Classification of Diabetic Rat Histopathology Images Using Convolutional Neural Networks

Yurttakal, Ahmet Haşim; Erbay, Hasan; Çınarer, Gökalp; Baş, Hatice

doi:10.2991/ijcis.d.201110.001

Cited by 7 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the activation layer, it is ensured that non‐linear data are included in certain intervals. In this way, the input data is normalized and the learning process in the hidden layers is accelerated (Yurttakal et al., 2021 ). In the architectures in this study, the process of reducing the size of the data from the feature map from the convolution layer is performed in the activation function rectified linear unit (ReLu) pooling layer.…”

Section: Methodsmentioning

confidence: 99%

Maize seeds forecasting with hybrid directional and bi‐directional long short‐term memory models

Isik,

Tasdemir,

Taspinar

et al. 2023

Food Science & Nutrition

View full text Add to dashboard Cite

The purity of the seeds is one of the important factors that increase the yield. For this reason, the classification of maize cultivars constitutes a significant problem. Within the scope of this study, six different classification models were designed to solve this problem. A special dataset was created to be used in the models designed for the study. The dataset contains a total of 14,469 images in four classes. Images belong to four different maize types, BT6470, CALIPOS, ES_ARMANDI, and HIVA, taken from the BIOTEK company. AlexNet and ResNet50 architectures, with the transfer learning method, were used in the models created for the image classification. In order to improve the classification success, LSTM (Directional Long Short‐Term Memory) and BiLSTM (Bi‐directional Long Short‐Term Memory) algorithms and AlexNet and ResNet50 architectures were hybridized. As a result of the classifications, the highest classification success was obtained from the ResNet50+BiLSTM model with 98.10%.

show abstract

Section: Methodsmentioning

confidence: 99%

Maize seeds forecasting with hybrid directional and bi‐directional long short‐term memory models

Isik,

Tasdemir,

Taspinar

et al. 2023

Food Science & Nutrition

View full text Add to dashboard Cite

show abstract

“…Several papers performing glomerular classification resized their glomerular ROIs using bicubic interpolation with antialiasing [34,47,86]. Bicubic interpolation is similar to bilinear interpolation whereby pixel coordinates (x, y) are interpolated in the (j+x, k+y) space.…”

Section: Pre-processingmentioning

confidence: 99%

“…A transfer learning approach was performed on three well-known deep CNNs to automatically initialize the network weights for better generalizing to the glomerular image diseases [87]. Generally, transfer learning is a method in which a network is pre-trained on a large dataset and is then used for a new problem [47]. This technique is a popular approach in deep learning because it requires little data to train a deep CNN and has the potential to reduce the problem of overfitting [87].…”

Section: Transfer Learningmentioning

confidence: 99%

Computational Classification Methods in Renal Pathology

Basso

2024

Preprint

View full text Add to dashboard Cite

When assessing kidney biopsies, pathologists use Light microscopy (LM), immunofluorescence, and electron microscopy to describe and diagnose glomerular lesions and diseases. These are laborious, costly, fraught with inter-observer variability, and can have delays in turn-around time. Thus, computational approaches can be designed as screening and/or diagnostic tools, potentially relieving pathologist time, healthcare resources, while also having the ability to identify novel biomarkers, including subvisual features. This thesis compares a novel Biomarker feature extraction (BFE) model and test several pre- trained deep learning models to diagnose three glomerular diseases using Periodic acid-Schiff (PAS) stained images. The BFE model extracted a panel of 233 explainable biomarkers related to colour, morphology, and microstructural texture that describe underlying pathology. These biomarkers were subsequently narrowed to ten morphological and microstructural texture fea- tures for classification. The proposed pre-trained deep learning models used data augmentation and Gradient-weighted Class Activation Mapping (Grad-CAM) for better performance and inter- pretability. All classification models were then used to classify Minimal change disease (MCD), Membranous nephropathy (MN), and Thin-basement membrane nephropathy (TBMN) diseases on a glomerular and patient-level basis. The BFE model resulted in a glomerular validation accuracy of 67.6% and testing accuracy of 76.8%. All deep learning approaches had higher validation accuracies (most for VGG16 at 78.5%) but lower testing accuracies. The highest testing accuracy at the glomerular level was VGG16 at 71.9%, while that at the patient-level was InceptionV3 at 73.3%. Patient-level classification results showed higher accuracy for the BFE model (86.76%) compared to all deep learning methods. The BFE model was superior to three established deep learning models. The small dataset was likely contributory to the lower performance of the deep learning models, while model in- terpretability was clearly superior for the BFE. The results highlight the technical performance of both the traditional and deep learning approaches and describe how they may translate to clinical utility. Furthermore, these algorithms can be applied to clinical datasets for novel prognostic and mechanistic biomarker discovery.

show abstract

“…This layer has a kind of neural network structure. Classification is made in this layer [45]. The structure of CNN models with high classification success emerges as a result of long trials [46].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Fire Detection inImages Using FrameworkBased on Image Processing, Motion Detection and Convolutional Neural Network

Taşpınar¹,

Köklü²,

Altin³

2021

ijisae

View full text Add to dashboard Cite

Fire detection in images has been frequently used recently to detect fire at an early stage. These methods play an important role in reducing the loss of life and property. Fire is not only chemically complex, but also physically very complex. The shape and color of the flame varies according to the type of fuel in the fire. This has made fire detection a very challenging problem. Advanced image processing algorithms are also needed to accurately detect fire. To solve this problem, a three-stage fire framework was created in this study. In the first stage, the flame region was extracted from the images containing the fire region with the basic image processing algorithms. At this stage, reduce brightness, HSL, YCbCr, median and herbaceous filters are applied successively to the image. Since the flame image has a polygonal structure by nature, the number of edges of the flame region has been found. In the second stage, the mobility feature of the flame was utilized. For this purpose, the mobility of the flame was determined by comparing the video frames containing the fire image. The CNN method was used to detect the fire in the images. The CNN model was trained with the transfer learning method using the Inception V3, SequeezeNet, VGG16 and VGG19 trained models. As a result of the tests of the models, 98.8%, 97.0%, 97.3% and 96.8% classification success were obtained, respectively. With the proposed fire detection framework, it is thought that the damage caused by the fire can be reduced by early detection of the fire and timely intervention.

show abstract

Classification of Diabetic Rat Histopathology Images Using Convolutional Neural Networks

Cited by 7 publications

References 37 publications

Maize seeds forecasting with hybrid directional and bi‐directional long short‐term memory models

Maize seeds forecasting with hybrid directional and bi‐directional long short‐term memory models

Computational Classification Methods in Renal Pathology

Fire Detection inImages Using FrameworkBased on Image Processing, Motion Detection and Convolutional Neural Network

Contact Info

Product

Resources

About