Train Deep Convolutional Neural Networks Research Articles

Quantification of cervical spinal stenosis by automated 3D MRI segmentation of spinal cord and cerebrospinal fluid space

Abstract Design Prospective diagnostic study. Objectives Anatomical evaluation and graduation of the severity of spinal stenosis is essential in degenerative cervical spine disease. In clinical practice, this is subjectively categorized on cervical MRI lacking an objective and reliable classification. We implemented a fully-automated quantification of spinal canal compromise through 3D T2-weighted MRI segmentation. Setting Medical Center - University of Freiburg, Germany. Methods Evaluation of 202 participants receiving 3D T2-weighted MRI of the cervical spine. Segments C2/3 to C6/7 were analyzed for spinal cord and cerebrospinal fluid space volume through a fully-automated segmentation based on a trained deep convolutional neural network. Spinal canal narrowing was characterized by relative values, across sever segments as adapted Maximal Canal Compromise (aMCC), and within the index segment as adapted Spinal Cord Occupation Ratio (aSCOR). Additionally, all segments were subjectively categorized by three observers as “no”, “relative” or “absolute” stenosis. Computed scores were applied on the subjective categorization. Results 798 (79.0%) segments were subjectively categorized as “no” stenosis, 85 (8.4%) as “relative” stenosis, and 127 (12.6%) as “absolute” stenosis. The calculated scores revealed significant differences between each category (p ≤ 0.001). Youden’s Index analysis of ROC curves revealed optimal cut-offs to distinguish between “no” and “relative” stenosis for aMCC = 1.18 and aSCOR = 36.9%, and between “relative” and “absolute” stenosis for aMCC = 1.54 and aSCOR = 49.3%. Conclusion The presented fully-automated segmentation algorithm provides high diagnostic accuracy and objective classification of cervical spinal stenosis. The calculated cut-offs can be used for convenient radiological quantification of the severity of spinal canal compromise in clinical routine.

Enhancing Skin Disease Classification: A Novel Approach With Tailored Loss Functions And SMOTE Sumeet Ghumare

Although skin disease like skin cancer is a common health problem worldwide, early identification is crucial to its recovery. By using medical photos, the rise of artificial intelligence (AI) has transformed the detection of skin diseases. Despite the reality that various deep learning models have been created with this goal in mind, class imbalance in multi class classification all poses a serious difficulty and imbalance among the classes. This work offers a novel strategy to reduce class imbalance in the categorization of skin diseases, leading to significant accuracy gains. One of the largest skin cancer datasets currently accessible, it consists of 33,106 dermoscopy photos from seven different kinds of skin diseases as a starting point. The main goal is to enhance skin disease classification algorithms’ performance on this imbalance dataset. We are going to use a two-pronged strategy to combat the class disparity and GAN (Generative adversarial network) Based Oversampling or Meta-learning in order to successfully equalize the representation of each class during training, we first design a balanced Dynamic Mini-Batch Size logic, SMOTE (Synthetic Minority Oversampling Technique) and Augmenter. Second, we provide a new loss function designed to take into account the unique features of the dataset. The outcomes are startling. These findings underscore the efficacy of our hybrid approach in training deep convolutional neural networks for imbalanced skin disease datasets. By combining data-level balancing techniques with a carefully designed loss function at the algorithm level, we address the challenge of among the classes, paving the way for more accurate and reliable skin cancer diagnoses. Key Words: Dermoscopy images, DenseNet169, Convolution neural network, SMOTE (Synthetic Minority Over-sampling Technique, GAN(Generative adversarial network), Mini-Batch Logic, Augmenter

Deep Learning-Based Leaf Disease Detection in Crop Using Images for Agricultural Application

The "Leaf Disease Detection" system addresses the critical challenge of plant diseases in agriculture through the implementation of an automated solution leveraging deep learning techniques. In this comprehensive endeavor, convolutional neural networks (CNNs), specifically DenseNet-121, ResNet-50, VGG-16, and Inception V4, are fine-tuned for efficient and accurate identification of plant diseases. The project utilizes the Plant Village dataset, encompassing 54,305 images across 38 plant disease classes, to conduct a comparative analysis of model performance. DenseNet-121 emerged as the top-performing model, achieving an exceptional 99.81% classification accuracy, surpassing other state-of-the-art models. The system's methodology strategically employs transfer learning to overcome computational challenges associated with training deep CNN layers. This approach, coupled with the multi-class classification strategy, proves robust in handling diverse plant species and diseases within each class. The results highlight the superior efficiency of transfer learning in comparison to building models from scratch, showcasing the potential for real-world applications in agriculture. The system's success is attributed to the careful optimization of hyper parameters and the adoption of advanced deep learning techniques, offering a promising avenue for automated and accurate plant disease detection, with implications for improving agricultural practices, minimizing economic losses, and ensuring global food security.

Human Visual Cortex and Deep Convolutional Neural Network Care Deeply about Object Background.

Deep convolutional neural networks (DCNNs) are able to partially predict brain activity during object categorization tasks, but factors contributing to this predictive power are not fully understood. Our study aimed to investigate the factors contributing to the predictive power of DCNNs in object categorization tasks. We compared the activity of four DCNN architectures with EEG recordings obtained from 62 human participants during an object categorization task. Previous physiological studies on object categorization have highlighted the importance of figure-ground segregation-the ability to distinguish objects from their backgrounds. Therefore, we investigated whether figure-ground segregation could explain the predictive power of DCNNs. Using a stimulus set consisting of identical target objects embedded in different backgrounds, we examined the influence of object background versus object category within both EEG and DCNN activity. Crucially, the recombination of naturalistic objects and experimentally controlled backgrounds creates a challenging and naturalistic task, while retaining experimental control. Our results showed that early EEG activity (< 100 msec) and early DCNN layers represent object background rather than object category. We also found that the ability of DCNNs to predict EEG activity is primarily influenced by how both systems process object backgrounds, rather than object categories. We demonstrated the role of figure-ground segregation as a potential prerequisite for recognition of object features, by contrasting the activations of trained and untrained (i.e., random weights) DCNNs. These findings suggest that both human visual cortex and DCNNs prioritize the segregation of object backgrounds and target objects to perform object categorization. Altogether, our study provides new insights into the mechanisms underlying object categorization as we demonstrated that both human visual cortex and DCNNs care deeply about object background.

AFEX-Net: Adaptive feature extraction convolutional neural network for classifying computerized tomography images.

Deep convolutional neural networks are favored methods that are widely used in medical image processing due to their demonstrated performance in this area. Recently, the emergence of new lung diseases, such as COVID-19, and the possibility of early detection of their symptoms from chest computerized tomography images has attracted many researchers to classify diseases by training deep convolutional neural networks on lung computerized tomography images. The trained networks are expected to distinguish between different lung indications in various diseases, especially at the early stages. The purpose of this study is to introduce and assess an efficient deep convolutional neural network, called AFEX-Net, that can classify different lung diseases from chest computerized tomography images. We designed a lightweight convolutional neural network called AFEX-Net with adaptive feature extraction layers, adaptive pooling layers, and adaptive activation functions. We trained and tested AFEX-Net on a dataset of more than 10,000 chest computerized tomography slices from different lung diseases (CC dataset), using an effective pre-processing method to remove bias. We also applied AFEX-Net to the public COVID-CTset dataset to assess its generalizability. The study was mainly conducted based on data collected over approximately six months during the pandemic outbreak in Afzalipour Hospital, Iran, which is the largest hospital in Southeast Iran. AFEX-Net achieved high accuracy and fast training on both datasets, outperforming several state-of-the-art convolutional neural networks. It has an accuracy of and on the CC and COVID-CTset datasets, respectively, with a learning speed that is 3 times faster compared to similar methods due to its lightweight structure. AFEX-Net was able to extract distinguishing features and classify chest computerized tomography images, especially at the early stages of lung diseases. The AFEX-Net is a high-performing convolutional neural network for classifying lung diseases from chest CT images. It is efficient, adaptable, and compatible with input data, making it a reliable tool for early detection and diagnosis of lung diseases.

Blind light field image quality assessment based on deep meta-learning.

In recent years, the use of deep convolutional neural networks (DCNNs) for light field image quality assessment (LFIQA) has gained significant attention. Despite their notable successes, it is widely accepted that training DCNNs heavily depends on a large amount of annotated data. Additionally, convolutional network-based LFIQA methods show a limitation in capturing long-range dependencies. Unfortunately, LFIQA is essentially a typical small-sample problem, leading to existing DCNN-based LFIQA metrics requiring data augmentation but with unsatisfactory performance. To address these issues, this study proposes utilizing the self-attention capability of the Swin Transformer to efficiently capture spatial-angular information while employing meta-learning for small-sample learning in the LFIQA task. Specifically, a collection of LFIQA tasks is gathered, representing different distortions. Then, meta-learning is employed to acquire shared prior knowledge across diverse distortions. Finally, the quality prior model is fine-tuned on a target LFIQA task to obtain the final LFIQA model quickly. Experimental results show that the proposed LFIQA metric achieves high consistency with subjective scores, and outperforms several state-of-the-art LFIQA approaches.

New Hybrid Graph Convolution Neural Network with Applications in Game Strategy

Deep convolutional neural networks (DCNNs) have enjoyed much success in many applications, such as computer vision, automated medical diagnosis, autonomous systems, etc. Another application of DCNNs is for game strategies, where the deep neural network architecture can be used to directly represent and learn strategies from expert players on different sides. Many game states can be expressed not only as a matrix data structure suitable for DCNN training but also as a graph data structure. Most of the available DCNN methods ignore the territory characteristics of both sides’ positions based on the game rules. Therefore, in this paper, we propose a hybrid approach to the graph neural network to extract the features of the model of game-playing strategies and fuse it into a DCNN. As a graph learning model, graph convolutional networks (GCNs) provide a scheme by which to extract the features in a graph structure, which can better extract the features in the relationship between the game-playing strategies. We validate the work and design a hybrid network to integrate GCNs and DCNNs in the game of Go and show that on the KGS Go dataset, the performance of the hybrid model outperforms the traditional DCNN model. The hybrid model demonstrates a good performance in extracting the game strategy of Go.

μPEWFace: Parallel ensemble of weighted deep convolutional neural networks with novel loss functions for face-based authentication

Training Deep Convolutional Neural Networks (DCNN) with large-scale face images takes a significant amount of processing resources and the tuning/optimization time cost for face-based authentication. It must continue to improve its accuracy and speed during the matching phase. In this study, we propose a method, μPEWFace, that inherits not only the benefits of recent DCNNs with adaptive loss functions, such as MagFace, ElasticFace, and AdaFace, for boosting accuracy but also the means to reduce matching time. Consequently, our method expands on the weighted voting mechanism that leverages suboptimal trained models to improve the discriminative capabilities of face-based authentication, as opposed to searching for the best optimal model. In order to boost the efficiency of face-based authentication, we also propose performing the matching phase for each model in parallel. To demonstrate the speed and accuracy of our method, we conduct exhaustive experiments using a variety of well-known benchmarks, including LFW, CFP-FP, AgeDB-30, CALFW, CPLFW, and IJB-B. The experimental findings demonstrate that the proposed method for face-based authentication achieves state-of-the-art results and exhibits remarkable performance.© 2023 Published by Elsevier Ltd.

Modular Neural Networks for Osteoporosis Detection in Mandibular Cone-Beam Computed Tomography Scans.

In this technical note, we examine the capabilities of deep convolutional neural networks (DCNNs) for diagnosing osteoporosis through cone-beam computed tomography (CBCT) scans of the mandible. The evaluation was conducted using 188 patients' mandibular CBCT images utilizing DCNN models built on the ResNet-101 framework. We adopted a segmented three-phase method to assess osteoporosis. Stage 1 focused on mandibular bone slice identification, Stage 2 pinpointed the coordinates for mandibular bone cross-sectional views, and Stage 3 computed the mandibular bone's thickness, highlighting osteoporotic variances. The procedure, built using ResNet-101 networks, showcased efficacy in osteoporosis detection using CBCT scans: Stage 1 achieved a remarkable 98.85% training accuracy, Stage 2 minimized L1 loss to a mere 1.02 pixels, and the last stage's bone thickness computation algorithm reported a mean squared error of 0.8377. These findings underline the significant potential of AI in osteoporosis identification and its promise for enhanced medical care. The compartmentalized method endorses a sturdier DCNN training and heightened model transparency. Moreover, the outcomes illustrate the efficacy of a modular transfer learning method for osteoporosis detection, even when relying on limited mandibular CBCT datasets. The methodology given is accompanied by the source code available on GitLab.

Hybrid morphological-convolutional neural networks for computer-aided diagnosis.

Training deep Convolutional Neural Networks (CNNs) presents challenges in terms of memory requirements and computational resources, often resulting in issues such as model overfitting and lack of generalization. These challenges can only be mitigated by using an excessive number of training images. However, medical image datasets commonly suffer from data scarcity due to the complexities involved in their acquisition, preparation, and curation. To address this issue, we propose a compact and hybrid machine learning architecture based on the Morphological and Convolutional Neural Network (MCNN), followed by a Random Forest classifier. Unlike deep CNN architectures, the MCNN was specifically designed to achieve effective performance with medical image datasets limited to a few hundred samples. It incorporates various morphological operations into a single layer and uses independent neural networks to extract information from each signal channel. The final classification is obtained by utilizing a Random Forest classifier on the outputs of the last neural network layer. We compare the classification performance of our proposed method with three popular deep CNN architectures (ResNet-18, ShuffleNet-V2, and MobileNet-V2) using two training approaches: full training and transfer learning. The evaluation was conducted on two distinct medical image datasets: the ISIC dataset for melanoma classification and the ORIGA dataset for glaucoma classification. Results demonstrate that the MCNN method exhibits reliable performance in melanoma classification, achieving an AUC of 0.94 (95% CI: 0.91 to 0.97), outperforming the popular CNN architectures. For the glaucoma dataset, the MCNN achieved an AUC of 0.65 (95% CI: 0.53 to 0.74), which was similar to the performance of the popular CNN architectures. This study contributes to the understanding of mathematical morphology in shallow neural networks for medical image classification and highlights the potential of hybrid architectures in effectively learning from medical image datasets that are limited by a small number of case samples.

CR-Conformer: a fusion network for clinical skin lesion classification.

Deep convolutional neural network (DCNN) models have been widely used to diagnose skin lesions, and some of them have achieved diagnostic results comparable to or even better than dermatologists. Most publicly available skin lesion datasets used to train DCNN were dermoscopic images. Expensive dermoscopic equipment is rarely available in rural clinics or small hospitals in remote areas. Therefore, it is of great significance to rely on clinical images for computer-aided diagnosis of skin lesions. This paper proposes an improved dual-branch fusion network called CR-Conformer. It integrates a DCNN branch that can effectively extract local features and a Transformer branch that can extract global features to capture more valuable features in clinical skin lesion images. In addition, we improved the DCNN branch to extract enhanced features in four directions through the convolutional rotation operation, further improving the classification performance of clinical skin lesion images. To verify the effectiveness of our proposed method, we conducted comprehensive tests on a private dataset named XJUSL, which contains ten types of clinical skin lesions. The test results indicate that our proposed method reduced the number of parameters by 11.17M and improved the accuracy of clinical skin lesion image classification by 1.08%. It has the potential to realize automatic diagnosis of skin lesions in mobile devices.

Effect of image resolution on automated classification of chest X-rays.

Deep learning (DL) models have received much attention lately for their ability to achieve expert-level performance on the accurate automated analysis of chest X-rays (CXRs). Recently available public CXR datasets include high resolution images, but state-of-the-art models are trained on reduced size images due to limitations on graphics processing unit memory and training time. As computing hardware continues to advance, it has become feasible to train deep convolutional neural networks on high-resolution images without sacrificing detail by downscaling. This study examines the effect of increased resolution on CXR classification performance. We used the publicly available MIMIC-CXR-JPG dataset, comprising 377,110 high resolution CXR images for this study. We applied image downscaling from native resolution to , , , and and then we used the DenseNet121 and EfficientNet-B4 DL models to evaluate clinical task performance using these four downscaled image resolutions. We find that while some clinical findings are more reliably labeled using high resolutions, many other findings are actually labeled better using downscaled inputs. We qualitatively verify that tasks requiring a large receptive field are better suited to downscaled low resolution input images, by inspecting effective receptive fields and class activation maps of trained models. Finally, we show that stacking an ensemble across resolutions outperforms each individual learner at all input resolutions while providing interpretable scale weights, indicating that diverse information is extracted across resolutions. This study suggests that instead of focusing solely on the finest image resolutions, multi-scale features should be emphasized for information extraction from high-resolution CXRs.

Malignant Mesothelioma subtyping via sampling driven multiple instance prediction on tissue image and cell morphology data

Malignant Mesothelioma is a difficult to diagnose and highly lethal cancer usually associated with asbestos exposure. It can be broadly classified into three subtypes: Epithelioid, Sarcomatoid, and a hybrid Biphasic subtype in which significant components of both of the previous subtypes are present. Early diagnosis and identification of the subtype informs treatment and can help improve patient outcome. However, the subtyping of malignant mesothelioma, and specifically the recognition of transitional features from routine histology slides has a high level of inter-observer variability.In this work, we propose an end-to-end multiple instance learning (MIL) approach for malignant mesothelioma subtyping. This uses an adaptive instance-based sampling scheme for training deep convolutional neural networks on bags of image patches that allows learning on a wider range of relevant instances compared to max or top-N based MIL approaches. We also investigate augmenting the instance representation to include aggregate cellular morphology features from cell segmentation. The proposed MIL approach enables identification of malignant mesothelial subtypes of specific tissue regions. From this a continuous characterisation of a sample according to predominance of sarcomatoid vs epithelioid regions is possible, thus avoiding the arbitrary and highly subjective categorisation by currently used subtypes. Instance scoring also enables studying tumor heterogeneity and identifying patterns associated with different subtypes. We have evaluated the proposed method on a dataset of 234 tissue micro-array cores with an AUROC of 0.89±0.05 for this task. The dataset and developed methodology is available for the community at: https://github.com/measty/PINS.

"Detecting and Removing Clouds Affected Regions from Satellite Images Using Deep Learning"

Deep Learning is becoming a very popular tool for generating and reconstructing images. Research has shown that deep learning algorithms can perform cutting-edge restoration tasks for various types of images. The performance of these algorithms can be achieved by training Deep Convolutional Neural Networks (DCNNs) with data from a large sample size. The processing of high-resolution satellite imagery becomes difficult when there are only a few images in a dataset. An approach based on the intrinsic properties of Deep Convolutional Neural Networks (DCNNs) is presented in this paper for the detection and removal of clouds from remote sensing images without any prior training. Our results demonstrated that the algorithm we used performed well when compared to trained algorithms.

Bridge the gap between full-reference and no-reference: A totally full-reference induced blind image quality assessment via deep neural networks

Blind image quality assessment (BIQA) is of fundamental importance in low-level computer vision community. Increasing interest has been drawn in exploiting deep neural networks for BIQA. Despite of the notable success achieved, there is a broad consensus that training deep convolutional neural networks (DCNN) heavily relies on massive annotated data. Unfortunately, BIQA is typically a small sample problem, resulting the generalization ability of BIQA severely restricted. In order to improve the accuracy and generalization ability of BIQA metrics, this work proposed a totally opinion-unaware BIQA in which no subjective annotations are involved in the training stage. Multiple full-reference image quality assessment (FR-IQA) metrics are employed to label the distorted image as a substitution of subjective quality annotation. A deep neural network (DNN) is trained to blindly predict the multiple FR-IQA score in absence of corresponding pristine image. In the end, a self-supervised FR-IQA score aggregator implemented by adversarial auto-encoder pools the predictions of multiple FR-IQA scores into the final quality predicting score. Even though none of subjective scores are involved in the training stage, experimental results indicate that our proposed full reference induced BIQA framework is as competitive as state-of-the-art BIQA metrics.

A Novel Hybrid Artificial Bee Colony-Based Deep Convolutional Neural Network to Improve the Detection Performance of Backscatter Communication Systems

Backscatter communication (BC) is a promising technology for low-power and low-data-rate applications, though the signal detection performance is limited since the backscattered signal is usually much weaker than the original signal. When the detection performance is poor, the backscatter device (BD) may not be able to accurately detect and interpret the incoming signal, leading to errors and degraded communication quality. This can result in data loss, slow data transfer rates, and reduced reliability of the communication link. This paper proposes a novel approach to improve the detection performance of backscatter communication systems using evolutionary deep learning. In particular, we focus on training deep convolutional neural networks (DCNNs) to improve the detection performance of BC. We first develop a novel hybrid algorithm based on artificial bee colony (ABC), biogeography-based optimization (BBO), and particle swarm optimization (PSO) to optimize the architecture of the DCNN, followed by training using a large set of benchmark datasets. To develop the hybrid ABC, the migration operator of the BBO is used to improve the exploitation. Moving towards the global best of PSO is also proposed to improve the exploration of the ABC. Then, we take advantage of the proposed deep architecture to improve the bit-error rate (BER) performance of the studied BC system. The simulation results demonstrate that the proposed algorithm has the best performance in training the benchmark datasets. The results also show that the proposed approach significantly improves the detection performance of backscattered signals compared to existing works.

A deep convolutional neural network for burn progression mapping using Sentinel-1 SAR time-series

ABSTRACT Forest fires burn various natural ecosystems worldwide and can harm the environment and human life. Accordingly, real-time monitoring of this phenomenon and early decision-making warning is vital. Active remote sensing systems, such as Synthetic Aperture Radar (SAR) sensors, provide an excellent opportunity for burn mapping because they can penetrate through clouds and smoke day and night. In this study, the potential of Sentinel-1 SAR data was investigated by deploying a deep convolutional neural network (CNN) based framework to map burn progression dynamically, in both supervised and transfer manners. Accordingly, an optimized deep architecture was designated to use SAR data features with high sensitivity to map the burned areas. The proposed method includes three main steps: 1) extraction of SAR indices, 2) training deep CNN model with a limited number of scenes and 3) assessing the transferability of the CNN for estimating burn progression for any unseen scene. Sentinel-1 SAR indices of log-ratio, radar burn difference (RBD), and difference of dual-polarization SAR vegetation index (ΔDPSVI) were obtained to be fed to the CNN. To validate the efficiency of the proposed approach, two fire events, i.e. the Derazno fire in Iran (2021) and the Rossomanno-Grottascura-Bellia fire in Italy (2017), were considered. For the scenes including training samples, the proposed method improved the overall accuracies (OAs) of classical machine learning techniques (i.e. SVM and RF) significantly (more than 4%). However, the improvement was minor when compared to a CNN using only log-ratio as the input channel (log-ratio CNN). For the scenes without training samples (unseen dates), the investigated transferred model performed substantially better (3% higher OA) compared to the other machine learning methods and the log-ratio CNN. This finding approves that the obtained SAR indices boost the transferability of the CNN model for burn progression mapping at unseen scenes.

Automated Asphalt Crack Detection Using Convolutional Neural Networks

Road damage caused by asphalt cracks is a significant issue in the civil engineering industry as it poses a threat to road and highway safety. Detecting and classifying cracks is a difficult undertaking because of the intricate pavement conditions created by various factors such as shadows, oil stains, and water spots. These factors can create challenges in differentiating cracks from the surrounding pavement. The focus of our study was to put forward a architecture of a deep convolutional neural network (DCNN) that can automatically detect and categorize pavement cracks. To train DCNN, we utilized RGB images of pavement cracks that were captured manually with a resolution of 1024x768 pixels. These images were then segmented into patches measuring 32x32 pixels. During the training of the DCNN, we employed two filter sizes, which were 3x3 and 5x5. Our presented approach achieved a recall of 98%, precision of 99%, and accuracy of 99%, successfully detecting the presence of cracks in the images. The DCNN was also capable of classifying With fair classification accuracy for both filter sizes and no noticeable difference in accuracy between the two filter sizes, pavement cracks into no cracks, transverse, longitudinal, and alligator. In contrast to bigger filter sizes, smaller filter sizes required greater processing time during training. Overall, 94.5% accuracy was achieved while using our suggested method to classify different kinds of cracks. Key Words: Crack detection, DCNN, Faster R-CNN, Unet, YOLO, ResNet-50

Semi‐supervised learning for ABUS tumor detection using deep learning method

AbstractAutomated breast ultrasound (ABUS) imaging system is a practical technique to automatically scan the whole breast. Automatic tumor detection plays a significant role in the clinic. However, training deep convolutional neural networks (CNNs) for tumor detection needs a large quantity of labeled data. It is time‐consuming and expensive to manually annotate tumor positions in ABUS images. In this paper, a novel semi‐supervised learning EfficientDet (SSL‐E) model is proposed for ABUS tumor detection. Our SSL‐E model solves the tumor detection problem from high similarity and serious unbalance between tumors and backgrounds. Considering the image contrast variation and tumor scale variations in ABUS images, color transformation and geometric transformation are employed for data augmentations. Then the consistency between image and its augmented version is developed, thus the robustness of the detector can be improved. Aiming at the problem of serious unbalance between tumors and backgrounds, a novel copy‐paste synthesis strategy is designed, which can generate more tumor samples and enhance tumor diversity. This method is tested on 68 tumor volumes and 68 normal volumes, including 43,248 slices (1683 tumor slices and 41,565 normal slices). It obtains a promising result with sensitivity of 90.2% and false positives per image (FPs/I) at 0.15.

Early Detection of Crop Disease With Automatic Image Based Classification Using CNN and Trans-fer Learning

In the current machine vision technology, accurate detection and classification of the crop dis-eases can protect against spoilage. Different diseases of tomato leaf have similar features or traits, making image disease detection confusing and challenging. Farmers cannot recognize whether a crop is infected or not just by looking at its leaves, because the healthy and infected crops resemble the same at first. Deep learning models can be used to overcome this prob-lem within less computational time. As a result, a new framework is implemented in this work through fine tuning the Deep Convolutional Neural Networks (DCNN) model using hyper parameters like learning rate, batch size, and epochs by applying transfer learning techniques for detecting tomato leaf disease. The data in this work is collected from the Plant Vil-lage database, which includes 20,639 images. The pro-posed model is implemented on three pre trained DCNN models-Alex Net, ResNet50 and VGG16. The proposed framework attains highest classification ac-curacy of 99.26% for fine tuning DCNN. The simula-tion results demonstrates that the fine-tuning Res-Net50 performs better classification of crop diseases when compared to the other DCNN models.