Early Detection of Lymph Node Metastasis Using Primary Head and Neck Cancer Computed Tomography and Fluorescence Lifetime Imaging DOI Creative Commons
Nimu Yuan,

Mohamed Abul Hassan,

Katjana Ehrlich

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(18), P. 2097 - 2097

Published: Sept. 23, 2024

Objectives: Early detection and accurate diagnosis of lymph node metastasis (LNM) in head neck cancer (HNC) are crucial for enhancing patient prognosis survival rates. Current imaging methods have limitations, necessitating new evaluation diagnostic techniques. This study investigates the potential combining pre-operative CT intra-operative fluorescence lifetime (FLIm) to enhance LNM prediction HNC using primary tumor signatures. Methods: FLIm data were collected from 46 patients. A total 42 features 924 radiomic extracted site fused. support vector machine (SVM) model with a radial basis function kernel was trained predict LNM. Hyperparameter tuning conducted 10-fold nested cross-validation. Prediction performance evaluated balanced accuracy (bACC) area under ROC curve (AUC). Results: The model, leveraging combined features, demonstrated improved testing (bACC: 0.71, AUC: 0.79) over CT-only 0.58, 0.67) FLIm-only 0.61, 0.72) models. Feature selection identified that subset 10 provided optimal predictive capability. contribution analysis high-pass low-pass wavelet-filtered images as well Laguerre coefficients key predictors. Conclusions: Combining improves compared either modality alone. Significance: underscores radiomics more HNC, offering promise outcomes.

Language: Английский

Overview of the HECKTOR Challenge at MICCAI 2022: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT DOI
Vincent Andrearczyk, Valentin Oreiller,

Moamen Abobakr

et al.

Lecture notes in computer science, Journal Year: 2023, Volume and Issue: unknown, P. 1 - 30

Published: Jan. 1, 2023

Language: Английский

Citations

42
Brain tumor segmentation using deep learning: A Review DOI Creative Commons
Beibei Hou, Saizong Guan

Journal of Computing and Electronic Information Management, Journal Year: 2025, Volume and Issue: 16(1), P. 26 - 32

Published: Feb. 25, 2025

Brain tumor segmentation is a crucial task in medical image analysis, as accurate delineation of regions vital for clinical diagnosis, treatment planning, and prognosis assessment. Traditional Convolutional Neural Network (CNN)-based models have demonstrated significant success capturing local features, but they face challenges modeling global context, which essential complex tasks. This review examines recent advancements brain segmentation, with focus on CNNs, Transformers, Mamba, Graph Networks (GNNs), well their hybrid models. critically evaluates the strengths limitations each approach respect to architecture, accuracy, real-world applicability. Additionally, it addresses key such computational complexity data scarcity, proposes future research directions enhance practical use these methods settings.

Language: Английский

Citations

0
Comparative Analysis of nnUNet and MedNeXt for Head and Neck Tumor Segmentation in MRI-Guided Radiotherapy DOI Creative Commons

Nikoo Moradi,

André Ferreira, Behrus Puladi

et al.

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 136 - 153

Published: Jan. 1, 2025

Language: Английский

Citations

0
Head and Neck Tumor Segmentation Using Pre-RT MRI Scans and Cascaded DualUNet DOI Creative Commons

Mikko Saukkoriipi,

Jaakko Sahlsten, Joel Jaskari

et al.

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 191 - 203

Published: Jan. 1, 2025

Language: Английский

Citations

0
A Coarse-to-Fine Framework for Mid-Radiotherapy Head and Neck Cancer MRI Segmentation DOI Creative Commons
Jing Ni, Qian Yao, Yanfei Liu

et al.

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 154 - 165

Published: Jan. 1, 2025

Language: Английский

Citations

0
Assessing Quantitative Performance and Expert Review of Multiple Deep Learning-Based Frameworks for Computed Tomography-based Abdominal Organ Auto-Segmentation DOI Creative Commons
Udbhav S. Ram, Joel A. Pogue, M. Soike

et al.

Published: March 1, 2025

Language: Английский

Citations

0
Uncertainty-Aware Deep Learning for Segmentation of Primary Tumor and Pathologic Lymph Nodes in Oropharyngeal Cancer: Insights from a Multi-Center Cohort DOI Creative Commons
Alessia de Biase, Nanna M. Sijtsema, Lisanne V. van Dijk

et al.

Computerized Medical Imaging and Graphics, Journal Year: 2025, Volume and Issue: unknown, P. 102535 - 102535

Published: March 1, 2025

Language: Английский

Citations

0
Clinical Evaluation of Deep Learning for Tumor Delineation on18F-FDG PET/CT of Head and Neck Cancer DOI Creative Commons

Dávid Kovács,

Claes Nøhr Ladefoged, Kim Francis Andersen

et al.

Journal of Nuclear Medicine, Journal Year: 2024, Volume and Issue: 65(4), P. 623 - 629

Published: Feb. 22, 2024

Artificial intelligence (AI) may decrease

Citations

2
PCNet: Prior Category Network for CT Universal Segmentation Model DOI
Yixin Chen, Yajuan Gao, Lei Zhu

et al.

IEEE Transactions on Medical Imaging, Journal Year: 2024, Volume and Issue: 43(9), P. 3319 - 3330

Published: April 30, 2024

Accurate segmentation of anatomical structures in Computed Tomography (CT) images is crucial for clinical diagnosis, treatment planning, and disease monitoring. The present deep learning methods are hindered by factors such as data scale model size. Inspired how doctors identify tissues, we propose a novel approach, the Prior Category Network (PCNet), that boosts performance leveraging prior knowledge between different categories structures. Our PCNet comprises three key components: category prompt (PCP), hierarchy system (HCS), loss (HCL). PCP utilizes Contrastive Language-Image Pretraining (CLIP), along with attention modules, to systematically define relationships identified clinicians. HCS guides distinguishing specific organs, structures, functional systems through hierarchical relationships. HCL serves consistency constraint, fortifying directional guidance provided enhance model's accuracy robustness. We conducted extensive experiments validate effectiveness our results indicate can generate high-performance, universal CT segmentation. framework also demonstrates significant transferability on multiple downstream tasks. ablation show methodology employed constructing critical importance. be accessed at https://github.com/PKU-MIPET/PCNet.

Language: Английский

Citations

1
Multi‐modal segmentation with missing image data for automatic delineation of gross tumor volumes in head and neck cancers DOI
Yao Zhao, Xin Wang, Jack Phan

et al.

Medical Physics, Journal Year: 2024, Volume and Issue: 51(10), P. 7295 - 7307

Published: June 19, 2024

Head and neck (HN) gross tumor volume (GTV) auto-segmentation is challenging due to the morphological complexity low image contrast of targets. Multi-modality images, including computed tomography (CT) positron emission (PET), are used in routine clinic assist radiation oncologists for accurate GTV delineation. However, availability PET imaging may not always be guaranteed.

Language: Английский

Citations

1