Convolutional Neural Network Training Research Articles

Data augmentation via warping transforms for modeling natural variability in the corneal endothelium enhances semi-supervised segmentation

Image segmentation of the corneal endothelium with deep convolutional neural networks (CNN) is challenging due to the scarcity of expert-annotated data. This work proposes a data augmentation technique via warping to enhance the performance of semi-supervised training of CNNs for accurate segmentation. We use a unique augmentation process for images and masks involving keypoint extraction, Delaunay triangulation, local affine transformations, and mask refinement. This approach accurately captures the natural variability of the corneal endothelium, enriching the dataset with realistic and diverse images. The proposed method achieved an increase in the mean intersection over union (mIoU) and Dice coefficient (DC) metrics of 17.2% and 4.8% respectively, for the segmentation task in corneal endothelial images on multiple CNN architectures. Our data augmentation strategy successfully models the natural variability in corneal endothelial images, thereby enhancing the performance and generalization capabilities of semi-supervised CNNs in medical image cell segmentation tasks.

Comprehensive Analysis of the Impact of Learning Rate and Dropout Rate on the Performance of Convolutional Neural Networks on the CIFAR-10 Dataset

Abstract. This study investigates the impact of two crucial hyperparameters, learning rate and dropout rate, on the performance of Convolutional Neural Networks (CNNs) on the CIFAR-10 dataset. Learning rate controls how quickly a model adapts to new data, while dropout rate helps prevent overfitting by randomly omitting neurons during training. These parameters are critical because they directly influence model convergence speed, accuracy, and generalization ability. By experimenting with various combinations of learning rates (0.01, 0.001, 0.0001) and dropout rates (0.3, 0.5, 0.7), we analyze the model's performance in terms of accuracy and overfitting. Our results suggest that a learning rate of 0.001 combined with a dropout rate of 0.5 yields the best balance between learning efficiency and generalization. This study offers important insights for optimizing hyperparameters in CNN training.

PIPET: A Pipeline to Generate PET Phantom Datasets for Reconstruction Based on Convolutional Neural Network Training

There has been a strong interest in using neural networks to solve several tasks in PET medical imaging. One of the main problems faced when using neural networks is the quality, quantity, and availability of data to train the algorithms. In order to address this issue, we have developed a pipeline that enables the generation of voxelized synthetic PET phantoms, simulates the acquisition of a PET scan, and reconstructs the image from the simulated data. In order to achieve these results, several pieces of software are used in the different steps of the pipeline. This pipeline solves the problem of generating diverse PET datasets and images of high quality for different types of phantoms and configurations. The data obtained from this pipeline can be used to train convolutional neural networks for PET reconstruction.

Development of an automated artificial intelligence-based system for urogenital schistosomiasis diagnosis using digital image analysis techniques and a robotized microscope.

Urogenital schistosomiasis is considered a Neglected Tropical Disease (NTD) by the World Health Organization (WHO). It is estimated to affect 150 million people worldwide, with a high relevance in resource-poor settings of the African continent. The gold-standard diagnosis is still direct observation of Schistosoma haematobium eggs in urine samples by optical microscopy. Novel diagnostic techniques based on digital image analysis by Artificial Intelligence (AI) tools are a suitable alternative for schistosomiasis diagnosis. Digital images of 24 urine sediment samples were acquired in non-endemic settings. S. haematobium eggs were manually labeled in digital images by laboratory professionals and used for training YOLOv5 and YOLOv8 models, which would achieve automatic detection and localization of the eggs. Urine sediment images were also employed to perform binary classification of images to detect erythrocytes/leukocytes with the MobileNetv3Large, EfficientNetv2, and NasNetLarge models. A robotized microscope system was employed to automatically move the slide through the X-Y axis and to auto-focus the sample. A total number of 1189 labels were annotated in 1017 digital images from urine sediment samples. YOLOv5x training demonstrated a 99.3% precision, 99.4% recall, 99.3% F-score, and 99.4% mAP0.5 for S. haematobium detection. NasNetLarge has an 85.6% accuracy for erythrocyte/leukocyte detection with the test dataset. Convolutional neural network training and comparison demonstrated that YOLOv5x for the detection of eggs and NasNetLarge for the binary image classification to detect erythrocytes/leukocytes were the best options for our digital image database. The development of low-cost novel diagnostic techniques based on the detection and identification of S. haematobium eggs in urine by AI tools would be a suitable alternative to conventional microscopy in non-endemic settings. This technical proof-of-principle study allows laying the basis for improving the system, and optimizing its implementation in the laboratories.

Multilevel attention mechanism for motion fatigue recognition based on sEMG and ACC signal fusion.

This study aims to develop a cost-effective and reliable motion monitoring device capable of comprehensive fatigue analysis. It achieves this objective by integrating surface electromyography (sEMG) and accelerometer (ACC) signals through a feature fusion strategy. The study introduces a multi-level attention mechanism for classification, leveraging convolutional neural networks (CNNs). The preprocessing phase involves a local feature attention mechanism that enhances local waveform features using the amplitude envelope. A dual-scale attention mechanism, operating at both channel and neuron levels, is employed to enhance the model's learning from high-dimensional fused data, improving feature extraction and generalization. The local feature attention mechanism significantly improves the model's classification accuracy and convergence, as demonstrated in ablation experiments. The model, optimized with multi-level attention mechanisms, excels in accuracy and generalization, particularly in handling data with pseudo-artifacts. Computational analysis indicates that the proposed optimization algorithm has minimal impact on CNN's training and testing times. The study achieves recognition accuracies of 92.52%, 92.38%, and 92.30%, as well as F1-scores of 91.92%, 92.13%, and 92.29% for the three fatigue states, affirming its reliability. This research provides technical support for the development of affordable and dependable wearable motion monitoring devices.

Gas Pipeline Leak Detection by Integrating Dynamic Modeling and Machine Learning Under the Transient State

This study focused on developing machine learning models to detect leak size and location in transient state conditions. The model was designed for an onshore methane–hydrogen blending gas pipeline in Canada. Base case simulations revealed significant effects on mass flow and pressure due to leaks, with the system taking approximately 6 h to reach a steady state from transient conditions. This made it essential to analyze the flow characteristics during the transient state. Trend data from the pipeline’s inlet and outlet were examined, considering the leak size and location. To better represent the data over time, a method was used to create two-dimensional images, which were then fed into a CNN (convolutional neural network) for training. The model’s accuracy was assessed using classification accuracy and a confusion matrix. By refining the data acquisition process and implementing targeted screening procedures, the model’s classification accuracy increased to over 80%. In conclusion, this study demonstrates that machine learning can enable rapid and accurate leak detection in transient state conditions. The findings are expected to complement existing leak detection methods and support operators in making faster, more informed decisions.

Artificial intelligence-based automated determination in breast and colon cancer and distinction between atypical and typical mitosis using a cloud-based platform

Artificial intelligence (AI) technology in pathology has been utilized in many areas and requires supervised machine learning. Notably, the annotations that define the ground truth for the identification of different confusing process pathologies, vary from study to study. In this study, we present our findings in the detection of invasive breast cancer for the IHC/ISH assessment system, along with the automated analysis of each tissue layer, cancer type, etc. in colorectal specimens. Additionally, models for the detection of atypical and typical mitosis in several organs were developed using existing whole-slide image (WSI) sets from other AI projects. All H&E slides were scanned by different scanners with a resolution of 0.12–0.50 μm/pixel, and then uploaded to a cloud-based AI platform. Convolutional neural networks (CNN) training sets consisted of invasive carcinoma, atypical and typical mitosis, and colonic tissue elements (mucosa-epithelium, lamina propria, muscularis mucosa, submucosa, muscularis propria, subserosa, vessels, and lymph nodes). In total, 59 WSIs from 59 breast cases, 217 WSIs from 54 colon cases, and 28 WSIs from 23 different types of tumor cases with relatively higher amounts of mitosis were annotated for the training. The harmonic average of precision and sensitivity was scored as F1 by AI. The final AI models of the Breast Project showed an F1 score of 94.49% for Invasive carcinoma. The mitosis project showed F1 scores of 80.18%, 97.40%, and 97.68% for mitosis, atypical, and typical mitosis layers, respectively. Overall F1 scores for the current results of the colon project were 90.02% for invasive carcinoma, 94.81% for the submucosa layer, and 98.02% for vessels and lymph nodes. After the training and optimization of the AI models and validation of each model, external validators evaluated the results of the AI models via blind-reader tasks. The AI models developed in this study were able to identify tumor foci, distinguish in situ areas, define colonic layers, detect vessels and lymph nodes, and catch the difference between atypical and typical mitosis. All results were exported for integration into our in-house applications for breast cancer and AI model development for both whole-block and whole-slide image-based 3D imaging assessment.

Kidney Disease Classification

Kidney diseases, such as tumors, cysts, and stones, are serious health conditions that affect millions globally. Medical imaging, particularly Computed-Tomography (CT) scans, plays an important role in diagnosing these conditions. Although, manual analysis of CT images by radiologist can be tiresome, fallible, and affected by human variability. This paper introduces a deep learning approach that employs Convolutional Neural Networks (CNN) for the automated classification of kidney CT scan images into four distinct categories : normal, cysts, tumors, and stones. The system is designed to boost diagnostic accuracy, reduce human error, and expedite clinical decision making. Through data preprocessing, CNN architecture design, training, and evaluation, the proposed model achieved a classification accuracy of 92%. This study highlights the significance of CNNs in medical image analysis anddtheir implicit for real- time deployment in clinical surroundings. Additionally, we compare our CNN-based approach with other advanced architectures like Vision Transformers, demonstrating CNNs' robustness and efficiency in this domain.

A student trained convolutional neural network competing with a commercial AI software and experts in organ at risk segmentation

This retrospective, multi-centered study aimed to improve high-quality radiation treatment (RT) planning workflows by training and testing a Convolutional Neural Network (CNN) to perform auto segmentations of organs at risk (OAR) for prostate cancer (PCa) patients, specifically the bladder and rectum. The objective of this project was to develop a clinically applicable and robust artificial intelligence (AI) system to assist radiation oncologists in OAR segmentation. The CNN was trained using manual contours in CT-datasets from diagnostic 68Ga-PSMA-PET/CTs by a student, then validated (n = 30, PET/CTs) and tested (n = 16, planning CTs). Further segmentations were generated by a commercial artificial intelligence (cAI) software. The ground truth were manual contours from expert radiation oncologists. The performance was evaluated using the Dice-Sørensen Coefficient (DSC), visual analysis and a Turing test. The CNN yielded excellent results in both cohorts and OARs with a DSCmedian > 0.87, the cAI resulted in a DSC > 0.78. In the visual assessment, 67% (bladder) and 75% (rectum) of the segmentations were rated as acceptable for treatment planning. With a misclassification rate of 45.5% (bladder) and 51.1% (rectum), the CNN passed the Turing test. The metrics, visual assessment and the Turing test confirmed the clinical applicability and therefore the support in clinical routine.

Transfer learning classification of suspicious lesions on breast ultrasound: is there room to avoid biopsies of benign lesions?

BackgroundBreast cancer (BC) is the most common malignancy in women and the second cause of cancer death. In recent years, there has been a strong development in artificial intelligence (AI) applications in medical imaging for several tasks. Our aim was to evaluate the potential of transfer learning with convolutional neural networks (CNNs) in discriminating suspicious breast lesions on ultrasound images.MethodsTransfer learning performances of five different CNNs (Inception V3, Xception, Densenet121, VGG 16, and ResNet50) were evaluated on a public and on an institutional dataset (526 and 392 images, respectively), customizing the top layers for the specific task. Institutional images were contoured by an expert radiologist and processed to feed the CNNs for training and testing. Postimaging biopsies were used as a reference standard for classification. The area under the receiver operating curve (AUROC) was used to assess diagnostic performance.ResultsNetworks performed very well on the public dataset (AUROC 0.938–0.996). The direct generalization to the institutional dataset resulted in lower performances (max AUROC 0.676); however, when tested on BI-RADS 3 and BI-RADS 5 only, results were improved (max AUROC 0.792). Good results were achieved on the institutional dataset (AUROC 0.759–0.818) and, when selecting a threshold of 2% for classification, a sensitivity of 0.983 was obtained for three of five CNNs, with the potential to spare biopsy in 15.3%–18.6% of patients.ConclusionIn conclusion, transfer learning with CNNs may achieve high sensitivity and might be used as a support tool in managing suspicious breast lesions on ultrasound images.Relevance statementTransfer learning is a powerful technique to exploit the performances of well-trained CNNs for image classification. In a clinical scenario, it might be useful for the management of suspicious breast lesions on breast ultrasound, potentially sparing biopsy in a non-negligible number of patients.Key PointsProperly trained CNNs with transfer learning are highly effective in differentiating benign and malignant lesions on breast ultrasound.Setting clinical thresholds increased sensitivity.CNNs might be useful as support tools in managing suspicious lesions on breast ultrasound.Graphical

Behavioral Cloning Strategies in Steering Angle Prediction: Applications in Mobile Robotics and Autonomous Driving

Artificial neural networks (ANNs) are artificial intelligence techniques that have made autonomous driving more efficient and accurate; however, autonomous driving faces ongoing challenges in the accuracy of decision making based on the analysis of the vehicle environment. A critical task of ANNs is steering angle prediction, which is essential for safe and effective navigation of mobile robots and autonomous vehicles. In this study, to optimize steering angle prediction, NVIDIA’s architecture was adapted and modified along with the implementation of the Swish activation function to train convolutional neural networks (CNNs) by behavioral cloning. The CNN used human driving data obtained from the UDACITY beta simulator and tests in real scenarios, achieving a significant improvement in the loss function during training, indicating a higher efficiency in replicating human driving behavior. The proposed neural network was validated through implementation on a differential drive mobile robot prototype, by means of a comparative analysis of trajectories in autonomous and manual driving modes. This work not only advances the accuracy of steering angle predictions but also provides valuable information for future research and applications in mobile robotics and autonomous driving. The performance results of the model trained with the proposed CNN show improved accuracy in various operational contexts.

Photodiode-based focus monitoring in ultrashort-pulsed laser structuring of graphite anodes for lithium-ion batteries

In recent years, there has been an increased demand for elaborate monitoring techniques in laser material processing. This has been driven by the need for fast and cost-efficient quality assurance processes. At the same time, ultrashort-pulsed (USP) laser radiation has emerged as a promising technology for creating intricate microstructures in lithium-ion battery graphite anodes due to its high precision and negligible thermal impact. However, the integration of process monitoring in USP laser applications for graphite anode structuring is still unexplored. There is a lack of clarity on suitable sensors, observable parameters, and extractable process-relevant insights. The presented study addressed this gap by demonstrating the capability of state-of-the-art photodiode-based monitoring systems in collecting process-relevant data and deriving valuable insights. A sensor equipped with three photodiodes was employed to address these challenges. Exploratory data analysis and machine learning methodologies were leveraged to develop a data pipeline for processing the acquired information. The data were used to train convolutional neural networks that could accurately predict the focal position. At the same time, the limitations of traditional regression approaches could be shown. The findings advanced the understanding of the possibilities of process monitoring in USP laser applications and emphasized the significance of data-driven approaches in optimizing manufacturing processes.

Reconstruction error based implicit regularization method and its engineering application to lung cancer diagnosis

The automatic diagnosis of lung cancer via artificial intelligence faces two hotspot issues: (1) insufficient data and (2) excessive redundant information, which make it difficult for convolutional neural networks (CNNs) to learn discriminative information of lung cancer. In this paper, we present the reconstruction error based implicit regularization method (REbIRM) that regularizes CNNs at the loss layer. During each training iteration, the reconstruction errors introduced by the two-stage discriminative auto-encoder are used to sharpen the generalization ability of deep CNNs by improving the decision boundary. In the application process, the trained deep CNN is used for completing computed tomography (CT) diagnostics. The main clinical benefit of our approach is that it is domain independent, requiring no specialized knowledge, and can therefore be applied to different types of datasets. To the best of our knowledge, this is the first attempt to implicitly regularize CNNs based on the reconstruction errors. Finally, experimental results on three CT image classification datasets show that REbIRM can achieve impressive results and that, in conjunction with Dropout, it obtains the state-of-the-art performance. REbIRM is also robust to the selection of hyper-parameters and only has the sublinear influence on the convergence of deep CNNs. Besides, empirical and theoretical evidence are provided to indicate that REbIRM prefers to converges in a constrained parameter space with flatter minima, which explains why it can generalize to new data. Finally, the nature of REbIRM is further explored through visualization techniques to analyze how it works in training deep CNNs.

PV Module Soiling Detection Using Visible Spectrum Imaging and Machine Learning

During the last decades photovoltaic solar energy has continuously increased its share in the electricity mix and has already surpassed 5% globally. Even though photovoltaic (PV) installations are considered to require very little maintenance, their efficient exploitation relies on accounting for certain environmental factors that affect energy generation. One of these factors is the soiling of the PV surface, which could be observed in different forms, such as dust and bird droppings. In this study, visible spectrum data and machine learning algorithms were used for the identification of soiling. A methodology for preprocessing the images is proposed, which puts focus on any soiling of the PV surface. The performance of six classification machine learning algorithms is evaluated and compared—convolutional neural network (CNN), support vector machine (SVM), random forest (RF), k-nearest neighbor (kNN), naïve-Bayes, and decision tree. During the training and validation phase, RF proved to be the best-performing model with an F1 score of 0.935, closely followed by SVM, CNN, and kNN. However, during the testing phase, the trained CNN achieved the highest performance, reaching F1 = 0.913. SVM closely followed it with a score of 0.895, while the other two models returned worse results. Some results from the application of the optimal model after specific weather events are also presented in this study. They confirmed once again that the trained convolutional neural network can be successfully used to evaluate the soiling state of photovoltaic surfaces.

Concrete crack classification based on fourier image enhancement and convolutional neural network

This paper investigates the application of Fourier image enhancement combined with Convolutional Neural Networks (CNNs) for detecting cracks in concrete structures. Fourier enhancement is used to preprocess crack images, improving their clarity and reducing noise, which in turn enhances the performance of the CNN in accurately classifying cracks. The results demonstrate that this combination improves the classification accuracy, with the enhanced images achieving a higher accuracy compared to non-enhanced images. Additionally, the study examines the effects of this preprocessing on CNN training time. However, accuracy varies depending on the dataset used, with one dataset reaching a maximum accuracy of 95% after enhancement. These findings highlight the potential of using frequency-domain image enhancement techniques in conjunction with deep learning models for structural health monitoring.

Characterization of AI-enhanced magnetophoretic transistors operating in a tri-axial magnetic field for on-chip bioparticle sorting.

We demonstrate two general classes of magnetophoretic transistors, called the "trap" and the "repel-and-collect" transistors, capable of switching single magnetically labeled cells and magnetic particles between different paths in a microfluidic chamber. Compared with prior work on magnetophoretic transistors operating in a two-dimensional in-plane rotating field, the use of a tri-axial magnetic field has the fundamental advantages of preventing particle cluster formation and better syncing of single particles with the general operating clock. We use finite element methods to investigate the energy distribution on the chip surface and to predict the particle behavior at various device geometries. We then fabricate the proposed transistors and compare the experimental results with the simulation predictions. We found that with gate electrical currents of ~ 40mA for a transistor with proper geometry, complete switching of magnetic particles with diameters in the range of 8-15μm is achieved. We show that the device is reliable and works well at different magnetic field strengths (50-100 Oe) and frequencies (0.05-0.5Hz). We also employed an image processing code with a trained convolutional neural network to automate the proposed transistors for identifying and sorting particles with various sizes and magnetic susceptibilities with accuracies higher than 98%. The proposed transistors can be used in designing novel magnetophoretic circuits for important applications in biomedical microdevices and single-cell biology.

Low-complexity short-time acoustic scene classification based on causal convolutions

Acoustic scene classification is vital for building smart cities. Most acoustic scene classification studies are performed by training convolutional neural networks. The networks constructed based on the general convolutional approach need to consider the temporal-frequency connections in the audio spectrogram. This work proposes a bottleneck structure neural network model for acoustic scene classification based on causal convolution and Sub-spectral normalization to overcome the abovementioned problem. To obtain more sample data, a new mix-spec augmentation data enhancement method is proposed by drawing on the existing classical mixup and spec augmentation methods, and the three are combined for sample augmentation. It was experimentally found that the proposed bottleneck structure helps improve the recognition accuracy and robustness of the model. In addition, the ablation experiment showed that the data augmentation training model combined with the mixup, SpecAugment, and the newly proposed mix-SpecAugment method had the highest classification accuracy. Finally, the near-square audio spectrogram has better training results by employing different shapes of audio spectrograms for the experiments. Compared with the baseline results, it is found that our proposed model significantly improved the accuracy of the baseline and reduced loss.

Privacy-preserving and verifiable convolution neural network inference and training in cloud computing

With the rapid development of cloud computing, outsourcing massive data and complex deep learning model to cloud servers (CSs) has become a popular trend, which also brings some security problems. One is that the model stored in the CSs may be corrupted, leading to incorrect inference and training results. The other is that the privacy of outsourced data and model may be compromised. However, existing privacy-preserving and verifiable inference schemes suffer from low detection probability, high communication overhead and substantial computational time. To solve the above problems, we propose a privacy-preserving and verifiable scheme for convolutional neural network inference and training in cloud computing. In our scheme, the model owner generates the authenticators for model parameters before uploading the model to CSs. In the phase of model integrity verification, model owner and user can utilize these authenticators to check model integrity with high detection probability. Furthermore, we design a set of privacy-preserving protocols based on replicated secret sharing for both the inference and training phases, significantly reducing communication overhead and computational time. Through security analysis, we demonstrate that our scheme is secure. Experimental evaluations show that the proposed scheme outperforms existing schemes in privacy-preserving inference and model integrity verification.

Predicting standardized uptake value of brown adipose tissue from CT scans using convolutional neural networks.

The standard method for identifying active Brown Adipose Tissue (BAT) is [18F]-Fluorodeoxyglucose ([18F]-FDG) PET/CT imaging, which is costly and exposes patients to radiation, making it impractical for population studies. These issues can be addressed with computational methods that predict [18F]-FDG uptake by BAT from CT; earlier population studies pave the way for developing such methods by showing some correlation between the Hounsfield Unit (HU) of BAT in CT and the corresponding [18F]-FDG uptake in PET. In this study, we propose training convolutional neural networks (CNNs) to predict [18F]-FDG uptake by BAT from unenhanced CT scans in the restricted regions that are likely to contain BAT. Using the Attention U-Net architecture, we perform experiments on datasets from four different cohorts, the largest study to date. We segment BAT regions using predicted [18F]-FDG uptake values, achieving 23% to 40% better accuracy than conventional CT thresholding. Additionally, BAT volumes computed from the segmentations distinguish the subjects with and without active BAT with an AUC of 0.8, compared to 0.6 for CT thresholding. These findings suggest CNNs can facilitate large-scale imaging studies more efficiently and cost-effectively using only CT.

CLASSIFICATION OF ACUTE LYMPHOBLASTIC LEUKEMIA CELLS USING ARTIFICIAL INTELLIGENCE

Due to the morphological similarity between immature lymphoblasts (cancerous cells) to lymphocytes (non-cancerous cells), detecting Acute Lymphoblastic Leukemia poses a significant challenge for pathologists. These cells, which exhibit a similar pattern, can lead to various errors during the diagnosis of the disease. In this study, the cancerous and non-cancerous cells were classified using 3 different artificial intelligence approaches. In the first approach, the classification process was carried out by training Convolutional Neural Networks in 4 different architectures. In the second approach, a hybrid approach was proposed by combining the convolution layer of the CNN model as the feature extractor with the Support Vector Machine, Naive Bayes and Random Forest algorithms as the classifier. The classification processes were carried out by training the proposed second approach. In the third approach, the classification process was performed using transfer learning process and ResNet50 and VGG16 networks. In all experiments, the effects of hyper-parameter and dataset changes on model performance were also examined. The results obtained by these three approaches were compared using the Accuracy, Precision, Recall, F-score, and AUC performance measures. It was determined that the most successful results were obtained with the 1st approach using the Dataset3.