KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Hamamoto, KazuhikoSubject: search.filters.subject.deep learning

Search Results

Now showing 1 - 4 of 4
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Glioma Brain Tumor Classification Using Convolution Neural Network and Majority Voting
    (2025-01-01)
    Pilaoon, Pongsak
    ;
    Hamamoto, Kazuhiko
    ;
    Maneerat, Noppadol
    Glioma brain tumors are malignant diseases for which early detection and instant treatment will increase the survival rate. Several studies have reported the efficiency of deep learning convolutional neural networks (CNN) in diagnosing brain tumors using magnetic resonance imaging (MRI). In this study, we investigated the potential of state-of-the-art classifiers to achieve the highest accuracy in the detection of brain tumors using MRI. For this purpose, we introduced a comparative study of eight state-of-the-art classifiers. The methodology comprised three different approaches: 1) an imbalanced dataset, 2) a balanced dataset using image augmentation, and 3) ensemble learning using the best of the top five models for majority hard and soft voting. The dataset comprised converted MRI data from the repository of molecular brain neoplasia data (REMBRANDT) and brain tumor segmentation 2021 (BraTS) databases. An increasing number of MRI images and datasets has prevented overfitting. Initially, a preprocessing stage morphological operation and contrast-limited adaptive histogram equalization (CLAHE) algorithms were used to remove skeletons and artifacts and optimize the image contrast for readiness classification. The stochastic gradient descent with the momentum algorithm option was used to train the network. The trained model was used to predict the testing dataset, and the results from each pretrained network were evaluated. The experimental results demonstrated that the prediction accuracy of the trained network was significantly improved using a balanced training dataset. The discriminative image region used to interpret the predicted result using the gradient-weighted class activation mapping (Grad-CAM) algorithm was proposed in the final stage for trustworthiness. The experimental results showed that the best approach was inceptionV3 with a balanced dataset. The accuracy, sensitivity, specificity, and area under the curve were 99.73%, 99.61%, 100%, and 1.00, respectively.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Banana Plant Nutrient Deficiencies Identification using Deep Learning
    (2023-01-01)
    Han, Kadipa Aung Myo
    ;
    Maneerat, Noppadol
    ;
    Sepsirisuk, Kasemsuk
    ;
    Hamamoto, Kazuhiko
    This paper presents nutrient deficiency multi-class classification in banana plant data sets using a deep convolutional neural network. In this paper, healthy and eight nutrient deficiency classes were studied. The performance was evaluated in different situations of two public data sets. The proposed method can provide sensitivity and specificity in Raw Images, Raw Images with combination, Augmented Images, and Augmented Images with the combination. Furthermore, nearly 88% of the F1-score was outperformed.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Automated Caries Screening Using Ensemble Deep Learning on Panoramic Radiographs
    (2022-10-01)
    Bui, Toan Huy
    ;
    Hamamoto, Kazuhiko
    ;
    Paing, May Phu
    Caries prevention is essential for oral hygiene. A fully automated procedure that reduces human labor and human error is needed. This paper presents a fully automated method that segments tooth regions of interest from a panoramic radiograph to diagnose caries. A patient’s panoramic oral radiograph, which can be taken at any dental facility, is first segmented into several segments of individual teeth. Then, informative features are extracted from the teeth using a pre-trained deep learning network such as VGG, Resnet, or Xception. Each extracted feature is learned by a classification model such as random forest, k-nearest neighbor, or support vector machine. The prediction of each classifier model is considered as an individual opinion that contributes to the final diagnosis, which is decided by a majority voting method. The proposed method achieved an accuracy of 93.58%, a sensitivity of 93.91%, and a specificity of 93.33%, making it promising for widespread implementation. The proposed method, which outperforms existing methods in terms of reliability, and can facilitate dental diagnosis and reduce the need for tedious procedures.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Tooth Localization using YOLOv3 for Dental Diagnosis on Panoramic Radiographs
    (2022-01-01)
    Bui, Toan Huy
    ;
    Hamamoto, Kazuhiko
    ;
    Paing, May Phu
    Oral health is one of most major concerns that affect the life quality of billions of people around the world. Diagnosis treatment usually takes time due to the lack of doctors compared to a huge number of patients. Many researchers proposed methods to make an early disease detection for patients to assist doctors using computer aid diagnosis (CAD). However, most previous methods are not end-to-end methods and still require human involvement. The biggest challenge is that most researchers do not provide a good tooth detection technique before diagnosis. Therefore, the main objective, that builds a system to assist doctors, remains unaccomplished or just fairly successful. This paper proposed a detection method to localize the tooth using the Yolov3 model as a base network in the dental panoramic radiograph. The method consists of two main parts: image preprocessing and tooth localization. Firstly, because deep learning requires a big dataset, the original image is applied augmentation technique to improve the size of the dataset as well as diversity. Then, each image is resized to fit the input layer of the network; however, to prevent the information loss and boost the performance, we keep the original ratio of the images and change the ratio of the input layer in the model that can fit the image ratio. Next, we feed images into Yolov3, which is specially modified to fit the problem, for training. We add more detection heads into the backbone and concatenate the previous head detection’s result with a proper layer to produce a more preeminent result. The final assessment shows an impressive result that the method reaches 95.58% and 94.90% for precision and recall, respectively. As a result, our proposed method is more reliable and practical in the tooth localization field, as well as helpful to reduce the doctor's effort.