Segmentation of glioblastomas via 3D FusionNet DOI Creative Commons
Xiangyu Guo, Botao Zhang, Peng Yue

и другие.

Frontiers in Oncology, Год журнала: 2024, Номер 14

Опубликована: Ноя. 15, 2024

Introduction This study presented an end-to-end 3D deep learning model for the automatic segmentation of brain tumors. Methods The MRI data used in this were obtained from a cohort 630 GBM patients University Pennsylvania Health System (UPENN-GBM). Data augmentation techniques such as flip and rotations employed to further increase sample size training set. performance models was evaluated by recall, precision, dice score, Lesion False Positive Rate (LFPR), Average Volume Difference (AVD) Symmetric Surface Distance (ASSD). Results When applying FLAIR, T1, ceT1, T2 modalities, FusionNet-A FusionNet-C best-performing overall, with particularly excelling enhancing tumor areas, while demonstrates strong necrotic core peritumoral edema regions. excels areas across all metrics (0.75 0.83 precision 0.74 scores) also performs well regions (0.77 0.77 0.75 scores). Combinations including FLAIR ceT1 tend have better performance, especially Using only achieves recall 0.73 Visualization results indicate that our generally similar ground truth. Discussion FusionNet combines benefits U-Net SegNet, outperforming both. Although effectively segments tumors competitive accuracy, we plan extend framework achieve even performance.

Язык: Английский

Brain magnetic resonance images segmentation via improved mixtures of factor analyzers based on dynamic co-clustering DOI
Rahman Farnoosh,

Fatemeh Aghagoli

Neurocomputing, Год журнала: 2024, Номер 583, С. 127551 - 127551

Опубликована: Март 14, 2024

Язык: Английский

Процитировано

2
Deep Learning Enhanced Internet of Medical Things to Analyze Brain Computed Tomography Images of Stroke Patients DOI Open Access
Батырхан Омаров, Azhar Tursynova,

Meruert Uzak

и другие.

International Journal of Advanced Computer Science and Applications, Год журнала: 2023, Номер 14(8)

Опубликована: Янв. 1, 2023

In the realm of advancing medical technology, this paper explores a revolutionary amalgamation deep learning algorithms and Internet Medical Things (IoMT), demonstrating their efficacy in decoding labyrinthine intricacies brain Computed Tomography (CT) images from stroke patients. Deploying an avant-garde framework, we lay bare system's ability to distill complex patterns, multifarious imaging data, that often elude traditional analysis techniques. Our research punctuates pioneering leap conventional, mostly uniform methods towards harnessing power nuanced, more perplexing approach embraces human brain. This system goes beyond mere novelty, evidencing substantial enhancement early detection prognosis strokes, expediting clinical decisions, thereby potentially saving lives. Contrasting sentences – some terse, others elongated packed with details delineate our innovative concept's contours, underpinning notion burstiness. Moreover, inclusion IoMT provides digital highway for seamless real-time data flow, enabling quick responses critical situations. We demonstrate, through array comprehensive tests studies, how synergy elevates precision, speed, overall effectiveness diagnosis treatment. By embracing untapped potential combined approach, nudges world closer future where technology is woven seamlessly into fabric healthcare, allowing personalized efficient patient

Язык: Английский

Процитировано

4
Da-resbigru -brain tumor classification using Dual attention residual bi directional gated recurrent unit using MRI images DOI

Paruvelli Sreedevi,

Ajmeera Kiran,

T. Santhi Sri

и другие.

Biomedical Signal Processing and Control, Год журнала: 2023, Номер 88, С. 105596 - 105596

Опубликована: Окт. 31, 2023

Язык: Английский

Процитировано

4
Letter: Chat-GPT on brain tumors: An examination of Artificial Intelligence/Machine Learning’s ability to provide diagnoses and treatment plans for example neuro-oncology cases DOI
Francisco Zarra, Dhruv Nihal Gandhi,

Aakriti Karki

и другие.

Clinical Neurology and Neurosurgery, Год журнала: 2024, Номер 240, С. 108270 - 108270

Опубликована: Апрель 2, 2024

Язык: Английский

Процитировано

1
Prediction of Postoperative Visual Acuity in Rhegmatogenous Retinal Detachment Using OCT Images DOI Creative Commons

Sinda Hosni,

Hajer Khachnaoui,

Hsouna Mehdi Zgolli

и другие.

IEEE Access, Год журнала: 2023, Номер 11, С. 135435 - 135448

Опубликована: Янв. 1, 2023

Deep Learning (DL) methods, such as Convolution Neural Networks (CNNs), have shown great potential in diagnosing complex diseases. Among these diseases, Rhegmatogenous Retinal Detachment (RRD) stands out a critical condition necessitating precise diagnosis and postoperative Visual Acuity (VA) prediction. This research introduces DL-based Computer-Aided Diagnosis (CAD) system that utilizes Optical Coherence Tomography (OCT) images for both the of RRD prediction VA. The CAD DL techniques diverse dataset, including OCT patients with from Hedi Raies Ophthalmology Institute Tunis large public dataset normal subjects OCT. Preprocessing steps, image cropping, enhancement, denoising, resizing, are applied to tomographic images. Data oversampling augmentation address class imbalance improve by generating additional samples. Various models, pre-trained CNN models (VGG-16, Inception-V3, Inception-ResNet-V2), Bilinear (BCNN) (BCNN (VGG-16) 2 BCNN (Inception-V3) ), custom architecture, implemented VA experimental outcomes demonstrate effectiveness proposed accurately predicting achieves high accuracy, 99.87% 98.06% using model. developed represents significant advancement field By combining imaging, provides automated accurate diagnosis, showing improving patient care treatment decisions.

Язык: Английский

Процитировано

2
Comparative analysis of deep learning techniques for accurate stroke detection DOI Open Access
Titipong Kaewlek, Ketmanee Sitinwan, Kunaporn Lueangaroon

и другие.

Journal of Associated Medical Sciences, Год журнала: 2024, Номер 57(2), С. 49 - 55

Опубликована: Фев. 13, 2024

Background: The traditional diagnosis of strokes through computed tomography (CT) heavily relies on radiologists’ expertise for accurate interpretation. However, the increasing demand this critical task exceeds available radiologist workforce, necessitating innovative solutions. This research addresses challenge by introducing deep learning techniques to enhance initial screening stroke cases, thereby augmenting diagnostic capabilities. Objective: study aims compare four classifying lesions in CT images. Materials and methods: Four distinct models-CNN-2-Model, LeNet, GoogleNet, VGG-16-were trained using a dataset comprising 1,636 images, including 1,111 normal brain images 525 Seventy percent were used train most effective model, subsequently, these utilized evaluate performance each model. evaluation involved assessing accuracy, precision, sensitivity, specificity, F1 score, false positive rate, AUC. Results: process included comprehensive statistical analysis models’ prediction results. findings revealed that VGG-16 emerged as top-performing achieving an impressive accuracy 0.969, precision 0.952, sensitivity specificity 0.978, score rate 0.022, AUC 0.965. Conclusion: In conclusion, techniques, particularly demonstrate significant promise enhancing lesion classification These underscore potential leveraging advanced technologies address growing challenges pave way more efficient accessible healthcare

Язык: Английский

Процитировано

0
Deep Learning Transfer Methods for Biomedical Classification of Images DOI Open Access
Adel Al-Janabi

International Journal of Innovative Research in Multidisciplinary Education, Год журнала: 2024, Номер 03(03)

Опубликована: Март 5, 2024

Research using computers has been carried out on the effectiveness of applying deep learning transfer methods to solve problem identifying human brain tumors MRI imaging. Various and fine-tuning methodologies models have proposed implemented. The convolution networks MobileNetV2, VGG-16, Xception ResNet-50, trained ImageNet image set, were used as basic models. A convolutional neural network 2D-CNN also developed trained. computer study performance indicators revealed that method was effective On an enlarged data model outperformed other in terms accuracy: clarity with which are classified images 94%, precision 97.7%, recall 94.01%, f1 score 96%, AUC 96.90%.

Язык: Английский

Процитировано

0
Shallow Convolution Neural Network Architecture for Malignancy Identification from Brain Images DOI

Chandni,

Monika Sachdeva, Alok Kumar Singh Kushwaha

и другие.

National Academy Science Letters, Год журнала: 2024, Номер 47(6), С. 687 - 690

Опубликована: Авг. 29, 2024

Язык: Английский

Процитировано

0
Automated Detection and Prediction of Brain Tumor using ML DOI

M Shanthini,

R Monica,

V. Srinivas

и другие.

Опубликована: Июль 3, 2024

Язык: Английский

Процитировано

0
Multiple-Point Metamaterial-Inspired Microwave Sensors for Early-Stage Brain Tumor Diagnosis DOI Creative Commons
Nantakan Wongkasem,

Gabriel Cabrera

Sensors, Год журнала: 2024, Номер 24(18), С. 5953 - 5953

Опубликована: Сен. 13, 2024

Simple, instantaneous, contactless, multiple-point metamaterial-inspired microwave sensors, composed of multi-band, low-profile antennas, were developed to detect and identify meningioma tumors, the most common primary brain tumors. Based on a typical tumor size 5-20 mm, higher operating frequency, where wavelength is similar or smaller than target, crucial. The designed for Ku band range (12-18 GHz), electromagnetic property values tumors are available, implemented in this study. A seven-layered head phantom, including was defined using actual parametric frequency interest mimic human head. reflection coefficients can be recorded analyzed instantaneously, reducing high radiation consumption. It has been shown that single-band detection point not adequate classify nonlinear model parameters. On other hand, dual-band tri-band with additional detecting points, create continuous function solution problem by adding extra observation points multiple-band excitation. mapping used enhance capability. Two-point showed consistent trend between S

Язык: Английский

Процитировано

0