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

A. Brawanski, Th. Schaffer, F. Raab et al.

Accurate identification of non-enhancing hypercellular (NEH) tumor regions is an unmet need in neuro-oncological imaging, with significant implications for patient management and treatment planning. We present a robust computational framework that generates probability maps of NEH regions from routine MRI data, leveraging multiple network architectures to address the inherent variability and lack of clear imaging boundaries. Our approach was validated against independent clinical markers -- relative cerebral blood volume (rCBV) and enhancing tumor recurrence location (ETRL) -- demonstrating both methodological robustness and biological relevance. This framework enables reliable, non-invasive mapping of NEH tumor compartments, supporting their integration as imaging biomarkers in clinical workflows and advancing precision oncology for brain tumor patients.

Dexuan He, Xiao Zhou, Wenbin Guan et al.

Rare cancers comprise 20-25% of all malignancies but face major diagnostic challenges due to limited expert availability-especially in pediatric oncology, where they represent over 70% of cases. While pathology vision-language (VL) foundation models show promising zero-shot capabilities for common cancer subtyping, their clinical performance for rare cancers remains limited. Existing multi-instance learning (MIL) methods rely only on visual features, overlooking cross-modal knowledge and compromising interpretability critical for rare cancer diagnosis. To address this limitation, we propose PathPT, a novel framework that fully exploits the potential of vision-language pathology foundation models through spatially-aware visual aggregation and task-specific prompt tuning. Unlike conventional MIL, PathPT converts WSI-level supervision into fine-grained tile-level guidance by leveraging the zero-shot capabilities of VL models, thereby preserving localization on cancerous regions and enabling cross-modal reasoning through prompts aligned with histopathological semantics. We benchmark PathPT on eight rare cancer datasets(four adult and four pediatric) spanning 56 subtypes and 2,910 WSIs, as well as three common cancer datasets, evaluating four state-of-the-art VL models and four MIL frameworks under three few-shot settings. Results show that PathPT consistently delivers superior performance, achieving substantial gains in subtyping accuracy and cancerous region grounding ability. This work advances AI-assisted diagnosis for rare cancers, offering a scalable solution for improving subtyping accuracy in settings with limited access to specialized expertise.

Elena Mulero Ayllón, Massimiliano Mantegna, Linlin Shen et al.

Accurate lung tumor segmentation is crucial for improving diagnosis, treatment planning, and patient outcomes in oncology. However, the complexity of tumor morphology, size, and location poses significant challenges for automated segmentation. This study presents a comprehensive benchmarking analysis of deep learning-based segmentation models, comparing traditional architectures such as U-Net and DeepLabV3, self-configuring models like nnUNet, and foundation models like MedSAM, and MedSAM~2. Evaluating performance across two lung tumor segmentation datasets, we assess segmentation accuracy and computational efficiency under various learning paradigms, including few-shot learning and fine-tuning. The results reveal that while traditional models struggle with tumor delineation, foundation models, particularly MedSAM~2, outperform them in both accuracy and computational efficiency. These findings underscore the potential of foundation models for lung tumor segmentation, highlighting their applicability in improving clinical workflows and patient outcomes.

C. Metz, S. Veldhoen, H. E. Deubzer et al.

Objectives: Magnetic resonance elastography (MRE) is a noninvasive technique for assessing the viscoelastic properties of soft biological tissues in vivo, with potential relevance for pediatric tumor evaluation. This study aimed to evaluate the feasibility of multifrequency MRE in children with solid tumors and to report initial findings on stiffness and fluidity across rare pediatric tumor entities. Additionally, the potential of viscoelastic properties as biomarkers of tumor malignancy was explored. Materials and Methods: Ten pediatric patients (mean age, 5.7 +/- 4.8 years; four female) with extracranial solid tumors underwent multifrequency MRE. Shear waves at 30 - 70 Hz were subsequently generated and measured with a phase-sensitive single-shot spin-echo planar imaging sequence. The obtained shear wave fields were processed by wavenumber (k-)based multi-frequency inversion to reconstruct tumor stiffness and fluidity. The viscoelastic properties within the tumors were quantified and correlated with the apparent diffusion coefficient (ADC). In addition, differences in stiffness and fluidity were assessed across the histopathologically confirmed tumor entities, which were stratified into malignancy-based groups. Results: MRE was successfully performed in all patients in under five minutes. Differences in viscoelastic properties were observed among tumor entities: Stiffness, fluidity, and their spatial variability increased significantly with tumor malignancy. Furthermore, a significant inverse correlation was observed between stiffness and tumor ADC values. Conclusion: Multifrequency MRE was feasible in pediatric MRI and provided insight into tumor biomechanics. Preliminary data revealed differences in stiffness and fluidity across pediatric solid tumors correlating with malignancy. MRE holds promise for diagnosis and classification of pediatric tumor entities and their malignancy.

Mingxing Chen, Jiangxi Li, Wei Su et al.

ABSTRACT Background The aim of this study was to estimate the global burden of lip and oral cavity cancer (LOC) and its trends in different genders, age groups, regions, and countries globally. Methods Data were sourced from the Global Burden of Disease 2021 study. Results During the 32‐year period, a 92.92% and 113.94% increase was estimated in the absolute counts of LOC deaths and disability‐adjusted life years (DALYs), respectively. Throughout the 32‐year period, males exhibited higher age‐standardized rates (ASRs) of incidence (ASIRs), prevalence (ASPRs), mortality (ASMRs), and DALYs (ASDRs) related to LOC. The age group of 60–64 years consistently recorded the highest numbers of new and prevalent cases across the years 1990, 2019, and 2021. In 2019 and 2021, the highest ASMR and ASDR were observed in individuals aged 95 years and older. Regions with low‐middle and low socio‐demographic index (SDI) consistently showed higher ASMRs and ASDRs associated with LOC from 1990 to 2021. Eastern Europe, South, North, and Southeast Asia exhibited a concentration of countries with higher ASIRs, ASPRs, ASMRs, and ASDRs in 2021. South Asia maintained high levels of ASIRs, ASPRs, ASMRs, and ASDRs in 2021. In 2021, Palau recorded the highest ASIR, ASPR, ASMR, and ASDR, followed by Pakistan. Projections indicate that ASIR, ASPR, ASMR, and ASDR are expected to increase by 7.40%, 10.10%, 2.85%, and 4.60%, respectively, from 2021 to 2040. Conclusion LOC remains a critical public health concern that requires immediate attention, particularly among certain demographics such as males, aged 60–64 or 95 and older, as well as in low‐ and middle‐SDI regions, particularly Eastern Europe, South Asia (notably Pakistan), North Asia, and Southeast Asia.

James Edward Mensah, Evans Akpakli, Mathew Kyei et al.

Purpose of the study: This study aims to determine the role of serum prostate-specific antigen (PSA) levels and digital rectal examination (DRE) in predicting the histological outcomes of prostate biopsies by analyzing a database of over 7000 patients who underwent transrectal ultrasound (TRUS)-guided prostate biopsies. Methods: We conducted a retrospective analysis of men who underwent TRUS-guided prostate biopsies at Korle Bu Teaching Hospital, a tertiary referral center in Accra, Ghana, from July 2005 to December 2022. The biopsies, which included 10 to 12 core samples, were prompted by PSA levels greater than 4.0 ng/mL, abnormal DRE findings, or both. We then correlated histopathology results with PSA and DRE findings. Results: Out of 7,338 patients who presented for biopsy, 76.3% were between the ages of 60 and 79. Histology reports were available for 5,289 patients, of whom 2,564 (48.5%) were diagnosed with prostate cancer. Cancer detection rates based on PSA levels were as follows: 21.6% for PSA <4 ng/mL, 21.7% for PSA 4-10 ng/mL, 32.7% for PSA 10-20 ng/mL, 53.0% for PSA 20-50 ng/mL, 71.5% for PSA 50-100 ng/mL, and 92.0% for PSA >100 ng/mL. When DRE findings were classified according to the 2016 TNM System (AJCC 8th Edition) as T1, T2, T3, and T4, cancer detection rates were 26.8%, 51.8%, 87.6%, and 95.7%, respectively. The overall cancer detection rate was significantly higher with abnormal DRE findings (64.6% vs. 26.7%, p < 0.001). Additionally, 78.2% of the detected cancers were high-grade (Gleason score of 7 or more). Conclusion: This extensive study of Ghanaian men undergoing TRUS biopsies reveals a high prostate cancer detection rate, with nearly 80% of the detected cancers being high-grade. These findings underscore the importance of PSA and DRE in the early detection of prostate cancer and should be considered in patient counseling and discussions regarding the implementation of prostate cancer screening programs in this population.

Jianhao Xie, Ziang Zhang, Guibo Luo et al.

Large pre-trained models with their numerous model parameters and extensive training datasets have shown excellent performance in various tasks. Many publicly available medical image datasets do not have a sufficient amount of data so there are few large-scale models in medical imaging. We propose a large-scale Tumor Segmentation Foundation Model (TSFM) with 1.6 billion parameters using Resblock-backbone and Transformer-bottleneck,which has good transfer ability for downstream tasks. To make TSFM exhibit good performance in tumor segmentation, we make full use of the strong spatial correlation between tumors and organs in the medical image, innovatively fuse 7 tumor datasets and 3 multi-organ datasets to build a 3D medical dataset pool, including 2779 cases with totally 300k medical images, whose size currently exceeds many other single publicly available datasets. TSFM is the pre-trained model for medical image segmentation, which also can be transferred to multiple downstream tasks for fine-tuning learning. The average performance of our pre-trained model is 2% higher than that of nnU-Net across various tumor types. In the transfer learning task, TSFM only needs 5% training epochs of nnU-Net to achieve similar performance and can surpass nnU-Net by 2% on average with 10% training epoch. Pre-trained TSFM and its code will be released soon.

Chi-en Amy Tai, Alexander Wong

In 2020, 685,000 deaths across the world were attributed to breast cancer, underscoring the critical need for innovative and effective breast cancer treatment. Neoadjuvant chemotherapy has recently gained popularity as a promising treatment strategy for breast cancer, attributed to its efficacy in shrinking large tumors and leading to pathologic complete response. However, the current process to recommend neoadjuvant chemotherapy relies on the subjective evaluation of medical experts which contain inherent biases and significant uncertainty. A recent study, utilizing volumetric deep radiomic features extracted from synthetic correlated diffusion imaging (CDI$^s$), demonstrated significant potential in noninvasive breast cancer pathologic complete response prediction. Inspired by the positive outcomes of optimizing CDI$^s$ for prostate cancer delineation, this research investigates the application of optimized CDI$^s$ to enhance breast cancer pathologic complete response prediction. Using multiparametric MRI that fuses optimized CDI$^s$ with diffusion-weighted imaging (DWI), we obtain a leave-one-out cross-validation accuracy of 93.28%, over 5.5% higher than that previously reported.

Amine Bechar, Youssef Elmir, Yassine Himeur et al.

This review article discusses the roles of federated learning (FL) and transfer learning (TL) in cancer detection based on image analysis. These two strategies powered by machine learning have drawn a lot of attention due to their potential to increase the precision and effectiveness of cancer diagnosis in light of the growing importance of machine learning techniques in cancer detection. FL enables the training of machine learning models on data distributed across multiple sites without the need for centralized data sharing, while TL allows for the transfer of knowledge from one task to another. A comprehensive assessment of the two methods, including their strengths, and weaknesses is presented. Moving on, their applications in cancer detection are discussed, including potential directions for the future. Finally, this article offers a thorough description of the functions of TL and FL in image-based cancer detection. The authors also make insightful suggestions for additional study in this rapidly developing area.

Yin‐Che Wang, Cheng‐Lun Lai, Tsung‐Chih Chen et al.

Abstract Background Haploidentical hematopoietic stem cell transplantation (haplo‐HSCT) has emerged as an effective approach for acute leukemia, primarily due to the inherent difficulty in finding human leukocyte antigen‐matched unrelated donors (MUD). Nevertheless, it remains uncertain whether haplo‐HSCT and MUD‐HSCT can provide comparable outcomes in patients with acute leukemia. Aims This study aimed to assess the overall survival (OS) and leukemia‐free survival (LFS) outcomes between the MUD‐HSCT and haplo‐HSCT groups. Methods and results This retrospective analysis encompassed adult patients with acute leukemia undergoing the initial allo‐HSCT. Among these 85 patients, we stratified 33 patients into the MUD‐HSCT group and 52 to the haplo‐HSCT group. The primary outcomes were OS and LFS. The median OS was not reached in the haplo‐HSCT group, while it reached 29.8 months in patients undergoing MUD‐HSCT (p = .211). Likewise, the median LFS periods were 52.6 months in the haplo‐HSCT group and 12.7 months in the MUD‐HSCT group (p = .212). Importantly, neither the OS nor LFS showed substantial differences between the MUD‐HSCT and haplo‐HSCT groups. Furthermore, univariate analyses revealed that haplo‐HSCT did not demonstrate a significantly higher risk of worse LFS (hazard ratio [HR], 0.69; 95% confidence interval [CI], 0.38–1.25; p = .216) or OS (HR, 0.67; 95% CI, 0.36–1.26; p = .214) than MUD‐HSCT. Notably, a high European Group for Blood and Marrow Transplantation risk score (HR, 1.44; 95% CI, 1.10–1.87; p = .007) and non‐complete remission (HR, 2.48; 95% CI, 1.17–5.23; p = .017) were significantly correlated with worse OS. Conclusion Haplo‐HSCT may serve as an alternative to MUD‐HSCT for the treatment of acute leukemia, offering similar survival outcomes.

J. Kaczmar, K. Papadopoulos, G. Ansstas et al.

Valerio Nardone, Federica Marmorino, Marco Maria Germani et al.

The integration of multidisciplinary tumor boards (MTBs) is fundamental in delivering state-of-the-art cancer treatment, facilitating collaborative diagnosis and management by a diverse team of specialists. Despite the clear benefits in personalized patient care and improved outcomes, the increasing burden on MTBs due to rising cancer incidence and financial constraints necessitates innovative solutions. The advent of artificial intelligence (AI) in the medical field offers a promising avenue to support clinical decision-making. This review explores the perspectives of clinicians dedicated to the care of cancer patients—surgeons, medical oncologists, and radiation oncologists—on the application of AI within MTBs. Additionally, it examines the role of AI across various clinical specialties involved in cancer diagnosis and treatment. By analyzing both the potential and the challenges, this study underscores how AI can enhance multidisciplinary discussions and optimize treatment plans. The findings highlight the transformative role that AI may play in refining oncology care and sustaining the efficacy of MTBs amidst growing clinical demands.

Prateek A. Meshram, Suraj Joshi, Devarshi Mahajan

The first MRI scan was done in the year 1978 by researchers at EML Laboratories. As per an estimate, approximately 251,329 people died due to primary cancerous brain and CNS (Central Nervous System) Tumors in the year 2020. It has been recommended by various medical professionals that brain tumor detection at an early stage would help in saving many lives. Whenever radiologists deal with a brain MRI they try to diagnose it with the histological subtype which is quite subjective and here comes the major issue. Upon that, in developing countries like India, where there is 1 doctor for every 1151 people, the need for efficient diagnosis to help radiologists and doctors come into picture. In our approach, we aim to solve the problem using swin transformers and deep learning to detect, classify, locate and provide the size of the tumor in the particular MRI scan which would assist the doctors and radiologists in increasing their efficiency. At the end, the medics would be able to download the predictions and measures in a PDF (Portable Document Format). Keywords: brain tumor, transformers, classification, medical, deep learning, detection

Zahra Mokhtari, Elham Amjadi, Hamidreza Bolhasani et al.

Colorectal Cancer (CRC) is the second most common cause of cancer death in the world, ad can be identified by the location of the primary tumor in the large intestine: right and left colon, and rectum. Based on the location, CRC shows differences in chromosomal and molecular characteristics, microbiomes incidence, pathogenesis, and outcome. It has been shown that tumors on left and right sides also have different immune landscape, so the prognosis may be different based on the primary tumor locations. It is widely accepted that immune components of the tumor microenvironment (TME) plays a critical role in tumor development. One of the critical regulatory molecules in the TME is immune checkpoints that as the gatekeepers of immune responses regulate the infiltrated immune cell functions. Inhibitory immune checkpoints such as PD-1, Tim3, and LAG3, as the main mechanism of immune suppression in TME overexpressed and result in further development of the tumor. The images of this dataset have been taken from colon tissues of patients with CRC, stained with specific antibodies for CD3, CD8, CD45RO, PD-1, LAG3 and Tim3. The name of this dataset is CRC-ICM and contains 1756 images related to 136 patients. The initial version of CRC-ICM is published on Elsevier Mendeley dataset portal, and the latest version is accessible via: https://databiox.com

Al-Akhir Nayan, Ahamad Nokib Mozumder, Md. Rakibul Haque et al.

The growth of abnormal cells in the brain's tissue causes brain tumors. Brain tumors are considered one of the most dangerous disorders in children and adults. It develops quickly, and the patient's survival prospects are slim if not appropriately treated. Proper treatment planning and precise diagnoses are essential to improving a patient's life expectancy. Brain tumors are mainly diagnosed using magnetic resonance imaging (MRI). As part of a convolution neural network (CNN)-based illustration, an architecture containing five convolution layers, five max-pooling layers, a Flatten layer, and two dense layers has been proposed for detecting brain tumors from MRI images. The proposed model includes an automatic feature extractor, modified hidden layer architecture, and activation function. Several test cases were performed, and the proposed model achieved 98.6% accuracy and 97.8% precision score with a low cross-entropy rate. Compared with other approaches such as adjacent feature propagation network (AFPNet), mask region-based CNN (mask RCNN), YOLOv5, and Fourier CNN (FCNN), the proposed model has performed better in detecting brain tumors.

Mohammad Mahdi Behzadi, Mohammad Madani, Hanzhang Wang et al.

Prostate cancer is the most common cancer in men worldwide and the second leading cause of cancer death in the United States. One of the prognostic features in prostate cancer is the Gleason grading of histopathology images. The Gleason grade is assigned based on tumor architecture on Hematoxylin and Eosin (H&E) stained whole slide images (WSI) by the pathologists. This process is time-consuming and has known interobserver variability. In the past few years, deep learning algorithms have been used to analyze histopathology images, delivering promising results for grading prostate cancer. However, most of the algorithms rely on the fully annotated datasets which are expensive to generate. In this work, we proposed a novel weakly-supervised algorithm to classify prostate cancer grades. The proposed algorithm consists of three steps: (1) extracting discriminative areas in a histopathology image by employing the Multiple Instance Learning (MIL) algorithm based on Transformers, (2) representing the image by constructing a graph using the discriminative patches, and (3) classifying the image into its Gleason grades by developing a Graph Convolutional Neural Network (GCN) based on the gated attention mechanism. We evaluated our algorithm using publicly available datasets, including TCGAPRAD, PANDA, and Gleason 2019 challenge datasets. We also cross validated the algorithm on an independent dataset. Results show that the proposed model achieved state-of-the-art performance in the Gleason grading task in terms of accuracy, F1 score, and cohen-kappa. The code is available at https://github.com/NabaviLab/Prostate-Cancer.

Jie Huang MM, Jia-Xin Li PhD, Lin-Rui Ma MM et al.

Lung carcinoma is the primary reason for cancer-associated mortality, and it exhibits the highest mortality and incidence in developed and developing countries. Non-small cell lung cancer (NSCLC) and SCLC are the 2 main types of lung cancer, with NSCLC contributing to 85% of all lung carcinoma cases. Conventional treatment mainly involves surgery, chemoradiotherapy, and immunotherapy, but has a dismal prognosis for many patients. Therefore, identifying an effective adjuvant therapy is urgent. Historically, traditional herbal medicine has been an essential part of complementary and alternative medicine, due to its numerous targets, few side effects and substantial therapeutic benefits. In China and other East Asian countries, traditional herbal medicine is increasingly popular, and is highly accepted by patients as a clinical adjuvant therapy. Numerous studies have reported that herbal extracts and prescription medications are effective at combating tumors. It emphasizes that, by mainly regulating the P13K/AKT signaling pathway, the Wnt signaling pathway, and the NF-κB signaling pathway, herbal medicine induces apoptosis and inhibits the proliferation and migration of tumor cells. The present review discusses the anti-NSCLC mechanisms of herbal medicines and provides options for future adjuvant therapy in patients with NSCLC.

M. Irmak-Yazicioglu, K. Ergun

Objective: Plasminogen Activator Inhibitor-1 has an important role in the progression of cancer. Although there are many studies about the relation of Plasminogen Activator Inhibitor-1 (PAI-1) with cancer, there exists only a few about showing the relation of PAI-1 with cancer stem cells. Materials and Methods: The purpose of this review is to explain the relation between PAI-1 and carcinogenesis and to at- tract attention to the possible role of this protein in cancer stem cell pathway in the light of literature data. Results: Tumor development harbors various biological processes such as resisting cell death, proliferative signaling, angiogenesis, invasion, and metastasis. Cancer Stem Cells (CSCs), known as subpopulation of tumor cells, are located within the tumor tissue with a great therapeutic resistance, self-renewal capacity, potential of induction of tumor initiation and progression. Processes involved in epithelial mesenchymal transition (EMT) and extracellular matrix (ECM) are important for cancer and CSC development since EMT increases plasticity in tumor cells; therefore, they are separated from other tissues. PAI-1 is the major inhibitor of plasmin and is associated with various diseases such as cardiovascular diseases, neuronal cell loss, and progression of hallmarks of cancer. PAI-1, which has high expression levels in most cancer types, has a role in ECM remodeling and regulation of EMT. Recent studies about cancer stem cells reveal the probable importance of PAI-1 in stemness part- way. Conclusions: These studies might be considered as a guide for therapeutic approaches that will be focused in near future.

S. Sajedeh Mousavi, Sara Razi

Breast cancer is the most common cancer in women worldwide, and discovering the biomarkers of this disease became so vital nowadays and Cell in Cell structure could be one of them, and it may be used as an available proxy for tumor malignancy. (CICs) are unusual in that keep morphologically healthy cells within another cell. They are found in various human cancers and result from active cell-cell interaction, and it has different kinds. In this study, we analyzed the microarray data from GEO (GSE103865) to genetically evaluate CICs' incidence in samples obtained from breast cancer patients to understand the relationship between the rate of CIC and the prognosis of breast cancer. The preprocessing was performed using R software. The DAVID website was used to analyze gene ontology (GO) and Gene and Genome (KEGG) pathways. The protein-protein interactions (PPIs) of the obtained DEGs were assessed using the STRING website, and hub modules in Cytoscape and cytoHubba were screened. According to the results from analyzing the 20 hub genes, we understood that overexpression of our Top genes is effective in focal adhesion, ECM-receptor interaction, platelet activation and PI3K-Akt signaling pathway, which shows that changes in these pathways could be the reason the overexpression of CICs in breast cancer. These data and research by many others have uncovered various genes involved in CIC formation and have started to give us an idea of why they are formed and how they could contribute to breast cancer

Kenji Morimoto, Junji Uchino, Takashi Yokoi et al.

Although previous studies suggest that cancer cachexia is a poor prognostic factor for immune checkpoint inhibitor monotherapy, the impact of cancer cachexia on chemoimmunotherapy is unclear. We investigated the impact of cancer cachexia on the therapeutic outcomes of chemoimmunotherapy for non-small cell lung cancer (NSCLC). We retrospectively analyzed patients’ medical records with NSCLC who received chemoimmunotherapy in 12 institutions in Japan between January and November 2019. We defined cancer cachexia as weight loss exceeding 5% of the total body weight or a body mass index of < 20 kg/m2 and weight loss of more than 2% of the total body weight within 6 months before chemoimmunotherapy initiation, with laboratory results exceeding reference values. This study enrolled 235 patients with NSCLC, among whom 196 were eligible for analysis, and 50 (25.5%) met the criteria for cachexia diagnosis. Patients with cancer cachexia had a significantly higher frequency of a programmed death-ligand 1 (PD-L1) expression of ≥ 50% (48%, p = .01) and shorter progression-free survival (PFS; log-rank test: p = .04) than patients without cachexia. There was no significant difference in overall survival (OS) between the cachexia and no-cachexia groups (log-rank test: p = .14). In the PD-L1 ≥ 50% population, there was no significant difference in PFS and OS (log-rank test: p = .19 and p = .79, respectively) between patients with NSCLC in the cachexia or no-cachexia groups. Cancer cachexia might be a poor prognostic factor in patients with NSCLC receiving chemoimmunotherapy.