Artifact Removal Research Articles

Generative Adversarial Networks (GANs) in the Field of Head and Neck Surgery: Current Evidence and Prospects for the Future-A Systematic Review.

Background: Generative Adversarial Networks (GANs) are a class of artificial neural networks capable of generating content such as images, text, and sound. For several years already, artificial intelligence algorithms have shown promise as tools in the medical field, particularly in oncology. Generative Adversarial Networks (GANs) represent a new frontier of innovation, as they are revolutionizing artificial content generation, opening opportunities in artificial intelligence and deep learning. Purpose: This systematic review aims to investigate what the stage of development of such technology is in the field of head and neck surgery, offering a general overview of the applications of such algorithms, how they work, and the potential limitations to be overcome in the future. Methods: The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed in conducting this study, and the PICOS framework was used to formulate the research question. The following databases were evaluated: MEDLINE, Embase, Cochrane Central Register of Controlled Trials (CENTRAL), Scopus, ClinicalTrials.gov, ScienceDirect, and CINAHL. Results: Out of 700 studies, only 9 were included. Eight applications of GANs in the head and neck region were summarized, including the classification of craniosynostosis, recognition of the presence of chronic sinusitis, diagnosis of radicular cysts in panoramic X-rays, segmentation of craniomaxillofacial bones, reconstruction of bone defects, removal of metal artifacts from CT scans, prediction of the postoperative face, and improvement of the resolution of panoramic X-rays. Conclusions: Generative Adversarial Networks may represent a new evolutionary step in the study of pathology, oncological and otherwise, making the approach to the disease much more precise and personalized.

Deep Learning Realizes Photoacoustic Imaging Artifact Removal

Photoacoustic imaging integrates the strengths of optics and ultrasound, offering high resolution, depth penetration, and multimodal imaging capabilities. Practical considerations with instrumentation and geometry limit the number of available acoustic sensors and their “view” of the imaging target, which result in image reconstruction artifacts degrading image quality. To address this problem, YOLOv8-Pix2Pix is proposed as a hybrid artifact-removal algorithm, which is advantageous in comprehensively eliminating various types of artifacts and effectively restoring image details compared to existing algorithms. The proposed algorithm demonstrates superior performance in artifact removal and segmentation of photoacoustic images of brain tumors. For the purpose of further expanding its application fields and aligning with actual clinical needs, an experimental system for photoacoustic detection is designed in this paper to be verified. The experimental results show that the processed images are better than the pre-processed images in terms of reconstruction metrics PSNR and SSIM, and also the segmentation performance is significantly improved, which provides an effective solution for the further development of photoacoustic imaging technology.

A Comparison of Automatically Extracted Quantitative EEG Features for Seizure Risk Stratification in Neonatal Encephalopathy.

Seizures occur in up to 40% of neonates with neonatal encephalopathy. Earlier identification of seizures leads to more successful seizure treatment, but is often delayed because of limited availability of continuous EEG monitoring. Clinical variables poorly stratify seizure risk, and EEG use to stratify seizure risk has previously been limited by need for manual review and artifact exclusion. The goal of this study is to compare the utility of automatically extracted quantitative EEG (qEEG) features for seizure risk stratification. We conducted a retrospective analysis of neonates with moderate-to-severe neonatal encephalopathy who underwent therapeutic hypothermia at a single center. The first 24 hours of EEG underwent automated artifact removal and qEEG analysis, comparing qEEG features for seizure risk stratification. The study included 150 neonates and compared the 36 (23%) with seizures with those without. Absolute spectral power best stratified seizure risk with area under the curve ranging from 63% to 71%, followed by range EEG lower and upper margin, median and SD of the range EEG lower margin. No features were significantly more predictive in the hour before seizure onset. Clinical examination was not associated with seizure risk. Automatically extracted qEEG features were more predictive than clinical examination in stratifying neonatal seizure risk during therapeutic hypothermia. qEEG represents a potential practical bedside tool to individualize intensity and duration of EEG monitoring and decrease time to seizure recognition. Future work is needed to refine and combine qEEG features to improve risk stratification.

Sentiment Analysis-Based Automatic Stress and Emotion Recognition using Weighted Fused Fusion-Based Cascaded DTCN with Attention Mechanism from EEG Signal

When loaded with difficulties in fulfilling daily requirements, a lot of people in today’s world experience an emotional pressure known as stress. Stress that lasts for a short duration of time has more advantages as they are good for mental health. But, the persistence of stress for a long duration of time may lead to serious health impacts in individuals, such as high blood pressure, cardiovascular disease, stroke and so on. Long-term stress, if unidentified and not treated, may also result in personality disorder, depression and anxiety. The initial detection of stress has become more important to prevent the health issues that arise due to stress. Detection of stress based on brain signals for analysing the emotion in humans leads to accurate detection outcomes. Using EEG-based detection systems and disease, disability and disorders can be identified from the brain by utilising the brain waves. Sentiment Analysis (SA) is helpful in identifying the emotions and mental stress in the human brain. So, a system to accurately and precisely detect depression in human based on their emotion through the utilisation of SA is of high necessity. The development of a reliable and precise Emotion and Stress Recognition (ESR) system in order to detect depression in real-time using deep learning techniques with the aid of Electroencephalography (EEG) signal-based SA is carried out in this paper. The essentials needed for performing stress and emotion detection are gathered initially from benchmark databases. Next, the pre-processing procedures, like the removal of artifacts from the gathered EEG signal, are carried out on the implemented model. The extraction of the spectral attributes is carried out from the pre- processed. The extracted spectral features are considered the first set of features. Then, with the aid of a Conditional Variational Autoencoder (CVA), the deep features are extracted from the pre-processed signals forming a second set of features. The weights are optimised using the Adaptive Egret Swarm Optimisation Algorithm (AESOA) so that the weighted fused features are obtained from these two sets of extracted features. Then, a Cascaded Deep Temporal Convolution Network with Attention Mechanism (CDTCN-AM) is used to recognise stress and emotion. The validation of the results from the developed stress and emotion recognition approach is carried out against traditional models in order to showcase the effectiveness of the suggested approach.

Efficient architecture for ocular artifacts removal from EEG: A Novel approach based on DWT-LMM

Medical practitioners use portable electroencephalogram (EEG) headset to identify Neuro Developmental Disorders (NDD). However, the analysis of EEG signals gets affected as the recorded electrical activity always contaminated with artifacts. A portable EEG headset requires area-efficient hardware and an effective method to remove ocular artifacts. In this paper, a method is proposed, which removes ocular artifacts efficiently and consumes less hardware. This proposed method involves determining the appropriate decomposition level to obtain approximation coefficients (ACs) and detail coefficients (DCs) for minimal loss of useful information present in the EEG signal. In addition, an algorithm is also proposed to perform wavelet thresholding on wavelet coefficients using Local Maximal and Minimal (LMM) to remove artifacts from EEG signals without disturbing the information related to brain activity. The functionality of the proposed method is verified using MATLAB R2021a tool by computing average correlation coefficient & RMSE performance metrics and the proposed method is also modeled using Verilog HDL. The results show that the proposed DWT-LMM approach had superior performance in removing artifacts from EEG signals with the average correlation coefficient and RMSE values of 0.9369 and 2.2252, respectively. The functionality of this HDL netlist is verified by the VCS simulator and synthesized by Synopsys design compiler 32 nm UMC library cells. The proposed architecture layout is generated after placement & routing using Synopsys IC Compiler tool by employing 32 nm cell libraries and the results shows that the layout consumes 6490.07 μm2 of area and 792.18 μw of power with supply voltage of 0.95 V. Hence, the proposed ocular artifacts removal method and architecture can be employed in portable/wearable brain-computer interface (BCI) devices.

Removal of Ocular and Muscular Artifacts From Multi-Channel EEG Using Improved Spatial-Frequency Filtering.

Over recent decades, electroencephalogram (EEG) has become an essential tool in the field of clinical analysis and neurological disease research. However, EEG recordings are notably vulnerable to artifacts during acquisition, especially in clinical settings, which can significantly impede the accurate interpretation of neuronal activity. Blind source separation is currently the most popular method for EEG denoising, but most of the sources it separates often contain both artifacts and brain activity, which may lead to substantial information loss if handled improperly. In this paper, we introduce a dual-threshold denoising method combining spatial filtering with frequency-domain filtering to automatically eliminate electrooculogram (EOG) and electromyogram (EMG) artifacts from multi-channel EEG. The proposed method employs a fusion of second-order blind identification (SOBI) and canonical correlation analysis (CCA) to enhance source separation quality, followed by adaptive threshold to localize the artifact sources, and strict fixed threshold to remove strong artifact sources. Stationary wavelet transform (SWT) is utilized to decompose the weak artifact sources, with subsequent adjustment of wavelet coefficients in respective frequency bands tailored to the distinct characteristics of each artifact. The results of synthetic and real datasets show that our proposed method maximally retains the time-domain and frequency-domain information in the EEG during denoising. Compared with existing techniques, the proposed method achieves better denoising performance, which establishes a reliable foundation for subsequent clinical analyses.

EEG Data Analysis Techniques for Precision Removal and Enhanced Alzheimer’s Diagnosis: Focusing on Fuzzy and Intuitionistic Fuzzy Logic Techniques

Effective management of EEG artifacts is pivotal for accurate neurological diagnostics, particularly in detecting early stages of Alzheimer’s disease. This review delves into the cutting-edge domain of fuzzy logic techniques, emphasizing intuitionistic fuzzy systems, which offer refined handling of uncertainties inherent in EEG data. These methods not only enhance artifact identification and removal but also integrate seamlessly with other AI technologies to push the boundaries of EEG analysis. By exploring a range of approaches from standard protocols to advanced machine learning models, this paper provides a comprehensive overview of current strategies and emerging technologies in EEG artifact management. Notably, the fusion of fuzzy logic with neural network models illustrates significant advancements in distinguishing between genuine neurological activity and noise. This synthesis of technologies not only improves diagnostic accuracy but also enriches the toolset available to researchers and clinicians alike, facilitating earlier and more precise identification of neurodegenerative diseases. The review ultimately underscores the transformative potential of integrating diverse computational techniques, setting a new standard in EEG analysis and paving the way for future innovations in medical diagnostics.

Methods for Processing Physiological Artifacts in Single/Few-Channel EEG Signals

Electroencephalogram (EEG) is a non-invasive measurement method of brain electrical activity. In recent years, single/few-channel EEG has been used more and more, but various types of physiological artifacts seriously affect the analysis and wide application of single/few-channel EEG. In this paper, the regression and filtering methods, decomposition methods, blind source separation methods and machine learning methods involved in the various physiological artifacts in single/few-channel EEG are reviewed. According to the characteristics of single/few-channel EEG signals, hybrid EEG artifact removal methods for different scenarios are analyzed and summarized, mainly including single-artifact/multi-artifact scenes and online/offline scenes. In addition, the methods and metrics for validating the performance of the algorithm on semi-simulated and real EEG data are also reviewed. Finally, the development trend of single/few-channel EEG application and physiological artifact processing is briefly described.

Enhancing early breast cancer diagnosis through automated microcalcification detection using an optimized ensemble deep learning framework

Background Breast cancer remains a pressing global health concern, necessitating accurate diagnostics for effective interventions. Deep learning models (AlexNet, ResNet-50, VGG16, GoogLeNet) show remarkable microcalcification identification (>90%). However, distinct architectures and methodologies pose challenges. We propose an ensemble model, merging unique perspectives, enhancing precision, and understanding critical factors for breast cancer intervention. Evaluation favors GoogleNet and ResNet-50, driving their selection for combined functionalities, ensuring improved precision, and dependability in microcalcification detection in clinical settings. Methods This study presents a comprehensive mammogram preprocessing framework using an optimized deep learning ensemble approach. The proposed framework begins with artifact removal using Otsu Segmentation and morphological operation. Subsequent steps include image resizing, adaptive median filtering, and deep convolutional neural network (D-CNN) development via transfer learning with ResNet-50 model. Hyperparameters are optimized, and ensemble optimization (AlexNet, GoogLeNet, VGG16, ResNet-50) are constructed to identify the localized area of microcalcification. Rigorous evaluation protocol validates the efficacy of individual models, culminating in the ensemble model demonstrating superior predictive accuracy. Results Based on our analysis, the proposed ensemble model exhibited exceptional performance in the classification of microcalcifications. This was evidenced by the model’s average confidence score, which indicated a high degree of dependability and certainty in differentiating these critical characteristics. The proposed model demonstrated a noteworthy average confidence level of 0.9305 in the classification of microcalcification, outperforming alternative models and providing substantial insights into the dependability of the model. The average confidence of the ensemble model in classifying normal cases was 0.8859, which strengthened the model’s consistent and dependable predictions. In addition, the ensemble models attained remarkably high performances in terms of accuracy, precision, recall, F1-score, and area under the curve (AUC). Conclusion The proposed model’s thorough dataset integration and focus on average confidence ratings within classes improve clinical diagnosis accuracy and effectiveness for breast cancer. This study introduces a novel methodology that takes advantage of an ensemble model and rigorous evaluation standards to substantially improve the accuracy and dependability of breast cancer diagnostics, specifically in the detection of microcalcifications.

Analysis and Comparison of Artifact Removal Techniques for Epilepsy EEG Signal

Objective: Accurate epilepsy diagnosis demands precise EEG analysis, hindered by non-neuronal artifacts. This study evaluates artifact removal methods, specifically Independent Component Analysis (ICA) and Empirical Mode Decomposition (EMD), aiming to enhance signal quality. We introduce a hybrid approach, combining ICA and EMD. Methods: ICA and EMD are applied to preprocess epilepsy EEG recordings. Quantitative evaluation metrics, including Signal-to-Noise Ratio (SNR), Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Standard Deviation (SD), are calculated and compared for both methods. Findings: ICA outperforms EMD, showing higher SNR and PSNR, notably in BONN and CHB-MIT datasets. ICA achieves significant reductions in MSE, RMSE, and SD. The hybrid approach surpasses existing methods, supported by quantitative data. Novelty: Rigorous application of ICA and EMD to diverse datasets quantitatively establishes ICA's superiority. The hybrid approach, backed by quantitative evidence, proves effective beyond epilepsy EEG. Conclusion: This abstract provides clear, quantitative support for ICA's superiority and the hybrid approach's efficacy, offering valuable insights into artifact removal in EEG analysis. Keywords: Epilepsy, Artifact removal, EEG, ICA, DWT, EMD, Performance metrics

Improvements of EEG Signal Quality: A Hybrid Method of Blind Source Separation and Variational Mode Destruction to Reduce Artifacts

The electroencephalogram (EEG) is a crucial tool for studying brain activity; yet it frequently encounters artifacts that distort meaningful neural signals. This paper addresses the challenge of artifact removal through a unique hybrid method, combining Variational Mode Decomposition (VMD) techniques with Blind Source Separation (BSS) algorithms. VMD, recognized for its adaptability to non-linear and non-stationary EEG data, as well as its ability to alleviate mode mixing and the “endpoint effect,” which serves as an effective preprocessing step. The paper evaluates the performance of two integrated BSS algorithms, AMICA and AMUSE, across various criteria. Comparisons across metrics such as Euclidean distance, Spearman correlation coefficient, and Root Mean Square Error reveal similar performance between AMICA and AMUSE. However, a distinct divergence is evident in the Signal to Artifact Ratio (SAR). When employed with VMD, AMICA demonstrates superiority in effectively discerning and segregating brain signals from artifacts, which gives a mean value of 1.0924. This study introduces a potent hybrid VMDBSS approach for enhancing EEG signal quality. The findings emphasize the notable impact of AMICA, particularly in achieving optimal results in artifact removal, as indicated by its superior performance in SAR. The abstract concludes by underlining the significance of these results, emphasizing AMICA’s pivotal role in achieving the highest measurable evaluation value, making it a compelling choice for researchers and practitioners in EEG signal processing.

Comparison of electrical microstimulation artifact removal methods for high-channel-count prostheses

BackgroundNeuroprostheses are used to electrically stimulate the brain, modulate neural activity and restore sensory and motor function following injury or disease, such as blindness, paralysis, and other movement and psychiatric disorders. Recordings are often made simultaneously with stimulation, allowing the monitoring of neural signals and closed-loop control of devices. However, stimulation-evoked artifacts may obscure neural activity, particularly when stimulation and recording sites are nearby. Several methods have been developed to remove stimulation artifacts, but it remains challenging to validate and compare these methods because the ‘ground-truth’ of the neuronal signals may be contaminated by artifacts. New methodHere, we delivered stimulation to the visual cortex via a high-channel-count prosthesis while recording neuronal activity and stimulation artifacts. We quantified the waveforms and temporal properties of stimulation artifacts from the cortical visual prosthesis (CVP) and used them to build a dataset, in which we simulated the neuronal activity and the stimulation artifacts. We illustrate how to use the simulated data to evaluate the performance of six software-based artifact removal methods (Template subtraction, Linear interpolation, Polynomial fitting, Exponential fitting, SALPA and ERAASR) in a CVP application scenario. ResultsWe here focused on stimulation artifacts caused by electrical stimulation through a high-channel-count cortical prosthesis device. We find that the Polynomial fitting and Exponential fitting methods outperform the other methods in recovering spikes and multi-unit activity. Linear interpolation and Template subtraction recovered the local-field potentials. ConclusionPolynomial fitting and Exponential fitting provided a good trade-off between the quality of the recovery of spikes and multi-unit activity (MUA) and the computational complexity for a cortical prosthesis.

Improved multi-layer wavelet transform and blind source separation based ECG artifacts removal algorithm from the sEMG signal: in the case of upper limbs.

Introduction: Surface electromyogram (sEMG) signals have been widely used in human upper limb force estimation and motion intention recognition. However, the electrocardiogram(ECG) artifact generated by the beating of the heart is a major factor that reduces the quality of the EMG signal when recording the sEMG signal from the muscle close to the heart. sEMG signals contaminated by ECG artifacts are difficult to be understood correctly. The objective of this paper is to effectively remove ECG artifacts from sEMG signals by a novel method. Methods: In this paper, sEMG and ECG signals of the biceps brachii, brachialis, and triceps muscle of the human upper limb will be collected respectively. Firstly, an improved multi-layer wavelet transform algorithm is used to preprocess the raw sEMG signal to remove the background noise and power frequency interference in the raw signal. Then, based on the theory of blind source separation analysis, an improved Fast-ICA algorithm was constructed to separate the denoising signals. Finally, an ECG discrimination algorithm was used to find and eliminate ECG signals in sEMG signals. This method consists of the following steps: 1) Acquisition of raw sEMG and ECG signals; 2) Decoupling the raw sEMG signal; 3) Fast-ICA-based signal component separation; 4) ECG artifact recognition and elimination. Results and discussion: The experimental results show that our method has a good effect on removing ECG artifacts from contaminated EMG signals. It can further improve the quality of EMG signals, which is of great significance for improving the accuracy of force estimation and motion intention recognition tasks. Compared with other state-of-the-art methods, our method can also provide the guiding significance for other biological signals.

Comparison of Independent Component Analysis, Linear Regression and Adaptive Filtering for Artifact Removal in SSVEP Registration

Comparison of Independent Component Analysis, Linear Regression and Adaptive Filtering for Artifact Removal in SSVEP Registration

Analysis of Methods and Algorithms for Remote Photoplethysmography Signal Diagnostic and Filtering

Remote photoplethysmography is becoming increasingly common in telemedicine for non-invasive physiological monitoring of the cardiovascular system. However, signal reliability has been reduced due to noise and artifacts, which requires reliable diagnostic and filtering methods. The research aim is to evaluate existing methods and algorithms for diagnosing and filtering remote photoplethysmography signals to improve the accuracy of human cardiovascular monitoring. A systematic review has identified methodologies for improving remote photoplethysmography signals by analyzing their principles, implementation, and effectiveness. Various approaches have been analyzed, including the use of statistical computing, adaptive filters, and machine learning algorithms. Each approach offers unique advantages and limitations in terms of noise reduction and artifact removal.

Linear-space-variant model for Fourier ptychographic microscopy.

Fourier ptychographic microscopy (FPM) needs to realize well-accepted reconstruction by image segmentation and discarding problematic data due to artifacts caused by vignetting. However, the imaging results have long suffered from uneven color blocks and the consequent digital stitching artifacts, failing to bring satisfying experiences to researchers and users over the past decade since the invention of FPM. In fact, the fundamental reason for vignetting artifacts lies in that the acquired data does not match the adopted linear-space-invariant (LSI) forward model, i.e., the actual object function is modulated by a quadratic phase factor during data acquisition, which has been neglected in the advancement of FPM. In this Letter, we rederive a linear-space-variant (LSV) model for FPM and design the corresponding loss function for FPM, termed LSV-FPM. Utilizing LSV-FPM for optimization enables the efficient removal of wrinkle artifacts caused by vignetting in the reconstruction results, without the need of segmenting or discarding images. The effectiveness of LSV-FPM is validated through data acquired in both 4f and finite conjugate single-lens systems.

Attempted movement classification of spinal cord injured patients using hybrid CNN‐LSTM networks

AbstractIndividuals who are suffering from the most severe of motor disabilities can improve their quality of life by controlling and directing mechanical and electronic devices. As for Spinal Cord Injured (SCI) patients', attempted hand movements can be classified using electroencephalography (EEG). The research aims to develop a hybrid CNN‐LSTM (Convolutional Neural Network—Long Short Term Memory) architecture for multichannel EEG signal classification. It is a challenging task to classify real‐world multichannel EEG data from SCI patients. The proposed research preprocessed the EEG data to improve the signal‐to‐noise ratio and arranged for them to extract additional information from the data. The preprocessing step includes filtering, downsampling, and artifact removal, while the postprocessing step includes time‐frequency representation and spatial information encoding. A hybrid CNN‐LSTM is used for feature extraction and classification. The proposed method has been implemented on a dataset consisting of 5 different classes of attempted hand movements from 10 SCI patients. The average classification accuracy of 92.36% is achieved for 5‐class classification. To check the global validity of the proposed network, the BCI competition IV data is classified by the proposed method and has found 92.70% overall accuracy.

A 1 Ma sedimentary ancient DNA (sedaDNA) record of catchment vegetation changes and the developmental history of tropical Lake Towuti (Sulawesi, Indonesia).

Studying past ecosystems from ancient environmental DNA preserved in lake sediments (sedaDNA) is a rapidly expanding field. This research has mainly involved Holocene sediments from lakes in cool climates, with little known about the suitability of sedaDNA to reconstruct substantially older ecosystems in the warm tropics. Here, we report the successful recovery of chloroplast trnL (UAA) sequences (trnL-P6 loop) from the sedimentary record of Lake Towuti (Sulawesi, Indonesia) to elucidate changes in regional tropical vegetation assemblages during the lake's Late Quaternary paleodepositional history. After the stringent removal of contaminants and sequence artifacts, taxonomic assignment of the remaining genuine trnL-P6 reads showed that native nitrogen-fixing legumes, C3 grasses, and shallow wetland vegetation (Alocasia) were most strongly associated with >1-million-year-old (>1 Ma) peats and silts (114-98.8 m composite depth; mcd), which were deposited in a landscape of active river channels, shallow lakes, and peat-swamps. A statistically significant shift toward partly submerged shoreline vegetation that was likely rooted in anoxic muddy soils (i.e., peatland forest trees and wetland C3 grasses (Oryzaceae) and nutrient-demanding aquatic herbs (presumably Oenanthe javanica)) occurred at 76 mcd (~0.8 Ma), ~0.2 Ma after the transition into a permanent lake. This wetland vegetation was most strongly associated with diatom ooze (46-37 mcd), thought to be deposited during maximum nutrient availability and primary productivity. Herbs (Brassicaceae), trees/shrubs (Fabaceae and Theaceae), and C3 grasses correlated with inorganic parameters, indicating increased drainage of ultramafic sediments and laterite soils from the lakes' catchment, particularly at times of inferred drying. Downcore variability in trnL-P6 from tropical forest trees (Toona), shady ground cover herbs (Zingiberaceae), and tree orchids (Luisia) most strongly correlated with sediments of a predominantly felsic signature considered to be originating from the catchment of the Loeha River draining into Lake Towuti during wetter climate conditions. However, the co-correlation with dry climate-adapted trees (i.e., Castanopsis or Lithocarpus) plus C4 grasses suggests that increased precipitation seasonality also contributed to the increased drainage of felsic Loeha River sediments. This multiproxy approach shows that despite elevated insitu temperatures, tropical lake sediments potentially comprise long-term archives of ancient environmental DNA for reconstructing ecosystems, which warrants further exploration.

Cross-Correlation of Confocal Images for Excised Breast Tissues of Total Mastectomy.

The purpose of this study is to develop an image artifact removal method for radar-based microwave breast imaging and demonstrates the detectability on excised breast tissues of total mastectomy. A cross-correlation method was proposed and measurements were conducted. A hand-held radar-based breast cancer detector was utilized to measure a breast at different orientations. Images were generated by multiplying the confocal image data from two scans after cross-correlation. The optimum reconstruction permittivity values were extracted by the local maxima of the confocal image intensity as a function of reconstruction permittivity. With the proposed cross-correlation method, the contrast of the imaging result was enhanced and the clutters were removed. The proposed method was applied to 50 cases of excised breast tissues and the detection sensitivity of 72% was achieved. With the limited number of samples, the dependency of detection sensitivity on the breast size, breast density, and tumor size were examined. The detection sensitivity was strongly influenced by the breast density. The sensitivity was high for fatty breasts, whereas the sensitivity was low for heterogeneously dense breasts. In addition, it was observed that the sensitivity was high for extremely dense breast. This is the first detailed report on the excised breast tissues.

Enhancing Skin Cancer Classification using Efficient Net B0-B7 through Convolutional Neural Networks and Transfer Learning with Patient-Specific Data.

Skin cancer diagnosis challenges dermatologists due to its complex visual variations across diagnostic categories. Convolutional neural networks (CNNs), specifically the Efficient Net B0-B7 series, have shown superiority in multiclass skin cancer classification. This study addresses the limitations of visual examination by presenting a tailored preprocessing pipeline designed for Efficient Net models. Leveraging transfer learning with pre-trained ImageNet weights, the research aims to enhance diagnostic accuracy in an imbalanced multiclass classification context. The study develops a specialized image preprocessing pipeline involving image scaling, dataset augmentation, and artifact removal tailored to the nuances of Efficient Net models. Using the Efficient Net B0-B7 dataset, transfer learning fine-tunes CNNs with pre-trained ImageNet weights. Rigorous evaluation employs key metrics like Precision, Recall, Accuracy, F1 Score, and Confusion Matrices to assess the impact of transfer learning and fine-tuning on each Efficient Net variant's performance in classifying diverse skin cancer categories. The research showcases the effectiveness of the tailored preprocessing pipeline for Efficient Net models. Transfer learning and fine-tuning significantly enhance the models' ability to discern diverse skin cancer categories. The evaluation of eight Efficient Net models (B0-B7) for skin cancer classification reveals distinct performance patterns across various cancer classes. While the majority class, Benign Kertosis, achieves high accuracy (>87%), challenges arise in accurately classifying Eczema classes. Melanoma, despite its minority representation (2.42% of images), attains an average accuracy of 80.51% across all models. However, suboptimal performance is observed in predicting warts molluscum (90.7%) and psoriasis (84.2%) instances, highlighting the need for targeted improvements in accurately identifying specific skin cancer types. The study on skin cancer classification utilizes EfficientNets B0-B7 with transfer learning from ImageNet weights. The pinnacle performance is observed with EfficientNet-B7, achieving a groundbreaking top-1 accuracy of 84.4% and top-5 accuracy of 97.1%. Remarkably efficient, it is 8.4 times smaller than the leading CNN. Detailed per-class classification exactitudes through Confusion Matrices affirm its proficiency, signaling the potential of EfficientNets for precise dermatological image analysis.