TCGA-TCIA Impact on Radiogenomics Cancer Research: A Systematic Review

Diagnosing Progression in Glioblastoma-Tackling a Neuro-Oncology Problem Using Artificial-Intelligence-Derived Volumetric Change over Time on Magnetic Resonance Imaging to Examine Progression-Free Survival in Glioblastoma

Glioblastoma (GBM) is the most aggressive and the most common primary brain tumor, defined by nearly uniform rapid progression despite the current standard of care involving maximal surgical resection followed by radiation therapy (RT) and temozolomide (TMZ) or concurrent chemoirradiation (CRT), with an overall survival (OS) of less than 30% at 2 years. The diagnosis of tumor progression in the clinic is based on clinical assessment and the interpretation of MRI of the brain using Response Assessment in Neuro-Oncology (RANO) criteria, which suffers from several limitations including a paucity of precise measures of progression. Given that imaging is the primary modality that generates the most quantitative data capable of capturing change over time in the standard of care for GBM, this renders it pivotal in optimizing and advancing response criteria, particularly given the lack of biomarkers in this space. In this study, we employed artificial intelligence (AI)-derived MRI volumetric parameters using the segmentation mask output of the nnU-Net to arrive at four classes (background, edema, non-contrast enhancing tumor (NET), and contrast-enhancing tumor (CET)) to determine if dynamic changes in AI volumes detected throughout therapy can be linked to PFS and clinical features. We identified associations between MR imaging AI-generated volumes and PFS independently of tumor location, MGMT methylation status, and the extent of resection while validating that CET and edema are the most linked to PFS with patient subpopulations separated by district rates of change throughout the disease. The current study provides valuable insights for risk stratification, future RT treatment planning, and treatment monitoring in neuro-oncology.

Identification of vitamin D-related signature for predicting the clinical outcome and immunotherapy response in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is one of the most common cancers globally, seriously endangering people health. Vitamin D was significantly associated with tumor progression and patients' prognosis. Integrative 10 machine learning algorithms were used to develop a Vitamin D-related signature (VRS) with one training cohort and 3 testing cohorts. The performance of VRS in predicting the immunology response was verified using several predicting approaches. The optimal VRS was constructed by stepCox + superPC algorithm. VRS acted as a risk factor for HCC patients. HCC patients with high-risk score had a poor clinical outcome and the AUCs of 1-, 3-, and 5-year ROC were 0.786, 0.755, and 0.786, respectively. A higher level of CD8 + cytotoxic T cells and B cells was obtained in HCC patients with low-risk score. There is higher PD1&CTLA4 immunophenoscore and TMB score in low-risk score in HCC patients. Lower TIDE score and tumor escape score was found in HCC cases with low-risk score. The IC50 value of camptothecin, docetaxel, crizotinib, dasatinib, and erlotinib was lower in HCC cases with high-risk score. HCC patients with high-risk score had a higher score of cancer-related hallmarks, including angiogenesis, glycolysis, and NOTCH signaling. Our study proposed a novel VRS for HCC, which served as an indicator for predicting clinical outcome and immunotherapy responses in HCC.

Knockdown of ADAM8 inhibits the proliferation, migration, invasion, and tumorigenesis of renal clear cell carcinoma cells to enhance the immunotherapy efficacy

The current study performed bioinformatics and in vitro and in vivo experiments to explore the effects of ADAM8 on the malignant behaviors and immunotherapeutic efficacy of renal clear cell carcinoma (ccRCC) Cells. The modular genes most associated with immune cells were screened. Then, prognostic risk models were constructed by univariate COX analysis, LASSO regression analysis and multivariate COX analysis, and their diagnostic value was determined. The correlation between tumor mutation load (TMB) scores and the prognosis of ccRCC patients was clarified. Finally, six key genes (ABI3, ADAM8, APOL3, MX2, CCDC69, and STAC3) were analyzed for immunotherapy efficacy. Human and mouse ccRCC cell lines and human proximal tubular epithelial cell lines were used for in vitro cell experiments. The effect of ADAM8 overexpression or knockdown on tumor formation and survival in ccRCC cells was examined by constructing subcutaneous transplanted tumor model. Totally, 636 Black module genes were screened as being most associated with immune cell infiltration. Six genes were subsequently confirmed for the construction of prognostic risk models, of which ABI3, APOL3 and CCDC69 were low-risk factors, while ADAM8, MX2 and STAC3 were high-risk factors. The constructed risk model based on the identified six genes could accurately predict the prognosis of ccRCC patients. Besides, TMB was significantly associated with the prognosis of ccRCC patients. Furthermore, ABI3, ADAM8, APOL3, MX2, CCDC69 and STAC3 might play important roles in treatment concerning CTLA4 inhibitors or PD-1 inhibitors or combined inhibitors. Finally, we confirmed that ADAM8 could promote the proliferation, migration and invasion of ccRCC cells through in vitro experiments, and further found that in in vivo experiments, ADAM8 knockdown could inhibit tumor formation in ccRCC cells, improve the therapeutic effect of anti-PD1, and prolong the survival of mice. Our study highlighted the alleviative role of silencing ADAM8 in ccRCC patients.

Standardizing digital biobanks: integrating imaging, genomic, and clinical data for precision medicine

Advancements in data acquisition and computational methods are generating a large amount of heterogeneous biomedical data from diagnostic domains such as clinical imaging, pathology, and next-generation sequencing (NGS), which help characterize individual differences in patients. However, this information needs to be available and suitable to promote and support scientific research and technological development, supporting the effective adoption of the precision medicine approach in clinical practice. Digital biobanks can catalyze this process, facilitating the sharing of curated and standardized imaging data, clinical, pathological and molecular data, crucial to enable the development of a comprehensive and personalized data-driven diagnostic approach in disease management and fostering the development of computational predictive models. This work aims to frame this perspective, first by evaluating the state of standardization of individual diagnostic domains and then by identifying challenges and proposing a possible solution towards an integrative approach that can guarantee the suitability of information that can be shared through a digital biobank. Our analysis of the state of the art shows the presence and use of reference standards in biobanks and, generally, digital repositories for each specific domain. Despite this, standardization to guarantee the integration and reproducibility of the numerical descriptors generated by each domain, e.g. radiomic, pathomic and -omic features, is still an open challenge. Based on specific use cases and scenarios, an integration model, based on the JSON format, is proposed that can help address this problem. Ultimately, this work shows how, with specific standardization and promotion efforts, the digital biobank model can become an enabling technology for the comprehensive study of diseases and the effective development of data-driven technologies at the service of precision medicine.

Magnetic resonance imaging-based radiomics was used to evaluate the level of prognosis-related immune cell infiltration in breast cancer tumor microenvironment

PURPOSE

The tumor immune microenvironment is a valuable source of information for predicting prognosis in breast cancer (BRCA) patients. To identify immune cells associated with BRCA patient prognosis from the Cancer Genetic Atlas (TCGA), we established an MRI-based radiomics model for evaluating the degree of immune cell infiltration in breast cancer patients.

METHODS

CIBERSORT was utilized to evaluate the degree of infiltration of 22 immune cell types in breast cancer patients from the TCGA database, and both univariate and multivariate Cox regressions were employed to determine the prognostic significance of immune cell infiltration levels in BRCA patients. We identified independent prognostic factors for BRCA patients. Additionally, we obtained imaging features from the Cancer Imaging Archive (TCIA) database for 73 patients who underwent preoperative MRI procedures, and used the Least Absolute Shrinkage and Selection Operator (LASSO) to select the best imaging features for constructing an MRI-based radiomics model for evaluating immune cell infiltration levels in breast cancer patients.

RESULTS

According to the results of Cox regression analysis, M2 macrophages were identified as an independent prognostic factor for BRCA patients (HR = 32.288, 95% CI: 3.100-357.478). A total of nine significant features were selected to calculate the radiomics-based score. We established an intratumoral model with AUCs (95% CI) of 0.662 (0.495-0.802) and 0.678 (0.438-0.901) in the training and testing cohorts, respectively. Additionally, a peritumoral model was created with AUCs (95% CI) of 0.826 (0.710-0.924) and 0.752 (0.525-0.957), and a combined model was established with AUCs (95% CI) of 0.843 (0.723-0.938) and 0.744 (0.491-0.965). The peritumoral model demonstrated the highest diagnostic efficacy, with an accuracy, sensitivity, and specificity of 0.773, 0.727, and 0.818, respectively, in its testing cohort.

CONCLUSION

The MRI-based radiomics model has the potential to evaluate the degree of immune cell infiltration in breast cancer patients, offering a non-invasive imaging biomarker for assessing the tumor microenvironment in this disease.

A clinically relevant computed tomography (CT) radiomics strategy for intracranial rodent brain tumour monitoring

Here, we establish a CT-radiomics based method for application in invasive, orthotopic rodent brain tumour models. Twenty four NOD/SCID mice were implanted with U87R-Luc2 GBM cells and longitudinally imaged via contrast enhanced (CE-CT) imaging. Pyradiomics was employed to extract CT-radiomic features from the tumour-implanted hemisphere and non-tumour-implanted hemisphere of acquired CT-scans. Inter-correlated features were removed (Spearman correlation > 0.85) and remaining features underwent predictive analysis (recursive feature elimination or Boruta algorithm). An area under the curve of the receiver operating characteristic curve was implemented to evaluate radiomic features for their capacity to predict defined outcomes. Firstly, we identified a subset of radiomic features which distinguish the tumour-implanted hemisphere and non- tumour-implanted hemisphere (i.e, tumour presence from normal tissue). Secondly, we successfully translate preclinical CT-radiomic pipelines to GBM patient CT scans (n = 10), identifying similar trends in tumour-specific feature intensities (E.g. 'glszm Zone Entropy'), thereby suggesting a mouse-to-human species conservation (a conservation of radiomic features across species). Thirdly, comparison of features across timepoints identify features which support preclinical tumour detection earlier than is possible by visual assessment of CT scans. This work establishes robust, preclinical CT-radiomic pipelines and describes the application of CE-CT for in-depth orthotopic brain tumour monitoring. Overall we provide evidence for the role of pre-clinical 'discovery' radiomics in the neuro-oncology space.

The Digital World of Cytogenetic and Cytogenomic Web Resources

The dynamic growth of technological capabilities at the cellular and molecular level has led to a rapid increase in the amount of data on the genes and genomes of organisms. In order to store, access, compare, validate, classify, and understand the massive data generated by different researchers, and to promote effective communication among research communities, various genome and cytogenetic online databases have been established. These data platforms/resources are essential not only for computational analyses and theoretical syntheses but also for helping researchers select future research topics and prioritize molecular targets. Furthermore, they are valuable for identifying shared recurrent genomic patterns related to human diseases and for avoiding unnecessary duplications among different researchers. The website interface, menu, graphics, animations, text layout, and data from databases are displayed by a front end on the screen of a monitor or smartphone. A database front-end refers to the user interface or application that enables accessing tabular, structured, or raw data stored in the database. The Internet makes it possible to reach a greater number of users around the world and gives them quick access to information stored in databases. The number of ways of presenting this data by front-ends increases as well. This requires unifying the ways of operating and presenting information by front-ends and ensuring contextual switching between front-ends of different databases. This chapter aims to present selected cytogenetic and cytogenomic Internet resources in terms of obtaining the needed information and to indicate how to increase the efficiency of access to stored information. Through a brief introduction of these databases and by providing examples of their usage in cytogenetic analyses, we aim to bridge the gap between cytogenetics and molecular genomics by encouraging their utilization.

From cancer big data to treatment: Artificial intelligence in cancer research

In recent years, developing the idea of "cancer big data" has emerged as a result of the significant expansion of various fields such as clinical research, genomics, proteomics and public health records. Advances in omics technologies are making a significant contribution to cancer big data in biomedicine and disease diagnosis. The increasingly availability of extensive cancer big data has set the stage for the development of multimodal artificial intelligence (AI) frameworks. These frameworks aim to analyze high-dimensional multi-omics data, extracting meaningful information that is challenging to obtain manually. Although interpretability and data quality remain critical challenges, these methods hold great promise for advancing our understanding of cancer biology and improving patient care and clinical outcomes. Here, we provide an overview of cancer big data and explore the applications of both traditional machine learning and deep learning approaches in cancer genomic and proteomic studies. We briefly discuss the challenges and potential of AI techniques in the integrated analysis of omics data, as well as the future direction of personalized treatment options in cancer.

Bioinformatics identification of a T-cell-related signature for predicting prognosis and drug sensitivity in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is a fatal disease with poor clinical outcomes. T cells play a vital role in the crosstalk between the tumour microenvironment and HCC. Single-cell RNA sequencing data were downloaded from the GSE149614 dataset. The T-cell-related prognostic signature (TRPS) was developed with the integrative procedure including 10 machine learning algorithms. The TRPS was established using 7 T-cell-related markers in the Cancer Genome Atlas cohort with 1-, 2- and 3-year area under curve values of 0.820, 0.725 and 0.678, respectively. TRPS acted as an independent risk factor for HCC patients. HCC patients with a high TRPS-based risk score had a higher Tumour Immune Dysfunction and Exclusion score, lower PD1 and CTLA4 immunophenoscore and lower level of immunoactivated cells, including CD8+ T cells and NK cells. The response rate was significantly higher in patients with low-risk scores in immunotherapy cohorts, including IMigor210 and GSE91061. The TRPS-based nomogram had a relatively good predictive value in evaluating the mortality risk at 1, 3 and 5 years in HCC. Overall, this study develops a TRPS by integrated bioinformatics analysis. This TRPS acted as an independent risk factor for the OS rate of HCC patients. It can screen for HCC patients who might benefit from immunotherapy, chemotherapy and targeted therapy.

Implications of different cell death patterns for prognosis and immunity in lung adenocarcinoma

In recent years, lung adenocarcinoma (LUAD) has become a focus of attention due to its low response to treatment, poor prognosis, and lack of reliable indicators to predict the progression or therapeutic effect of LUAD. Different cell death patterns play a crucial role in tumor development and are promising for predicting LUAD prognosis. From the TCGA and GEO databases, we obtained bulk transcriptomes, single-cell transcriptomes, and clinical information. Genes in 15 types of cell death were analyzed for cell death index (CDI) signature establishment. The CDI signature using necroptosis + immunologic cell death-related genes was established in the TCGA cohort with the 1-, 2-, 3-, 4- and 5-year AUC values were 0.772, 0.736, 0.723, 0.795, and 0.743, respectively. The prognosis was significantly better in the low CDI group than in the high CDI group. We also investigated the relationship between the CDI signature and clinical variables, published prognosis biomarkers, immune cell infiltration, functional enrichment pathways, and immunity biomarkers. In vitro assay showed that HNRNPF and FGF2 promoted lung cancer cell proliferation and migration and were also involved in cell death. Therefore, as a robust prognosis biomarker, CDI signatures can screen for patients who might benefit from immunotherapy and improve diagnostic accuracy and LUAD patient outcomes.

Machine Learning-Based Integration Develops a Macrophage-Related Index for Predicting Prognosis and Immunotherapy Response in Lung Adenocarcinoma

BACKGROUND

Macrophages play a critical role in tumor immune microenvironment (TIME) formation and cancer progression in lung adenocarcinoma (LUAD). However, few studies have comprehensively and systematically described the characteristics of macrophages in LUAD.

METHODS

This study identified macrophage-related markers with single-cell RNA sequencing data from the GSE189487 dataset. An integrative machine learning-based procedure based on 10 algorithms was developed to construct a macrophage-related index (MRI) in The Cancer Genome Atlas (TCGA), GSE30219, GSE31210, and GSE72094 datasets. Several algorithms were used to evaluate the associations of MRI with TIME and immunotherapy-related biomarkers. The role of MRI in predicting the immunotherapy response was evaluated with the GSE91061 dataset.

RESULTS

The optimal MRI constructed by the combination of the Lasso algorithm and plsRCox was an independent risk factor in LUAD and showed a stable and powerful performance in predicting the overall survival rate of patients with LUAD. Those with low MRI scores had a higher TIME score, a higher level of immune cells, a higher immunophenoscore, and a lower Tumor Immune Dysfunction and Exclusion (TIDE) score, indicating a better response to immunotherapy. The IC50 value of common drugs for chemotherapy and target therapy with low MRI scores was higher compared to high MRI scores. Moreover, the survival prediction nomogram, developed from MRI, had good potential for clinical application in predicting the 1-, 3-, and 5-year overall survival rate of LUAD.

CONCLUSION

Our study constructed for the first time a consensus MRI for LUAD with 10 machine learning algorithms. The MRI could be helpful for risk stratification, prognosis, and selection of treatment approach in LUAD.

Identification of M2-like macrophage-related signature for predicting the prognosis, ecosystem and immunotherapy response in hepatocellular carcinoma

BACKGROUND

Hepatocellular carcinoma is one of the most common malignancies worldwide, representing a big health-care challenge globally. M2-like macrophages are significantly correlated with tumor progression, metastasis and treatment resistance.

METHODS

Integrative 10 machine learning algorithms were performed to developed a M2-like macrophage related prognostic signature (MRPS). Single-cell RNA-sequencing analysis was performed to dissect the ecosystem of HCC. Several approaches, including TIDE score, immunophenoscore, TMB score and tumor escape score were used to evaluate the predictive role of MRPS in immunology response.

RESULTS

The optimal MRPS constructed by the combination of stepCox + superPC algorithm served as an independent risk factor and showed stable and powerful performances in predicting the overall survival rate of HCC patients with 2-, 3-, and 4-year AUCs of 0. 763, 0.751, and 0.699 in TCGA cohort. HCC patients with low risk score possessed a more interaction of immunoactivated cells, including NK, CD8+ cytotoxic T, and activated B, and a less interaction of immunosuppressive cells, including Treg, CD4+ exhauster T, and M2-like macrophage. Low risk score indicated a higher PD1&CTLA4 immunophenoscore, higher TMB score, lower TIDE score and lower tumor escape score in HCC, suggesting a better immunotherapy response. The IC50 value of docetaxel, gemcitabine, crizotinib and Osimertinib in HCC with high risk score were lower versus that with low risk score. HCC patients with high risk score had a higher score of cancer-related hallmarks, including angiogenesis, DNA repair, EMT, glycolysis, and NOTCH signaling.

CONCLUSION

Our study proposed a novel MRPS for predicting the prognosis, ecosystem and immunotherapy response in HCC.

Analyzing molecular typing and clinical application of immunogenic cell death-related genes in hepatocellular carcinoma

BACKGROUND

Hepatocellular carcinoma (HCC) is considered one of the most common cancers, characterized by low early detection and high mortality rates, and is a global health challenge. Immunogenic cell death (ICD) is defined as a specific type of regulated cell death (RCD) capable of reshaping the tumor immune microenvironment by releasing danger signals that trigger immune responses, which would contribute to immunotherapy.

METHODS

The ICD gene sets were collected from the literature. We collected expression data and clinical information from public databases for the HCC samples in our study. Data processing and mapping were performed using R software to analyze the differences in biological characteristics between different subgroups. The expression of the ICD representative gene in clinical specimens was assessed by immunohistochemistry, and the role of the representative gene in HCC was evaluated by various in vitro assays, including qRT-PCR, colony formation, and CCK8 assay. Lasso-Cox regression was used to screen prognosis-related genes, and an ICD-related risk model (ICDRM) was constructed. To improve the clinical value of ICDRM, Nomograms and calibration curves were created to predict survival probabilities. Finally, the critical gene of ICDRM was further investigated through pan-cancer analysis and single-cell analysis.

RESULTS

We identified two ICD clusters that differed significantly in terms of survival, biological function, and immune infiltration. As well as assessing the immune microenvironment of tumors in HCC patients, we demonstrate that ICDRM can differentiate ICD clusters and predict the prognosis and effectiveness of therapy. High-risk subpopulations are characterized by high TMB, suppressed immunity, and poor survival and response to immunotherapy, whereas the opposite is true for low-risk subpopulations.

CONCLUSIONS

This study reveals the potential impact of ICDRM on the tumor microenvironment (TME), immune infiltration, and prognosis of HCC patients, but also a potential tool for predicting prognosis.

Radiogenomics in Renal Cancer Management-Current Evidence and Future Prospects

Renal cancer management is challenging from diagnosis to treatment and follow-up. In cases of small renal masses and cystic lesions the differential diagnosis of benign or malignant tissues has potential pitfalls when imaging or even renal biopsy is applied. The recent artificial intelligence, imaging techniques, and genomics advancements have the ability to help clinicians set the stratification risk, treatment selection, follow-up strategy, and prognosis of the disease. The combination of radiomics features and genomics data has achieved good results but is currently limited by the retrospective design and the small number of patients included in clinical trials. The road ahead for radiogenomics is open to new, well-designed prospective studies, with large cohorts of patients required to validate previously obtained results and enter clinical practice.

Six Genes Associated with Lymphatic Metastasis in Colon Adenocarcinoma Linked to Prognostic Value and Tumor Immune Cell Infiltration

Objective. The aim of the study is to explore the relationship between lymphatic metastasis genes, prognosis, and immune cell infiltration in patients with colon cancer. Methods. Based on the Cancer Genome Atlas Program (TCGA) database, differentially expressed genes and prognostic genes related to colon adenocarcinoma (COAD) lymphatic metastasis were screened and intersected. We used lasso and univariate Cox regression analysis to screen core genes and establish a preliminary prediction model. GO and KEGG enrichment analysis was used for lymphatic metastasis-related genes, and single GSEA was used for the final screening results. Finally, we evaluated the relationship between identified genes and immune cell infiltration. Results. A total of 1727 genes were differentially expressed between COAD patients with TNM stages of N0 and N1. After further screening, six core genes (RNU4-2, ZNF556, RNVU1-15, NSA2P6, RN7SL767P, and RN7SL473P) were obtained, and a preliminary prediction model was established, in which ZNF556 was a risk factor, and the rest were protective factors. Single GSEA showed that pathways such as systemic lupus erythematosus might play an important role in the initial lymphatic metastasis of COAD. GO and KEGG enrichment analysis of 1727 genes supported this result. Immune infiltration analysis showed that six genes were significantly correlated with T cell and NK cell families. Conclusion. Six core genes may affect COAD initial lymphatic metastasis through the systemic lupus erythematosus pathway and immune cell infiltration.

The potential value of cuprotosis (copper-induced cell death) in the therapy of clear cell renal cell carcinoma

Clear cell renal cell carcinoma (ccRCC) accounts for 75% of the total incidence of renal cancer, and every year the number of morbidity and mortality increases, posing a serious threat to public health. The current main treatment methods for kidney cancer include drug-targeted therapy and immunotherapy. Although there are many treatment options for kidney cancer, they all have limitations, including drug resistance, unsatisfied long-term benefits, and adverse effects. Therefore, it is crucial to identify more effective therapeutic targets. As a newly discovered mechanism of cell death, copper-induced cell death (cuprotosis) is closely related to changes in cell metabolism, particularly in copper metabolism. Current studies have shown that the key signaling pathway of cuprotosis, the FDX1 (Ferredoxin 1)-LIAS (Lipoic Acid Synthetase) axis, plays an important role in the regulation of cellular oxidative stress, which can directly affect cell survival via inducing or promoting cancer cell death. Therefore, we speculated that this regulatory cell death mechanism might serve as a potential therapeutic target for the clinical treatment of renal cancer. To test this, we first performed a pan-cancer analysis based on cuprotosis-related genomic and transcriptomic levels to reveal the expression of cuprotosis in cancer. Next, GSVA-clustering analysis was performed with data from the Cancer Genome Atlas (TCGA) cohort, and the cohort was divided into three clusters according to the gene enrichment levels of cuprotosis marker genes. In addition, we analyzed the potential of using cuprotosis in clinical treatment from multiple perspectives, including chemotherapeutic drug susceptibility test, immune target inhibition treatment responsiveness, and histone modification. Combining the results of multi-omics analysis, we focused on the feasibility of this novel regulatory cell death mechanism in ccRCC treatment and further constructed a prognostic model. Finally, we verified our results by integrating the patient's gene expression information and radiomics information. Our study provides new insights into the development and clinical application of targeting cuprotosis pathway.

Machine learning-assisted prediction of pneumonia based on non-invasive measures

Background

Pneumonia is an infection of the lungs that is characterized by high morbidity and mortality. The use of machine learning systems to detect respiratory diseases via non-invasive measures such as physical and laboratory parameters is gaining momentum and has been proposed to decrease diagnostic uncertainty associated with bacterial pneumonia. Herein, this study conducted several experiments using eight machine learning models to predict pneumonia based on biomarkers, laboratory parameters, and physical features.

Methods

We perform machine-learning analysis on 535 different patients, each with 45 features. Data normalization to rescale all real-valued features was performed. Since it is a binary problem, we categorized each patient into one class at a time. We designed three experiments to evaluate the models: (1) feature selection techniques to select appropriate features for the models, (2) experiments on the imbalanced original dataset, and (3) experiments on the SMOTE data. We then compared eight machine learning models to evaluate their effectiveness in predicting pneumonia

Results

Biomarkers such as C-reactive protein and procalcitonin demonstrated the most significant discriminating power. Ensemble machine learning models such as RF (accuracy = 92.0%, precision = 91.3%, recall = 96.0%, f1-Score = 93.6%) and XGBoost (accuracy = 90.8%, precision = 92.6%, recall = 92.3%, f1-score = 92.4%) achieved the highest performance accuracy on the original dataset with AUCs of 0.96 and 0.97, respectively. On the SMOTE dataset, RF and XGBoost achieved the highest prediction results with f1-scores of 92.0 and 91.2%, respectively. Also, AUC of 0.97 was achieved for both RF and XGBoost models.

Conclusions

Our models showed that in the diagnosis of pneumonia, individual clinical history, laboratory indicators, and symptoms do not have adequate discriminatory power. We can also conclude that the ensemble ML models performed better in this study.

What Genetics Can Do for Oncological Imaging: A Systematic Review of the Genetic Validation Data Used in Radiomics Studies

(1) Background: Radiogenomics is motivated by the concept that biomedical images contain information that reflects underlying pathophysiology. This review focused on papers that used genetics to validate their radiomics models and outcomes and assess their contribution to this emerging field. (2) Methods: All original research with the words radiomics and genomics in English and performed in humans up to 31 January 2022, were identified on Medline and Embase. The quality of the studies was assessed with Radiomic Quality Score (RQS) and the Cochrane recommendation for diagnostic accuracy study Quality Assessment 2. (3) Results: 45 studies were included in our systematic review, and more than 50% were published in the last two years. The studies had a mean RQS of 12, and the studied tumors were very diverse. Up to 83% investigated the prognosis as the main outcome, with the rest focusing on response to treatment and risk assessment. Most applied either transcriptomics (54%) and/or genetics (35%) for genetic validation. (4) Conclusions: There is enough evidence to state that new science has emerged, focusing on establishing an association between radiological features and genomic/molecular expression to explain underlying disease mechanisms and enhance prognostic, risk assessment, and treatment response radiomics models in cancer patients.

FAM198B promotes colorectal cancer progression by regulating the polarization of tumor-associated macrophages via the SMAD2 signaling pathway

Colorectal cancer (CRC) is one of the most common malignant tumors. Tumor-associated macrophages (TAMs) promote the progression of CRC, but the mechanism is not completely clear. The present study aimed to reveal the expression and function of FAM198B in TAMs, and the role of FAM198B in mediating macrophage polarization in CRC. The role of FAM198B in macrophage activity, cell cycle, and angiogenesis was evaluated by CCK-8 assay, flow cytometry, and vasculogenic mimicry assay. The effects of FAM198B on macrophage polarization were determined by flow cytometry. The function of FAM198B-mediated macrophage polarization on CRC progression was evaluated by transwell assays. Bioinformatic analyses and rescue assays were performed to identify biological functions and signaling pathways involved in FAM198B regulation of macrophage polarization. Increased FAM198B expression in TAMs is negatively associated with poor CRC prognosis. Functional assays showed that FAM198B promotes M2 macrophage polarization, which leads to CRC cell proliferation, migration, and invasion. Mechanistically, FAM198B regulates the M2 polarization of macrophages by targeting SMAD2, identifying the SMAD2 pathway as a mechanism by which FAM198B promotes CRC progression through regulating macrophage polarization. These findings provide a possible molecular mechanism for FAM198B in TAMs in CRC and suggest that FAM198B may be a novel therapeutic target in CRC.

Development and validation of an MRI-based nomogram for the preoperative prediction of tumor mutational burden in lower-grade gliomas

BACKGROUND

High tumor mutational burden (TMB) is an emerging biomarker of sensitivity to immune checkpoint inhibitors. In this study, we aimed to determine the value of magnetic resonance (MR)-based preoperative nomogram in predicting TMB status in lower-grade glioma (LGG) patients.

METHODS

Overall survival (OS) data were derived from The Cancer Genome Atlas (TCGA) and then analyzed by using the Kaplan-Meier method and time-dependent receiver operating characteristic (tdROC) analysis. The magnetic resonance imaging (MRI) data of 168 subjects obtained from The Cancer Imaging Archive (TCIA) were retrospectively analyzed. The correlation was explored by univariate and multivariate regression analyses. Finally, we performed tenfold cross validation. TMB values were retrieved from the supplementary information of a previously published article.

RESULTS

The high TMB subtype was associated with the shortest median OS (high vs. low: 50.9 vs. 95.6 months, P<0.05). The tdROC for the high-TMB tumors was 74% (95% CI: 61-86%) for survival at 12 months, and 71% (95% CI: 60-82%) for survival at 24 months. Multivariate logistic regression analysis confirmed that three risk factors [extranodular growth: odds ratio (OR): 8.367, 95% CI: 3.153-22.199, P<0.01; length-width ratio ≥ median: OR: 1.947, 95% CI: 1.025-3.697, P<0.05; frontal lobe: OR: 0.455, 95% CI: 0.229-0.903, P<0.05] were significant independent predictors of high-TMB tumors. The nomogram showed good calibration and discrimination. This model had an area under the curve (AUC) of 0.736 (95% CI: 0.655-0.817). Decision curve analysis (DCA) demonstrated that the nomogram was clinically useful. The average accuracy of the tenfold cross validation was 71.6% for high-TMB tumors.

CONCLUSIONS

Our results indicated that a distinct OS disadvantage was associated with the high TMB group. In addition, extranodular growth, nonfrontal lobe tumors and length-width ratio ≥ median can be conveniently used to facilitate the prediction of high-TMB tumors.

An artificial intelligence method to assess the tumor microenvironment with treatment outcomes for gastric cancer patients after gastrectomy

Background

The tumor microenvironment (TME) plays an important role in the occurrence and development of gastric cancer (GC) and is widely used to assess the treatment outcomes of GC patients. Immunohistochemistry (IHC) and gene sequencing are the main analysis methods for the TME but are limited due to the subjectivity of observers, the high cost of equipment and the need for professional analysts.

Methods

The ImmunoScore (IS) was developed in the TCGA cohort and validated in GEO cohorts. The Radiomic ImmunoScore (RIS) was developed in the TCGA cohort and validated in the Nanfang cohort. A nomogram was developed and validated in the Nanfang cohort based on RIS and clinical features.

Results

For IS, the area under the curves (AUCs) were 0.798 for 2-year overall survival (OS) and 0.873 for 4-year overall survival. For RIS, in the TCGA cohort, the AUCs distinguishing High-IS or Low-IS and predicting prognosis were 0.85 and 0.81, respectively; in the Nanfang cohort, the AUC predicting prognosis was 0.72. The nomogram performed better than the TNM staging system according to the ROC curve (all P < 0.01). Patients with TNM stage II and III in the High-nomogram group were more likely to benefit from adjuvant chemotherapy than Low-nomogram group patients.

Conclusions

The RIS and the nomogram can be used to assess the TME, prognosis and adjuvant chemotherapy benefit of GC patients after radical gastrectomy and are valuable additions to the current TNM staging system. High-nomogram GC patients may benefit more from adjuvant chemotherapy than Low-nomogram GC patients.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12967-022-03298-7.

Radiomics in Triple Negative Breast Cancer: New Horizons in an Aggressive Subtype of the Disease

In the last decade, the analysis of the medical images has evolved significantly, applications and tools capable to extract quantitative characteristics of the images beyond the discrimination capacity of the investigator's eye being developed. The applications of this new research field, called radiomics, presented an exponential growth with direct implications in the diagnosis and prediction of response to therapy. Triple negative breast cancer (TNBC) is an aggressive breast cancer subtype with a severe prognosis, despite the aggressive multimodal treatments applied according to the guidelines. Radiomics has already proven the ability to differentiate TNBC from fibroadenoma. Radiomics features extracted from digital mammography may also distinguish between TNBC and non-TNBC. Recent research has identified three distinct subtypes of TNBC using IRM breast images voxel-level radiomics features (size/shape related features, texture features, sharpness). The correlation of these TNBC subtypes with the clinical response to neoadjuvant therapy may lead to the identification of biomarkers in order to guide the clinical decision. Furthermore, the variation of some radiomics features in the neoadjuvant settings provides a tool for the rapid evaluation of treatment efficacy. The association of radiomics features with already identified biomarkers can generate complex predictive and prognostic models. Standardization of image acquisition and also of radiomics feature extraction is required to validate this method in clinical practice.

Extendable and explainable deep learning for pan-cancer radiogenomics research

Radiogenomics is a field where medical images and genomic profiles are jointly analyzed to answer critical clinical questions. Specifically, people want to identify non-invasive imaging biomarkers that are associated with both genomic features and clinical outcomes. Deep learning is an advanced computer science technique that has been applied in many fields, including medical image and genomic data analysis. This review summarizes the current state of deep learning in pan-cancer radiogenomic research, discusses its limitations, and indicates the potential future directions. Traditional machine learning in radiomics, genomics, and radiogenomics have also been briefly discussed. We also summarize the main pan-cancer radiogenomic research resources. Two characteristics of deep learning are emphasized when discussing its application to pan-cancer radiogenomics, which are extendibility and explainability.

Assessing Versatile Machine Learning Models for Glioma Radiogenomic Studies across Hospitals

Simple Summary

Radiogenomics enables prediction of the status and prognosis of patients using non-invasively obtained imaging data. Current machine learning (ML) methods used in radiogenomics require huge datasets, which involve the handling of large heterogeneous datasets from multiple cohorts/hospitals. In this study, two different glioma datasets were used to test various ML and image pre-processing methods to confirm whether the models trained on one dataset are universally applicable to other datasets. Our result suggested that the ML method that yielded the highest accuracy in a single dataset was likely to be overfitted. We demonstrated that implementation of standardization and dimension reduction procedures prior to classification, enabled the development of ML methods that are less affected by the multiple cohort difference. We advocate using caution in interpreting the results of radiogenomic studies of the training and testing datasets that are small or mixed, with a view to implementing practical ML methods in radiogenomics.

Abstract

Radiogenomics use non-invasively obtained imaging data, such as magnetic resonance imaging (MRI), to predict critical biomarkers of patients. Developing an accurate machine learning (ML) technique for MRI requires data from hundreds of patients, which cannot be gathered from any single local hospital. Hence, a model universally applicable to multiple cohorts/hospitals is required. We applied various ML and image pre-processing procedures on a glioma dataset from The Cancer Image Archive (TCIA, n = 159). The models that showed a high level of accuracy in predicting glioblastoma or WHO Grade II and III glioma using the TCIA dataset, were then tested for the data from the National Cancer Center Hospital, Japan (NCC, n = 166) whether they could maintain similar levels of high accuracy. Results: we confirmed that our ML procedure achieved a level of accuracy (AUROC = 0.904) comparable to that shown previously by the deep-learning methods using TCIA. However, when we directly applied the model to the NCC dataset, its AUROC dropped to 0.383. Introduction of standardization and dimension reduction procedures before classification without re-training improved the prediction accuracy obtained using NCC (0.804) without a loss in prediction accuracy for the TCIA dataset. Furthermore, we confirmed the same tendency in a model for IDH1/2 mutation prediction with standardization and application of dimension reduction that was also applicable to multiple hospitals. Our results demonstrated that overfitting may occur when an ML method providing the highest accuracy in a small training dataset is used for different heterogeneous data sets, and suggested a promising process for developing an ML method applicable to multiple cohorts.

Lower-Grade Gliomas: Predicting DNA Methylation Subtyping and its Consequences on Survival with MR Features

RATIONALE AND OBJECTIVES

To explore associations between MR imaging features, DNA methylation subtyping, and survival in lower-grade gliomas (LGG).

MATERIALS AND METHODS

The MR data from 170 patients generated with the Cancer Imaging Archive were reviewed. The correlation was evaluated by Fisher's Exact Test, Pearson Chi-Square and binary regression analysis. Survival analysis was conducted by using time-dependent ROC analysis and the Kaplan-Meier method (the worst prognosis subgroup).

RESULTS

Identified were 9 (5.3%) M1-subtype, 18 (10.6%) M2-subtype, 48 (28.2%) M3-subtype, 31 (18.2%) M4-subtype and 64 (37.6%) M5-subtype. Patients with M4-subtype had the shortest median OS (49.3 vs. 28.4) months(p < 0.05). The time-dependent ROC for the M4-subtype was 0.83 (95% confidence interval 0.72-0.95) for survival at 12 months, 0.82 (95% confidence interval 0.70-0.94) for survival at 24 months, and 0.74 (95% confidence interval 0.62-0.86) for survival at 36 months. After uni- and multivariate analysis, a nomogram was built based on proportion contrast-enhanced (CE) tumor, extranodular growth, volume_{_cutoff_median}, and location. For the prediction of M4-subtype, the nomogram showed good discrimination, with an area under the curve (AUC) of 0.886 (95% CI: 0.820-952) and was well calibrated. On multivariate logistic regression analysis, volume ≥60cm³ (OR: 0.200; p < 0.001; 95%CI: 0.048-0.834) was associated with M1-subtype (AUC: 0.690). Hemorrhage (OR: 5.443; p = 0.002; 95%CI: 1.844-16.069) and volume > median (OR: 3.256; p = 0.05; 95%CI: 0.992-10.686) were associated with M2-subtype (AUC: 0.733). Proportion CE tumor<=5% (OR: 3.968; P=0.002; 95%CI: 1.634-9.635) was associated with M3-subtype (AUC: 0.632). Poorly-defined (OR: 2.258; p = 0.05; 95%CI: 1.000-5.101) and volume > median (OR: 2.447; p = 0.01; 95%CI: 1.244-4.813) were associated with M5-subtype (AUC: 0.645). Decision curve analysis indicated predictions for all models were clinically useful.

CONCLUSION

This preliminary radiogenomics analysis of lower-grade gliomas demonstrated associations between MR features and DNA methylation subtyping. The shortest survival was observed in patients with M4-subtype. And we have constructed nomogram that enables more accurate predictions of M4-subtype.

TCGA-TCIA-Based CT Radiomics Study for Noninvasively Predicting Epstein-Barr Virus Status in Gastric Cancer

OBJECTIVE. The purpose of this study was to investigate the value of TCGA-TCIA (The Cancer Genome Atlas and The Cancer Imaging Archive)-based CT radiomics for noninvasive prediction of Epstein-Barr virus (EBV) status in gastric cancer (GC). MATERIALS AND METHODS. A total of 133 patients with pathologically confirmed GC (94 in the training cohort and 39 in the validation cohort) who were identified from the TCGA-TCIA public data repository and two hospitals were retrospectively enrolled in the study. Two-dimensional and 3D radiomics features were extracted to construct corresponding radiomics signatures. Then, 2D and 3D nomograms were built by combining radiomics signatures and clinical information on the basis of multivariable analysis. Their performance and clinical practicability were determined, validated, and compared with respect to discrimination, calibration, reclassification, and time spent on tumor segmentation. RESULTS. Both 2D and 3D nomograms were robust and showed good calibration. The AUCs of the 2D and 3D nomograms showed no significant difference in the training cohort (0.919 vs 0.945, respectively; p = .41) or validation cohort (0.939 vs 0.955, respectively; p = .71). The net reclassification index showed that the 3D nomogram revealed no significant improvement in risk reclassification when compared with the 2D nomogram in the training cohort (net reclassification index, 0.68%; p = .14) and the validation cohort (net reclassification index, 6.06%; p = .08). Of note, the time spent on 3D segmentation (median, 907 seconds) was higher than that spent on 2D segmentation (median, 129 seconds). CONCLUSION. The 2D and 3D radiomics nomograms might have the potential to be used as effective tools for prediction of EBV in GC. When time spent on segmentation is considered, the 2D nomogram is more highly recommended for clinical application.

Radiomic and Genomic Machine Learning Method Performance for Prostate Cancer Diagnosis: Systematic Literature Review

BACKGROUND

Machine learning algorithms have been drawing attention at the joining of pathology and radiology in prostate cancer research. However, due to their algorithmic learning complexity and the variability of their architecture, there is an ongoing need to analyze their performance.

OBJECTIVE

This study assesses the source of heterogeneity and the performance of machine learning applied to radiomic, genomic, and clinical biomarkers for the diagnosis of prostate cancer. One research focus of this study was on clearly identifying problems and issues related to the implementation of machine learning in clinical studies.

METHODS

Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) protocol, 816 titles were identified from the PubMed, Scopus, and OvidSP databases. Studies that used machine learning to detect prostate cancer and provided performance measures were included in our analysis. The quality of the eligible studies was assessed using the QUADAS-2 (quality assessment of diagnostic accuracy studies-version 2) tool. The hierarchical multivariate model was applied to the pooled data in a meta-analysis. To investigate the heterogeneity among studies, I2 statistics were performed along with visual evaluation of coupled forest plots. Due to the internal heterogeneity among machine learning algorithms, subgroup analysis was carried out to investigate the diagnostic capability of machine learning systems in clinical practice.

RESULTS

In the final analysis, 37 studies were included, of which 29 entered the meta-analysis pooling. The analysis of machine learning methods to detect prostate cancer reveals the limited usage of the methods and the lack of standards that hinder the implementation of machine learning in clinical applications.

CONCLUSIONS

The performance of machine learning for diagnosis of prostate cancer was considered satisfactory for several studies investigating the multiparametric magnetic resonance imaging and urine biomarkers; however, given the limitations indicated in our study, further studies are warranted to extend the potential use of machine learning to clinical settings. Recommendations on the use of machine learning techniques were also provided to help researchers to design robust studies to facilitate evidence generation from the use of radiomic and genomic biomarkers.

Understanding Sources of Variation to Improve the Reproducibility of Radiomics

Radiomics is the method of choice for investigating the association between cancer imaging phenotype, cancer genotype and clinical outcome prediction in the era of precision medicine. The fast dispersal of this new methodology has benefited from the existing advances of the core technologies involved in radiomics workflow: image acquisition, tumor segmentation, feature extraction and machine learning. However, despite the rapidly increasing body of publications, there is no real clinical use of a developed radiomics signature so far. Reasons are multifaceted. One of the major challenges is the lack of reproducibility and generalizability of the reported radiomics signatures (features and models). Sources of variation exist in each step of the workflow; some are controllable or can be controlled to certain degrees, while others are uncontrollable or even unknown. Insufficient transparency in reporting radiomics studies further prevents translation of the developed radiomics signatures from the bench to the bedside. This review article first addresses sources of variation, which is illustrated using demonstrative examples. Then, it reviews a number of published studies and progresses made to date in the investigation and improvement of feature reproducibility and model performance. Lastly, it discusses potential strategies and practical considerations to reduce feature variability and improve the quality of radiomics study. This review focuses on CT image acquisition, tumor segmentation, quantitative feature extraction, and the disease of lung cancer.

MuSA: a graphical user interface for multi-OMICs data integration in radiogenomic studies

Analysis of large-scale omics data along with biomedical images has gaining a huge interest in predicting phenotypic conditions towards personalized medicine. Multiple layers of investigations such as genomics, transcriptomics and proteomics, have led to high dimensionality and heterogeneity of data. Multi-omics data integration can provide meaningful contribution to early diagnosis and an accurate estimate of prognosis and treatment in cancer. Some multi-layer data structures have been developed to integrate multi-omics biological information, but none of these has been developed and evaluated to include radiomic data. We proposed to use MultiAssayExperiment (MAE) as an integrated data structure to combine multi-omics data facilitating the exploration of heterogeneous data. We improved the usability of the MAE, developing a Multi-omics Statistical Approaches (MuSA) tool that uses a Shiny graphical user interface, able to simplify the management and the analysis of radiogenomic datasets. The capabilities of MuSA were shown using public breast cancer datasets from TCGA-TCIA databases. MuSA architecture is modular and can be divided in Pre-processing and Downstream analysis. The pre-processing section allows data filtering and normalization. The downstream analysis section contains modules for data science such as correlation, clustering (i.e., heatmap) and feature selection methods. The results are dynamically shown in MuSA. MuSA tool provides an easy-to-use way to create, manage and analyze radiogenomic data. The application is specifically designed to guide no-programmer researchers through different computational steps. Integration analysis is implemented in a modular structure, making MuSA an easily expansible open-source software.

Molecular Mechanisms of Hepatoblastoma

Hepatoblastoma (HB) is the predominant primary liver tumor in children. While the prognosis is favorable when the tumor can be resected, the outcome is dismal for patients with progressed HB. Therefore, a better understanding of the molecular mechanisms responsible for HB is imperative for early detection and effective treatment. Sequencing analysis of human HB specimens unraveled the pivotal role of Wnt/β-catenin pathway activation in this disease. Nonetheless, β-catenin activation alone does not suffice to induce HB, implying the need for additional alterations. Perturbations of several pathways, including Hippo, Hedgehog, NRF2/KEAP1, HGF/c-Met, NK-1R/SP, and PI3K/AKT/mTOR cascades and aberrant activation of c-MYC, n-MYC, and EZH2 proto-oncogenes, have been identified in HB, although their role requires additional investigation. Here, we summarize the current knowledge on HB molecular pathogenesis, the relevance of the preclinical findings for the human disease, and the innovative therapeutic strategies that could be beneficial for the treatment of HB patients.

Technical Note: MRQy - An open-source tool for quality control of MR imaging data

PURPOSE

There is an increasing availability of large imaging cohorts [such as through The Cancer Imaging Archive (TCIA)] for computational model development and imaging research. To ensure development of generalizable computerized models, there is a need to quickly determine relative quality differences in these cohorts, especially when considering MRI datasets which can exhibit wide variations in image appearance. The purpose of this study is to present a quantitative quality control tool, MRQy, to help interrogate MR imaging datasets for: (a) site- or scanner-specific variations in image resolution or image contrast, and (b) imaging artifacts such as noise or inhomogeneity; which need correction prior to model development.

METHODS

Unlike existing imaging quality control tools, MRQy has been generalized to work with images from any body region to efficiently extract a series of quality measures (e.g., noise ratios, variation metrics) and MR image metadata (e.g., voxel resolution and image dimensions). MRQy also offers a specialized HTML5-based front-end designed for real-time filtering and trend visualization of quality measures.

RESULTS

MRQy was used to evaluate (a) n = 133 brain MRIs from TCIA (7 sites) and (b) n = 104 rectal MRIs (3 local sites). MRQy measures revealed significant site-specific variations in both cohorts, indicating potential batch effects. Before processing, MRQy measures could be used to identify each of the seven sites within the TCIA cohort with 87.5%, 86.4%, 90%, 93%, 90%, 60%, and 92.9% accuracy and the three sites within the rectal cohort with 91%, 82.8%, and 88.9% accuracy using unsupervised clustering. After processing, none of the sites could be distinctively clustered via MRQy measures in either cohort; suggesting that batch effects had been largely accounted for. Marked differences in specific MRQy measures were also able to identify outlier MRI datasets that needed to be corrected for common acquisition artifacts.

CONCLUSIONS

MRQy is designed to be a standalone, unsupervised tool that can be efficiently run on a standard desktop computer. It has been made freely accessible and open-source at http://github.com/ccipd/MRQy for community use and feedback.

New Roadmaps for Non-muscle-invasive Bladder Cancer With Unfavorable Prognosis

About 70% of bladder cancers (BCs) are diagnosed as non-muscle-invasive BCs (NMIBCs), while the remaining are muscle-invasive BCs (MIBCs). The European Association of Urology (EAU) guidelines stratify NMIBCs into low, intermediate, and high risk for treatment options. Low-risk NMIBCs undergo only the transurethral resection of the bladder (TURB), whereas for intermediate-risk and high-risk NMIBCs, the transurethral resection of the bladder (TURB) with or without Bacillus Calmette-Guérin (BCG) immune or chemotherapy is the standard treatment. A minority of NMIBCs show unfavorable prognosis. High-risk NMIBCs have a high rate of disease recurrence and/or progression to muscle-invasive tumor and BCG treatment failure. The heterogeneous nature of NMIBCs poses challenges for clinical decision-making. In 2020, the EAU made some changes to NMIBCs BCG failure definitions and treatment options, highlighting the need for reliable molecular markers for improving the predictive accuracy of currently available risk tables. Nowadays, next-generation sequencing (NGS) has revolutionized the study of cancer biology, providing diagnostic, prognostic, and therapy response biomarkers in support of precision medicine. Integration of NGS with other cutting-edge technologies might help to decipher also bladder tumor surrounding aspects such as immune system, stromal component, microbiome, and urobiome; altogether, this might impact the clinical outcomes of NMBICs especially in the BCG responsiveness. This review focuses on NMIBCs with unfavorable prognoses, providing molecular prognostic factors from tumor immune and stromal cells, and the perspective of urobiome and microbiome profiling on therapy response. We provide information on the cornerstone of immunotherapy and new promising bladder-preserving treatments and ongoing clinical trials for BCG–unresponsive NMIBCs.

Artificial intelligence in radiotherapy: a technological review

Radiation therapy (RT) is widely used to treat cancer. Technological advances in RT have occurred in the past 30 years. These advances, such as three-dimensional image guidance, intensity modulation, and robotics, created challenges and opportunities for the next breakthrough, in which artificial intelligence (AI) will possibly play important roles. AI will replace certain repetitive and labor-intensive tasks and improve the accuracy and consistency of others, particularly those with increased complexity because of technological advances. The improvement in efficiency and consistency is important to manage the increasing cancer patient burden to the society. Furthermore, AI may provide new functionalities that facilitate satisfactory RT. The functionalities include superior images for real-time intervention and adaptive and personalized RT. AI may effectively synthesize and analyze big data for such purposes. This review describes the RT workflow and identifies areas, including imaging, treatment planning, quality assurance, and outcome prediction, that benefit from AI. This review primarily focuses on deep-learning techniques, although conventional machine-learning techniques are also mentioned.

The Impact of Normalization Approaches to Automatically Detect Radiogenomic Phenotypes Characterizing Breast Cancer Receptors Status

In breast cancer studies, combining quantitative radiomic with genomic signatures can help identifying and characterizing radiogenomic phenotypes, in function of molecular receptor status. Biomedical imaging processing lacks standards in radiomic feature normalization methods and neglecting feature normalization can highly bias the overall analysis. This study evaluates the effect of several normalization techniques to predict four clinical phenotypes such as estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), and triple negative (TN) status, by quantitative features. The Cancer Imaging Archive (TCIA) radiomic features from 91 T1-weighted Dynamic Contrast Enhancement MRI of invasive breast cancers were investigated in association with breast invasive carcinoma miRNA expression profiling from the Cancer Genome Atlas (TCGA). Three advanced machine learning techniques (Support Vector Machine, Random Forest, and Naïve Bayesian) were investigated to distinguish between molecular prognostic indicators and achieved an area under the ROC curve (AUC) values of 86%, 93%, 91%, and 91% for the prediction of ER+ versus ER-, PR+ versus PR-, HER2+ versus HER2-, and triple-negative, respectively. In conclusion, radiomic features enable to discriminate major breast cancer molecular subtypes and may yield a potential imaging biomarker for advancing precision medicine.