Hasil untuk "Neoplasms. Tumors. Oncology. Including cancer and carcinogens"

Hao Zheng, Shenglong Li, Ye Wang et al.

BackgroundColorectal cancer (CRC) remains a significant cause of cancer-related mortality worldwide. Curcumin, a natural polyphenol, has shown promise in targeting key cancer pathways, but its precise molecular mechanisms in CRC are not fully understood. This study investigates the anti-cancer mechanisms of curcumin on CRC progression, focusing on PTBP1 and CDK2 as critical regulators.MethodsThe expression of PTBP1 was assessed in clinical CRC samples and curcumin-treated cells via PCR and Western blot. Functional assays—including CCK8, colony formation, flow cytometry, Transwell migration/invasion, and apoptosis/autophagy staining—were conducted to evaluate curcumin’s effects. CDK2 was identified as a direct target using pull-down, kinase activity, and immunoprecipitation assays. CDK2 knockout models were used to validate curcumin’s effects in vitro and in vivo.ResultsCurcumin markedly downregulated PTBP1 expression, and suppressed CRC cell proliferation, migration, and invasion while promoting apoptosis and autophagy. Mechanistic analysis revealed direct inhibition of CDK2 by curcumin, disrupting the CDK2–c-MYC–PTBP1 regulatory axis. CDK2 knockout mimicked curcumin’s effects but reduced the cells’ sensitivity to the treatment. In vivo, curcumin significantly inhibited tumor growth and activated autophagy-related pathways.ConclusionsThis study uncovers a novel mechanism in which curcumin suppresses CRC progression by targeting the CDK2–c-MYC–PTBP1 axis. These findings provide compelling evidence for curcumin’s therapeutic potential and support further clinical investigation.

Abdurrahim Yilmaz, Serra Atilla Aydin, Deniz Temur et al.

Mohs micrographic surgery (MMS) is the gold standard technique for removing high risk nonmelanoma skin cancer however, intraoperative histopathological examination demands significant time, effort, and professionality. The objective of this study is to develop a deep learning model to detect basal cell carcinoma (BCC) and artifacts on Mohs slides. A total of 731 Mohs slides from 51 patients with BCCs were used in this study, with 91 containing tumor and 640 without tumor which was defined as non-tumor. The dataset was employed to train U-Net based models that segment tumor and non-tumor regions on the slides. The segmented patches were classified as tumor, or non-tumor to produce predictions for whole slide images (WSIs). For the segmentation phase, the deep learning model success was measured using a Dice score with 0.70 and 0.67 value, area under the curve (AUC) score with 0.98 and 0.96 for tumor and non-tumor, respectively. For the tumor classification, an AUC of 0.98 for patch-based detection, and AUC of 0.91 for slide-based detection was obtained on the test dataset. We present an AI system that can detect tumors and non-tumors in Mohs slides with high success. Deep learning can aid Mohs surgeons and dermatopathologists in making more accurate decisions.

Carlos Diego H. Lopes, Marcello M. Queiroz, Luana A.F. Sampaio et al.

PURPOSETo investigate the discordance in sarcoma diagnoses between nonspecialized institutions following revision by dedicated sarcoma pathologists at a reference center in Brazil and the relevance of molecular pathology in this context.METHODSWe conducted a retrospective analysis of sarcoma samples initially analyzed at outside laboratories and subsequently reviewed by two specialized pathologists between January 2014 and December 2020. After obtaining demographic and tumor characteristics, pathology results were matched and classified as complete discordance (CD; benign v malignant, sarcoma v other malignancies), partial concordance (similar diagnosis of connective tumor, but different grade/histological subtype/differentiation), and complete concordance (CC). The concordance for histology or grade, and the role of molecular assessments supporting the diagnosis were also independently determined. Statistical analyses were conducted through the kappa coefficient of agreement and adherence by χ2 test, χ2 test by Person, and Fisher exact test.RESULTSIn total, 197 cases were included, with samples obtained predominately from male patients (57.9%) and localized/primary tumors (86.8%). Following revision, the most frequent final diagnoses were undifferentiated pleomorphic sarcoma (17.8%), well-differentiated/dedifferentiated liposarcoma (8.6%), and leiomyosarcoma (7.6%). CD was found in 13.2%, partial discordance in 45.2%, and CC in 41.6% of reviews (P < .001). We found a concordance for histology or grade of 53.5% (P < .001) and 51.8% (P < .001), respectively. Molecular assessments, comprising next-generation sequencing panels (79.5%) and fluorescent in situ hybridization (20.5%), were performed in 44 (22.3%) cases, with findings classified as of diagnostic relevance in 31.8%.CONCLUSIONIn nearly 60% of the cases, the initial sarcoma diagnosis was modified when revised by a reference center and dedicated pathologists, assisted by molecular pathology techniques. These results justify the assembly of referral networks in countries with limited health care resources.

Mahesh Sultania, Priyansh Jain, Itisha Chaudhary et al.

Objective The preoperative (clinical and radiological) depth of invasion (DOI) in early tumours can guide the surgeons in deciding elective neck dissection, the extent of invasive surgery, the need for reconstruction, potential adjuvant treatment and the patient's prognosis. This study aimed to validate the 8th AJCC clinical T stage using DOI, assess interobserver bias, and correlate the clinical, radiological and pathological T stages. Materials and methods: This was a prospective clinical study carried out from December 2019 to June 2023 at an academic tertiary care centre. Patients with squamous cell carcinoma of oral cavity and lip without involvement of skin or bone undergoing upfront surgery were included. The clinical assessment of T stage using DOI was done by three examiners, blinded to each other. The radiological T stage was assessed by an MRI and pathological T stage on fixed formalin surgical specimen. Results: A total of 173 patients were assessed during the study period, out of which 44 met the inclusion criteria. There was a fair agreement regarding the combined clinical T stage between all three examines. A statistically significant correlation was found between the clinical and pathological T stage (p-value 0.010), the radiological and pathological T stage (p-value 0.001) and clinical and radiological T stage (p-value 0.004). Conclusion: The clinical and radiological T stage using DOI correlated well with the pathological T stage. The 8th AJCC clinical T stage of oral squamous cell carcinoma was accurate in our study population.

Hairong Wang, Lingchao Mao, Zihan Zhang et al.

Liver cancer is a leading cause of mortality worldwide, and accurate Computed Tomography (CT)-based tumor segmentation is essential for diagnosis and treatment. Manual delineation is time-intensive, prone to variability, and highlights the need for reliable automation. While deep learning has shown promise for automated liver segmentation, precise liver tumor segmentation remains challenging due to the heterogeneous nature of tumors, imprecise tumor margins, and limited labeled data. We present SmoothSegNet, a novel deep learning framework that addresses these challenges with the three key designs: (1) A novel knowledge-informed label smoothing technique that distills knowledge from clinical data to generate smooth labels, which are used to regularize model training, reducing the overfitting risk and enhancing model performance; (2) A global and local segmentation framework that breaks down the main task into two simpler sub-tasks, allowing optimized preprocessing and training for each; and (3) Pre- and post-processing pipelines customized to the challenges of each subtask aimed to enhance tumor visibility and refines tumor boundaries. We apply the proposed model on a challenging HCC-TACE-Seg dataset and show that SmoothSegNet outperformed various benchmarks in segmentation performance, particularly at smaller tumors (<10cm). Our ablation studies show that the three design components complementarily contribute to the model improved performance. Code for the proposed method are available at https://github.com/lingchm/medassist-liver-cancer.

Lorna Wheaton, Sylwia Bujkiewicz

Objectives: Surrogate endpoints, used to substitute for and predict final clinical outcomes, are increasingly being used to support submissions to health technology assessment agencies. The increase in use of surrogate endpoints has been accompanied by literature describing frameworks and statistical methods to ensure their robust validation. The aim of this review was to assess how surrogate endpoints have recently been used in oncology technology appraisals by the National Institute for Health and Care Excellence (NICE) in England and Wales. Methods: This paper identified technology appraisals in oncology published by NICE between February 2022 and May 2023. Data are extracted on methods for the use and validation of surrogate endpoints. Results: Of the 47 technology appraisals in oncology available for review, 18 (38 percent) utilised surrogate endpoints, with 37 separate surrogate endpoints being discussed. However, the evidence supporting the validity of the surrogate relationship varied significantly across putative surrogate relationships with 11 providing RCT evidence, 7 providing evidence from observational studies, 12 based on clinical opinion and 7 providing no evidence for the use of surrogate endpoints. Conclusions: This review supports the assertion that surrogate endpoints are frequently used in oncology technology appraisals in England and Wales. Despite increasing availability of statistical methods and guidance on appropriate validation of surrogate endpoints, this review highlights that use and validation of surrogate endpoints can vary between technology appraisals which can lead to uncertainty in decision-making.

Arghavan Alisoltani, Xinru Qiu, L. Jaroszewski et al.

Both gender and smoking are correlated with prevalence and outcomes in many types of cancers. Tobacco smoke is a known carcinogen through its genotoxicity but can also affect cancer progression through its effect on the immune system. In this study, we aim to evaluate the hypothesis that the effects of smoking on the tumor immune microenvironment will be influenced differently by gender using large-scale analysis of publicly available cancer datasets. We used The Cancer Genomic Atlas (TCGA) datasets (n = 2724) to analyze effects of smoking on different cancer immune subtypes and the relative abundance of immune cell types between male and female cancer patients. We further validated our results by analyzing additional datasets, including Expression Project for Oncology (expO) bulk RNA-seq dataset (n = 1118) and single-cell RNA-seq dataset (n = 14). Results of our study indicate that in female patients, two immune subtypes, C1 and C2, are respectively over and under abundant in smokers vs. never smokers. In males, the only significant difference is underabundance of the C6 subtype in smokers. We identified gender-specific differences in the population of immune cell types between smokers and never smokers in all TCGA and expO cancer types. Increased plasma cell population was identified as the most consistent feature distinguishing smokers and never smokers, especially in current female smokers based on both TCGA and expO data. Our analysis of existing single-cell RNA-seq data further revealed that smoking differentially affects the gene expression profile of cancer patients based on the immune cell type and gender. In our analysis, female and male smokers show different smoking-induced patterns of immune cells in tumor microenvironment. Besides, our results suggest cancer tissues directly exposed to tobacco smoke undergo the most significant changes, but all other cancer types are affected as well. Findings of current study also indicate that changes in the populations of plasma cells and their correlations to survival outcomes are stronger in female current smokers, with implications for cancer immunotherapy of women smokers. In conclusion, results of this study can be used to develop personalized treatment plans for cancer patients who smoke, particularly women smokers, taking into account the unique immune cell profile of their tumors.

A. F. Poveshchenko, Valeria N. Cherkas, A. Kabakov et al.

The microbiota, together with the host, form a symbiotic relationship in which the microbiota plays a key role in maintaining the homeostasis of the human body, performing a number of significant functions such as energy metabolism, maturation and maintenance of the immune system, vitamin synthesis, regulation of bile acid reabsorption in the intestine, and much more. Scientific research in recent years has made a significant contribution to understanding the complex relationship between the microbiota and a range of human pathologies, including malignant neoplasms. The review considers the mechanisms of the possible influence of bacteria on the development and progression of cancer with an emphasis on the procarcinogenic properties of the microbiota. The most important factor in the mechanism of influence of the microbiota on carcinogenesis are toxins produced by microorganisms that induce direct damage to host cell DNA, causing DNA mutations, disruption of its exact replication, and also provoke an imbalance in the proliferation and apoptosis of host cells, their rapid aging and oncogenesis. The probable mechanisms of participation of microorganisms in the development of cancer through the activation of TLRs and NLRs receptors, which have a tumor-activating effect, are considered. A brief review is given on the mechanisms of carcinogenesis associated with the metabolic activity of the microbiota due to the processes of regulation of the production of secondary bile acids, activation of pro-carcinogenic compounds: phenols, ethanol, sulfides, ammonia, nitrosamines. The influence of the microbiota on the metabolism of sex hormones and the development of hormone-dependent cancers mediated by the mechanisms of enterohepatic circulation and estrogen deconjugation is described. The study of the carcinogenic mechanisms of action of the microbiota in the host organism opens up prospects for the development of new successful personalized approaches to the diagnosis, treatment, and prevention of cancer. Changing the composition of the microbiota should become a way to fight cancer, along with surgical treatment, chemotherapy, radiation therapy, targeted therapy and immunotherapy.

Yiming Zhang, Nan Ru, Zhaowen Xue et al.

Mitochondrial damage is related to the functional properties of immune cells as well as to tumorigenesis and progression. Nevertheless, there is an absence concerning the systematic evaluation of mitochondria-associated lncRNAs (MALs) in the immune profile and tumor microenvironment of osteosarcoma patients. Based on transcriptomic and clinicopathological data from the TARGET database, MAL-related patterns were ascertained by consistent clustering, and gene set variation analysis of the different patterns was completed. Next, a MAL-derived scoring system was created using Cox and LASSO regression analyses and validated by Kaplan-Meier and ROC curves. The GSEA, ESTIMATE, and CIBERSORT algorithms were utilized to characterize the immune status and underlying biological functions in the different MAL score groups. MAL-derived risk scores were well stabilized and outperformed traditional clinicopathological features to reliably predict 5-year survival in osteosarcoma cohorts. Moreover, patients with increased MAL scores were observed to suffer from poorer prognosis, higher tumor purity, and an immunosuppressive microenvironment. Based on estimated half-maximal inhibitory concentrations, the low-MAL score group benefited more from gemcitabine and docetaxel, and less from thapsigargin and sunitinib compared to the high-MAL score group. Pan-cancer analysis demonstrated that six hub MALs were strongly correlated with clinical outcomes, immune subtypes, and tumor stemness indices in various common cancers. Finally, we verified the expression patterns of hub MALs in osteosarcoma with qRT-PCR. In summary, we identified the crosstalk between prognostic MALs and tumor-infiltrating immune cells in osteosarcoma, providing a potential strategy to ameliorate clinical stratification management.

Rowa Bakadlag, Georgia Limniatis, Gabriel Georges et al.

Abstract Background P-glycoprotein (P-gp), a member of the ATP Binding Cassette B1 subfamily (ABCB1), confers resistance to clinically relevant anticancer drugs and targeted chemotherapeutics. However, paradoxically P-glycoprotein overexpressing drug resistant cells are “collaterally sensitive” to non-toxic drugs that stimulate its ATPase activity. Methods Cell viability assays were used to determine the effect of low concentrations of tamoxifen on the proliferation of multidrug resistant cells (CHORC5 and MDA-Doxo400), expressing P-gp, their parental cell lines (AuxB1 and MDA-MB-231) or P-gp-CRISPR knockout clones of AuxB1 and CHORC5 cells. Western blot analysis was used to estimate P-gp expression in different cell lines. Apoptosis of tamoxifen-induced cell death was estimated by flow cytometry using Annexin-V-FITC stained cells. Oxidative stress of tamoxifen treated cells was determined by measuring levels of reactive oxygen species and reduced thiols using cell-permeant 2',7'-dichlorodihydrofluorescein diacetate (H2DCFDA) and 5,5-dithio-bis-(2-nitrobenzoic acid) DTNB, respectively. Results In this report, we show that P-gp-expressing drug resistant cells (CHORC5 and MDA-Doxo400) are collaterally sensitive to the anti-estrogen tamoxifen or its metabolite (4-hydroxy-tamoxifen). Moreover, P-gp-knockout clones of CHORC5 cells display complete reversal of collateral sensitivity to tamoxifen. Drug resistant cells exposed to low concentrations of tamoxifen show significant rise in reactive oxygen species, drop of reduced cellular thiols and increased apoptosis. Consistent with the latter, CHORC5 cells expressing high levels of human Bcl-2 (CHORC5-Bcl-2) show significant resistance to tamoxifen. In addition, the presence of the antioxidant N-acetylcysteine or P-gp ATPase inhibitor, PSC-833, reverse the collateral sensitivity of resistant cells to tamoxifen. By contrast, the presence of rotenone (specific inhibitor of mitochondria complex I) synergizes with tamoxifen. Conclusion This study demonstrates the use of tamoxifen as collateral sensitivity drug that can preferentially target multidrug resistant cells expressing P-gp at clinically achievable concentrations. Given the widespread use of tamoxifen in the treatment of estrogen receptor-positive breast cancers, this property of tamoxifen may have clinical applications in treatment of P-gp-positive drug resistant breast tumors. Graphical Abstract

Nosheen Masood, San-Gang Wu

Emily A. Henderson, Slawomir Lukomski, Slawomir Lukomski et al.

Pancreatic cancer is a highly aggressive form of cancer with a five-year survival rate of only ten percent. Pancreatic ductal adenocarcinoma (PDAC) accounts for ninety percent of those cases. PDAC is associated with a dense stroma that confers resistance to current treatment modalities. Increasing resistance to cancer treatments poses a challenge and a need for alternative therapies. Bacterial mediated cancer therapies were proposed in the late 1800s by Dr. William Coley when he injected osteosarcoma patients with live streptococci or a fabrication of heat-killed Streptococcus pyogenes and Serratia marcescens known as Coley’s toxin. Since then, several bacteria have gained recognition for possible roles in potentiating treatment response, enhancing anti-tumor immunity, and alleviating adverse effects to standard treatment options. This review highlights key bacterial mechanisms and structures that promote anti-tumor immunity, challenges and risks associated with bacterial mediated cancer therapies, and applications and opportunities for use in PDAC management.

Heng Zhang, Chao Lin, Hongyong He et al.

Objective Immunotherapy has not yielded satisfactory therapeutic responses in gastric cancer (GC). However, targeting myeloid checkpoints holds promise for expanding the potential of immunotherapy. This study aims to evaluate the critical role of Siglec-10+ tumor-associated macrophages (TAMs) in regulating antitumor immunity and to explore the potential of the myeloid checkpoint Siglec-10 as an interventional target.Design Siglec-10+ TAMs were assessed based on immunohistochemistry on tumor microarrays and RNA-sequencing data. Flow cytometry, RNA sequencing, and single-cell RNA-sequencing analysis were employed to characterize the phenotypic and transcriptional features of Siglec-10+ TAMs and their impact on CD8+ T cell-mediated antitumor immunity. The effectiveness of Siglec-10 blockade, either alone or in combination with anti-programmed cell death 1 (PD-1), was evaluated using an ex vivo GC tumor fragment platform based on fresh tumor tissues.Results Siglec-10 was predominantly expressed on TAMs in GC, and associated with tumor progression. In Zhongshan Hospital cohort, Siglec-10+ TAMs predicted unfavorable prognosis (n=446, p&lt;0.001) and resistance to adjuvant chemotherapy (n=331, p&lt;0.001), which were further validated in exogenous cohorts. In the Samsung Medical Center cohort, Siglec-10+ TAMs demonstrated inferior response to pembrolizumab in GC (n=45, p=0.008). Furthermore, Siglec-10+ TAMs exhibited an immunosuppressive phenotype and hindered T cell-mediated antitumor immune response. Finally, blocking Siglec-10 reinvigorated the antitumor immune response and synergistically enhances anti-PD-1 immunotherapy in an ex vivo GC tumor fragment platform.Conclusions In GC, the myeloid checkpoint Siglec-10 contributes to the regulation of immunosuppressive property of TAMs and promotes the depletion of CD8+ T cells, ultimately facilitating immune evasion. Targeting Siglec-10 represents a potential strategy for immunotherapy in GC.

Gong Zhang, Fangfang Nie, Weinan Zhao et al.

Abstract Background Endometrial carcinoma (EC) is the second most common gynecological malignancy, and the differences between different pathological types are not entirely clear. Here, we retrospectively collected eligible EC patients to explore their differences regarding clinical characteristics and prognosis. Methods Five hundred seventy EC patients from the First Affiliated Hospital of Zhengzhou University were included. Prognostic factors were measured using the univariate/multivariate Cox models. Overall survival (OS) and progression-free survival (PFS) were the primary and secondary endpoints, respectively. Results In total, 396 patients with uterine endometrioid carcinoma (UEC), 106 patients with uterine serous carcinoma (USC), 34 patients with uterine mixed carcinoma (UMC), and 34 patients with uterine clear cell carcinoma (UCCC) were included. Comparison of baseline characteristics revealed patients diagnosed with UEC were younger, had more early clinical stage, and had lower incidence of menopause and lymph node metastasis. Compared to UEC, other pathological EC obtained more unfavorable OS (UCCC: HR = 12.944, 95%CI = 4.231–39.599, P < 0.001; USC: HR = 5.958, 95%CI = 2.404–14.765, P < 0.001; UMC: HR = 1.777, 95%CI = 0.209–15.114, P = 0.599) and PFS (UCCC: HR = 8.696, 95%CI = 1.972–38.354, P = 0.004; USC: HR = 4.131, 95%CI = 1.243–13.729, P = 0.021; UMC: HR = 5.356, 95%CI = 0.935–30.692, P = 0.060). Compared with UEC patients, the OS of UCCC patients in stage I–II and USC patients in stage III–IV were significantly worse, while UMC patients in stage I–II favored poorer PFS. The OS of UCCC patients receiving no postoperative adjuvant therapy or chemotherapy alone were significantly worse. Conclusions The baseline characteristics of UEC and other rare EC types varied greatly, and the prognostic significance of different pathological types on EC patients depended on clinical tumor stages and therapeutic options.

Minmin Wang

This study compares electric field and temperature distributions between non-invasive and invasive tumor treatment fields (TTFields). We employ four-layer spherical head models, representing the scalp, skull, cerebrospinal fluid, and brain, for simulation analysis. Non-invasive TTFields utilize scalp transducers, while invasive methods involve electrode implantation into tumors. Our findings underscore the advantages of invasive TTFields, showcasing their superior tumor-targeting abilities and reduced energy requirements. Furthermore, our analysis of brain tissue temperature changes in response to TTFields indicates that non-invasive TTFields primarily generate heat on the scalp, whereas implantation methods concentrate heat production within tumors, preserving normal brain tissue. In conclusion, invasive TTFields demonstrates potential for precise and effective tumor treatment. Its enhanced targeting capabilities and limited impact on healthy tissue make it a promising avenue for further research in the realm of cancer treatment.

Patrick Diaba-Nuhoho

PHF5A is a member of the zinc-finger proteins. To advance knowledge on their role in carcinogenesis, data from experimental studies, animal models and clinical studies in different tumorigenesis have been reviewed. Furthermore, PHF5A as an oncogenic function, is frequently expressed in tumor cells and a potential prognostic marker for different cancers. PHF5A is implicated in the regulation of cancer cell proliferation, invasion, migration and metastasis. Knockdown of PHF5A prevented the invasion and metastasis of tumor cells. Here, the role of PHF5A in different cancers and their possible mechanism in relation to recent literature is reviewed and discussed. However, there is an open promising perspective to their therapeutic management for different cancer types.

Condori Condori Nelyda Ayde, Mamani Mamani Ilma Magda, Cruz Paredes Soledad Epifania et al.

Abstract Cancer is a tumor that affects people worldwide, with a higher incidence in females but not excluding males. It ranks among the top five deadliest types of cancer, particularly prevalent in less developed countries with deficient healthcare programs. Finding the best algorithm for effective breast cancer prediction with minimal error is crucial. In this scientific article, we employed the SMOTE method in conjunction with the R package Shiny to enhance the algorithms and improve prediction accuracy. We classified the tumor types as benign and malignant (B/M). Various algorithms were analyzed using a Kaggle dataset, and our study identified the superior algorithm as logistic regression. We evaluated algorithm performance using confusion matrices to visualize results and the ROC Curve to obtain a comprehensive measure of performance. Additionally, we calculated precision by dividing the number of correct predictions by the total predictions Keywords Breast cancer, Smote, Benign, Malignant.

Taro Hatsutani, Akimichi Ichinose, Keigo Nakamura et al.

Many renal cancers are incidentally found on non-contrast CT (NCCT) images. On contrast-enhanced CT (CECT) images, most kidney tumors, especially renal cancers, have different intensity values compared to normal tissues. However, on NCCT images, some tumors called isodensity tumors, have similar intensity values to the surrounding normal tissues, and can only be detected through a change in organ shape. Several deep learning methods which segment kidney tumors from CECT images have been proposed and showed promising results. However, these methods fail to capture such changes in organ shape on NCCT images. In this paper, we present a novel framework, which can explicitly capture protruded regions in kidneys to enable a better segmentation of kidney tumors. We created a synthetic mask dataset that simulates a protuberance, and trained a segmentation network to separate the protruded regions from the normal kidney regions. To achieve the segmentation of whole tumors, our framework consists of three networks. The first network is a conventional semantic segmentation network which extracts a kidney region mask and an initial tumor region mask. The second network, which we name protuberance detection network, identifies the protruded regions from the kidney region mask. Given the initial tumor region mask and the protruded region mask, the last network fuses them and predicts the final kidney tumor mask accurately. The proposed method was evaluated on a publicly available KiTS19 dataset, which contains 108 NCCT images, and showed that our method achieved a higher dice score of 0.615 (+0.097) and sensitivity of 0.721 (+0.103) compared to 3D-UNet. To the best of our knowledge, this is the first deep learning method that is specifically designed for kidney tumor segmentation on NCCT images.

Guillermo Lorenzo, Syed Rakin Ahmed, David A. Hormuth et al.

Despite the remarkable advances in cancer diagnosis, treatment, and management that have occurred over the past decade, malignant tumors remain a major public health problem. Further progress in combating cancer may be enabled by personalizing the delivery of therapies according to the predicted response for each individual patient. The design of personalized therapies requires patient-specific information integrated into an appropriate mathematical model of tumor response. A fundamental barrier to realizing this paradigm is the current lack of a rigorous, yet practical, mathematical theory of tumor initiation, development, invasion, and response to therapy. In this review, we begin by providing an overview of different approaches to modeling tumor growth and treatment, including mechanistic as well as data-driven models based on ``big data" and artificial intelligence. Next, we present illustrative examples of mathematical models manifesting their utility and discussing the limitations of stand-alone mechanistic and data-driven models. We further discuss the potential of mechanistic models for not only predicting, but also optimizing response to therapy on a patient-specific basis. We then discuss current efforts and future possibilities to integrate mechanistic and data-driven models. We conclude by proposing five fundamental challenges that must be addressed to fully realize personalized care for cancer patients driven by computational models.

O. V. Feger, R. Yu. Pogorilyak