Computer-aided Diagnosis Research Articles

Data-Efficient Vision Transformer Models for Robust Classification of Sugarcane

Sugar cane is an important agricultural product that provides 75% of the world's sugar production. As with all plant species, any disease affecting sugarcane can significantly impact yields and planning. Diagnosing diseases in sugarcane leaves using traditional methods is slow, inefficient, and often lacking in accuracy. This study presents a deep learning-based approach for accurate diagnosis of diseases in sugarcane leaves. Specifically, training and evaluation were conducted on the publicly available Sugarcane Leaf Dataset using leading ViT (Vision Transformer) architectures such as DeiT3-Small and DeiT-Tiny. This dataset includes 11 different disease classes and a total of 6748 images. Additionally, these models were compared with popular CNN models. The findings of the study show that there is no direct relationship between model complexity, depth, and accuracy for the 11-class sugarcane dataset. Among the 12 models tested, the DeiT3-Small model showed the highest performance with 93.79% accuracy, 91.27% precision, and 90.96% F1-score. These results highlight that rapid, accurate, and automatic disease diagnosis systems developed using deep learning techniques can significantly improve sugarcane disease management and contribute to increased yields.

Neural Network Classification Algorithm Based on Self-attention Mechanism and Ensemble Learning for MASLD Ultrasound Images

BackgroundUltrasound image examination has become the preferred choice for diagnosing metabolic dysfunction-associated steatotic liver disease (MASLD) due to its non-invasive nature. Computer-aided diagnosis (CAD) technology can assist doctors in avoiding deviations in the detection and classification of MASLD. MethodWe propose a hybrid model that integrates the pre-trained VGG16 network with an attention mechanism and a stacking ensemble learning model, which is capable of multi-scale feature aggregation based on the self-attention mechanism and multi-classification model fusion (Logistic regression, random forest, support vector machine) based on stacking ensemble learning. The proposed hybrid method achieves four classifications of normal, mild, moderate, and severe fatty liver based on ultrasound images. Result and conclusionOur proposed hybrid model reaches an accuracy of 91.34% and exhibits superior robustness against interference, which is better than traditional neural network algorithms. Experimental results show that, compared with the pre-trained VGG16 model, adding the self-attention mechanism improves the accuracy by 3.02%. Using the stacking ensemble learning model as a classifier further increases the accuracy to 91.34%, exceeding any single classifier such as LR (89.86%) and SVM (90.34%) and RF (90.73%). The proposed hybrid method can effectively improve the efficiency and accuracy of MASLD ultrasound image detection.

NFMPAtt-Unet: Neighborhood Fuzzy C-means Multi-scale Pyramid Hybrid Attention Unet for medical image segmentation

Medical image segmentation is crucial for understanding anatomical or pathological changes, playing a key role in computer-aided diagnosis and advancing intelligent healthcare. Currently, important issues in medical image segmentation need to be addressed, particularly the problem of segmenting blurry edge regions and the generalizability of segmentation models. Therefore, this study focuses on different medical image segmentation tasks and the issue of blurriness. By addressing these tasks, the study significantly improves diagnostic efficiency and accuracy, contributing to the overall enhancement of healthcare outcomes. To optimize segmentation performance and leverage feature information, we propose a Neighborhood Fuzzy c-Means Multiscale Pyramid Hybrid Attention Unet (NFMPAtt-Unet) model. NFMPAtt-Unet comprises three core components: the Multiscale Dynamic Weight Feature Pyramid module (MDWFP), the Hybrid Weighted Attention mechanism (HWA), and the Neighborhood Rough Set-based Fuzzy c-Means Feature Extraction module (NFCMFE). The MDWFP dynamically adjusts weights across multiple scales, improving feature information capture. The HWA enhances the network’s ability to capture and utilize crucial features, while the NFCMFE, grounded in neighborhood rough set concepts, aids in fuzzy C-means feature extraction, addressing complex structures and uncertainties in medical images, thereby enhancing adaptability. Experimental results demonstrate that NFMPAtt-Unet outperforms state-of-the-art models, highlighting its efficacy in medical image segmentation.

Computer-aided diagnosis of cystic lung diseases using CT scans and deep learning.

Auxiliary diagnosis of different types of cystic lung diseases (CLDs) is important in the clinic and is instrumental in facilitating early and specific treatments. Current clinical methods heavily depend on accumulated experience, restricting their applicability in regions with less developed medical resources. Thus, how to realize the computer-aided diagnosis of CLDs is of great clinical value. This work proposed a deep learning-based method for automatically segmenting the lung parenchyma in computed tomography (CT) slice images and accurately diagnosing the CLDs using CT scans. A two-stage deep learning method was proposed for the automatic classification of normal cases and five different CLDs using CT scans. Lung parenchyma segmentation is the foundation of CT image analysis and auxiliary diagnosis. To meet the requirements of different sizes of the lung parenchyma, an adaptive region-growing and improved U-Net model was employed for mask acquisition and automatic segmentation. The former was achieved by a self-designed adaptive seed point selection method based on similarity measurement, and the latter introduced multiscale input and multichannel output into the original U-Net model and effectively achieved the lightweight design by adjusting the structure and parameters. After that, the middle 30 consecutive CT slice images of each sample were segmented to obtain lung parenchyma, which was employed for training and testing the proposed multichannel parallel input recursive MLP-Mixer network (MPIRMNet) model, achieving the computer-aided diagnosis of CLDs. A total of 4718 and 16290 CT slice images collected from 543 patients were employed to validate the proposed segmentation and classification methods, respectively. Experimental results showed that the improved U-Net model can accurately segment the lung parenchyma in CT slice images, with the Dice, precision, volumetric overlap error, and relative volume difference of 0.96±0.01, 0.93±0.04, 0.05±0.02, and 0.05±0.03, respectively. Meanwhile, the proposed MPIRMNet model achieved appreciable classification effect for normal cases and different CLDs, with the accuracy, sensitivity, specificity, and F1 score of 0.8823±0.0324, 0.8897±0.0325, 0.9746±0.0078, and 0.8831±0.0334, respectively. Compared with classical machine learning and convolutional neural networks-based methods for this task, the proposed classification method had a preferable performance, with a significant improvement of accuracy of 10.74%. The work introduced a two-stage deep learning method, which can achieve the segmentation of lung parenchyma and the classification of CLDs. Compared to previous diagnostic tasks targeting single CLD, this work can achieve various CLDs' diagnosis in the early stage, thereby achieving targeted treatment and increasing the potential and value of clinical applications.

ConvLSNet: A lightweight architecture based on ConvLSTM model for the classification of pulmonary conditions using multichannel lung sound recordings

Characterization of lung sounds (LS) is indispensable for diagnosing respiratory pathology. Although conventional neural networks (NNs) have been widely employed for the automatic diagnosis of lung sounds, deep neural networks can potentially be more useful than conventional NNs by allowing accurate classification without requiring preprocessing and feature extraction. Utilizing the long short-term memory (LSTM) layers to reveal the sequence-based properties of the LS time series, a novel architecture consisting of a cascade of convolutional long short-term memory (ConvLSTM) and LSTM layers, namely ConvLSNet is developed, which permits highly accurate diagnosis of pulmonary disease states. By modeling the multichannel lung sounds through the ConvLSTM layer, the proposed ConvLSNet architecture can concurrently deal with the spatial and temporal properties of the six-channel LS recordings without heavy preprocessing or data transformation. Notably, the proposed model achieves a classification accuracy of 97.4 % based on LS data corresponding to three pulmonary conditions, namely asthma, COPD, and the healthy state. Compared with architectures consisting exclusively of CNN or LSTM layers, as well as those employing a cascade integration of 2DCNN and LSTM layers, the proposed ConvLSNet architecture exhibited the highest classification accuracy, while imposing the lowest computational cost as quantified by the number of parameters, training time, and learning rate.

Software advancements in automatic epilepsy diagnosis and seizure detection: 10-year review

Epilepsy is a chronic neurological disorder that may be diagnosed and monitored using routine diagnostic tests like Electroencephalography (EEG). However, manual introspection and analysis of EEG signals is presently difficult and repetitive task even for experienced neuro-technologists with high false-positive rates and inter- and intra-rater reliability. Software advancements using Artificial Intelligence (AI) algorithms have the potential to early detect and predict abnormal patterns observed in EEG signals. The present review focuses on systematically reporting software advancements and their implementation using hardware systems in automatic epilepsy diagnosis and seizure detection for the past 10 years. Traditional, hybrid, and end-to-end AI-based pipelines and associated EEG datasets have been discussed. The review summarizes and compares reported articles, datasets, and patents through various subjective and objective parameters in this field. Latest advancements demonstrate that AI-based pipelines can reduce the introspection time by at least 50% without compromising the diagnostic accuracy or abnormal event detection. A significant rise in hardware implementation of software-based pipelines, end-to-end deep learning architectures for real-time analysis, and granted patents has been noticed since 2011. More than twenty-eight datasets have been developed to automatically diagnose epileptic EEG signals from 2001 to 2023. Extensive analysis using explainability tools, cross-dataset generalizations, reproducibility analysis, and ablation experiments can further improve the existing AI-based pipelines in this field. There is a need for the development of standardized protocols for data collection and its AI pipeline for a robust, inter- and intra-rater reliability-free, and real-time automatic epilepsy diagnosis.

Novel Deep Learning Neural Networks for Breast Cancer Malignancy Estimation

Medicine has become one of the huge fields which has its own growth each and every day. Few diseases are still a threat to medical field. Because of its destructive nature, cancer is a disease that causes fear in many people throughout the world. However, most cancers are curable if detected early and treated with the right medical care and computer-assisted diagnosis. These days, diagnosis is more popular because it works well as a primary screening test for many diseases, particularly cancer. Deep learning is a method of artificial intelligence where the computer is given intelligence that attempts to emulate the way a human brain thinks. This research focuses on creating a deep neural network that can accurately predict the malignancy of breast cancer up to 98%, allowing medical personnel to diagnose patients more quickly and administer therapy more effectively.

Potential of digital chest radiography-based deep learning in screening and diagnosing pneumoconiosis: An observational study.

The diagnosis of pneumoconiosis is complex and subjective, leading to inevitable variability in readings. This is especially true for inexperienced doctors. To improve accuracy, a computer-assisted diagnosis system is used for more effective pneumoconiosis diagnoses. Three models (Resnet50, Resnet101, and DenseNet) were used for pneumoconiosis classification based on 1250 chest X-ray images. Three experienced and highly qualified physicians read the collected digital radiography images and classified them from category 0 to category III in a double-blinded manner. The results of the 3 physicians in agreement were considered the relative gold standards. Subsequently, 3 models were used to train and test these images and their performance was evaluated using multi-class classification metrics. We used kappa values and accuracy to evaluate the consistency and reliability of the optimal model with clinical typing. The results showed that ResNet101 was the optimal model among the 3 convolutional neural networks. The AUC of ResNet101 was 1.0, 0.9, 0.89, and 0.94 for detecting pneumoconiosis categories 0, I, II, and III, respectively. The micro-average and macro-average mean AUC values were 0.93 and 0.94, respectively. The accuracy and Kappa values of ResNet101 were 0.72 and 0.7111 for quadruple classification and 0.98 and 0.955 for dichotomous classification, respectively, compared with the relative standard classification of the clinic. This study develops a deep learning based model for screening and staging of pneumoconiosis is using chest radiographs. The ResNet101 model performed relatively better in classifying pneumoconiosis than radiologists. The dichotomous classification displayed outstanding performance, thereby indicating the feasibility of deep learning techniques in pneumoconiosis screening.

A spatiotemporal graph transformer approach for Alzheimer’s disease diagnosis with rs-fMRI

Alzheimer’s disease (AD) is a neurodegenerative disease accompanied by cognitive impairment. Early diagnosis is crucial for the timely treatment and intervention of AD. Resting-state functional magnetic resonance imaging (rs-fMRI) records the temporal dynamics and spatial dependency in the brain, which have been utilized for automatically diagnosis of AD in the community. Existing approaches of AD diagnosis using rs-fMRI only assess functional connectivity, ignoring the spatiotemporal dependency mining of rs-fMRI. In addition, it is difficult to increase diagnosis accuracy due to the shortage of rs-fMRI sample and the poor anti-noise ability of model. To deal with these problems, this paper proposes a novel approach for the automatic diagnosis of AD, namely spatiotemporal graph transformer network (STGTN). The proposed STGTN can effectively extract spatiotemporal features of rs-fMRI. Furthermore, to solve the sample-limited problem and to improve the anti-noise ability of the proposed model, an adversarial training strategy is adopted for the proposed STGTN to generate adversarial examples (AEs) and augment training samples with AEs. Experimental results indicate that the proposed model achieves the classification accuracy of 92.58%, and 85.27% with the adversarial training strategy for AD vs. normal control (NC), early mild cognitive impairment (eMCI) vs. late mild cognitive impairment (lMCI) respectively, outperforming the state-of-the-art methods. Besides, the spatial attention coefficients reflected from the designed model reveal the importance of brain connections under different classification tasks.

Unsupervised autoencoders with features in the electromechanical impedance domain for early damage assessment in FRP-strengthened concrete elements

This paper presents the development of a robust automatic diagnosis technique that uses raw Electro-Mechanical Impedance (EMI) signals and deep autoencoder models to detect damage in fiber-reinforced-polymers (FRP) strengthened reinforced concrete (RC) elements, for which the most common failure modes occur in a sudden and brittle way by debonding. The contribution of this work is threefold: First, for the first time, two autoencoder models, convolutional and fully connected, based on an unsupervised learning framework supplemented by appropriate pre-processing techniques, are proposed for effective tracking of FRP-strengthened RC elements from raw EMI response variations in different locations of the auscultated structure; their implementation is also extensively investigated. The proposed framework consists of two main components, namely, dimensionality reduction and relationship learning. The first component is to reduce the dimensionality of the raw EMI signal while preserving the necessary information required, and the second component is to perform the relationship learning between the features with the reduced dimensionality and the stiffness reduction parameters of the structure. The approach is beneficial as only the EMI spectrum from the healthy structure state is considered for the training of the autoencoders. Second, the superior performance of the proposed framework is demonstrated. The results show that the proposed technique can accurately detect minor damage in its earliest stages for this kind of strengthened structures, while removing the need for manual or signal processing-based damage sensitive feature extraction from EMI signals for damage diagnosis. Finally, research presented in this work can potentially open up new opportunities for successful condition monitoring of this type of strengthened structures.

An Approach in Melanoma Skin Cancer Segmentation With Bat Optimization Algorithm

ABSTRACTNumerous advancements and significant progress have been made in computer methods for medical applications, alongside technological developments. Automatic image analysis plays a crucial role in the realm of medical diagnosis and therapy. Recent breakthroughs, especially in the field of medical image processing, have enabled the automatic detection of various characteristics, alterations, diseases, and degenerative conditions using skin scans. Utilizing image processing methods, skin image analysis is instrumental in the identification and monitoring of conditions manifesting through alterations in skin structure. Notably, accurate segmentation of cancerous regions from the background remains a challenging task in the area of melanoma image analysis. The primary objective of this study is to achieve exceptional precision in delineating melanoma boundaries. Leveraging the Bat Optimization algorithm, we determine the optimal threshold for melanoma segmentation, effectively identifying the most accurate cancerous area boundaries. To evaluate the results, standard metrics such as accuracy, sensitivity, specificity, Dice coefficient, and F1 score are employed. In this study, we applied the Bat Optimization algorithm to determine the optimal threshold value for segmenting melanoma skin cancer, effectively identifying the most accurate cancerous area boundaries. For result evaluation, we employed standard metrics including accuracy, sensitivity, specificity, Dice coefficient, and F1 score, which yielded impressive values of 99.8%, 98.99%, 98.87%, 98.45%, and 98.24%, respectively.

Precise Prostate Cancer Assessment Using IVIM-Based Parametric Estimation of Blood Diffusion from DW-MRI.

Prostate cancer is a significant health concern with high mortality rates and substantial economic impact. Early detection plays a crucial role in improving patient outcomes. This study introduces a non-invasive computer-aided diagnosis (CAD) system that leverages intravoxel incoherent motion (IVIM) parameters for the detection and diagnosis of prostate cancer (PCa). IVIM imaging enables the differentiation of water molecule diffusion within capillaries and outside vessels, offering valuable insights into tumor characteristics. The proposed approach utilizes a two-step segmentation approach through the use of three U-Net architectures for extracting tumor-containing regions of interest (ROIs) from the segmented images. The performance of the CAD system is thoroughly evaluated, considering the optimal classifier and IVIM parameters for differentiation and comparing the diagnostic value of IVIM parameters with the commonly used apparent diffusion coefficient (ADC). The results demonstrate that the combination of central zone (CZ) and peripheral zone (PZ) features with the Random Forest Classifier (RFC) yields the best performance. The CAD system achieves an accuracy of 84.08% and a balanced accuracy of 82.60%. This combination showcases high sensitivity (93.24%) and reasonable specificity (71.96%), along with good precision (81.48%) and F1 score (86.96%). These findings highlight the effectiveness of the proposed CAD system in accurately segmenting and diagnosing PCa. This study represents a significant advancement in non-invasive methods for early detection and diagnosis of PCa, showcasing the potential of IVIM parameters in combination with machine learning techniques. This developed solution has the potential to revolutionize PCa diagnosis, leading to improved patient outcomes and reduced healthcare costs.

Computer-assisted urine cytology: Faster, cheaper, better?

Recent advancements in computer-assisted diagnosis (CAD) have catalysed significant progress in pathology, particularly in the realm of urine cytopathology. This review synthesizes the latest developments and challenges in CAD for diagnosing urothelial carcinomas, addressing the limitations of traditional urinary cytology. Through a literature review, we identify and analyse CAD models and algorithms developed for urine cytopathology, highlighting their methodologies and performance metrics. We discuss the potential of CAD to improve diagnostic accuracy, efficiency and patient outcomes, emphasizing its role in streamlining workflow and reducing errors. Furthermore, CAD tools have shown potential in exploring pathological conditions, uncovering novel biomarkers and prognostic/predictive features previously unknown or unseen. Finally, we examine the practical issues surrounding the integration of CAD into clinical practice, including regulatory approval, validation and training for pathologists. Despite the promising results, challenges remain, necessitating further research and validation efforts. Overall, CAD presents a transformative opportunity to revolutionize diagnostic practices in urine cytopathology, paving the way for enhanced patient care and outcomes.

An extensive analysis of artificial intelligence and segmentation methods transforming cancer recognition in medical imaging

Recent advancements in computational intelligence, deep learning, and computer-aided detection have had a significant impact on the field of medical imaging. The task of image segmentation, which involves accurately interpreting and identifying the content of an image, has garnered much attention. The main objective of this task is to separate objects from the background, thereby simplifying and enhancing the significance of the image. However, existing methods for image segmentation have their limitations when applied to certain types of images. This survey paper aims to highlight the importance of image segmentation techniques by providing a thorough examination of their advantages and disadvantages. The accurate detection of cancer regions in medical images is crucial for ensuring effective treatment. In this study, we have also extensive analysis of Computer-Aided Diagnosis (CAD) systems for cancer identification, with a focus on recent research advancements. The paper critically assesses various techniques for cancer detection and compares their effectiveness. Convolutional neural networks (CNNs) have attracted particular interest due to their ability to segment and classify medical images in large datasets, thanks to their capacity for self- learning and decision-making.

UDBRNet: A novel uncertainty driven boundary refined network for organ at risk segmentation.

Organ segmentation has become a preliminary task for computer-aided intervention, diagnosis, radiation therapy, and critical robotic surgery. Automatic organ segmentation from medical images is a challenging task due to the inconsistent shape and size of different organs. Besides this, low contrast at the edges of organs due to similar types of tissue confuses the network's ability to segment the contour of organs properly. In this paper, we propose a novel convolution neural network based uncertainty-driven boundary-refined segmentation network (UDBRNet) that segments the organs from CT images. The CT images are segmented first and produce multiple segmentation masks from multi-line segmentation decoder. Uncertain regions are identified from multiple masks and the boundaries of the organs are refined based on uncertainty data. Our method achieves remarkable performance, boasting dice accuracies of 0.80, 0.95, 0.92, and 0.94 for Esophagus, Heart, Trachea, and Aorta respectively on the SegThor dataset, and 0.71, 0.89, 0.85, 0.97, and 0.97 for Esophagus, Spinal Cord, Heart, Left-Lung, and Right-Lung respectively on the LCTSC dataset. These results demonstrate the superiority of our uncertainty-driven boundary refinement technique over state-of-the-art segmentation networks such as UNet, Attention UNet, FC-denseNet, BASNet, UNet++, R2UNet, TransUNet, and DS-TransUNet. UDBRNet presents a promising network for more precise organ segmentation, particularly in challenging, uncertain conditions. The source code of our proposed method will be available at https://github.com/riadhassan/UDBRNet.

Privacy-Preserving Byzantine-Resilient Swarm Learning for E-Healthcare

An automatic medical diagnosis service based on deep learning has been introduced in e-healthcare, bringing great convenience to human life. However, due to privacy regulations, insufficient data sharing among medical centers has led to many severe challenges for automated medical diagnostic services, including diagnostic accuracy. To solve such problems, swarm learning (SL), a blockchain-based federated learning (BCFL), has been proposed. Although SL avoids single-point-of-failure attacks and offers an incentive mechanism, it still faces privacy breaches and poisoning attacks. In this paper, we propose a new privacy-preserving Byzantine-resilient swarm learning (PBSL) that is resistant to poisoning attacks while protecting data privacy. Specifically, we adopt threshold fully homomorphic encryption (TFHE) to protect data privacy and provide secure aggregation. And the cosine similarity is used to judge the malicious gradient uploaded by malicious medical centers. Through security analysis, PBSL is able to defend against a variety of known security attacks. Finally, PBSL is implemented by uniting deep learning with blockchain-based smart contract platforms. Experiments based on different datasets show that the PBSL algorithm is practical and efficient.

Recent metaheuristic algorithms for medical object localization using MSER detector in computer-aided diagnosis system

Recent metaheuristic algorithms for medical object localization using MSER detector in computer-aided diagnosis system

Automatic diagnosis of myopic maculopathy using continuous severity ranking labels

Automatic diagnosis of myopic maculopathy using continuous severity ranking labels

Iterative enhancement fusion-based cascaded model for detection and localization of multiple disease from CXR-Images

The lungs are a vital organ of the human body. Malfunctioning of the lungs caused a direct threat to life. In recent years the world has witnessed massive medical insufficiency to handle the lung diseases caused by numerous agents including COVID-19. According to the recommended course of treatment, medical imaging tests including X-rays and CT scans have been very helpful in identifying multiple chest infections. Automatic detection of chest disease is the need of the modern time as it will speed up patient care and reduce doctors’ workload. An Iterative Enhancement Fusion-based Cascaded (IEFCM) model to identify multiple diseases from chest X-ray images is suggested in the present paper. If a chest infection is discovered in the imaging, the suggested model additionally localizes the precise infected area on the CXR image. Experimental outcome clearly demonstrates that the performance of suggested model is significantly superior to the pre-trained model, that is the Golden standard dataset and data from the local population. In terms of sensitivity and specificity, IEFCM achieved 95.62 % sensitivity, which indicates an accurate diagnosis of lung disease, reducing the risk of missing any instances. Similarly, the specificity is 96.23 %, which denotes, the IEFCM model correctly identified the healthy people. It resulted decrease of misdiagnosis and unnecessary follow-up testings.

Few-shot learning for COVID-19 chest X-ray classification with imbalanced data: an inter vs. intra domain study

Medical image datasets are essential for training models used in computer-aided diagnosis, treatment planning, and medical research. However, some challenges are associated with these datasets, including variability in data distribution, data scarcity, and transfer learning issues when using models pre-trained from generic images. This work studies the effect of these challenges at the intra- and inter-domain level in few-shot learning scenarios with severe data imbalance. For this, we propose a methodology based on Siamese neural networks in which a series of techniques are integrated to mitigate the effects of data scarcity and distribution imbalance. Specifically, different initialization and data augmentation methods are analyzed, and four adaptations to Siamese networks of solutions to deal with imbalanced data are introduced, including data balancing and weighted loss, both separately and combined, and with a different balance of pairing ratios. Moreover, we also assess the inference process considering four classifiers, namely Histogram, kNN, SVM, and Random Forest. Evaluation is performed on three chest X-ray datasets with annotated cases of both positive and negative COVID-19 diagnoses. The accuracy of each technique proposed for the Siamese architecture is analyzed separately. The results are compared to those obtained using equivalent methods on a state-of-the-art CNN, achieving an average F1 improvement of up to 3.6%, and up to 5.6% of F1 for intra-domain cases. We conclude that the introduced techniques offer promising improvements over the baseline in almost all cases and that the technique selection may vary depending on the amount of data available and the level of imbalance.