J Environ Manage. 2024 Nov 1;371:123096. doi: 10.1016/j.jenvman.2024.123096. Online ahead of print.

ABSTRACT

Ambient carbon monoxide (CO) is a primary air pollutant that poses significant health risks and contributes to the formation of secondary atmospheric pollutants, such as ozone (O3). This study aims to elucidate global CO pollution in relation to health risks and the influence of natural events like wildfires. Utilizing artificial intelligence (AI) big data techniques, we developed a high-performance Convolutional Neural Network (CNN)-based Residual Network (ResNet) model to estimate daily global CO concentrations at a high spatial resolution of 0.07° from June 2018 to May 2021. Our model integrated the global TROPOMI Total Column of atmospheric CO (TCCO) product and reanalysis datasets, achieving desirable estimation accuracies with R-values (correlation coefficients) of 0.90 and 0.96 for daily and monthly predictions, respectively. The analysis reveals that the CO concentrations were relatively high in northern and central China, as well as northern India, particularly during winter months. Given the significant role of wildfires in increasing surface CO levels, we examined their impact in the Indochina Peninsula, the Amazon Rain Forest, and Central Africa. Our results show increases of 60.0%, 28.7%, and 40.8% in CO concentrations for these regions during wildfire seasons, respectively. Additionally, we estimated short-term mortality cases related to CO exposure in 17 countries for 2019, with China having the highest mortality cases of 23,400 (95% confidence interval: 0-99,500). Our findings highlight the critical need for ongoing monitoring of CO levels and their health implications. The daily surface CO concentration dataset is publicly available and can support future relevant sustainable studies, which is accessible at https://doi.org/10.5281/zenodo.11806178.

PMID:39488180 | DOI:10.1016/j.jenvman.2024.123096

Neural Netw. 2024 Oct 24;181:106829. doi: 10.1016/j.neunet.2024.106829. Online ahead of print.

ABSTRACT

Sharpness-aware minimization (SAM) aims to enhance model generalization by minimizing the sharpness of the loss function landscape, leading to a robust model performance. To protect sensitive information and enhance privacy, prevailing approaches add noise to models. However, additive noises would inevitably degrade the generalization and robustness of the model. In this paper, we propose a noise-resistant SAM method, based on a noise-resistant parameter update rule. We analyze the convergence and noise resistance properties of the proposed method under noisy conditions. We elaborate on experimental results with several networks on various benchmark datasets to demonstrate the advantages of the proposed method with respect to model generalization and privacy protection.

PMID:39488109 | DOI:10.1016/j.neunet.2024.106829

Neural Netw. 2024 Oct 28;181:106855. doi: 10.1016/j.neunet.2024.106855. Online ahead of print.

ABSTRACT

Timely detecting epileptic seizures can significantly reduce accidental injuries of epilepsy patients and offer a novel intervention approach to improve their quality of life. Investigation on seizure detection based on deep learning models has achieved great success. However, there still remain challenging issues, such as the high computational complexity of the models and overfitting caused by the scarce availability of ictal electroencephalogram (EEG) signals for training. Therefore, we propose a novel end-to-end automatic seizure detection model named CNN-Informer, which leverages the capability of Convolutional Neural Network (CNN) to extract EEG local features of multi-channel EEGs, and the low computational complexity and memory usage ability of the Informer to capture the long-range dependencies. In view of the existence of various artifacts in long-term EEGs, we filter those raw EEGs using Discrete Wavelet Transform (DWT) before feeding them into the proposed CNN-Informer model for feature extraction and classification. Post-processing operations are further employed to achieve the final detection results. Our method is extensively evaluated on the CHB-MIT dataset and SH-SDU dataset with both segment-based and event-based criteria. The experimental outcomes demonstrate the superiority of the proposed CNN-Informer model and its strong generalization ability across two EEG datasets. In addition, the lightweight architecture of CNN-Informer makes it suitable for real-time implementation.

PMID:39488107 | DOI:10.1016/j.neunet.2024.106855

Microsc Res Tech. 2024 Nov 2. doi: 10.1002/jemt.24709. Online ahead of print.

ABSTRACT

In the worldwide working-age population, visual disability and blindness are common conditions caused by diabetic retinopathy (DR) and diabetic macular edema (DME). Nowadays, due to diabetes, many people are affected by eye-related issues. Among these, DR and DME are the two foremost eye diseases, the severity of which may lead to some eye-related problems and blindness. Early detection of DR and DME is essential to preventing vision loss. Therefore, an enhanced capsule generation adversarial network (ECGAN) optimized with the rat swarm optimization (RSO) approach is proposed in this article to coincide with DR and DME grading (DR-DME-ECGAN-RSO-ISBI 2018 IDRiD). The input images are obtained from the ISBI 2018 unbalanced DR grading data set. Then, the input fundus images are preprocessed using the Savitzky-Golay (SG) filter filtering technique, which reduces noise from the input image. The preprocessed image is fed to the discrete shearlet transform (DST) for feature extraction. The extracting features of DR-DME are given to the ECGAN-RSO algorithm to categorize the grading of DR and DME disorders. The proposed approach is implemented in Python and achieves better accuracy by 7.94%, 36.66%, and 4.88% compared to the existing models, such as the combined DR with DME grading for the cross-disease attention network (DR-DME-CANet-ISBI 2018 IDRiD), category attention block for unbalanced grading of DR (DR-DME-HDLCNN-MGMO-ISBI 2018 IDRiD), combined DR-DME classification with a deep learning-convolutional neural network-based modified gray-wolf optimizer with variable weights (DR-DME-ANN-ISBI 2018 IDRiD).

PMID:39487733 | DOI:10.1002/jemt.24709

BMC Med Imaging. 2024 Nov 1;24(1):297. doi: 10.1186/s12880-024-01476-1.

ABSTRACT

Detecting brain tumors early on is critical for effective treatment and life-saving efforts. The analysis of the brain with MRI scans is fundamental to the diagnosis because it contains detailed structural views of the brain, which is vital in identifying any of its abnormalities. The other option of performing an invasive biopsy is very painful and uncomfortable, which is not the case with MRI as it is free from surgically invasive margins and pieces of equipment. This helps patients to feel more at ease and hasten the diagnostic procedure, allowing physicians to formulate and practice action plans quicker. It is very difficult to locate a human brain tumor by manual because MRI scans produce large numbers of three-dimensional images. Complete applicability of pre-written computerized diagnostics, affords high possibilities in providing areas of interest earlier through the application of machine learning techniques and algorithms. The proposed work in the present study was to develop a deep learning model which will classify brain tumor grade images (BTGC), and hence enhance accuracy in diagnosing patients with different grades of brain tumors using MRI. A MobileNetV2 model, was used to extract the features from the images. This model increases the efficiency and generalizability of the model further. In this study, six standard Kaggle brain tumor MRI datasets were used to train and validate the developed and tested model of a brain tumor detection and classification algorithm into several types. This work consists of two key components: (i) brain tumor detection and (ii) classification of the tumor. The tumor classifications are conducted in both three classes (Meningioma, Pituitary, and glioma) and two classes (malignant, benign). The model has been reported to detect brain tumors with 99.85% accuracy, to distinguish benign and malignant tumors with 99.87% accuracy, and to type meningioma, pituitary, and glioma tumors with 99.38% accuracy. The results of this study indicate that the described technique is useful in the detection and classification of brain tumors.

PMID:39487431 | DOI:10.1186/s12880-024-01476-1

BMC Oral Health. 2024 Nov 1;24(1):1332. doi: 10.1186/s12903-024-05126-4.

ABSTRACT

Periapical periodontitis may manifest as a radiographic lesion radiographically. Periapical lesions are amongst the most common dental pathologies that present as periapical radiolucencies on panoramic radiographs. The objective of this research is to assess the diagnostic accuracy of an artificial intelligence (AI) model based on U²-Net architecture in the detection of periapical lesions on dental panoramic radiographs and to determine whether they can be useful in aiding clinicians with diagnosis of periapical lesions and improving their clinical workflow. 400 panoramic radiographs that included at least one periapical radiolucency were selected retrospectively. 780 periapical radiolucencies in these anonymized radiographs were manually labeled by two independent examiners. These radiographs were later used to train the AI model based on U²-Net architecture trained using a deep supervision algorithm. An AI model based on the U²-Net architecture was implemented. The model achieved a dice score of 0.8 on the validation set and precision, recall, and F1-score of 0.82, 0.77, and 0.8 respectively on the test set. This study has shown that an AI model based on U²-Net architecture can accurately diagnose periapical lesions on panoramic radiographs. The research provides evidence that AI-based models have promising applications as adjunct tools for dentists in diagnosing periapical radiolucencies and procedure planning. Further studies with larger data sets would be required to improve the diagnostic accuracy of AI-based detection models.

PMID:39487404 | DOI:10.1186/s12903-024-05126-4

BMC Bioinformatics. 2024 Nov 1;25(1):341. doi: 10.1186/s12859-024-05970-9.

ABSTRACT

BACKGROUND: The study focuses on enhancing the effectiveness of precision agriculture through the application of deep learning technologies. Precision agriculture, which aims to optimize farming practices by monitoring and adjusting various factors influencing crop growth, can greatly benefit from artificial intelligence (AI) methods like deep learning. The Agro Deep Learning Framework (ADLF) was developed to tackle critical issues in crop cultivation by processing vast datasets. These datasets include variables such as soil moisture, temperature, and humidity, all of which are essential to understanding and predicting crop behavior. By leveraging deep learning models, the framework seeks to improve decision-making processes, detect potential crop problems early, and boost agricultural productivity.

RESULTS: The study found that the Agro Deep Learning Framework (ADLF) achieved an accuracy of 85.41%, precision of 84.87%, recall of 84.24%, and an F1-Score of 88.91%, indicating strong predictive capabilities for improving crop management. The false negative rate was 91.17% and the false positive rate was 89.82%, highlighting the framework's ability to correctly detect issues while minimizing errors. These results suggest that ADLF can significantly enhance decision-making in precision agriculture, leading to improved crop yield and reduced agricultural losses.

CONCLUSIONS: The ADLF can significantly improve precision agriculture by leveraging deep learning to process complex datasets and provide valuable insights into crop management. The framework allows farmers to detect issues early, optimize resource use, and improve yields. The study demonstrates that AI-driven agriculture has the potential to revolutionize farming, making it more efficient and sustainable. Future research could focus on further refining the model and exploring its applicability across different types of crops and farming environments.

PMID:39487390 | DOI:10.1186/s12859-024-05970-9

Commun Eng. 2024 Nov 1;3(1):151. doi: 10.1038/s44172-024-00303-3.

ABSTRACT

Physics-informed neural network has emerged as a promising approach for solving partial differential equations. However, it is still a challenge for the computation of structural mechanics problems since it involves solving higher-order partial differential equations as the governing equations are fourth-order nonlinear equations. Here we develop a multi-level physics-informed neural network framework where an aggregation model is developed by combining multiple neural networks, with each one involving only first-order or second-order partial differential equations representing different physics information such as geometrical, constitutive, and equilibrium relations of the structure. The proposed framework demonstrates a remarkable advancement over the classical neural networks in terms of the accuracy and computation time. The proposed method holds the potential to become a promising paradigm for structural mechanics computation and facilitate the intelligent computation of digital twin systems.

PMID:39487342 | DOI:10.1038/s44172-024-00303-3

Sci Rep. 2024 Nov 1;14(1):26302. doi: 10.1038/s41598-024-77507-2.

ABSTRACT

Deep Neural Networks (DNNs) have achieved remarkable accuracy for numerous applications, yet their complexity often renders the explanation of predictions a challenging task. This complexity contrasts with easily interpretable statistical models, which, however, often suffer from lower accuracy. Our work suggests that this underperformance may stem more from inadequate training methods than from the inherent limitations of model structures. We hereby introduce the Synced Explanation-Enhanced Neural Network (SEE-Net), a novel architecture integrating a guiding DNN with a shallow neural network, functionally equivalent to a two-layer mixture of linear models. This shallow network is trained under the guidance of the DNN, effectively bridging the gap between the prediction power of deep learning and the need for explainable models. Experiments on image and tabular data demonstrate that SEE-Net can leverage the advantage of DNNs while providing an interpretable prediction framework. Critically, SEE-Net embodies a new paradigm in machine learning: it achieves high-level explainability with minimal compromise on prediction accuracy by training an almost "white-box" model under the co-supervision of a "black-box" model, which can be tailored for diverse applications.

PMID:39487274 | DOI:10.1038/s41598-024-77507-2

Sci Rep. 2024 Nov 2;14(1):26373. doi: 10.1038/s41598-024-78280-y.

ABSTRACT

This study evaluated cone density (CD) in the macular region and assess macular perfusion in children with varying degrees of myopia. This was a prospective, cross-sectional, observational study. Children underwent confocal scanning laser ophthalmoscopy (cSLO), optical coherence tomography (OCT), and OCT angiography (OCTA) imaging. A built-in software was used to measure mean CD (cells/mm2), retinal vessel density, choriocapillaris perfusion area, and choroidal thickness (CT). The study included 140 eyes from children categorized into four groups: emmetropia (31 eyes), low myopia (44 eyes), moderate myopia (31 eyes), and high myopia (34 eyes). The high myopia group exhibited significantly lower macular CD than the emmetropia group (P < 0.05). Additionally, the high myopia group showed thinner CT and higher choriocapillaris perfusion area in the macular region than the emmetropia group (all P < 0.01). Macular CD was significantly correlated with age, spherical equivalent, axial length, and CT (all P < 0.05). Generalized linear models revealed CT as the independent factor associated with macular CD (Wald χ2 = 9.265, P = 0.002). Children with high myopia demonstrate reduced CD in the macular region, accompanied by reduced CT. These findings may have important implications for future myopia prevention and management strategies.

PMID:39487258 | DOI:10.1038/s41598-024-78280-y

Sci Rep. 2024 Nov 2;14(1):26382. doi: 10.1038/s41598-024-76968-9.

ABSTRACT

Understanding and predicting viewers' emotional responses to videos has emerged as a pivotal challenge due to its multifaceted applications in video indexing, summarization, personalized content recommendation, and effective advertisement design. A major roadblock in this domain has been the lack of expansive datasets with videos paired with viewer-reported emotional annotations. We address this challenge by employing a deep learning methodology trained on a dataset derived from the application of System1's proprietary methodologies on over 30,000 real video advertisements, each annotated by an average of 75 viewers. This equates to over 2.3 million emotional annotations across eight distinct categories: anger, contempt, disgust, fear, happiness, sadness, surprise, and neutral, coupled with the temporal onset of these emotions. Leveraging 5-second video clips, our approach aims to capture pronounced emotional responses. Our convolutional neural network, which integrates both video and audio data, predicts salient 5-second emotional clips with an average balanced accuracy of 43.6%, and shows particularly high performance for detecting happiness (55.8%) and sadness (60.2%). When applied to full advertisements, our model achieves a strong average AUC of 75% in determining emotional undertones. To facilitate further research, our trained networks are freely available upon request for research purposes. This work not only overcomes previous data limitations but also provides an accurate deep learning solution for video emotion understanding.

PMID:39487244 | DOI:10.1038/s41598-024-76968-9

Sci Rep. 2024 Nov 1;14(1):26312. doi: 10.1038/s41598-024-76197-0.

ABSTRACT

Clinical sleep diagnosis traditionally relies on polysomnography (PSG) and expert manual classification of sleep stages. Recent advancements in deep learning have shown promise in automating sleep stage classification using a single PSG channel. However, variations in PSG acquisition devices and environments mean that the number of PSG channels can differ across sleep centers. To integrate a sleep staging method into clinical practice effectively, it must accommodate a flexible number of PSG channels. In this paper, we proposed FlexSleepTransformer, a transformer-based model designed to handle varying number of input channels, making it adaptable to diverse sleep staging datasets. We evaluated FlexSleepTransformer using two distinct datasets: the public SleepEDF-78 dataset and the local SleepUHS dataset. Notably, FlexSleepTransformer is the first model capable of simultaneously training on datasets with differing number of PSG channels. Our experiments showed that FlexSleepTransformer trained on both datasets together achieved 98% of the accuracy compared to models trained on each dataset individually. Furthermore, it outperformed models trained exclusively on one dataset when tested on the other dataset. Additionally, FlexSleepTransformer surpassed state-of-the-art CNN and RNN-based models on both datasets. Due to its adaptability with varying channels numbers, FlexSleepTransformer holds significant potential for clinical adoption, especially when trained with data from a wide range of sleep centers.

PMID:39487223 | DOI:10.1038/s41598-024-76197-0

Sci Rep. 2024 Nov 1;14(1):26287. doi: 10.1038/s41598-024-74305-8.

ABSTRACT

The objective of this investigation was to improve the diagnosis of breast cancer by combining two significant datasets: the Wisconsin Breast Cancer Database and the DDSM Curated Breast Imaging Subset (CBIS-DDSM). The Wisconsin Breast Cancer Database provides a detailed examination of the characteristics of cell nuclei, including radius, texture, and concavity, for 569 patients, of which 212 had malignant tumors. In addition, the CBIS-DDSM dataset-a revised variant of the Digital Database for Screening Mammography (DDSM)-offers a standardized collection of 2,620 scanned film mammography studies, including cases that are normal, benign, or malignant and that include verified pathology data. To identify complex patterns and trait diagnoses of breast cancer, this investigation used a hybrid deep learning methodology that combines Convolutional Neural Networks (CNNs) with the stochastic gradients method. The Wisconsin Breast Cancer Database is used for CNN training, while the CBIS-DDSM dataset is used for fine-tuning to maximize adaptability across a variety of mammography investigations. Data integration, feature extraction, model development, and thorough performance evaluation are the main objectives. The diagnostic effectiveness of the algorithm was evaluated by the area under the Receiver Operating Characteristic Curve (AUC-ROC), sensitivity, specificity, and accuracy. The generalizability of the model will be validated by independent validation on additional datasets. This research provides an accurate, comprehensible, and therapeutically applicable breast cancer detection method that will advance the field. These predicted results might greatly increase early diagnosis, which could promote improvements in breast cancer research and eventually lead to improved patient outcomes.

PMID:39487199 | DOI:10.1038/s41598-024-74305-8

J Med Internet Res. 2024 Nov 1;26:e50631. doi: 10.2196/50631.

ABSTRACT

BACKGROUND: Scoliosis is a spinal deformity in which one or more spinal segments bend to the side or show vertebral rotation. Some artificial intelligence (AI) apps have already been developed for measuring the Cobb angle in patients with scoliosis. These apps still require doctors to perform certain measurements, which can lead to interobserver variability. The AI app (cobbAngle pro) in this study will eliminate the need for doctor measurements, achieving complete automation.

OBJECTIVE: We aimed to evaluate the reliability and accuracy of our new AI app that is based on deep learning to automatically measure the Cobb angle in patients with scoliosis.

METHODS: A retrospective analysis was conducted on the clinical data of children with scoliosis who were treated at the Pediatric Orthopedics Department of the Children's Hospital affiliated with Fudan University from July 2019 to July 2022. Three measurers used the Picture Archiving and Communication System (PACS) to measure the coronal main curve Cobb angle in 802 full-length anteroposterior and lateral spine X-rays of 601 children with scoliosis, and recorded the results of each measurement. After an interval of 2 weeks, the mobile AI app was used to remeasure the Cobb angle once. The Cobb angle measurements from the PACS were used as the reference standard, and the accuracy of the Cobb angle measurements by the app was analyzed through the Bland-Altman test. The intraclass correlation coefficient (ICC) was used to compare the repeatability within measurers and the consistency between measurers.

RESULTS: Among 601 children with scoliosis, 89 were male and 512 were female (age range: 10-17 years), and 802 full-length spinal X-rays were analyzed. Two functionalities of the app (photography and photo upload) were compared with the PACS for measuring the Cobb angle. The consistency was found to be excellent. The average absolute errors of the Cobb angle measured by the photography and upload methods were 2.00 and 2.08, respectively. Using a clinical allowance maximum error of 5°, the 95% limits of agreement (LoAs) for Cobb angle measurements by the photography and upload methods were -4.7° to 4.9° and -4.9° to 4.9°, respectively. For the photography and upload methods, the 95% LoAs for measuring Cobb angles were -4.3° to 4.6° and -4.4° to 4.7°, respectively, in mild scoliosis patients; -4.9° to 5.2° and -5.1° to 5.1°, respectively, in moderate scoliosis patients; and -5.2° to 5.0° and -6.0° to 4.8°, respectively, in severe scoliosis patients. The Cobb angle measured by the 3 observers twice before and after using the photography method had good repeatability (P<.001). The consistency between the observers was excellent (P<.001).

CONCLUSIONS: The new AI platform is accurate and repeatable in the automatic measurement of the Cobb angle of the main curvature in patients with scoliosis.

PMID:39486021 | DOI:10.2196/50631

JMIR Res Protoc. 2024 Nov 1;13:e58149. doi: 10.2196/58149.

ABSTRACT

BACKGROUND: Digital microscopy combined with artificial intelligence (AI) is increasingly being implemented in health care, predominantly in advanced laboratory settings. However, AI-supported digital microscopy could be especially advantageous in primary health care settings, since such methods could improve access to diagnostics via automation and lead to a decreased need for experts on site. To our knowledge, no scoping or systematic review had been published on the use of AI-supported digital microscopy within primary health care laboratories when this scoping review was initiated. A scoping review can guide future research by providing insights to help navigate the challenges of implementing these novel methods in primary health care laboratories.

OBJECTIVE: The objective of this scoping review is to map peer-reviewed studies on AI-supported digital microscopy in primary health care laboratories to generate an overview of the subject.

METHODS: A systematic search of the databases PubMed, Web of Science, Embase, and IEEE will be conducted. Only peer-reviewed articles in English will be considered, and no limit on publication year will be applied. The concept inclusion criteria in the scoping review include studies that have applied AI-supported digital microscopy with the aim of achieving a diagnosis on the subject level. In addition, the studies must have been performed in the context of primary health care laboratories, as defined by the criteria of not having a pathologist on site and using simple sample preparations. The study selection and data extraction will be performed by 2 independent researchers, and in the case of disagreements, a third researcher will be involved. The results will be presented in a table developed by the researchers, including information on investigated diseases, sample collection, preparation and digitization, AI model used, and results. Furthermore, the results will be described narratively to provide an overview of the studies included. The proposed methodology is in accordance with the JBI methodology for scoping reviews.

RESULTS: The scoping review was initiated in January 2023, and a protocol was published in the Open Science Framework in January 2024. The protocol was completed in March 2024, and the systematic search will be performed after the protocol has been peer reviewed. The scoping review is expected to be finalized by the end of 2024.

CONCLUSIONS: A systematic review of studies on AI-supported digital microscopy in primary health care laboratories is anticipated to identify the diseases where these novel methods could be advantageous, along with the shared challenges encountered and approaches taken to address them.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/58149.

PMID:39486020 | DOI:10.2196/58149

Neurogastroenterol Motil. 2024 Nov 1:e14954. doi: 10.1111/nmo.14954. Online ahead of print.

ABSTRACT

BACKGROUND: Patients' report of bowel movement consistency is unreliable. We demonstrate the feasibility of long-term automated stool image data collection using a novel Smart Toilet and evaluate a deterministic computer-vision analytic approach to assess stool form according to the Bristol Stool Form Scale (BSFS).

METHODS: Our smart toilet integrates a conventional toilet bowl with an engineered portal to image feces in a predetermined region of the plumbing post-flush. The smart toilet was installed in a workplace bathroom and used by six healthy volunteers. Images were annotated by three experts. A computer vision method based on deep learning segmentation and mathematically defined hand-crafted features was developed to quantify morphological attributes of stool from images.

KEY RESULTS: 474 bowel movements images were recorded in total from six subjects over a mean period of 10 months. 3% of images were rated abnormal with stool consistency BSFS 2 and 4% were BSFS 6. Our image analysis algorithm leverages interpretable morphological features and achieves classification of abnormal stool form with 94% accuracy, 81% sensitivity and 95% specificity.

CONCLUSIONS: Our study supports the feasibility and accuracy of long-term, non-invasive automated stool form monitoring with the novel smart toilet system which can eliminate the patient burden of tracking bowel forms.

PMID:39486001 | DOI:10.1111/nmo.14954

PLoS One. 2024 Nov 1;19(11):e0307916. doi: 10.1371/journal.pone.0307916. eCollection 2024.

ABSTRACT

Breast cancer is the most common cancer in women. Breast masses are one of the distinctive signs for diagnosing breast cancer, and ultrasound is widely used for screening as a non-invasive and effective method for breast examination. In this study, we used the Mendeley and BUSI datasets, comprising 250 images (100 benign, 150 malignant) and 780 images (133 normal, 487 benign, 210 malignant), respectively. The datasets were split into 80% for training and 20% for validation. The accurate measurement and characterization of different breast tumors play a crucial role in guiding clinical decision-making. The area and shape of the different breast tumors detected are critical for clinicians to make accurate diagnostic decisions. In this study, a deep learning method for mass segmentation in breast ultrasound images is proposed, which uses densely connected U-net with attention gates (AGs) as well as channel attention modules and scale attention modules for accurate breast tumor segmentation.The densely connected network is employed in the encoding stage to enhance the network's feature extraction capabilities. Three attention modules are integrated in the decoding stage to better capture the most relevant features. After validation on the Mendeley and BUSI datasets, the experimental results demonstrate that our method achieves a Dice Similarity Coefficient (DSC) of 0.8764 and 0.8313, respectively, outperforming other deep learning approaches. The source code is located at github.com/zhanghaoCV/plos-one.

PMID:39485757 | DOI:10.1371/journal.pone.0307916

PLoS One. 2024 Nov 1;19(11):e0310304. doi: 10.1371/journal.pone.0310304. eCollection 2024.

ABSTRACT

Cell shape reflects the spatial configuration resulting from the equilibrium of cellular and environmental signals and is considered a highly relevant indicator of its function and biological properties. For cancer cells, various physiological and environmental challenges, including chemotherapy, cause a cell state transition, which is accompanied by a continuous morphological alteration that is often extremely difficult to recognize even by direct microscopic inspection. To determine whether deep learning-based image analysis enables the detection of cell shape reflecting a crucial cell state alteration, we used the oral cancer cell line resistant to chemotherapy but having cell morphology nearly indiscernible from its non-resistant parental cells. We then implemented the automatic approach via deep learning methods based on EfficienNet-B3 models, along with over- and down-sampling techniques to determine whether image analysis of the Convolutional Neural Network (CNN) can accomplish three-class classification of non-cancer cells vs. cancer cells with and without chemoresistance. We also examine the capability of CNN-based image analysis to approximate the composition of chemoresistant cancer cells within a population. We show that the classification model achieves at least 98.33% accuracy by the CNN model trained with over- and down-sampling techniques. For heterogeneous populations, the best model can approximate the true proportions of non-chemoresistant and chemoresistant cancer cells with Root Mean Square Error (RMSE) reduced to 0.16 by Ensemble Learning (EL). In conclusion, our study demonstrates the potential of CNN models to identify altered cell shapes that are visually challenging to recognize, thus supporting future applications with this automatic approach to image analysis.

PMID:39485749 | DOI:10.1371/journal.pone.0310304

Technol Health Care. 2024 Aug 29. doi: 10.3233/THC-240750. Online ahead of print.

ABSTRACT

BACKGROUND: Leukemia is a cancer that develops in the bone marrow and blood that is brought on by an excessive generation of abnormal white blood cells. This disease damages deoxyribonucleic acid (DNA), which is associated with immature cells, particularly white blood cells. It is time-consuming and requires enhanced accuracy for radiologists to diagnose acute leukemia cells.

OBJECTIVE: To overcome this issue, we have studied the use of a novel proposed LEU-EHO NET.

METHODS: LEU-EHO NET has been proposed for classifying blood smear images based on leukemia-free and leukemia-infected images. Initially, the input blood smear images are pre-processed using two techniques: normalization and cropping black edges in images. The pre-processed images are then subjected to MobileNet for feature extraction. After that, Elephant Herding Optimization (EHO) is used to select the relevant feature from the retrieved characteristics. Finally, Faster RCNN is trained with the selected features to perform the classification task and discriminate between Normal and Abnormal.

RESULTS: The total accuracy of the proposed LEU-EHO NET is 99.30%. The proposed LEU-EHO NET model enhances the overall accuracy by 0.69%, 16.21%, 1.10%, 1.71%, and 1.38% better than Inception v3 XGBoost, VGGNet, DNN, SVM and MobilenetV2 respectively.

CONCLUSION: The approach needs to be improved so that overlapped cells can be segmented more accurately. Additionally, future work might improve classification accuracy by utilizing different deep learning models.

PMID:39485713 | DOI:10.3233/THC-240750

IEEE Trans Biomed Eng. 2024 Nov 1;PP. doi: 10.1109/TBME.2024.3490187. Online ahead of print.

ABSTRACT

OBJECTIVE: Ventricular arrhythmias are the primary arrhythmias that cause sudden cardiac death. We address the problem of classification between ventricular tachycardia (VT), ventricular fibrillation (VF) and non-ventricular rhythms (NVR).

METHODS: To address the challenging problem of the discrimination between VT and VF, we develop similarity maps - a novel set of features designed to capture regularity within an ECG trace. These similarity maps are combined with features extracted through learnable Parzen band-pass filters and derivative features to discriminate between VT, VF, and NVR. To combine the benefits of these different features, we propose a hierarchical multi-stream ResNet34 architecture.

RESULTS: Our empirical results demonstrate that the similarity maps significantly improve the accuracy of distinguishing between VT and VF. Overall, the proposed approach achieves an average class sensitivity of 89.68%, and individual class sensitivities of 81.46% for VT, 89.29% for VF, and 98.28% for NVR.

CONCLUSION: The proposed method achieves a high accuracy of ventricular arrhythmia detection and classification.

SIGNIFICANCE: Correct detection and classification of ventricular fibrillation and ventricular tachycardia are essential for effective intervention and for the development of new therapies and translational medicine.

PMID:39485690 | DOI:10.1109/TBME.2024.3490187