Optimizing Automated Hematoma Expansion Classification from Baseline and Follow-Up Head Computed Tomography DOI Creative Commons
Tran Anh Tuan, Dmitriy Desser, Tal Zeevi

и другие.

Applied Sciences, Год журнала: 2024, Номер 15(1), С. 111 - 111

Опубликована: Дек. 27, 2024

Hematoma expansion (HE) is an independent predictor of poor outcomes and a modifiable treatment target in intracerebral hemorrhage (ICH). Evaluating HE large datasets requires segmentation hematomas on admission follow-up CT scans, process that time-consuming labor-intensive large-scale studies. Automated can expedite this process; however, cumulative errors from scans hamper accurate classification. In study, we combined tandem deep-learning classification model with automated to generate probability measures for false classifications. With strategy, limit expert review hematoma segmentations subset the dataset, tailored research team's preferred sensitivity or specificity thresholds their tolerance false-positive versus false-negative results. We utilized three separate multicentric cohorts cross-validation/training, internal testing, external validation (n = 2261) develop test pipeline ground truth binary annotations (≥3, ≥6, ≥9, ≥12.5 mL). Applying 95% threshold showed practical efficient strategy annotation ICH datasets. This excluded 47-88% test-negative predictions different definitions, less than 2% misclassification both cohorts. Our offers time-efficient optimizable method generating classifications datasets, reducing burden while minimizing rate.

Язык: Английский

Enhancing medical image classification via federated learning and pre-trained model DOI Creative Commons
Parvathaneni Naga Srinivasu,

G. Jaya Lakshmi,

Sujatha Canavoy Narahari

и другие.

Egyptian Informatics Journal, Год журнала: 2024, Номер 27, С. 100530 - 100530

Опубликована: Авг. 28, 2024

Язык: Английский

Процитировано

8
MRI intracranial Neoplasm classification using hybrid LOA-based deep learning classifier DOI

Jérémie Mary,

M. Suganthi

Biomedical Signal Processing and Control, Год журнала: 2025, Номер 104, С. 107560 - 107560

Опубликована: Янв. 28, 2025

Язык: Английский

Процитировано

0
Computer-aided diagnosis for multi-class classification of brain tumors using CNN features via transfer-learning DOI
Agnesh Chandra Yadav,

Krish Shah,

Aaryan Purohit

и другие.

Multimedia Tools and Applications, Год журнала: 2025, Номер unknown

Опубликована: Март 15, 2025

Язык: Английский

Процитировано

0
Machine learning fusion for glioma tumor detection DOI Creative Commons

C. Gunasundari,

K. Selva Bhuvaneswari

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 2, 2025

The early detection of brain tumors is very important for treating them and improving the quality life patients. Through advanced imaging techniques, doctors can now make more informed decisions. This paper introduces a framework tumor system capable grading gliomas. system's implementation begins with acquisition analysis magnetic resonance images. Key features indicative gliomas are extracted classified as independent components. A deep learning model then employed to categorize these proposed classifies into three primary categories: meningioma, pituitary, glioma. Performance evaluation demonstrates high level accuracy (99.21%), specificity (98.3%), sensitivity (97.83%). Further research validation essential refine ensure its clinical applicability. development accurate efficient systems holds significant promise enhancing patient care survival rates.

Язык: Английский

Процитировано

0
Efficient and accurate brain tumor detection and classification using advanced hybrid filtering and self-attention generative adversarial networks DOI

R. Rajakumari,

A. Selvapandian

Neural Computing and Applications, Год журнала: 2025, Номер unknown

Опубликована: Май 7, 2025

Язык: Английский

Процитировано

0
X-Brain: Explainable recognition of brain tumors using robust deep attention CNN DOI
Moshiur Rahman Tonmoy, Maria Shams, Md. Akhtaruzzaman Adnan

и другие.

Biomedical Signal Processing and Control, Год журнала: 2024, Номер 100, С. 106988 - 106988

Опубликована: Окт. 16, 2024

Язык: Английский

Процитировано

1
Optimized attention-based lightweight CNN using particle swarm optimization for brain tumor classification DOI
Okan Güder, Yasemın Çetın-Kaya

Biomedical Signal Processing and Control, Год журнала: 2024, Номер 100, С. 107126 - 107126

Опубликована: Ноя. 14, 2024

Язык: Английский

Процитировано

1
A Dual-Branch Lightweight Model for Extracting Characteristics to Classify Brain Tumors DOI Open Access

G. Sangeetha,

G. Vadivu,

Sundara Raja Perumal R.

и другие.

Journal of Advances in Information Technology, Год журнала: 2024, Номер 15(9), С. 1035 - 1046

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

0
A method for measuring hairline length and discriminating hairline recession grades based on the BiSeNet model DOI

Yuhua Ai,

Guoliang Wei, Junke Wu

и другие.

Measurement Science and Technology, Год журнала: 2024, Номер 36(1), С. 015705 - 015705

Опубликована: Окт. 18, 2024

Abstract Hair plays an important role in a person’s appearance. According to survey by the World Health Organization, approximately 70% of adults have scalp and hair problems. Doctors currently make hairline recession diagnoses based on loss criteria, but this approach is subjective. This paper proposes novel method for objectively assessing grades. First, Bilateral Segmentation Network model utilized obtain facial segmentation image. Second, utilizes connected components improve results. Next, labeling key points used extract part features eyebrow region calculate related values. Finally, judgment length grade realized combining these with camera calibration. In paper, front-face images 50 volunteers were collected determination. The results expert doctors compared method. showed 1.3 cm difference average about 80% similarity judgments. conclusion, using machine vision methods measure height provides objective repeatable

Язык: Английский

Процитировано

0
Optimizing Automated Hematoma Expansion Classification from Baseline and Follow-Up Head Computed Tomography DOI Creative Commons
Tran Anh Tuan, Dmitriy Desser, Tal Zeevi

и другие.

Applied Sciences, Год журнала: 2024, Номер 15(1), С. 111 - 111

Опубликована: Дек. 27, 2024

Hematoma expansion (HE) is an independent predictor of poor outcomes and a modifiable treatment target in intracerebral hemorrhage (ICH). Evaluating HE large datasets requires segmentation hematomas on admission follow-up CT scans, process that time-consuming labor-intensive large-scale studies. Automated can expedite this process; however, cumulative errors from scans hamper accurate classification. In study, we combined tandem deep-learning classification model with automated to generate probability measures for false classifications. With strategy, limit expert review hematoma segmentations subset the dataset, tailored research team's preferred sensitivity or specificity thresholds their tolerance false-positive versus false-negative results. We utilized three separate multicentric cohorts cross-validation/training, internal testing, external validation (n = 2261) develop test pipeline ground truth binary annotations (≥3, ≥6, ≥9, ≥12.5 mL). Applying 95% threshold showed practical efficient strategy annotation ICH datasets. This excluded 47-88% test-negative predictions different definitions, less than 2% misclassification both cohorts. Our offers time-efficient optimizable method generating classifications datasets, reducing burden while minimizing rate.

Язык: Английский

Процитировано

0