Improve Cancer Diagnosis Research Articles

Recent and Advanced Trends in Cancer Treatments

Background: Cancer treatment remains a critical area of clinical research, with numerous approaches developed depending on tumor type and stage. Recent advances in genetic and immunotherapy, bioinformatics, and genetic science have revolutionized cancer diagnosis and treatment. Emerging technologies such as gene delivery, oncolytic virotherapy, suicide gene therapy, and CRISPR/Cas9 offer promising therapeutic avenues. Methods: This review provides a detailed analysis of the latest techniques of Gene therapy, artificial intelligence, Nanocarrier Delivery Systems, Immunotherapy, CAR T-Cell Therapy, Epigenetics, Vaccines, and Clinical translation and assessing their therapeutic potential in cancer treatment. A review of early critical studies focused on the integration of immunotherapy, nanotechnology, and artificial intelligence (AI) in cancer therapies with emphasis on targeted delivery systems and precision medicine. Results: The review highlights the synergistic effects of combining targeted therapies with immunotherapy, particularly immune checkpoint inhibitors and CAR-T cell therapy. Therapies such as CRISPR/Cas9 demonstrate significant potential in cancer targeting, while advancements in nanocarrier delivery systems offer enhanced precision with reduced side effects. AI's role in improving cancer diagnosis and personalized treatment is also underscored. Conclusion: This comprehensive analysis of recent therapeutic approaches and technological advancements addresses gaps in previous reviews and offers updated insights into cutting-edge cancer treatments. The review emphasizes the evolving role of immunotherapy, nanotechnology, AI, and nanotechnology, providing clinicians and researchers with the most current and relevant information for optimizing cancer treatment strategies.

Heterojunction semiconductor nanocatalysts as cancer theranostics.

Cancer nanotechnology is a promising area of cross-disciplinary research aiming to develop facile, effective, and noninvasive strategies to improve cancer diagnosis and treatment. Catalytic therapy based on exogenous stimulus-responsive semiconductor nanomaterials has shown its potential to address the challenges under the most global medical needs. Semiconductor nanocatalytic therapy is usually triggered by the catalytic action of hot electrons and holes during local redox reactions within the tumor, which represent the response of nontoxic semiconductor nanocatalysts to pertinent internal or external stimuli. However, careful architecture design of semiconductor nanocatalysts has been the major focus since the catalytic efficiency is often limited by facile hot electron/hole recombination. Addressing these challenges is vital for the progress of cancer catalytic therapy. In recent years, diverse strategies have been developed, with heterojunctions emerging as a prominent and extensively explored method. The efficiency of charge separation under exogenous stimulation can be heightened by manipulating the semiconducting performance of materials through heterojunction structures, thereby enhancing catalytic capabilities. This review summarizes the recent applications of exogenous stimulus-responsive semiconducting nanoheterojunctions for cancer theranostics. The first part of the review outlines the construction of different heterojunction types. The next section summarizes recent designs, properties, and catalytic mechanisms of various semiconductor heterojunctions in tumor therapy. The review concludes by discussing the challenges and providing insights into their prospects within this dynamic and continuously evolving field of research.

DeePathNet: a transformer-based deep learning model integrating multi-omic data with cancer pathways.

Multi-omic data analysis incorporating machine learning has the potential to significantly improve cancer diagnosis and prognosis. Traditional machine learning methods are usually limited to omic measurements, omitting existing domain knowledge, such as the biological networks that link molecular entities in various omic data types. Here we develop a Transformer-based explainable deep learning model, DeePathNet, which integrates cancer-specific pathway information into multi-omic data analysis. Using a variety of big datasets, including ProCan-DepMapSanger, CCLE, and TCGA, we demonstrate and validate that DeePathNet outperforms traditional methods for predicting drug response and classifying cancer type and subtype. Combining biomedical knowledge and state-of-the-art deep learning methods, DeePathNet enables biomarker discovery at the pathway level, maximizing the power of data-driven approaches to cancer research. DeePathNet is available on GitHub at https://github.com/CMRI-ProCan/DeePathNet.

AI in Healthcare: Breaking New Ground in the Management and Treatment of Cancer

Artificial intelligence (AI) is revolutionizing cancer treatment by enhancing patient management, diagnosis, and therapy. Through advanced AI algorithms, early diagnosis of tumors is made more accurate by detecting subtle abnormalities that might be missed by the human eye. This early detection is critical for successful treatment and better patient outcomes. The objective of this research is to evaluate the impact of AI on improving cancer diagnosis, treatment customization, and drug development processes. The findings reveal that AI significantly accelerates the drug discovery process by analyzing large datasets to identify potential candidates, thus reducing the time and costs associated with developing new treatments. Furthermore, AI enhances clinical trials by improving patient recruitment and optimizing trial design, leading to higher success rates. AI-driven telemedicine solutions also help bridge healthcare gaps in underserved areas, ensuring more equitable access to cancer treatment. The research’s implications suggest that, despite challenges such as data security and the need for improved infrastructure, AI holds great potential to further individualize, streamline, and expand the availability of cancer care. Future advancements are likely to make cancer treatment even more precise, effective, and accessible worldwide.

A comparative performance assessment of artificial intelligence based classifiers and optimized feature reduction technique for breast cancer diagnosis

Breast cancer (BC) is a catastrophic global health concern that causes numerous fatalities worldwide. Early detection of breast cancer may mitigate death rates; however, the prevailing diagnostic procedure for the malignancy necessitates numerous multifaceted laboratory tests that must be performed by medical professionals. In this article machine learning, a branch of Artificial Intelligence (AI), has been employed to improve cancer diagnosis, prognoses and survival rates while reducing the vulnerability of humans. Support Vector Machine (SVM), K-nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF) and Grey Wolf Optimizer (GWO) are implemented to prognosticate breast cancer. Comprehensive insights into the efficacy of these approaches for breast cancer prognosis are provided by the performance assessment that is accomplished using the confusion matrix, Receiver Operating Characteristic (ROC) curves and parallel coordinate plots. Both UCI (University of California Irvine) and SEER (Surveillance, Epidemiology and End Results) datasets have been utilized to confirm the investigation's findings and ensure their generalizability across diverse data sources. The results conclusively demonstrate that SVM is the cohort's most accurate classifier. With a stupendous accuracy rate of 99.1 %, the GWO-SVM compares favorably to all other algorithms. Furthermore, feature reduction approaches such as Minimum Redundancy Maximum Relevance (mRMR), ReliefF and Principal Component Analysis (PCA) are utilized. ReliefF has demonstrated exceptional effectiveness with a maximum accuracy of 98.2 %.

Artificial Intelligence in Cancer Research: Predictive Modeling of Angiogenesis and Biomarker Discovery

Background: The integration of Artificial Intelligence (AI) in cancer research has dramatically enhanced the study, diagnosis, and treatment of cancer. AI’s advanced algorithms, especially recurrent neural networks (RNNs), have proven effective in analyzing complex datasets, facilitating novel biomarker discovery, and improving cancer diagnostics and prognostics. Angiogenesis, the process of new blood vessel formation, plays a crucial role in tumor growth and metastasis, making it a promising target for therapeutic strategies. This study explores the use of AI to identify angiogenesis-related biomarkers and develop personalized treatment strategies. Methods: This study utilized a large dataset from The Cancer Genome Atlas (TCGA), encompassing over 20,000 primary tumor and normal samples across 33 cancer types. Preprocessing techniques such as data cleaning, normalization, and outlier detection were applied. Dimensionality reduction through Principal Component Analysis (PCA) and data visualization using t-Distributed Stochastic Neighbor Embedding (t-SNE) were employed. A Recurrent Neural Network (RNN) was chosen to analyze the sequential biological data and identify potential biomarkers related to angiogenesis. Results: The AI model demonstrated excellent performance across multiple evaluation metrics, including accuracy (0.85), precision (0.82), recall (0.88), F1-score (0.85), and AUC-ROC (0.92), highlighting its effectiveness in predicting cancer progression and identifying key biomarkers. The RNN model was particularly adept at identifying complex patterns in angiogenesis data, facilitating a deeper understanding of tumor biology and revealing novel therapeutic targets. Conclusion: The results underscore the significant potential of AI, specifically RNNs, in advancing cancer research and personalized treatment planning. AI-driven insights into angiogenesis-related biomarkers enable targeted therapies, offering new avenues for effective cancer treatment. These findings not only improve cancer diagnosis and prognosis but also emphasize the role of AI in developing precision oncology approaches, enhancing patient outcomes, and guiding future research in cancer therapeutics.

ADVANCING SKIN CANCER DETECTION USING MULTIMODAL DATA FUSION AND AI TECHNIQUES

Cancer remains a leading cause of death worldwide, driving the need for continuous advancements in early detection and treatment. Deep learning, a subset of artificial intelligence, has become a transformative tool in medical image analysis, significantly improving cancer diagnosis. This study explores various modalities used in lung cancer diagnosis, including medical imaging (e.g., radiology, pathology), genomics, and clinical data, addressing the specific challenges of each domain. The proposed Multimodal Fusion Deep Neural Network (MFDNN) effectively integrates these diverse data sources to enhance diagnostic accuracy. Additionally, it emphasizes the integration of clinical data and electronic health records, demonstrating the value of multimodal approaches for improving reliability in lung cancer diagnosis. Ethical considerations related to AI in clinical settings, along with the need for validation and regulatory guidelines, are also discussed.

Recent advances in label-free imaging techniques based on nonlinear optical microscopy to reveal the heterogeneity of the tumor microenvironment.

The tumor microenvironment (TME) is a complex and dynamic network that significantly influences cancer progression. Understanding its intricate components, including the extracellular matrix (ECM), stromal cells, immune cells, and vascular endothelial cells, is crucial for developing effective cancer therapies. Conventional diagnostic methods, while essential, have limitations in sensitivity, specificity, and invasiveness. Label-free multimodal nonlinear optical (MNLO) microscopy offers a promising alternative, enabling detailed imaging without external labels. Techniques such as second harmonic generation (SHG), third harmonic generation (THG), coherent anti-Stokes Raman scattering (CARS), and two-photon fluorescence (TPF) provide complementary insights into the TME. SHG is particularly effective for imaging collagen fibers, while CARS highlights lipid-rich structures, and THG and TPF offer high-resolution imaging of cellular and subcellular structures. These modalities reveal crucial information about tumor progression, including changes in collagen organization and lipid metabolism, and allow for the study of cellular interactions and ECM remodeling. Multimodal setups, combining SHG, CARS, THG, and TPF, enable comprehensive analysis of the TME, facilitating the identification of early-stage cancerous changes and tracking of tumor progression. Despite the advantages of MNLO microscopy, such as reduced photodamage and the ability to image live tissues, challenges remain, including the complexity and cost of the setups. Addressing these challenges through technological advancements and optimization can enhance the applicability of MNLO microscopy in clinical diagnostics and cancer research, ultimately contributing to improved cancer diagnosis, prognosis, and treatment strategies.

A novel pipeline employing deep multi-attention channels network for the autonomous detection of metastasizing cells through fluorescence microscopy

Metastasis driven by cancer cell migration is the leading cause of cancer-related deaths. It involves significant changes in the organization of the cytoskeleton, which includes the actin microfilaments and the vimentin intermediate filaments. Understanding how these filament change cells from normal to invasive offers insights that can be used to improve cancer diagnosis and therapy. We have developed a computational, transparent, large-scale and imaging-based pipeline, that can distinguish between normal human cells and their isogenically matched, oncogenically transformed, invasive and metastasizing counterparts, based on the spatial organization of actin and vimentin filaments in the cell cytoplasm. Due to the intricacy of these subcellular structures, manual annotation is not trivial to automate. We used established deep learning methods and our new multi-attention channel architecture. To ensure a high level of interpretability of the network, which is crucial for the application area, we developed an interpretable global explainable approach correlating the weighted geometric mean of the total cell images and their local GradCam scores. The methods offer detailed, objective and measurable understanding of how different components of the cytoskeleton contribute to metastasis, insights that can be used for future development of novel diagnostic tools, such as a nanometer level, vimentin filament-based biomarker for digital pathology, and for new treatments that significantly can increase patient survival.

Evaluation of tumor budding with virtual panCK stains generated by novel multi-model CNN framework

As the global incidence of cancer continues to rise rapidly, the need for swift and precise diagnoses has become increasingly pressing. Pathologists commonly rely on H&E-panCK stain pairs for various aspects of cancer diagnosis, including the detection of occult tumor cells and the evaluation of tumor budding. Nevertheless, conventional chemical staining methods suffer from notable drawbacks, such as time-intensive processes and irreversible staining outcomes. The virtual stain technique, leveraging generative adversarial network (GAN), has emerged as a promising alternative to chemical stains. This approach aims to transform biopsy scans (often H&E) into other stain types. Despite achieving notable progress in recent years, current state-of-the-art virtual staining models confront challenges that hinder their efficacy, particularly in achieving accurate staining outcomes under specific conditions. These limitations have impeded the practical integration of virtual staining into diagnostic practices. To address the goal of producing virtual panCK stains capable of replacing chemical panCK, we propose an innovative multi-model framework. Our approach involves employing a combination of Mask-RCNN (for cell segmentation) and GAN models to extract cytokeratin distribution from chemical H&E images. Additionally, we introduce a tailored dynamic GAN model to convert H&E images into virtual panCK stains, integrating the derived cytokeratin distribution. Our framework is motivated by the fact that the unique pattern of the panCK is derived from cytokeratin distribution. As a proof of concept, we employ our virtual panCK stains to evaluate tumor budding in 45 H&E whole-slide images taken from breast cancer-invaded lymph nodes . Through thorough validation by both pathologists and the QuPath software, our virtual panCK stains demonstrate a remarkable level of accuracy. In stark contrast, the accuracy of state-of-the-art single cycleGAN virtual panCK stains is negligible. To our best knowledge, this is the first instance of a multi-model virtual panCK framework and the utilization of virtual panCK for tumor budding assessment. Our framework excels in generating dependable virtual panCK stains with significantly improved efficiency, thereby considerably reducing turnaround times in diagnosis. Furthermore, its outcomes are easily comprehensible even to pathologists who may not be well-versed in computer technology. We firmly believe that our framework has the potential to advance the field of virtual stain, thereby making significant strides towards improved cancer diagnosis.

A Genomics-Driven Artificial Intelligence-Based Model Classifies Breast Invasive Lobular Carcinoma and Discovers CDH1 Inactivating Mechanisms.

Artificial intelligence (AI) systems can improve cancer diagnosis, yet their development often relies on subjective histologic features as ground truth for training. Herein, we developed an AI model applied to histologic whole-slide images using CDH1 biallelic mutations, pathognomonic for invasive lobular carcinoma (ILC) in breast neoplasms, as ground truth. The model accurately predicted CDH1 biallelic mutations (accuracy = 0.95) and diagnosed ILC (accuracy = 0.96). A total of 74% of samples classified by the AI model as having CDH1 biallelic mutations but lacking these alterations displayed alternative CDH1 inactivating mechanisms, including a deleterious CDH1 fusion gene and noncoding CDH1 genetic alterations. Analysis of internal and external validation cohorts demonstrated 0.95 and 0.89 accuracy for ILC diagnosis, respectively. The latent features of the AI model correlated with human-explainable histopathologic features. Taken together, this study reports the construction of an AI algorithm trained using a genetic rather than histologic ground truth that can robustly classify ILCs and uncover CDH1 inactivating mechanisms, providing the basis for orthogonal ground truth utilization for development of diagnostic AI models applied to whole-slide image. Significance: Genetic alterations linked to strong genotypic-phenotypic correlations can be utilized to develop AI systems applied to pathology that facilitate cancer diagnosis and biologic discoveries.

Categorizing Dermatological Malignancies Via Computational Methods

In this study, a machine learning model is developed to classify different types of cancer using convolutional neural networks (CNNs) for image processing. The core objective is to achieve a performance level comparable to that of dermatologists. The model is trained on a substantial dataset of medical images, enabling it to learn and recognize various characteristics indicative of different cancer types. By leveraging the power of CNNs, the model can process these images effectively, identifying subtle patterns and features that are often challenging to detect with the naked eye. The training process involves feeding the CNN with labelled images, enabling it to differentiate between benign and malignant cases with high accuracy. Through rigorous testing, the model demonstrates competence on par with experienced dermatologists, both in terms of sensitivity and specificity. This equivalence in performance is particularly significant as it underscores the model's potential to aid in clinical settings, providing reliable second opinions and enhancing diagnostic workflows. A user interface is also developed to allow input images to be analysed by the trained CNN model. This interface not only displays the model’s predictions but also provides essential metrics such as confidence scores and probability distributions. These metrics offer valuable insights into the model's decision-making process, aiding clinicians in understanding and trusting the AI's assessments. Overall, the findings suggest that convolutional neural networks hold substantial promise for improving cancer diagnosis. The model's high performance in classification tasks demonstrates its viability as a tool for supporting dermatologists in clinical practice. By reducing diagnostic errors and accelerating the identification process, this technology has the potential to significantly impact patient outcomes and advance the field of medical imaging and diagnostics. Keywords: Convolutional Neural Networks (CNNs); Cancer Classification; Medical Image Processing; Dermatology AI; Diagnostic Accuracy

Enhancing cancer detection through AI-driven high content analysis of circulating tumor cells.

3054 Background: The advancements in automated High Content Analysis (HCA) for Circulating Tumor Cells (CTCs) detection necessitate the integration of high-throughput screening (HTS) and Artificial Intelligence (AI) to improve cancer diagnosis efficiency and accuracy. Traditional approaches to cancer detection have faced limitations in speed, cost, and analysis depth, driving the need for innovative solutions in assay development and execution. Methods: We obtained peripheral blood from 150 asymptomatic individuals and 63 newly diagnosed cases of solid organ cancers including Lung, Breast, Head and Neck, Colorectal, Pancreas, Esophagus, Gynecologic cancers. We used differential apoptosis based negative enrichment technique and HCS fluorescent imaging for identification of CTCs and CTC like immune cells from the relevant blood samples. We devised AutoML algorithms which were trained on a cohort of 4,135 cropped region of interest (ROI) images of true CTCs and CTC-mimicking immune cells. These images were annotated with the coordinates of the top-left and bottom-right corners of rectangles to specify ROIs. This method employs a combination of automated sample processing, integration with the Laboratory Information Management System (LIMS) integration, digital filtration, and decision matrix algorithms for sample classification and smooth data flow. The image quality criteria were established prior to dataset analysis. The algorithms underwent training, testing, and validation based on expert recommendations, with dataset splitting of 80% for training, 10% for testing, and 10% for validation phases. Results: The automated deep learning model achieved remarkable performance metrics, presenting an accuracy of 96.66% (95% CI, 96.07%-97.19%), a specificity of 95.34% (95% CI, 94.37%-96.18%), and a sensitivity of 98.14% (95% CI, 97.44%-98.69%) in detecting true CTCs. Additional analysis included the area under the curve and confusion matrix evaluations, indicating the model's robustness in distinguishing between true positive and true negative specimens. This efficiency and precision in data handling, processing, and analysis demonstrate significant advancements in HCA screening, offering enhanced assay development, execution flexibility, and the facilitation of detailed cell-by-cell analysis for cancer detection from a large set of Peripheral Blood Mononuclear Cells (PBMCs) from samples obtained for screening or diagnosis. Conclusions: This study successfully evaluated a deep learning model for the detection of circulating tumor cells (CTCs) in peripheral blood mononuclear cells (PBMCs) using image data from HTS platform. The model achieved superior performance, demonstrating its potential for cancer detection from blood samples.

Evaluating the Efficacy and Accuracy of AI-Assisted Diagnostic Techniques in Endometrial Carcinoma: A Systematic Review.

Diagnosing endometrial carcinoma correctly is essential for appropriate treatment, as it is a major health risk.As machine learning (ML) and artificial intelligence (AI) have grown in popularity, so has interest in their potential to improve cancer diagnosis accuracy.In the context of endometrial cancer, this study attempts to examine the efficacy as well as the accuracy of AI-assisted diagnostic approaches. Additionally, it aims to methodically evaluate the contribution of AI and ML techniques to the improvement of endometrial cancer diagnosis. Following PRISMA guidelines, we performed a thorough search of numerous databases, including Medline via Ovid, PubMed, Scopus, Web of Science, and Google Scholar. Ten years were searched, encompassing both basic and advanced research. Peer-reviewed papers and original research studies that explicitly looked at the application of AI/ML in endometrial cancer diagnosis were the main targets of the well-defined selection criteria. Using the Critical Appraisal Skills Programme (CASP) methodology, two independent researchers conducted a thorough screening process and quality assessment of included studies. The review found a notable inclination towards the effective use of AI in endometrial carcinoma diagnostics, namely in the identification and categorization of endometrial cancer.Artificial intelligence models, particularly Convolutional Neural Networks (CNNs) and deep learning algorithms have shown remarkable precision in detecting endometrial cancer. They frequently achieve or even exceed the diagnostic proficiency of human specialists.The use of artificial intelligence in medical diagnostics signifies revolutionary progress in the field of oncology.AI-assisted diagnostic tools have demonstrated the potential to improve the precision and effectiveness of cancer diagnosis, namely in cases of endometrial carcinoma.This innovation not only enhances the quality of patient care but also indicates a transition towards more individualized and efficient treatment approaches in the field of oncology. The advancement of AI technology is expected to play a crucial role in medical diagnostics, particularly in the field of cancer detection and treatment, perhaps leading to a significant transformation in the approach to these areas.

Recent Advances and Clinical Approach to Cancer Treatment with Nanotechnology Derived Biomolecule.

Cancer nanomedicine has the potential to take advantage of the multifunctionality and diverse biological activity of nanostructures based on biomolecules. Novel drug delivery vehicles can be designed by programming the supramolecular features of biomolecules to achieve multiple therapeutic goals at once, including efficient in vivo transport and targeted drug administration. Proteins, peptides, nucleic acids, and polysaccharides can all be engineered into multipurpose nanomedicines. Even while numerous cancer medications reduce mortality, they are still insufficient. Early cancer cell detection and high-specificity therapeutic administration optimise treatment and prevent toxicity. Nanotechnology is improving cancer diagnosis and treatment due to increased systemic toxicity and refractoriness with current methods. Nanotechnology-based immunotherapeutic drugs have reduced cancer cell invasiveness while protecting healthy cells in several cancer types. Carbon nanotubes, polymeric micelles, and liposomes improve cancer medication pharmacokinetics and pharmacodynamics. Nanomedicines' use in patient care and promising nanotechnology-based cancer interventions have been covered in this article. Nanomaterials used in treating cancer have been discussed. Additionally, nanomaterial obstacles that hinder their applicability and clinical translation in certain cancer types are addressed.

Undetectable circulating tumor DNA confirms the inability of pseudomyxoma peritonei to systemic dissemination

The study of circulating tumor DNA (ctDNA) plays a pivotal role in advancing precision oncology, providing valuable information for individualized patient care and contributing to the ongoing effort to improve cancer diagnosis, treatment, and management. However, its applicability in pseudomyxoma peritonei (PMP) remains unexplored. In this multicenter retrospective study involving 21 PMP patients, we investigated ctDNA presence in peripheral blood using three distinct methodologies. Despite mucinous tumor tissues exhibiting KRAS and GNAS mutations, ctDNA for these mutations was undetectable in blood samples. In this pilot study, circulating tumor DNA was not detected in blood when the tumor harbored mutations of known significance. In the future, a study with a larger sample size is needed to confirm these findings and to determine whether ctDNA could identify patients at risk for early recurrence and/or systemic metastases.

Trends in incidence and survival of childhood cancers in Khon Kaen, Thailand (2000–2019): a population-based Khon Kaen Cancer Registry study

BackgroundIn Thailand, the national health care system and nationwide standard treatment protocols have evolved over time, potentially influencing the trends in the incidence and survival rates of childhood cancers. However, further investigations are required to comprehensively study these trends in Khon Kaen, Thailand.MethodsChildhood cancer patients aged 0–14 years (n = 541) who were diagnosed with one of the five most common cancers between 2000 and 2019 from the population-based Khon Kaen Cancer Registry were enrolled. Descriptive statistics were used to analyse the demographic data, which are presented as numbers, percentages, means, and standard deviations. The trends in incidence between 2000 and 2019, including age-standardized incidence rates (ASRs) and annual percent changes (APCs), were analysed using the Joinpoint regression model. Survival analysis was performed for 5-year relative survival rates (RSRs) according to the Pohar Perme estimator and Kaplan–Meier survival curves.ResultsThe ASRs of the overall top 5 childhood cancer groups were 67.96 and 106.12 per million person-years in 2000 and 2019, respectively. Overall, the APC significantly increased by 2.37% each year for both sexes. The overall 5-year RSRs were 60.5% for both sexes, 58.2% for males, and 63.9% for females. The highest 5-year RSR was for germ cell tumours (84.3%), whereas the lowest 5-year RSR was for neuroblastoma (29.1%).ConclusionsThe incidence and survival rates of childhood cancers in Khon Kaen, Thailand, varied according to sex. The incidence trends increased over time, meanwhile, the relative survival rates rose to satisfactory levels and were comparable to those of other nations with similar financial status. The implementation of national health policies and adherence to national treatment guidelines have improved cancer diagnosis and treatment outcomes.

Abstract PO4-20-09: Successful outcome of locally advanced HR+HER2+ breast cancer treatment in a young female after pancreas-kidney transplantation. 3-year follow-up

Abstract Background Solid organs recipients with subsequent cancer comprise a group of patients with unmet medical needs: they lack any clinical trials or guidelines for treatment. There are only individual case reports in literature. Meanwhile their number is growing due to achievements in transplantology and improved cancer diagnosis. Case presentation А young 34-year-old female attended our center in September 2019 with a palpable mass and peau d'orange of the left breast. A core-needle biopsy of the left breast mass revealed invasive ductal carcinoma G3, estrogen receptor 7 (Allred), progesterone receptor 6 (Allred), HER-2 (3+), Ki-67 49%. Left axillary lymph node biopsy revealed metastatic breast cancer. After a complete examination the clinical stage was cT4bN1fM0, IIIB stage. The patient had a history of Type 1 diabetes mellitus since 2003 leading to multiple complications including terminal diabetic nephropathy, which required renal replacement therapy with the use of long-term hemodialysis since July 2014. The other complications consisted of severe retinopathy with corneal transplantation on the left eye in April 2013, an episode of right eye hemophthalmia in March 2016 with consequent loss of vision in the right eye, polyneuropathy, gastropathy and enteropathy. The patient underwent a simultaneous pancreas-kidney transplantation in April, 2016 and was on permanent immunosuppressive therapy with tacrolimus 8 mg daily and methylprednisolone 8 mg daily. The function of both transplants was satisfactory. This unique case was published by Pinchuk A. et al. in Transplant Proceedings, 2017 [doi: 10.1016/j.transproceed.2017.10.005]. A multidisciplinary approach was applied to tailoring treatment plan for this patient. Initially immunosuppressive therapy was modified: the patient discontinued methylprednisolone and started everolimus with simultaneous tacrolimus dose reduction (their doses adjusted according to blood concentrations). The tumor board decision was to start neoadjuvant therapy with regimen with the mildest and the most manageable toxicity profile and to avoid anthracyclines. From October to December 2019 the patient received 12 cycles of paclitaxel 80 mg/m2 day 1 weekly and 4 cycles of anti-HER2 dual blockade: trastuzumab 8 mg/kg day 1 followed by 6 mg/kg day 1 every 21 days + pertuzumab 840 mg day 1 followed by 420 mg day 1 every 21 days. Adverse events were: stomatitis grade 1, palmar-plantar erythrodysesthesia grade 1, diarrhea grade 2. Partial response was evaluated in the end of December 2019, but due to persistent skin edema, she was not a candidate for surgical treatment. The tumor board decision was to proceed with T-DM1 + pertuzumab based on the results of the KRISTINE trial [doi:10.1016/s1470-2045(17)30716-7]. From January to March 2020 the patient received 4 cycles of trastuzumab-emtansine 3,6 mg/kg day 1 every 21 days + pertuzumab 420 mg day 1 every 21 days. The patient tolerated this treatment with mild toxicity: ALT & AST increase grade 2 and diarrhea grade 2. Considering that the edema was significantly reduced, surgical treatment was planned. The patient underwent a modified radical mastectomy for left breast cancer on 14 of April 2020. The pathological stage was ypT1аN0 R0, RCB I. The patient continued trastuzumab emtansine until November 2020 (up to 1 year of anti-HER2 targeted therapy) in the adjuvant setting. In June 2020 she underwent locoregional radiation therapy. Tamoxifen with ovarian function suppression (LHRH agonists) for 5 years was started in June 2020. Fortunately, after 3 years of follow-up after surgery there is no evidence of disease and no delayed cancer treatment complications. Conclusion: Personalized multidisciplinary team decisions for cancer patients after organ transplantation are crucial to further improve the long-term outcome of these patients. Citation Format: Lyudmila Zhukova, Natalya Polshina. Successful outcome of locally advanced HR+HER2+ breast cancer treatment in a young female after pancreas-kidney transplantation. 3-year follow-up [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO4-20-09.

Digital Pathology for Better Clinical Practice.

(1) Background: Digital pathology (DP) is transforming the landscape of clinical practice, offering a revolutionary approach to traditional pathology analysis and diagnosis. (2) Methods: This innovative technology involves the digitization of traditional glass slides which enables pathologists to access, analyze, and share high-resolution whole-slide images (WSI) of tissue specimens in a digital format. By integrating cutting-edge imaging technology with advanced software, DP promises to enhance clinical practice in numerous ways. DP not only improves quality assurance and standardization but also allows remote collaboration among experts for a more accurate diagnosis. Artificial intelligence (AI) in pathology significantly improves cancer diagnosis, classification, and prognosis by automating various tasks. It also enhances the spatial analysis of tumor microenvironment (TME) and enables the discovery of new biomarkers, advancing their translation for therapeutic applications. (3) Results: The AI-driven immune assays, Immunoscore (IS) and Immunoscore-Immune Checkpoint (IS-IC), have emerged as powerful tools for improving cancer diagnosis, prognosis, and treatment selection by assessing the tumor immune contexture in cancer patients. Digital IS quantitative assessment performed on hematoxylin-eosin (H&E) and CD3+/CD8+ stained slides from colon cancer patients has proven to be more reproducible, concordant, and reliable than expert pathologists' evaluation of immune response. Outperforming traditional staging systems, IS demonstrated robust potential to enhance treatment efficiency in clinical practice, ultimately advancing cancer patient care. Certainly, addressing the challenges DP has encountered is essential to ensure its successful integration into clinical guidelines and its implementation into clinical use. (4) Conclusion: The ongoing progress in DP holds the potential to revolutionize pathology practices, emphasizing the need to incorporate powerful AI technologies, including IS, into clinical settings to enhance personalized cancer therapy.

Factors Contributing to the Accuracy of PET Scans in Detecting Cancer Metastases in Cairo Hospitals, Egypt

Introduction: Positron emission tomography (PET) has become an important diagnostic tool in oncology, providing metabolic information that can aid in the detection and evaluation of cancer. However, the accuracy of PET scans in detecting cancer metastases can be influenced by various factors, including the type of cancer, location of metastases, and image acquisition protocol. This study aims to evaluate the factors that influence the accuracy of PET scans in detecting cancer metastases in patients at Cairo Hospital, Egypt.
 Methods: Patient data were collected retrospectively. A total of 5000 research subjects participated in this study. Data were analyzed to identify factors associated with false-positive or false-negative PET scan results.
 Results: Patients with lung or colorectal cancer were 2.45 times more likely to experience accurate positive PET scan results than patients with other types of cancer. Patients with metastases in lymph nodes were 1.93 times more likely to experience accurate positive PET scan results than patients with metastases in solid organs. Patients with a long PET scan image acquisition protocol were 1.78 times more likely to experience accurate positive PET scan results than patients with a short image acquisition protocol.
 Conclusion: PET scan is a valuable diagnostic tool in oncology, but its accuracy in detecting cancer metastases can be influenced by various factors. These factors should be considered when interpreting PET scan results and to improve cancer diagnosis and management.