a healthy microenvironment, plausibly associated with normal cellular phosphate concentrations. Evidence also suggests that the sequestration and containment of excessive phosphate within encapsulated tumors is protective in cancer patients, preventing the release of potentially lethal amounts of phosphate into the general circulation. Reducing dietary phosphate overload has the potential to provide a novel, safe, and effective reversion therapy for cancer patients, and further research is warranted.","PeriodicalId":504676,"journal":{"name":"Cancers","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141272193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
French Guiana is a French Overseas territory with singular features: it has a high prevalence of HIV and HTLV-1, its population is ethnically mixed, with widespread poverty, and up to 20% of the population lives in geographic isolation. In this context, we used registry data to estimate incidence and mortality due to hematological malignancies and to compare them with France and tropical Latin America. ICD codes C90 and C88 were compiled between 2005 and 2014. The direct standardization of age structure was performed using the world population. Survival analysis was performed, and Kaplan–Meier curves were drawn. The overall standardized incidence rate was 32.9 per 100,000 male years and 24.5 per 100,000 female years. Between 2005 and 2009, the standardized incidence rate was 29.6 per 100,000 among men and 23.6 per 100,000 among women, and between 2010 and 2014, it was 35.6 per 100,000 among men and 25.2 per 100,000 among women. Multiple myeloma/plasmocytoma and mature t/NK cell lymphomas, notably adult t-cell lymphoma/leukemia due to HTLV-1 infection, were the two most common hematologic malignancies and causes of death. Non-Hodgkin’s lymphoma incidence estimates were greater than global estimates. After adjusting for age, sex, and type of malignancy, people born in a foreign country independently had a poorer case-fatality rate, presumably reflecting difficulties in accessing care. The epidemiology of hematological malignancies in French Guiana has features that distinguish it from mainland France or from Latin America. The incidence of multiple myeloma and adult t-cell lymphoma/leukemia was significantly greater in French Guiana than in France or other Latin American countries.
{"title":"The Epidemiological Particularities of Malignant Hemopathies in French Guiana: 2005–2014","authors":"Mathieu Nacher, Qiannan Wang, Béatrice Cenciu, Alolia Aboikoni, Florin Santa, Fabrice Quet, Fanja Vergeade, A. Adenis, Nathalie Deschamps, Kinan Drak Alsibai","doi":"10.3390/cancers16112128","DOIUrl":"https://doi.org/10.3390/cancers16112128","url":null,"abstract":"French Guiana is a French Overseas territory with singular features: it has a high prevalence of HIV and HTLV-1, its population is ethnically mixed, with widespread poverty, and up to 20% of the population lives in geographic isolation. In this context, we used registry data to estimate incidence and mortality due to hematological malignancies and to compare them with France and tropical Latin America. ICD codes C90 and C88 were compiled between 2005 and 2014. The direct standardization of age structure was performed using the world population. Survival analysis was performed, and Kaplan–Meier curves were drawn. The overall standardized incidence rate was 32.9 per 100,000 male years and 24.5 per 100,000 female years. Between 2005 and 2009, the standardized incidence rate was 29.6 per 100,000 among men and 23.6 per 100,000 among women, and between 2010 and 2014, it was 35.6 per 100,000 among men and 25.2 per 100,000 among women. Multiple myeloma/plasmocytoma and mature t/NK cell lymphomas, notably adult t-cell lymphoma/leukemia due to HTLV-1 infection, were the two most common hematologic malignancies and causes of death. Non-Hodgkin’s lymphoma incidence estimates were greater than global estimates. After adjusting for age, sex, and type of malignancy, people born in a foreign country independently had a poorer case-fatality rate, presumably reflecting difficulties in accessing care. The epidemiology of hematological malignancies in French Guiana has features that distinguish it from mainland France or from Latin America. The incidence of multiple myeloma and adult t-cell lymphoma/leukemia was significantly greater in French Guiana than in France or other Latin American countries.","PeriodicalId":504676,"journal":{"name":"Cancers","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141271143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Magdalena Fryze, Patrycja Wisniewska, Jadwiga Wiertlewska-Bielarz, M. Moskalewicz
Understanding the impact of cancer on the experience of time is crucial in the context of hope and recovery. This study, a follow-up to a previous qualitative study of ovarian cancer patients – explored two types of such experiences—the memory of past happiness and the limited future planning. A sociodemographic questionnaire with nine questions about the experience of time was used on a convenience sample of 202 patients with various cancers, predominantly women with breast, ovarian, and cervical cancer. It was found that the respondents experienced increased focus on the present, decreased focus on the future, and a sense of unpredictability, with a relatively short temporal horizon measured in weeks and months, not years. Almost half of the respondents (46%) measured time during treatment by the rhythm of chemotherapy and check-ups, which thus appeared as the most meaningful events. The increase in the frequency with which patients underwent chemotherapy mildly affected their focus on the present (R = 0.25, p < 0.05), likely because of the discomfort of the side effects. The correlations between age and time in treatment, on the one hand, and the experience of time, on the other, were negligible. Changed temporal experience during chemotherapy is a factor that can have an impact on patients’ well-being and ability to cope with the disease. It thus should be taken into account when planning oncology care.
{"title":"Past Happiness and Broken Future Horizon of Oncological Patients during Chemotherapy—A Quantitative Exploration of a Phenomenological Hypothesis","authors":"Magdalena Fryze, Patrycja Wisniewska, Jadwiga Wiertlewska-Bielarz, M. Moskalewicz","doi":"10.3390/cancers16112124","DOIUrl":"https://doi.org/10.3390/cancers16112124","url":null,"abstract":"Understanding the impact of cancer on the experience of time is crucial in the context of hope and recovery. This study, a follow-up to a previous qualitative study of ovarian cancer patients – explored two types of such experiences—the memory of past happiness and the limited future planning. A sociodemographic questionnaire with nine questions about the experience of time was used on a convenience sample of 202 patients with various cancers, predominantly women with breast, ovarian, and cervical cancer. It was found that the respondents experienced increased focus on the present, decreased focus on the future, and a sense of unpredictability, with a relatively short temporal horizon measured in weeks and months, not years. Almost half of the respondents (46%) measured time during treatment by the rhythm of chemotherapy and check-ups, which thus appeared as the most meaningful events. The increase in the frequency with which patients underwent chemotherapy mildly affected their focus on the present (R = 0.25, p < 0.05), likely because of the discomfort of the side effects. The correlations between age and time in treatment, on the one hand, and the experience of time, on the other, were negligible. Changed temporal experience during chemotherapy is a factor that can have an impact on patients’ well-being and ability to cope with the disease. It thus should be taken into account when planning oncology care.","PeriodicalId":504676,"journal":{"name":"Cancers","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141273452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","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：