On comparing optimizer of UNet-VGG16 architecture for brain tumor image segmentation

Pravitasari, Anindya Apriliyanti; Iriawan, Nur; Nuraini, Ulfa Siti; Rasyid, Dwilaksana Abdullah

doi:10.1016/b978-0-323-91171-9.00004-1

Cited by 7 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The training of some classification models are mainly including VGG16, 15,16,31 ResNet18/50/101, 17,32,33 MobileNetV1/V2, 20,34 and some classification network models of Transformer. 35 The specific classification results are displayed in Table 3.…”

Section: Comparison Of Classification Resultsmentioning

confidence: 99%

“…At present, the mainstream classification algorithms, such as VGG 15,16 and ResNet, 17,18 exhibit high accuracy for object classification but are unsuitable for clinical practice due to slow detection speeds. The MobileNetV2 is a lightweight CNN network, which uses deep separable convolution to achieve end‐to‐end object classification 19,20 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A lightweight hybrid model for the automatic recognition of uterine fibroid ultrasound images based on deep learning

Cai,

Yang,

Xie

et al. 2024

J of Clinical Ultrasound

View full text Add to dashboard Cite

PurposeUterine fibroids (UF) are the most frequent tumors in ladies and can pose an enormous threat to complications, such as miscarriage. The accuracy of prognosis may also be affected by way of doctor inexperience and fatigue, underscoring the want for automatic classification fashions that can analyze UF from a giant wide variety of images.MethodsA hybrid model has been proposed that combines the MobileNetV2 community and deep convolutional generative adversarial networks (DCGAN) into useful resources for medical practitioners in figuring out UF and evaluating its characteristics. Real‐time automated classification of UF can aid in diagnosing the circumstance and minimizing subjective errors. The DCGAN science is utilized for superior statistics augmentation to create first‐rate UF images, which are labeled into UF and non‐uterine‐fibroid (NUF) classes. The MobileNetV2 model then precisely classifies the photos based totally on this data.ResultsThe overall performance of the hybrid model contrasts with different models. The hybrid model achieves a real‐time classification velocity of 40 frames per second (FPS), an accuracy of 97.45%, and an F1 rating of 0.9741.ConclusionBy using this deep learning hybrid approach, we address the shortcomings of the current classification methods of uterine fibroid.

show abstract

Section: Comparison Of Classification Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A lightweight hybrid model for the automatic recognition of uterine fibroid ultrasound images based on deep learning

Cai,

Yang,

Xie

et al. 2024

J of Clinical Ultrasound

View full text Add to dashboard Cite

show abstract

“…These measures show that the suggested technique outperforms state-of-the-art methods. [16] Examined that Image segmentation as a computerbased diagnostic approach in brain tumour magnetic resonance imaging (MRI) is critical for medical diagnosis. The primary goal of picture segmentation is to see the distinct form of the tumour.…”

Section: Ease Of Usementioning

confidence: 99%

Optimized Brain Tumour Segmentation and Classification Using VGG UNET and VGG-19 with ABC-WOA Algorithm

Sharma

2024

IJSREM

View full text Add to dashboard Cite

Accurate brain tumour classification is essential for treatment planning and patient care in medical image analysis. In this study, we used sophisticated deep learning algorithms to improve brain tumour categorization. We used VGG-UNET for segmentation to precisely delineate tumour locations in MRI scans and VGG-19 for classification, a popular convolutional neural network architecture for image classification. We used a hybrid ABC-WOA hyperparameter tweaking technique to increase the accuracy and resilience of our VGG-19 model. We compared our model against ResNet- 50 and AlexNet, two popular convolutional neural network designs, on accuracy, precision, recall, and F1-scores. Hyperparameter-tuned VGG-19 model had excellent discrimination, with accuracy metrics topping 99.1% and a remarkable AUC value of 0.99. ResNet-50 and AlexNet performed well, however they were not as accurate and precise as VGG-19. These data show that our technique could revolutionize brain tumour classification, providing doctors with a trustworthy tool for precise diagnosis and treatment planning. Future study might examine the scalability and generalizability of our findings in larger datasets and clinical contexts, improving patient outcomes and neuro-oncology research. VGG-UNET segmentation, VGG-19 classification, and a hybrid ABC-WOA hyperparameter tuning approach improve brain tumour classification accuracy. The hyperparameter-tuned VGG-19 model's proven performance makes it a promising choice for clinical brain tumour classification tasks, providing physicians with accurate diagnosis and prognosis. Keywords— VGG-UNET, VGG-19, ResNet-50, Alexnet, Brain-Tumour, ABC-WOA, Segmentation, MRI Images.

show abstract

“…Yani girdi olarak (224,224.3) tensor bulunmaktadır. Eğitim setinde hesaplanan ortalama RGB değerinin her pikselden çıkarılması burada yapılan tek ön işlemedir [24].…”

Section: Vvg16 Modeliunclassified

Görüntülerden Derin Öğrenmeye Dayalı Otomatik Metin Çıkarma: Bir Görüntü Yakalama Sistemi

Karaca

Daş

2022

Fırat Üniversitesi Mühendislik Bilimleri Dergisi

View full text Add to dashboard Cite

Bilgisayarlı görme ve doğal dil işlemenin çalışma alanlarından biri olan görüntü yakalama (image capturing), doğal bir dil kullanarak görüntü içeriğini otomatik olarak tanımlama görevidir. Bu çalışmada, MS COCO veri seti üzerinde İngilizce dili için encoder-decoder tekniğine dayalı bir otomatik altyazı oluşturma yaklaşımı önerilmiştir. Önerilen yaklaşımda, görüntü özniteliklerini çıkarmak için encoder olarak Evrişimli Sinir Ağı (CNN) mimarisi ve görüntülerden altyazı oluşturmak için bir decoder olarak Tekrarlayan Sinir Ağı (RNN) mimarisi kullanılmıştır. Önerilen yaklaşımın performansı BLEU, METEOR ve ROUGE_L değerlendirme kriterleri kullanılarak değerlendirilmiş ve her bir görüntüden 5 cümle elde edilmiştir. Deneysel sonuçlar, modelin görüntülerdeki nesneleri doğru bir şekilde algılamada tatmin edici olduğunu göstermektedir.

show abstract

On comparing optimizer of UNet-VGG16 architecture for brain tumor image segmentation

Cited by 7 publications

References 11 publications

A lightweight hybrid model for the automatic recognition of uterine fibroid ultrasound images based on deep learning

A lightweight hybrid model for the automatic recognition of uterine fibroid ultrasound images based on deep learning

Optimized Brain Tumour Segmentation and Classification Using VGG UNET and VGG-19 with ABC-WOA Algorithm

Görüntülerden Derin Öğrenmeye Dayalı Otomatik Metin Çıkarma: Bir Görüntü Yakalama Sistemi

Contact Info

Product

Resources

About