The progress of multimodal imaging combination and subregion based radiomics research of cancers

In recent years, with the standardization of radiomics methods; development of tools; and popularization of the concept, radiomics has been widely used in all aspects of tumor diagnosis; treatment; and prognosis. As the study of radiomics in cancer has become more advanced, the currently used methods have revealed their shortcomings. The performance of cancer radiomics based on single-modality medical images, which based on their imaging principles, only partially reflects tumor information, has been necessarily compromised. Using the whole tumor as a region of interest to extract radiomic features inevitably leads to the loss of intra-tumoral heterogeneity of, which also affects the performance of radiomics. Radiomics of multimodal images extracts various aspects of information from images of each modality and then integrates them together for model construction; thus, avoiding missing information. Subregional segmentation based on multimodal medical image combinations allows radiomics features acquired from subregions to retain tumor heterogeneity, further improving the performance of radiomics. In this review, we provide a detailed summary of the current research on the radiomics of multimodal images of cancer and tumor subregion-based radiomics, and then raised some of the research problems and also provide a thorough discussion on these issues.     

Machine learning helps identifying volume-confounding effects in radiomics

PurposeHighlighting the risk of biases in radiomics-based models will help improve their quality and increase usage as decision support systems in the clinic. In this study we use machine learning-based methods to identify the presence of volume-confounding effects in radiomics features.Methods841 radiomics features were extracted from two retrospective publicly available datasets of lung and head neck cancers using open source software. Unsupervised hierarchical clustering and principal component analysis (PCA) identified relations between radiomics and clinical outcomes (overall survival). Bootstrapping techniques with logistic regression verified features’ prognostic power and robustness.ResultsOver 80% of the features had large pairwise correlations. Nearly 30% of the features presented strong correlations with tumor volume. Using volume-independent features for clustering and PCA did not allow risk stratification of patients. Clinical predictors outperformed radiomics features in bootstrapping and logistic regression.ConclusionsThe adoption of safeguards in radiomics is imperative to improve the quality of radiomics studies. We proposed machine learning (ML) – based methods for robust radiomics signatures development.     

A deep survival interpretable radiomics model of hepatocellular carcinoma patients

This work aims to identify a new radiomics signature using imaging phenotypes and clinical variables for risk prediction of overall survival (OS) in hepatocellular carcinoma (HCC) patients treated with stereotactic body radiation therapy (SBRT). 167 patients were retrospectively analyzed with repeated nested cross-validation to mitigate overfitting issues. 56 radiomic features were extracted from pre-treatment contrast-enhanced (CE) CT images. 37 clinical factors were obtained from patients' electronic records. Variational autoencoders (VAE) based survival models were designed for radiomics and clinical features and a convolutional neural network (CNN) survival model was used for the CECT. Finally, radiomics, clinical and raw image deep learning network (DNN) models were combined to predict the risk probability for OS. The final models yielded c-indices of 0.579 (95%CI: 0.544–0.621), 0.629 (95%CI: 0.601–0.643), 0.581 (95%CI: 0.553–0.613) and 0.650 (95%CI: 0.635–0.683) for radiomics, clinical, image input and combined models on nested cross validation scheme, respectively. Integrated gradients method was used to interpret the trained models. Our interpretability analysis of the DNN showed that the top ranked features were clinical liver function and liver exclusive of tumor radiomics features, which suggests a prominent role of side effects and toxicities in liver outside the tumor region in determining the survival rate of these patients. In summary, novel deep radiomic analysis provides improved performance for risk assessment of HCC prognosis compared with Cox survival models and may facilitate stratification of HCC patients and personalization of their treatment strategies. Liver function was found to contribute most to the OS for these HCC patients and radiomics can aid in their management.     

Radiomics in radiooncology – Challenging the medical physicist

PurposeNoticing the fast growing translation of artificial intelligence (AI) technologies to medical image analysis this paper emphasizes the future role of the medical physicist in this evolving field. Specific challenges are addressed when implementing big data concepts with high-throughput image data processing like radiomics and machine learning in a radiooncology environment to support clinical decisions.MethodsBased on the experience of our interdisciplinary radiomics working group, techniques for processing minable data, extracting radiomics features and associating this information with clinical, physical and biological data for the development of prediction models are described. A special emphasis was placed on the potential clinical significance of such an approach.ResultsClinical studies demonstrate the role of radiomics analysis as an additional independent source of information with the potential to influence the radiooncology practice, i.e. to predict patient prognosis, treatment response and underlying genetic changes. Extending the radiomics approach to integrate imaging, clinical, genetic and dosimetric data (‘panomics’) challenges the medical physicist as member of the radiooncology team.ConclusionsThe new field of big data processing in radiooncology offers opportunities to support clinical decisions, to improve predicting treatment outcome and to stimulate fundamental research on radiation response both of tumor and normal tissue. The integration of physical data (e.g. treatment planning, dosimetric, image guidance data) demands an involvement of the medical physicist in the radiomics approach of radiooncology. To cope with this challenge national and international organizations for medical physics should organize more training opportunities in artificial intelligence technologies in radiooncology.     

Intravoxel incoherent motion radiomics nomogram for predicting tumor treatment responses in nasopharyngeal carcinoma

BackgroundIntravoxel incoherent motion (IVIM) plays an important role in predicting treatment responses in patient with nasopharyngeal carcinoma (NPC). The goal of this study was to develop and validate a radiomics nomogram based on IVIM parametric maps and clinical data for the prediction of treatment responses in NPC patients.MethodsEighty patients with biopsy-proven NPC were enrolled in this study. Sixty-two patients had complete responses and 18 patients had incomplete responses to treatment. Each patient received a multiple b-value diffusion-weighted imaging (DWI) examination before treatment. Radiomics features were extracted from IVIM parametric maps derived from DWI image. Feature selection was performed by the least absolute shrinkage and selection operator method. Radiomics signature was generated by support vector machine based on the selected features. Receiver operating characteristic (ROC) curves and area under the ROC curve (AUC) values were used to evaluate the diagnostic performance of radiomics signature. A radiomics nomogram was established by integrating the radiomics signature and clinical data.ResultsThe radiomics signature showed good prognostic performance to predict treatment response in both training (AUC = 0.906, P<0.001) and testing (AUC = 0.850, P<0.001) cohorts. The radiomic nomogram established by integrating the radiomic signature with clinical data significantly outperformed clinical data alone (C-index, 0.929 vs 0.724; P<0.0001).ConclusionsThe IVIM-based radiomics nomogram provided high prognostic ability to treatment responses in patients with NPC. The IVIM-based radiomics signature has the potential to be a new biomarker in prediction of the treatment responses and may affect treatment strategies in patients with NPC.     

Tumor Necrosis Factor Inhibition and Head and Neck Cancer Recurrence and Death in Rheumatoid Arthritis

The objective of this retrospective cohort study was to determine the effect of tumor necrosis factor inhibitor (TNFi) therapy on the risk of head and neck cancer (HNC) recurrence or HNC-attributable death in patients with rheumatoid arthritis (RA). RA patients with HNC were assembled from the US national Veterans’ Affairs (VA) administrative databases, and diagnoses confirmed and data collected by electronic medical record review. The cohort was divided into those treated with non-biologic disease-modifying anti-rheumatic drugs (nbDMARDs) versus TNF inhibitors (TNFi) after a diagnosis of HNC. Likelihood of a composite endpoint of recurrence or HNC-attributable death was determined by Cox proportional hazards regression. Of 180 patients with RA and HNC, 31 were treated with TNFi and 149 with nbDMARDs after the diagnosis of HNC. Recurrence or HNC-attributable death occurred in 5/31 (16.1%) patients in the TNFi group and 44/149 (29.5%) patients in the nbDMARD group (p = 0.17); it occurred in 2/16 (13%) patients who received TNFi in the year prior to HNC diagnosis but not after. Overall stage at diagnosis (p = 0.03) and stage 4 HNC (HR 2.49 [CI 1.06–5.89]; p = 0.04) were risk factors for recurrence or HNC-attributable death; treatment with radiation or surgery was associated with a lower risk (HR 0.35 [CI 0.17–0.74]; p = 0.01 and HR 0.39 [CI 0.20–0.76]; p = 0.01 respectively). Treatment with TNFi was not a risk factor for recurrence or HNC-attributable death (HR 0.75; CI 0.31–1.85; p = 0.54). We conclude that treatment with TNFi may be safe in patients with RA and HNC, especially as the time interval between HNC treatment and non-recurrence increases. In this study, TNF inhibition was not associated with an increase in recurrence or HNC-attributable death.     

Significance of Lymph Node Metastasis in Cancer Dissemination of Head and Neck Cancer

Lymph node metastasis (LNM) in many solid cancers is a well-known prognostic factor; however, it has been debated whether regional LNM simply reflects tumor aggressiveness or is a source for further tumor dissemination. Similarly, the metastatic process in head and neck cancer (HNC) has not been fully evaluated. Thus, we aimed to investigate the relative significance of LNM in metastatic cascade of HNC using functional imaging of HNC patients and molecular imaging in in vivo models. First, we analyzed ¹⁸Fluorodeoxyglucose positron emission tomography (PET) parameters of 117 patients with oral cancer. The primary tumor and nodal PET parameters were measured separately, and survival analyses were conducted on the basis of clinical and PET variables to identify significant prognostic factors. In multivariate analyses, we found that only the metastatic node PET values were significant. Next, we compared the relative frequency of lung metastasis in primary ear tumors versus lymph node (LN) tumors, and we tested the rate of lung metastasis in another animal model, in which each animal had both primary and LN tumors that were expressing different colors. As a result, LN tumors showed higher frequencies of lung metastasis compared to orthotopic primary tumors. In color-matched comparisons, the relative contribution to lung metastasis was higher in LN tumors than in primary tumors, although both primary and LN tumors caused lung metastases. In summary, tumors growing in the LN microenvironment spread to systemic sites more commonly than primary tumors in HNC, suggesting that the adequate management of LNM can reduce further systemic metastasis.     

Role of DNA methylation in head and neck cancer

Head and neck cancer (HNC) is a heterogenous and complex entity including diverse anatomical sites and a variety of tumor types displaying unique characteristics and different etilogies. Both environmental and genetic factors play a role in the development of the disease, but the underlying mechanism is still far from clear. Previous studies suggest that alterations in the genes acting in cellular signal pathways may contribute to head and neck carcinogenesis. In cancer, DNA methylation patterns display specific aberrations even in the early and precancerous stages and may confer susceptibility to further genetic or epigenetic changes. Silencing of the genes by hypermethylation or induction of oncogenes by promoter hypomethylation are frequent mechanisms in different types of cancer and achieve increasing diagnostic and therapeutic importance since the changes are reversible. Therefore, methylation analysis may provide promising clinical applications, including the development of new biomarkers and prediction of the therapeutic response or prognosis. In this review, we aimed to analyze the available information indicating a role for the epigenetic changes in HNC.     

Characterization of laryngopharyngeal tumors. Tumor size and vascularization

A recent survey of head and neck cancer indicated a sharp difference in survival between cancer of the hypopharyx and cancers formed in other head and neck sites. We have analyzed tumor size relative to clinical stage and vascularization as possible causes for such a difference in a series of 21 patients with cancers of the laryngopharynx (11 glottic and 10 hypopharyngeal). We found that the volume of the smallest cancers of the larynx at stage 2 are significantly larger than the volume of the cancers of the hypopharynx at stage 4 (p<0.05). Next, we have determined by immunohistochemistry and morphometry the microvessel density (MVD), microvessel perimeter (MVP) and VEGF expression of laryngo-hypopharyngeal cancers. Analysis of these data indicates that there is no difference in vascularization and VEGF expression between these two tumor types. These data strongly suggest that the invasive-but not the angiogenic phenotype of hypopharyngeal cancer cells could be responsible for the more aggressive biological behavior of this head and neck cancer subtype.     

AI applications to medical images: From machine learning to deep learning

PurposeArtificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context.MethodsA narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections.ResultsWe first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way.ConclusionsBiomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practice.     

Oral malignant melanomas and other head and neck neoplasms in Danish dogs - data from the Danish Veterinary Cancer Registry

Background  

Head and neck cancers (HNC) are relatively common and often very serious diseases in both dogs and humans. Neoplasms originating in the head and neck region are a heterogeneous group. HNC often has an unfavourable prognosis and the proximity of the tissue structures renders extirpation of tumours with sufficient margins almost incompatible with preservation of functionality. In humans oral malignant melanoma (OMM) is extremely rare, but represents a particular challenge since it is highly aggressive as is the canine counterpart, which thus may be of interest as a spontaneous animal model.     

非可控性炎症与头颈恶性肿瘤的关系

"癌症源于慢性炎症"之说越来越被人们关注与认可,已成为近年肿瘤领域研究的热点。与肿瘤密切相关的炎症实质为非可控性炎症,触发并参与肿瘤的发生、发展、浸润转移等各个病理过程;而在肿瘤发生发展过程中,肿瘤细胞同样可通过自分泌或其他方式调控非可控性炎症反应,以利于自身生长。非可控性炎症在头颈恶性肿瘤发生、进展过程中均扮演着十分重要的角色,在此过程中涉及众多分子和信号通路的参与。本文就非可控性炎症与头颈恶性肿瘤(鼻咽癌、喉癌、口腔癌、甲状腺肿瘤及皮肤肿瘤)的相互关系进行简要综述。     

HSPA5 negatively regulates lysosomal activity through ubiquitination of MUL1 in head and neck cancer

HSPA5/GRP78/BiP plays an important role in cell survival or tumor progression. For these reasons, HSPA5 is an emerging therapeutic target in cancer development. Here we report that HSPA5 contributes to head and neck cancer (HNC) survival via maintenance of lysosomal activity; however, a nonthermal plasma (NTP, considered as a next-generation cancer therapy)-treated solution (NTS) inhibits HNC progression through HSPA5-dependent alteration of lysosomal activity. HSPA5 prevents NTS-induced lysosome inhibition through lysosomal-related proteins or regulation of gene expression. However, NTS-induced MUL1/MULAN/GIDE/MAPL (mitochondrial ubiquitin ligase activator of NFKB 1) leads to downregulation of HSPA5 via K48-linked ubiquitination at the lysine 446 (K446) residue. MUL1 knockdown hinders NTS-induced lysosome inhibition or cytotoxicity through the reduction of HSPA5 ubiquitination in HNC cells. While MUL1 was suppressed, HSPA5 was overexpressed in tissues of HNC patients. NTS strongly inhibited HNC progression via alterations of expression of MUL1 and HSPA5, in vivo in a xenograft model. However, NTS did not induce inhibition of tumor progression or HSPA5 reduction in MUL1 knockout (KO) HNC cells which were generated by CRISPR/Cas9 system. The data provide compelling evidence to support the idea that the regulation of the MUL1-HSPA5 axis can be a novel strategy for the treatment of HNC.     

The role of imaging in adaptive radiotherapy for head and neck cancer

Radiotherapy (RT), alone or combined with surgery and/or chemotherapy is given to almost all head and neck cancer (HNC). The goal of RT is to increase as much as possible the dose in the tumor to cure the patient, while limiting the dose in the organs at risk, mainly the parotids gland to limit the xerostomia. HNC RT appears particularly challenging due to the complexity of the shape of the anatomical structures, which also changes during the 7 weeks of treatment. Advances in imaging-modalities, -processing and -integration at the different RT steps have been crucial to develop a new image and dose-guided adaptive RT (ART) strategy. Moreover, the integration of functional imaging such as FDG-PET (performed before and during the treatment) leads to an even more highly targeted and dose-escalated ART. This article is an overview of the place and role of imaging at the different steps of HNCART, from a medical point of view.     

Targeting Nrf2 with wogonin overcomes cisplatin resistance in head and neck cancer

A principal limitation to the clinical use of cisplatin is the high incidence of chemoresistance to this drug. Combination treatments with other drugs may help to circumvent this problem. Wogonin, one of the major natural flavonoids, is known to reverse multidrug resistance in several types of cancers. We investigated the ability of wogonin to overcome cisplatin resistance in head and neck cancer (HNC) cells and further clarified its molecular mechanisms of action. Two cisplatin-resistant HNC cell lines (AMC-HN4R and -HN9R) and their parental and other human HNC cell lines were used. The effects of wogonin, either alone or in combination with cisplatin, were assessed in HNC cells and normal cells using cell cycle and death assays and by measuring cell viability, reactive oxygen species (ROS) production, and protein expression, and in tumor xenograft mouse models. Wogonin selectively killed HNC cells but spared normal cells. It inhibited nuclear factor erythroid 2-related factor 2 and glutathione S-transferase P in cisplatin-resistant HNC cells, resulting in increased ROS accumulation in HNC cells, an effect that could be blocked by the antioxidant N-acetyl-l-cysteine. Wogonin also induced selective cell death by targeting the antioxidant defense mechanisms enhanced in the resistant HNC cells and activating cell death pathways involving PUMA and PARP. Hence, wogonin significantly sensitized resistant HNC cells to cisplatin both in vitro and in vivo. Wogonin is a promising anticancer candidate that induces ROS accumulation and selective cytotoxicity in HNC cells and can help to overcome cisplatin-resistance in this cancer.     

EphA3 maintains radioresistance in head and neck cancers through epithelial mesenchymal transition

Radiotherapy is a well-established therapeutic modality used in the treatment of many cancers. However, radioresistance remains a serious obstacle to successful treatment. Radioresistance can cause local recurrence and distant metastases in some patients after radiation treatment. Thus, many studies have attempted to identify effective radiosensitizers. Eph receptor functions contribute to tumor development, modulating cell-cell adhesion, invasion, neo-angiogenesis, tumor growth and metastasis. However, the role of EphA3 in radioresistance remains unclear. In the current study, we established a stable radioresistant head and neck cancer cell line (AMC HN3R cell line) and found that EphA3 was expressed predominantly in the radioresistant head and neck cancer cell line through DNA microarray, real time PCR and Western blotting. Additionally, we found that EphA3 was overexpressed in recurrent laryngeal cancer specimens after radiation therapy. EphA3 mediated the tumor invasiveness and migration in radioresistant head and neck cancer cell lines and epithelial mesenchymal transition- related protein expression. Inhibition of EphA3 enhanced radiosensitivity in the AMC HN 3R cell line in vitro and in vivo study. In conclusion, our results suggest that EphA3 is overexpressed in radioresistant head and neck cancer and plays a crucial role in the development of radioresistance in head and neck cancers by regulating the epithelial mesenchymal transition pathway.     

Human Papillomavirus and the use of nanoparticles for immunotherapy in HPV-related cancer: A review

Human Papillomavirus (HPV) remains one of the most commonly contracted sexually transmitted diseases around the world. There are a multitude of HPV types, some of which may never present any symptoms. Others, however, are considered high-risk types, which increase the chance of the person infected to develop cancer. In recent years, the utilization of nanotechnology has allowed researchers to employ and explore the use of nanoparticles in immunotherapies.The new nanoparticle frontier has opened many doors in this area of research as a form of prevention, diagnosis, and treatment in cancers resulting from HPV. This review will provide a brief background of HPV, its relationship to head and neck cancer (HNC) and present some insight into the field of immunotherapeutic nanoparticles.     

Report of the National Oncology Research and Developement Consortium, 2003

Consorcial projects focused on 5 cancer types, breast-, colorectal-, head and neck- and pediatric cancers, and malignant melanoma. Breast cancer studies revealed unique splicing mechanisms concerning BRCA1. In sporadic breast cancers the involvement of DNA-repair genes was proved to be dependent on the histological type. Bone-metastatic tumors have been characterized by decreased NM23 and increased c-met and p53 expressions. C-erbB2 genotype of the primary tumor was not maintained frequently in bone metastases. Application of DNA-microarray and quantitative PCR technologies improved the prediction of therapeutic sensitivity of breast cancers. Colorectal cancer studies revealed regional inhomogenities (clusters) in various geographical regions of Hungary, which were distinct in the case of colonic and rectal cancers. To increase the sensitivity of fecal blood test of colorectal cancer screening, a new double-antibody test was developed and tested in a large cohort of patients. Genetic analysis revealed that hypermethylation is a significant factor in microsatellite instability which, and plays a role in silencing of APC and E-cadherin genes as well. The Hungarian pattern of TS polymorphism was also determined and was correlated not only with the efficacy of 5-FU treatment but with the progression of the disease as well. Population-based studies have been carried out in head and neck cancer patients (HNC) and smokers as well to reveal the genetic background of increasing tumor incidence. These studies revealed polymorphism in XRCC1/3 methylation enzyme gene which has preventive role. Other studies found frequent local immunosuppression in HNC patients. Studies indicated that the success of irradiation in this cancer type is dependent on the anti-vascular effects. Pediatric cancer studies determined the parameters of neuroblastoma screening based on VMA measurements. New splice variants of the WT1 gene involved in the monitoring of MRD of ALL patients was also described this year. We also obtained positive experimental data for the retinoic acid therapy of ALL. Melanoma studies extensively used DNA-microarray technology which identified 4 melanoma-specific and 2 melanoma progression-specific genes. In experimental human melanoma xenograft models we have identified 3 anti-metastatic agents: low molecular weight heparin, 2-methoxyestradiol and erythropoietin-alpha, where the later was characterized by specific effects on tumor vasculature.     

Anti-cancer effects of celecoxib in head and neck carcinoma

Although many studies highlighted cyclooxygenase2 (COX2) inhibition as a promising therapeutic strategy for cancer, more evidence is needed for clinical application. The purpose of this study was to investigate the feasibility of COX2 inhibition as a strategic treatment modality for head and neck carcinoma (HNC). We tested COX2 inhibitor, celecoxib in six types of HNC cells and analyzed the expression changes in proteins related to angiogenesis and apoptosis in vitro. We also evaluated proliferation, gelatinolysis and in vitro invasion. We used a hamster carcinogenesis model and a mouse tumorigenesis model for the in vivo evaluation of COX2 inhibition. We performed immunohistochemistry to assess changes in the expression of COX2, survivin and angiogenesis. Celecoxib administration caused decreases in the expressions of COX2, VEGF and survivin in vitro. Proliferation, in vitro invasion and gelatinolytic activity were reduced in HNC cell lines, but the effect was inconsistent across lines. COX2 inhibition retarded oral carcinogenesis from an early carcinogenic stage with increased apoptosis and decreased survivin expression. COX2 inhibition did not inhibit tumor growth, even with the COX2 downregulation and decrease in neovascularization. We conclude that COX2 inhibition has a chemopreventive effect, but its application as a treatment of HNC in a clinical setting still requires further research to overcome its limited anti-cancer effects.