Suchen
Filtern nach:
Stichwort
Deep learning
Entfernen Zwang Stichwort: Deep learning
Fach
Data Science
Entfernen Zwang Fach: Data Science
1 - 3 von 3
Anzahl der Ergebnisse pro Seite angezeigt werden
Suchergebnisse
-
- Beschreibung:
- Early diagnosis of brain tumors is crucial for treatment planning and increasing the survival rates of infected patients. In fact, brain tumors exist in a range of different forms, sizes, and features, as well as treatment choices. One of the essential roles of neurologists and radiologists is the diagnosis of brain tumors in their early stages. However, manual brain tumor diagnosis is difficult, time-consuming, and prone to error. Based on the problem highlighted, an automated brain tumor detection system is mandatory to identify the tumor in its initial stages. This research presents an efficient deep learningbased system for the classification of brain tumors from brain MRI using the deep convolutional network and salp swarm algorithm. All experiments are performed using the publicly available brain tumor Kaggle dataset. To enhance the classification rate, preprocessing and data augmentation such as skewed data ideas are devised. In addition, AlexNet and VGG19 are leveraged to perform specific functionality. Finally, all features merged into a single feature vector for brain tumor classification. Some of the extracted features found insignificant towards effective classification. Hence, we employed an efficient feature selection technique named slap swarm to find the most discriminative features to attain best tumor classification rate. Finally, several SVM kernels are merged for the final classification and 99.1% accuracy is achieved by selecting 4111 optimal features from 8192.
- Stichwort:
- Brain tumor, Public health, Health risks, Deep learning, Transfer learning, and MRI
- Fach:
- Artificial Intelligence and Data Science
- Schöpfer:
- Almutairi, Fahad , Roy, Sudipta , Alkhurim, Alhassan , Saba, Tanzila , Fayyaz, Abdul Muiz , Rehman, Amjad , and Alyami, Jaber
- Owner:
- n.sakthivel@jioinstitute.edu.in
- Herausgeber:
- Springer Nature
- Ort:
- Switzerland
- Sprache:
- English
- Datum hochgeladen:
- 11-02-2023
- Datum geändert:
- 16-02-2023
- Datum erstellt:
- 01-01-2023
- Rights Statement Tesim:
- In Copyright
- License Tesim:
- All rights reserved
- Resource Type:
- Article
- Identifikator:
- 10.1007/s12559-022-10096-2
-
- Beschreibung:
- Identification and recognition of number plate is very difficult from low resolution images due to poor boundary and contrast. Our goal is to identify the digits from a low-quality number plate image correctly, but correct detection was exceedingly difficult in some cases due to the low-resolution image. Another goal of this paper was to upscale the image from a very low resolution to high resolution to recover helpful information to improve the accuracy of number plate detection and recognition. We have used Enhanced- Super-Resolution with Generative Adversarial Network (SRGAN). We modified native Dense Blocks of the Generative Adversarial Network with a Residual in Residual Dense Block model. In addition to Convolutional Neural Networks for thresholding. We also used a Rectified Linear Unit (ReLU) activation layer. The plate image is then used for segmentation using the OCR model for detection and recognizing the characters in the number plates. The Optical character recognition (OCR) model reaches an average accuracy of 84% for high resolution, whereas the accuracy is 4% - 7% for low resolution. The model’s accuracy increases with the resolution enhancement of the plate images. ESRGAN provides better enhancement of low-resolution images than SRGAN and Pro-SRGAN, which the OCR model validates. The accuracy significantly increased digit/alphabet detection in the number plate than the original low-resolution image when converted to a high-resolution image using ESRGAN.
- Stichwort:
- Structural similarity of images, Number plate detection, Residual dense block, Super-resolution, Deep learning, and Optical character recognition
- Fach:
- Artificial Intelligence and Data Science
- Schöpfer:
- Roy, Sudipta, Ganguly, Debayan , Pal, Debojyoti , Chatterjee, Kingshuk , and Kabiraj, Anwesh
- Mitwirkender:
- Jio Institute, CVMIComputer Vision in Medical Imaging Project
- Owner:
- n.sakthivel@jioinstitute.edu.in
- Herausgeber:
- Springer Nature
- Ort:
- Switzerland
- Sprache:
- English
- Datum hochgeladen:
- 11-02-2023
- Datum geändert:
- 16-02-2023
- Datum erstellt:
- 01-09-2022
- Rights Statement Tesim:
- In Copyright
- License Tesim:
- All rights reserved
- Resource Type:
- Article
- Identifikator:
- 10.1007/s11042-022-14018-0
-
- Beschreibung:
- Fetal brain segmentation and gestational age prediction have been under active research in the field of medical image processing for a long time. However, both these tasks are challenging due to factors like difficulty in acquiring a proper fetal brain image owing to the fetal movement during the scan. With the recent advancements in deep learning, many models have been proposed for performing both the tasks, individually, with good accuracy. In this paper, we present Multi-Tasking Single Encoder U-Net, MTSE U-Net, a deep learning architecture for performing three tasks on fetal brain images. The first task is the segmentation of the fetal brain into its seven components: intracranial space and extra-axial cerebrospinal fluid spaces, gray matter, white matter, ventricles, cerebellum, deep gray matter, and brainstem, and spinal cord. The second task is the prediction of the type of the fetal brain (pathological or neurotypical). The third task is the prediction of the gestational age of the fetus from its brain. All of this will be performed by a single model. The fetal brain images can be obtained by segmenting it from the fetal magnetic resonance images using any of the previous works on fetal brain segmentation, thus showing our work as an extension of the already existing segmentation works. The Jaccard similarity and Dice score for the segmentation task by this model are 77 and 82%, respectively, accuracy for the type of prediction task is 89% and the mean absolute error for the gestational age task is 0.83 weeks. The salient region identification by the model is also tested and these results show that a single model can perform multiple, but related, tasks simultaneously with good accuracy, thus eliminating the need to use separate models for each task.
- Stichwort:
- Medical image processing, Fetal brain segmentation, Deep learning, Fetal gestational age prediction, and Convolutional neural networks
- Fach:
- Data Science and Artificial Intelligence
- Schöpfer:
- Ganguly, Debayan , Chatterjee, Kingshuk , Gangopadhyay, Tuhinangshu , Sarkar, Surjadeep , Halder, Shinjini , Dasgupta, Paramik , and Roy, Sudipta
- Owner:
- n.sakthivel@jioinstitute.edu.in
- Herausgeber:
- Springer Nature
- Ort:
- Switzerland
- Sprache:
- English
- Datum hochgeladen:
- 11-02-2023
- Datum geändert:
- 16-02-2023
- Datum erstellt:
- 01-11-2022
- Rights Statement Tesim:
- In Copyright
- License Tesim:
- All rights reserved
- Resource Type:
- Article
- Identifikator:
- 10.1007/s13721-022-00394-y