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

Xinzhe Luo, Shuai Shao, Yan Wang et al.

Deep intracranial tumors situated in eloquent brain regions controlling vital functions present critical diagnostic challenges. Clinical practice has shifted toward stereotactic biopsy for pathological confirmation before treatment. Yet biopsy carries inherent risks of hemorrhage and neurological deficits and struggles with sampling bias due to tumor spatial heterogeneity, because pathological changes are typically region-selective rather than tumor-wide. Therefore, advancing non-invasive MRI-based pathology prediction is essential for holistic tumor assessment and modern clinical decision-making. The primary challenge lies in data scarcity: low tumor incidence requires long collection cycles, and annotation demands biopsy-verified pathology from neurosurgical experts. Additionally, tiny lesion volumes lacking segmentation masks cause critical features to be overwhelmed by background noise. To address these challenges, we construct the ICT-MRI dataset - the first public biopsy-verified benchmark with 249 cases across four categories. We propose a Virtual Biopsy framework comprising: MRI-Processor for standardization; Tumor-Localizer employing vision-language models for coarse-to-fine localization via weak supervision; and Adaptive-Diagnoser with a Masked Channel Attention mechanism fusing local discriminative features with global contexts. Experiments demonstrate over 90% accuracy, outperforming baselines by more than 20%.

Marcelo Antonini, André Mattar, Denise Joffily Pereira da Costa Pinheiro et al.

Background: Trastuzumab has significantly improved the treatment of HER2-positive breast cancer, particularly in the neoadjuvant setting, where its combination with chemotherapy increases the pathologic complete response (pCR) rate. This retrospective cohort study assesses the implications of disparities in access to trastuzumab within the Brazilian public healthcare system, focusing on pCR, overall survival (OS) and disease-free survival (DFS) in non-metastatic, HER2-positive breast cancer patients undergoing neoadjuvant chemotherapy (NAC). Methods: The study was conducted in the Hospital Pérola Byington (PEROLA), a public institution, and in the Hospital do Servidor Público Estadual (HSPE), a private institution. pCR was defined as the absence of residual invasive or in situ tumors in the breast and axillary nodes. OS and DFS were calculated by Kaplan-Meier survival analysis for a 5-year period. Results: From 2011 to 2020, 381 patients at PEROLA and 78 at HSPE underwent NAC. Trastuzumab availability was higher at HSPE (83.4 % vs. 60.0 %, p < 0.0001). Use of trastuzumab correlated with significantly higher pCR rates at both the PEROLA (54.3 % vs. 26.4 %, p < 0.0001) and the HSPE (52.7 % vs. 26.4 %, p < 0.0001). HER2-positive patients with pCR at HSPE also had better OS (80 % vs. 61 %, p < 0.0001) and DFS (89 % vs. 67 %, p < 0.0001) compared to those at PEROLA. Conclusion: There were significant differences in the provision of trastuzumab between the public and private healthcare systems, adversely affecting clinical outcomes and patient survival. The current data highlight the pressing need to address equity in cancer treatment to improve prognosis for every patient.

Yulong Tan, Wenhao Wang, Xuan Wang et al.

Abstract Background Preoperative localization of pulmonary nodules is crucial for sublobar resection under thoracoscopy; however, controversy persists over the optimal localization method in terms of accuracy and safety. This study evaluates a novel technique integrating indocyanine green (ICG) with medical adhesive for pulmonary nodule localization. Materials and methods In this single-center retrospective cohort, 168 consecutive patients (188 pulmonary nodules ≤ 2 cm) undergoing preoperative localization followed by uniportal thoracoscopic resection (July 2023 to June 2024) were divided into two groups: ICG combined with medical adhesive group (n = 86) versus medical adhesive group (n = 82). Localization outcomes, related complications, surgical and pathological outcomes were compared between the two groups. Results There were no deaths or serious complications. All nodules were successfully resected thoracoscopically. The combined group demonstrated a shorter operative duration than the medical adhesive group (46.3 ± 6.7 min vs. 53.1 ± 5.9 min, P < 0.001). No statistically significant differences were identified in surgical type, length of stay, duration of drain tube retention, and total postoperative drainage volume between the two groups (P > 0.05). Conclusion The combined use of ICG and medical adhesive for preoperative localization in uniportal thoracoscopic sublobar resection of small pulmonary nodules reduces operative time compared with medical adhesive positioning and demonstrates favorable safety profiles.

Ganggang Miao, Ganggang Miao, De Zhang et al.

Gastric schwannoma is a relatively rare submucosal mesenchymal tumor with low probability of metastasis and arises from Schwann cells of the gastrointestinal nervous plexus. Surgical therapy is the main treatment of gastric schwannoma with symptoms or malignant tendency. Gastroparesis is a potential complication following gastrointestinal surgery, which is a clinical syndrome caused by gastric emptying disorder and characterized by nausea, vomiting, and bloating, resulting in insufficient nutrient intake. Generally, post-surgical etiology is the main potential etiology of gastroparesis, while the most common underlying etiology is diabetes mellitus. So far, reports of gastroparesis arising from resection of gastric schwannoma are rare. We present an 80-year-old woman who was diagnosed with gastrointestinal stromal tumor (GIST) primarily and has undergone laparoscopic wedge-shaped gastrectomy. The pathological and immunohistochemical examination ultimately established the diagnosis of gastric schwannoma. The patient experienced belching, nausea, vomiting, and bloating 1 week after the surgery and confirmed as gastroparesis through gastrointestinal series and gastroscopic examination. A series of treatments were performed, including correcting fluid-electrolyte disorders and vitamin deficiencies, and nutritional support and pharmacological treatments. The patient ultimately recovered well, and the relevant literatures were reviewed to identify and handle similar cases hereafter.

Aidan D. Meade, Adrian Maguire, Adrian Maguire et al.

Although significant advances in understanding the molecular drivers of acquired and inherited radiosensitivity have occurred in recent decades, a single analytical method which can detect and classify radiosensitivity remains elusive. Raman microspectroscopy has demonstrated capabilities in the objective classification of various diseases, and more recently in the detection and modelling of radiobiological effect. In this study, Raman spectroscopy is presented as a potential tool for the detection of radiosensitivity subpopulations represented by four lymphoblastoid cell lines derived from individuals with ataxia telangiectasia (2 lines), non-Hodgkins lymphoma, and Turner’s syndrome. These are classified with respect to a population with mixed radiosensitivity, represented by lymphocytes drawn from both healthy controls, and prostate cancer patients. Raman spectroscopic measurements were made ex-vivo after exposure to X-ray doses of 0 Gy, 50 mGy and 500 mGy, in parallel to radiation-induced G2 chromosomal radiosensitivity scores, for all samples. Support vector machine models developed on the basis of the spectral data were capable of discrimination of radiosensitive populations before and after irradiation, with superior discrimination when spectra were subjected to a non-linear dimensionality reduction (UMAP) as opposed to a linear (PCA) approach. Models developed on spectral data acquired on samples irradiated in-vitro with a dose of 0Gy were found to provide the highest level of performance in discriminating between classes, with performances of F1 = 0.92 ± 0.06 achieved on a held-out test set. Overall, this study suggests that Raman spectroscopy may have potential as a tool for the detection of intrinsic radiosensitivity using liquid biopsies.

Hao Yao, Shi-hui Ren, Lin-hui Wang et al.

Abstract Relapsed/refractory multiple myeloma (RRMM) with extramedullary disease (EMD) represents a challenging condition, with limited treatment options and poor prognosis. We conducted a phase 1 clinical trial to evaluate the safety and effectiveness of a novel bispecific chimeric antigen receptor (CAR) T-cell therapy targeting two antigens, B-cell maturation antigen and G protein-coupled receptor class C group 5 member D (BCMA/GPRC5D), in this high-risk population. A total of 12 patients were enrolled, of whom 3 were excluded due to disease progression or death before CAR T-cell infusion, despite meeting the inclusion criteria, leaving 9 for analysis. The median follow-up was 6.08 months (Interquartile Range [IQR]: 0.9–16.5). All patients received BCMA/GPRC5D bispecific CAR T-cell therapy after bridging therapy with localized radiotherapy or Elranatamab. Efficacy assessments revealed that 100% of patients achieved partial response (PR) or better, with 44.4% achieving complete response (CR). Common adverse events included hematological toxicities such as anemia, leukopenia, and thrombocytopenia. Cytokine release syndrome (CRS) occurred in 66.7% of patients, all of which were grade 1–2, and no neurotoxicity (ICANS) was observed. The 1-year overall survival (OS) and progression-free survival (PFS) rates were 60% and 63%, respectively. Median OS and PFS were not reached. Collectively, these findings highlight a potential therapeutic strategy involving BCMA/GPRC5D dual-targeted CAR T-cell therapy for patients with aggressive forms of multiple myeloma, particularly those with extramedullary disease, and support the need for further exploration and validation in larger, multi-center clinical studies.

Nastaran Ghorbani, Bitasadat Jamshidi, Mohsen Rostamy-Malkhalifeh

Liver cancer is one of the most prevalent and lethal forms of cancer, making early detection crucial for effective treatment. This paper introduces a novel approach for automated liver tumor segmentation in computed tomography (CT) images by integrating a 3D U-Net architecture with the Bat Algorithm for hyperparameter optimization. The method enhances segmentation accuracy and robustness by intelligently optimizing key parameters like the learning rate and batch size. Evaluated on a publicly available dataset, our model demonstrates a strong ability to balance precision and recall, with a high F1-score at lower prediction thresholds. This is particularly valuable for clinical diagnostics, where ensuring no potential tumors are missed is paramount. Our work contributes to the field of medical image analysis by demonstrating that the synergy between a robust deep learning architecture and a metaheuristic optimization algorithm can yield a highly effective solution for complex segmentation tasks.

Liwen Sun, Hao-Ren Yao, Gary Gao et al.

Cancer screening, leading to early detection, saves lives. Unfortunately, existing screening techniques require expensive and intrusive medical procedures, not globally available, resulting in too many lost would-be-saved lives. We present CATCH-FM, CATch Cancer early with Healthcare Foundation Models, a cancer pre-screening methodology that identifies high-risk patients for further screening solely based on their historical medical records. With millions of electronic healthcare records (EHR), we establish the scaling law of EHR foundation models pretrained on medical code sequences, pretrain compute-optimal foundation models of up to 2.4 billion parameters, and finetune them on clinician-curated cancer risk prediction cohorts. In our retrospective evaluation comprising of thirty thousand patients, CATCH-FM achieves strong efficacy, with 50% sensitivity in predicting first cancer risks at 99% specificity cutoff, and outperforming feature-based tree models and both general and medical LLMs by up to 20% AUPRC. Despite significant demographic, healthcare system, and EHR coding differences, CATCH-FM achieves state-of-the-art pancreatic cancer risk prediction on the EHRSHOT few-shot leaderboard, outperforming EHR foundation models pretrained using on-site patient data. Our analysis demonstrates the robustness of CATCH-FM in various patient distributions, the benefits of operating in the ICD code space, and its ability to capture non-trivial cancer risk factors. Our code will be open-sourced.

Jianfeng Li, Hongjie Zhu, Nanzhi Luo et al.

Abstract The optimal surgical approach for elderly patients with early-stage non-small cell lung cancer (NSCLC) remains a topic of debate. A retrospective analysis was conducted on patients who underwent pulmonary resection for early-stage NSCLC at our single institution between January 2018 and December 2022. Propensity score matching was used to balance baseline characteristics between the sublobar resection and lobectomy groups. Perioperative outcomes, pulmonary function recovery, postoperative quality of life, and survival were compared between the two groups. A total of 151 patients were included, with 42 undergoing sublobar resection and 109 undergoing lobectomy. After propensity score matching, baseline characteristics were well-balanced between the two groups. Sublobar resection was associated with shorter operative time (125.83 ± 33.56 min vs. 161.14 ± 61.54 min, p = 0.048), less intraoperative blood loss [65 (30, 75) ml vs. 120 (70, 170) ml, p < 0.001], shorter drainage duration [3 (2, 5) days vs. 5 (3, 6) days, p < 0.001], shorter hospital stay [6 (4, 8) days vs. 10 (7, 13) days, p < 0.001], and fewer postoperative complications (11.9% vs. 47.6%, p < 0.001), compared to lobectomy. Moreover, sublobar resection led to better pulmonary function recovery and higher postoperative quality of life scores, with no significant difference in overall and disease-free survival between the groups. Sublobar resection in patients aged 80 and above with early-stage NSCLC offered comparable oncological outcomes to lobectomy while preserving more lung function and providing better postoperative recovery and long-term quality of life. These findings have important implications for treatment decision-making in elderly NSCLC patients.

Valentin Benboubker, George M. Ramzy, Sacha Jacobs et al.

Abstract Patient-derived organoids (PDOs) established from tissues from various tumor types gave the foundation of ex vivo models to screen and/or validate the activity of many cancer drug candidates. Due to their phenotypic and genotypic similarity to the tumor of which they were derived, PDOs offer results that effectively complement those obtained from more complex models. Yet, their potential for predicting sensitivity to combination therapy remains underexplored. In this review, we discuss the use of PDOs in both validation and optimization of multi-drug combinations for personalized treatment strategies in CRC. Moreover, we present recent advancements in enriching PDOs with diverse cell types, enhancing their ability to mimic the complexity of in vivo environments. Finally, we debate how such sophisticated models are narrowing the gap in personalized medicine, particularly through immunotherapy strategies and discuss the challenges and future direction in this promising field.

Caitlin Hurley, Caitlin Hurley, Jennifer McArthur et al.

IntroductionDiffuse alveolar hemorrhage (DAH) is a devastating disease process with 50-100% mortality in oncology and hematopoietic cell transplant (HCT) recipients. High concentrations of tissue factors have been demonstrated in the alveolar wall in acute respiratory distress syndrome and DAH, along with elevated levels of tissue factor pathway inhibitors. Activated recombinant factor VII (rFVIIa) activates the tissue factor pathway, successfully overcoming the tissue factor pathway inhibitor (TFPI) inhibition of activation of Factor X. Intrapulmonary administration (IP) of rFVIIa in DAH is described in small case series with successful hemostasis and minimal complications.MethodsWe completed a single center retrospective descriptive study of treatment with rFVIIa and outcomes in pediatric oncology and HCT patients with pulmonary hemorrhage at a quaternary hematology/oncology hospital between 2011 and 2019. We aimed to assess the safety and survival of patients with pulmonary hemorrhage who received of IP rFVIIa.ResultsWe identified 31 patients with pulmonary hemorrhage requiring ICU care. Thirteen patients received intrapulmonary rFVIIa, while eighteen patients did not. Overall, 13 of 31 patients (41.9%) survived ICU discharge. ICU survival (n=6) amongst those in the IP rFVIIa group was 46.2% compared to 38.9% (n=7) in those who did not receive IP therapy (p=0.69). Hospital survival was 46.2% in the IP group and 27.8% in the non-IP group (p=0.45). There were no adverse events noted from use of IP FVIIa.ConclusionsIntrapulmonary rFVIIa can be safely administered in pediatric oncology patients with pulmonary hemorrhage and should be considered a viable treatment option for these patients.

Max Bengtsson, Elif Keles, Gorkem Durak et al.

In this paper, we present a novel approach for segmenting pediatric brain tumors using a deep learning architecture, inspired by expert radiologists' segmentation strategies. Our model delineates four distinct tumor labels and is benchmarked on a held-out PED BraTS 2024 test set (i.e., pediatric brain tumor datasets introduced by BraTS). Furthermore, we evaluate our model's performance against the state-of-the-art (SOTA) model using a new external dataset of 30 patients from CBTN (Children's Brain Tumor Network), labeled in accordance with the PED BraTS 2024 guidelines and 2023 BraTS Adult Glioma dataset. We compare segmentation outcomes with the winning algorithm from the PED BraTS 2023 challenge as the SOTA model. Our proposed algorithm achieved an average Dice score of 0.642 and an HD95 of 73.0 mm on the CBTN test data, outperforming the SOTA model, which achieved a Dice score of 0.626 and an HD95 of 84.0 mm. Moreover, our model exhibits strong generalizability, attaining a 0.877 Dice score in whole tumor segmentation on the BraTS 2023 Adult Glioma dataset, surpassing existing SOTA. Our results indicate that the proposed model is a step towards providing more accurate segmentation for pediatric brain tumors, which is essential for evaluating therapy response and monitoring patient progress. Our source code is available at https://github.com/NUBagciLab/Pediatric-Brain-Tumor-Segmentation-Model.

Minmin Wang, Xu Xie, Zhengbo Fan et al.

Objective: Tumor Treating Fields (TTFields) is an emerging approach for cancer therapy that inhibits tumor cell proliferation by applying alternating electric fields (EF) of intermediate frequency and low intensity. The TTFields-induced electric field intensity at the tumor site is closely related to the therapeutic efficacy. Therefore, the EF simulation based on realistic head models have been utilized for the dosage analysis and treatment optimization of TTFields. However, current modeling methods require manual segmentation of tumors and rely on commercial software, which is time-consuming and labor-intensive. Approach: We introduce AutoSimTTF, a fully automatic pipeline for simulating and optimizing the EF distribution for TTFields. The main steps of AutoSimTTF utilize open-source toolkits, enabling fully automated processing of individual MRI data for TTFields. Additionally, AutoSimTTF allows for parameter optimization based on individual anatomical information, thereby achieving a more focused and higher EF distribution at the tumor site. Main results: Compared to conventional EF calculation processes, deviations in AutoSimTTF are below 20%. The optimal treatment parameters generated by AutoSimTTF produces a higher EF intensity at the tumor site (111.9%) and better focality (19.4%) compared to traditional TTFields settings. Significance: AutoSimTTF provides significant reference value and guidance for the clinical application and treatment planning of TTFields.

César R. Lacruz, Eugenio Leonardo

Xuefeng Sun MD, Ting Zhang MD, Chi Shao MD et al.

Background: Aspirations without a tissue core are common in endobronchial ultrasound-guided transbronchial needle aspiration procedures. However, the diagnostic value of all-shot aspirations and no-tissue-core aspirations is unclear. Patients and Methods: A retrospective analysis of patients who underwent endobronchial ultrasound-guided transbronchial needle aspiration with the description of all-shot or no-tissue-core aspirations was conducted at a tertiary hospital between January 2017 and March 2021. Patients’ pathologic and clinical diagnoses were retrieved and compared between all-shot patients (all aspirations had a tissue core) and no-tissue-core patients (at least one aspiration had no tissue core). Results: Among all 505 patients with 1402 aspirations, 356 (70.5%) patients, and 1184 (84.5%) aspirations were all-shot. Pathologic diagnosis after endobronchial ultrasound-guided transbronchial needle aspiration revealed neoplasms in 46.1% of all-shot patients, but 33.6% of no-tissue-core patients (odds ratio, 1.69; 95% confidence interval, 1.14-2.52; P  = .009). Final clinical diagnosis revealed malignancy in 53.1% of all-shot patients, but 37.6% of no-tissue-core patients (odds ratio, 1.88; 95% confidence interval, 1.27-2.78; P  = .001). In 133 patients with pathologic nonspecific findings, a clinical diagnosis of malignancy was proven in 25 of 79 (31.6%) of all-shot patients, but only 6 of 54 (11.1%) of no-tissue-core patients (odds ratio, 3.70; 95% confidence interval, 1.40-9.79; P  = .006). Conclusions: Patients with all-shot aspirations in endobronchial ultrasound-guided transbronchial needle aspiration are more likely to have the pathologic and clinical diagnosis of malignancy. More measures should be taken to exclude malignancy in all-shot patients when the endobronchial ultrasound-guided transbronchial needle aspiration was nondiagnostic.

Yu Ren, Guoli Wang, Pingping Wang et al.

Background and Objective: Bladder cancer is a common malignant urinary carcinoma, with muscle-invasive and non-muscle-invasive as its two major subtypes. This paper aims to achieve automated bladder cancer invasiveness localization and classification based on MRI. Method: Different from previous efforts that segment bladder wall and tumor, we propose a novel end-to-end multi-scale multi-task spatial feature encoder network (MM-SFENet) for locating and classifying bladder cancer, according to the classification criteria of the spatial relationship between the tumor and bladder wall. First, we built a backbone with residual blocks to distinguish bladder wall and tumor; then, a spatial feature encoder is designed to encode the multi-level features of the backbone to learn the criteria. Results: We substitute Smooth-L1 Loss with IoU Loss for multi-task learning, to improve the accuracy of the classification task. By testing a total of 1287 MRIs collected from 98 patients at the hospital, the mAP and IoU are used as the evaluation metrics. The experimental result could reach 93.34\% and 83.16\% on test set. Conclusions: The experimental result demonstrates the effectiveness of the proposed MM-SFENet on the localization and classification of bladder cancer. It may provide an effective supplementary diagnosis method for bladder cancer staging.

Dechao Tang, Tianming Du, Deguo Ma et al.

Endometrial cancer is one of the most common tumors in the female reproductive system and is the third most common gynecological malignancy that causes death after ovarian and cervical cancer. Early diagnosis can significantly improve the 5-year survival rate of patients. With the development of artificial intelligence, computer-assisted diagnosis plays an increasingly important role in improving the accuracy and objectivity of diagnosis, as well as reducing the workload of doctors. However, the absence of publicly available endometrial cancer image datasets restricts the application of computer-assisted diagnostic techniques.In this paper, a publicly available Endometrial Cancer PET/CT Image Dataset for Evaluation of Semantic Segmentation and Detection of Hypermetabolic Regions (ECPC-IDS) are published. Specifically, the segmentation section includes PET and CT images, with a total of 7159 images in multiple formats. In order to prove the effectiveness of segmentation methods on ECPC-IDS, five classical deep learning semantic segmentation methods are selected to test the image segmentation task. The object detection section also includes PET and CT images, with a total of 3579 images and XML files with annotation information. Six deep learning methods are selected for experiments on the detection task.This study conduct extensive experiments using deep learning-based semantic segmentation and object detection methods to demonstrate the differences between various methods on ECPC-IDS. As far as we know, this is the first publicly available dataset of endometrial cancer with a large number of multiple images, including a large amount of information required for image and target detection. ECPC-IDS can aid researchers in exploring new algorithms to enhance computer-assisted technology, benefiting both clinical doctors and patients greatly.

Haopeng Kuang, Dingkang Yang, Shunli Wang et al.

Accurate visualization of liver tumors and their surrounding blood vessels is essential for noninvasive diagnosis and prognosis prediction of tumors. In medical image segmentation, there is still a lack of in-depth research on the simultaneous segmentation of liver tumors and peritumoral blood vessels. To this end, we collect the first liver tumor, and vessel segmentation benchmark datasets containing 52 portal vein phase computed tomography images with liver, liver tumor, and vessel annotations. In this case, we propose a 3D U-shaped Cross-Attention Network (UCA-Net) that utilizes a tailored cross-attention mechanism instead of the traditional skip connection to effectively model the encoder and decoder feature. Specifically, the UCA-Net uses a channel-wise cross-attention module to reduce the semantic gap between encoder and decoder and a slice-wise cross-attention module to enhance the contextual semantic learning ability among distinct slices. Experimental results show that the proposed UCA-Net can accurately segment 3D medical images and achieve state-of-the-art performance on the liver tumor and intrahepatic vessel segmentation task.

Andreas Wagner, Pirmin Schlicke, Marvin Fritz et al.

Formulating tumor models that predict growth under therapy is vital for improving patient-specific treatment plans. In this context, we present our recent work on simulating non-small-scale cell lung cancer (NSCLC) in a simple, deterministic setting for two different patients receiving an immunotherapeutic treatment. At its core, our model consists of a Cahn-Hilliard-based phase-field model describing the evolution of proliferative and necrotic tumor cells. These are coupled to a simplified nutrient model that drives the growth of the proliferative cells and their decay into necrotic cells. The applied immunotherapy decreases the proliferative cell concentration. Here, we model the immunotherapeutic agent concentration in the entire lung over time by an ordinary differential equation (ODE). Finally, reaction terms provide a coupling between all these equations. By assuming spherical, symmetric tumor growth and constant nutrient inflow, we simplify this full 3D cancer simulation model to a reduced 1D model. We can then resort to patient data gathered from computed tomography (CT) scans over several years to calibrate our model. For the reduced 1D model, we show that our model can qualitatively describe observations during immunotherapy by fitting our model parameters to existing patient data. Our model covers cases in which the immunotherapy is successful and limits the tumor size, as well as cases predicting a sudden relapse, leading to exponential tumor growth. Finally, we move from the reduced model back to the full 3D cancer simulation in the lung tissue. Thereby, we show the predictive benefits a more detailed patient-specific simulation including spatial information could yield in the future.

Manu Goyal, Laura J. Tafe, James X. Feng et al.

Endometrial cancer, the fourth most common cancer in females in the United States, with the lifetime risk for developing this disease is approximately 2.8% in women. Precise histologic evaluation and molecular classification of endometrial cancer is important for effective patient management and determining the best treatment modalities. This study introduces EndoNet, which uses convolutional neural networks for extracting histologic features and a vision transformer for aggregating these features and classifying slides based on their visual characteristics into high- and low- grade. The model was trained on 929 digitized hematoxylin and eosin-stained whole-slide images of endometrial cancer from hysterectomy cases at Dartmouth-Health. It classifies these slides into low-grade (Endometroid Grades 1 and 2) and high-grade (endometroid carcinoma FIGO grade 3, uterine serous carcinoma, carcinosarcoma) categories. EndoNet was evaluated on an internal test set of 110 patients and an external test set of 100 patients from the public TCGA database. The model achieved a weighted average F1-score of 0.91 (95% CI: 0.86-0.95) and an AUC of 0.95 (95% CI: 0.89-0.99) on the internal test, and 0.86 (95% CI: 0.80-0.94) for F1-score and 0.86 (95% CI: 0.75-0.93) for AUC on the external test. Pending further validation, EndoNet has the potential to support pathologists without the need of manual annotations in classifying the grades of gynecologic pathology tumors.