IEEE Trans Med Imaging. 2024 Jun 20;PP. doi: 10.1109/TMI.2024.3417007. Online ahead of print.

ABSTRACT

Several deep learning-based methods have been proposed to extract vulnerable plaques of a single class from intravascular optical coherence tomography (OCT) images. However, further research is limited by the lack of publicly available large-scale intravascular OCT datasets with multi-class vulnerable plaque annotations. Additionally, multi-class vulnerable plaque segmentation is extremely challenging due to the irregular distribution of plaques, their unique geometric shapes, and fuzzy boundaries. Existing methods have not adequately addressed the geometric features and spatial prior information of vulnerable plaques. To address these issues, we collected a dataset containing 70 pullback data and developed a multi-class vulnerable plaque segmentation model, called PolarFormer, that incorporates the prior knowledge of vulnerable plaques in spatial distribution. The key module of our proposed model is Polar Attention, which models the spatial relationship of vulnerable plaques in the radial direction. Extensive experiments conducted on the new dataset demonstrate that our proposed method outperforms other baseline methods. Code and data can be accessed via this link: https://github.com/sunjingyi0415/IVOCT-segementaion.

PMID:38900618 | DOI:10.1109/TMI.2024.3417007

IEEE Trans Neural Netw Learn Syst. 2024 Jun 20;PP. doi: 10.1109/TNNLS.2024.3412528. Online ahead of print.

ABSTRACT

For hyperspectral image (HSI) and multispectral image (MSI) fusion, it is often overlooked that multisource images acquired under different imaging conditions are difficult to be perfectly registered. Although some works attempt to fuse unregistered images, two thorny challenges remain. One is that registration and fusion are usually modeled as two independent tasks, and there is no yet a unified physical model to tightly couple them. Another is that deep learning (DL)-based methods may lack sufficient interpretability and generalization. In response to the above challenges, we propose an unregistered HSI fusion framework energized by a unified model of registration and fusion. First, a novel registration-fusion consistency physical perception model (RFCM) is designed, which uniformly models the image registration and fusion problem to greatly reduce the sensitivity of fusion performance to registration accuracy. Then, an HSI fusion framework (MoE-PNP) is proposed to learn the knowledge reasoning process for solving RFCM. Each basic module of MoE-PNP one-to-one corresponds to the operation in the optimization algorithm of RFCM, which can ensure clear interpretability of the network. Moreover, MoE-PNP captures the general fusion principle for different unregistered images and therefore has good generalization. Extensive experiments demonstrate that MoE-PNP achieves state-of-the-art performance for unregistered HSI and MSI fusion. The code is available at https://github.com/Jiahuiqu/MoE-PNP.

PMID:38900617 | DOI:10.1109/TNNLS.2024.3412528

IEEE Trans Neural Syst Rehabil Eng. 2024 Jun 20;PP. doi: 10.1109/TNSRE.2024.3417311. Online ahead of print.

ABSTRACT

Motor imagery-based Brain-Computer Interfaces (MI-BCIs) have gained a lot of attention due to their potential usability in neurorehabilitation and neuroprosthetics. However, the accurate recognition of MI patterns in electroencephalography signals (EEG) is hindered by several data-related limitations, which restrict the practical utilization of these systems. Moreover, leveraging deep learning (DL) models for MI decoding is challenged by the difficulty of accessing user-specific MI-EEG data on large scales. Simulated MI-EEG signals can be useful to address these issues, providing well-defined data for the validation of decoding models and serving as a data augmentation approach to improve the training of DL models. While substantial efforts have been dedicated to implementing effective data augmentation strategies and model-based EEG signal generation, the simulation of neurophysiologically plausible EEG-like signals has not yet been exploited in the context of data augmentation. Furthermore, none of the existing approaches have integrated user-specific neurophysiological information during the data generation process. Here, we present PySimMIBCI, a framework for generating realistic MI-EEG signals by integrating neurophysiologically meaningful activity into biophysical forward models. By means of PySimMIBCI, different user capabilities to control an MI-BCI can be simulated and fatigue effects can be included in the generated EEG. Results show that our simulated data closely resemble real data. Moreover, the proposed data augmentation strategy based on our simulated user-specific data significantly outperforms other state-of-the-art augmentation approaches, enhancing DL models performance by up to 15%.

PMID:38900612 | DOI:10.1109/TNSRE.2024.3417311

Phys Eng Sci Med. 2024 Jun 20. doi: 10.1007/s13246-024-01444-7. Online ahead of print.

ABSTRACT

The ECG is a crucial tool in the medical field for recording the heartbeat signal over time, aiding in the identification of various cardiac diseases. Commonly, the interpretation of ECGs necessitates specialized knowledge. However, this paper explores the application of machine learning algorithms and deep learning algorithm to autonomously identify cardiac diseases in diabetic patients in the absence of expert intervention. Two models are introduced in this study: The MLP model effectively distinguishes between individuals with heart diseases and those without, achieving a high level of accuracy. Subsequently, the deep CNN model further refines the identification of specific cardiac conditions. The PTB-Diagnostic ECG dataset commonly used in the field of biomedical signal processing and machine learning, particularly for tasks related to electrocardiogram (ECG) analysis. a widely recognized dataset in the field, is employed for training, testing, and validation of both the MLP and CNN models. This dataset comprises a diverse range of ECG recordings, providing a comprehensive representation of cardiac conditions. The proposed models feature two hidden layers with weights and biases in the MLP, and a three-layer CNN, facilitating the mapping of ECG data to different disease classes. The experimental results demonstrate that the MLP and deep CNN based models attain accuracy levels of up to 90.0% and 98.35%, and sensitivity 97.8%, 95.77%, specificity 88.9%, 96.3% F1-Score 93.13%, 95.84% respectively. These outcomes underscore the efficacy of deep learning approaches in automating the diagnosis of cardiac diseases through ECG analysis, showcasing the potential for accurate and efficient healthcare solutions.

PMID:38900229 | DOI:10.1007/s13246-024-01444-7

Radiol Artif Intell. 2024 Jun 20:e230601. doi: 10.1148/ryai.230601. Online ahead of print.

ABSTRACT

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To evaluate the performance of an automated deep learning method in detecting ascites and subsequently quantifying its volume in patients with liver cirrhosis and ovarian cancer. Materials and Methods This retrospective study included contrast-enhanced and noncontrast abdominal-pelvic CT scans of patients with cirrhotic ascites and patients with ovarian cancer from two institutions, National Institutes of Health (NIH) and University of Wisconsin (UofW). The model, trained on The Cancer Genome Atlas Ovarian Cancer dataset (mean age, 60 years ± 11 [SD]; 143 female), was tested on two internal (NIH-LC and NIH-OV) and one external dataset (UofW-LC). Its performance was measured by the Dice coefficient, standard deviations, and 95% confidence intervals, focusing on ascites volume in the peritoneal cavity. Results On NIH-LC (25 patients; mean age, 59 years ± 14; 14 male) and NIH-OV (166 patients; mean age, 65 years ± 9; all female), the model achieved Dice scores of 85.5% ± 6.1% (CI: 83.1%-87.8%) and 82.6% ± 15.3% (CI: 76.4%-88.7%), with median volume estimation errors of 19.6% (IQR: 13.2%-29.0%) and 5.3% (IQR: 2.4%- 9.7%), respectively. On UofW-LC (124 patients; mean age, 46 years ± 12; 73 female), the model had a Dice score of 83.0% ± 10.7% (CI: 79.8%-86.3%) and median volume estimation error of 9.7% (IQR: 4.5%-15.1%). The model showed strong agreement with expert assessments, with r2 values of 0.79, 0.98, and 0.97 across the test sets. Conclusion The proposed deep learning method performed well in segmenting and quantifying the volume of ascites in concordance with expert radiologist assessments. ©RSNA, 2024.

PMID:38900043 | DOI:10.1148/ryai.230601

Radiol Artif Intell. 2024 Jun 20:e230348. doi: 10.1148/ryai.230348. Online ahead of print.

ABSTRACT

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To determine whether time-dependent deep learning models can outperform single timepoint models in predicting preoperative upgrade of ductal carcinoma in situ (DCIS) to invasive malignancy on dynamic contrastenhanced (DCE) breast MRI without lesion segmentation prerequisite. Materials and Methods In this exploratory study, 154 cases of biopsy-proven DCIS (25 upgraded at surgery and 129 not upgraded) were selected consecutively from a retrospective cohort of preoperative DCE MRI in women with an average age of 58.6 years at time of diagnosis from 2012 to 2022. Binary classification was implemented with convolutional neural network-long short-term memory (CNN-LSTM) architectures benchmarked against traditional CNNs without manual segmentation of the lesions. Combinatorial performance analysis of ResNet50 versus VGG16-based models was performed with each contrast phase. Binary classification area under the receiver operating characteristic curve (AUC) was reported. Results VGG16-based models consistently provided better hold-out test AUCs than ResNet50 in CNN and CNNLSTM studies (multiphase test AUC: 0.67 versus 0.59, respectively, for CNN models; P = .04 and 0.73 versus 0.62 for CNN-LSTM models; P = .008). The time-dependent model (CNN-LSTM) provided a better multiphase test AUC over single-timepoint (CNN) models (0.73 versus 0.67, P = .04). Conclusion Compared with single-timepoint architectures, sequential deep learning algorithms using preoperative DCE MRI improved prediction of DCIS lesions upgraded to invasive malignancy without the need for lesion segmentation. ©RSNA, 2024.

PMID:38900042 | DOI:10.1148/ryai.230348

Infect Immun. 2024 Jun 20:e0026323. doi: 10.1128/iai.00263-23. Online ahead of print.

ABSTRACT

Because most humans resist Mycobacterium tuberculosis infection, there is a paucity of lung samples to study. To address this gap, we infected Diversity Outbred mice with M. tuberculosis and studied the lungs of mice in different disease states. After a low-dose aerosol infection, progressors succumbed to acute, inflammatory lung disease within 60 days, while controllers maintained asymptomatic infection for at least 60 days, and then developed chronic pulmonary tuberculosis (TB) lasting months to more than 1 year. Here, we identified features of asymptomatic M. tuberculosis infection by applying computational and statistical approaches to multimodal data sets. Cytokines and anti-M. tuberculosis cell wall antibodies discriminated progressors vs controllers with chronic pulmonary TB but could not classify mice with asymptomatic infection. However, a novel deep-learning neural network trained on lung granuloma images was able to accurately classify asymptomatically infected lungs vs acute pulmonary TB in progressors vs chronic pulmonary TB in controllers, and discrimination was based on perivascular and peribronchiolar lymphocytes. Because the discriminatory lesion was rich in lymphocytes and CD4 T cell-mediated immunity is required for resistance, we expected CD4 T-cell genes would be elevated in asymptomatic infection. However, the significantly different, highly expressed genes were from B-cell pathways (e.g., Bank1, Cd19, Cd79, Fcmr, Ms4a1, Pax5, and H2-Ob), and CD20+ B cells were enriched in the perivascular and peribronchiolar regions of mice with asymptomatic M. tuberculosis infection. Together, these results indicate that genetically controlled B-cell responses are important for establishing asymptomatic M. tuberculosis lung infection.

PMID:38899881 | DOI:10.1128/iai.00263-23

MAbs. 2024 Jan-Dec;16(1):2362775. doi: 10.1080/19420862.2024.2362775. Epub 2024 Jun 20.

ABSTRACT

Over the past two decades, therapeutic antibodies have emerged as a rapidly expanding domain within the field of biologics. In silico tools that can streamline the process of antibody discovery and optimization are critical to support a pipeline that is growing more numerous and complex every year. High-quality structural information remains critical for the antibody optimization process, but antibody-antigen complex structures are often unavailable and in silico antibody docking methods are still unreliable. In this study, DeepAb, a deep learning model for predicting antibody Fv structure directly from sequence, was used in conjunction with single-point experimental deep mutational scanning (DMS) enrichment data to design 200 potentially optimized variants of an anti-hen egg lysozyme (HEL) antibody. We sought to determine whether DeepAb-designed variants containing combinations of beneficial mutations from the DMS exhibit enhanced thermostability and whether this optimization affected their developability profile. The 200 variants were produced through a robust high-throughput method and tested for thermal and colloidal stability (Tonset, Tm, Tagg), affinity (KD) relative to the parental antibody, and for developability parameters (nonspecific binding, aggregation propensity, self-association). Of the designed clones, 91% and 94% exhibited increased thermal and colloidal stability and affinity, respectively. Of these, 10% showed a significantly increased affinity for HEL (5- to 21-fold increase) and thermostability (>2.5C increase in Tm1), with most clones retaining the favorable developability profile of the parental antibody. Additional in silico tests suggest that these methods would enrich for binding affinity even without first collecting experimental DMS measurements. These data open the possibility of in silico antibody optimization without the need to predict the antibody-antigen interface, which is notoriously difficult in the absence of crystal structures.

PMID:38899735 | DOI:10.1080/19420862.2024.2362775

Acta Oncol. 2024 Jun 20;63:477-481. doi: 10.2340/1651-226X.2024.34986.

ABSTRACT

BACKGROUND: Deep learning (DL) models for auto-segmentation in radiotherapy have been extensively studied in retrospective and pilot settings. However, these studies might not reflect the clinical setting. This study compares the use of a clinically implemented in-house trained DL segmentation model for breast cancer to a previously performed pilot study to assess possible differences in performance or acceptability.

MATERIAL AND METHODS: Sixty patients with whole breast radiotherapy, with or without an indication for locoregional radiotherapy were included. Structures were qualitatively scored by radiotherapy technologists and radiation oncologists. Quantitative evaluation was performed using dice-similarity coefficient (DSC), 95th percentile of Hausdorff Distance (95%HD) and surface DSC (sDSC), and time needed for generating, checking, and correcting structures was measured.

RESULTS: Ninety-three percent of all contours in clinic were scored as clinically acceptable or usable as a starting point, comparable to 92% achieved in the pilot study. Compared to the pilot study, no significant changes in time reduction were achieved for organs at risks (OARs). For target volumes, significantly more time was needed compared to the pilot study for patients including lymph node levels 1-4, although time reduction was still 33% compared to manual segmentation. Almost all contours have better DSC and 95%HD than inter-observer variations. Only CTVn4 scored worse for both metrics, and the thyroid had a higher 95%HD value.

INTERPRETATION: The use of the DL model in clinical practice is comparable to the pilot study, showing high acceptability rates and time reduction.

PMID:38899395 | DOI:10.2340/1651-226X.2024.34986

Kidney Int Rep. 2024 Apr 4;9(6):1802-1809. doi: 10.1016/j.ekir.2024.04.002. eCollection 2024 Jun.

ABSTRACT

INTRODUCTION: The Mayo imaging classification model (MICM) requires a prestep qualitative assessment to determine whether a patient is in class 1 (typical) or class 2 (atypical), where patients assigned to class 2 are excluded from the MICM application.

METHODS: We developed a deep learning-based method to automatically classify class 1 and 2 from magnetic resonance (MR) images and provide classification confidence utilizing abdominal T 2 -weighted MR images from 486 subjects, where transfer learning was applied. In addition, the explainable artificial intelligence (XAI) method was illustrated to enhance the explainability of the automated classification results. For performance evaluations, confusion matrices were generated, and receiver operating characteristic curves were drawn to measure the area under the curve.

RESULTS: The proposed method showed excellent performance for the classification of class 1 (97.7%) and 2 (100%), where the combined test accuracy was 98.01%. The precision and recall for predicting class 1 were 1.00 and 0.98, respectively, with F 1 -score of 0.99; whereas those for predicting class 2 were 0.87 and 1.00, respectively, with F 1 -score of 0.93. The weighted averages of precision and recall were 0.98 and 0.98, respectively, showing the classification confidence scores whereas the XAI method well-highlighted contributing regions for the classification.

CONCLUSION: The proposed automated method can classify class 1 and 2 cases as accurately as the level of a human expert. This method may be a useful tool to facilitate clinical trials investigating different types of kidney morphology and for clinical management of patients with autosomal dominant polycystic kidney disease (ADPKD).

PMID:38899202 | PMC:PMC11184252 | DOI:10.1016/j.ekir.2024.04.002

IEEE J Transl Eng Health Med. 2024 May 9;12:457-467. doi: 10.1109/JTEHM.2024.3399261. eCollection 2024.

ABSTRACT

OBJECTIVE: Pulmonary cavity lesion is one of the commonly seen lesions in lung caused by a variety of malignant and non-malignant diseases. Diagnosis of a cavity lesion is commonly based on accurate recognition of the typical morphological characteristics. A deep learning-based model to automatically detect, segment, and quantify the region of cavity lesion on CT scans has potential in clinical diagnosis, monitoring, and treatment efficacy assessment.

METHODS: A weakly-supervised deep learning-based method named CSA2-ResNet was proposed to quantitatively characterize cavity lesions in this paper. The lung parenchyma was firstly segmented using a pretrained 2D segmentation model, and then the output with or without cavity lesions was fed into the developed deep neural network containing hybrid attention modules. Next, the visualized lesion was generated from the activation region of the classification network using gradient-weighted class activation mapping, and image processing was applied for post-processing to obtain the expected segmentation results of cavity lesions. Finally, the automatic characteristic measurement of cavity lesions (e.g., area and thickness) was developed and verified.

RESULTS: the proposed weakly-supervised segmentation method achieved an accuracy, precision, specificity, recall, and F1-score of 98.48%, 96.80%, 97.20%, 100%, and 98.36%, respectively. There is a significant improvement (P < 0.05) compared to other methods. Quantitative characterization of morphology also obtained good analysis effects.

CONCLUSIONS: The proposed easily-trained and high-performance deep learning model provides a fast and effective way for the diagnosis and dynamic monitoring of pulmonary cavity lesions in clinic. Clinical and Translational Impact Statement: This model used artificial intelligence to achieve the detection and quantitative analysis of pulmonary cavity lesions in CT scans. The morphological features revealed in experiments can be utilized as potential indicators for diagnosis and dynamic monitoring of patients with cavity lesions.

PMID:38899144 | PMC:PMC11186646 | DOI:10.1109/JTEHM.2024.3399261

IEEE Open J Eng Med Biol. 2024 May 15;5:376-382. doi: 10.1109/OJEMB.2024.3401098. eCollection 2024.

ABSTRACT

Goal: In this study, we demonstrate that a deep neural network (DNN) can be trained to reconstruct high-contrast images, resembling those produced by the multistatic Synthetic Aperture (SA) method using a 128-element array, leveraging pre-beamforming radiofrequency (RF) signals acquired through the monostatic SA approach. Methods: A U-net was trained using 27200 pairs of RF signals, simulated considering a monostatic SA architecture, with their corresponding delay-and-sum beamformed target images in a multistatic 128-element SA configuration. The contrast was assessed on 500 simulated test images of anechoic/hyperechoic targets. The DNN's performance in reconstructing experimental images of a phantom and different in vivo scenarios was tested too. Results: The DNN, compared to the simple monostatic SA approach used to acquire pre-beamforming signals, generated better-quality images with higher contrast and reduced noise/artifacts. Conclusions: The obtained results suggest the potential for the development of a single-channel setup, simultaneously providing good-quality images and reducing hardware complexity.

PMID:38899024 | PMC:PMC11186640 | DOI:10.1109/OJEMB.2024.3401098

IEEE Open J Eng Med Biol. 2023 May 17;5:434-442. doi: 10.1109/OJEMB.2023.3277219. eCollection 2024.

ABSTRACT

Goal: Diagnosing the corpus-predominant gastritis index (CGI) which is an early precancerous lesion in the stomach has been shown its effectiveness in identifying high gastric cancer risk patients for preventive healthcare. However, invasive biopsies and time-consuming pathological analysis are required for the CGI diagnosis. Methods: We propose a novel gastric section correlation network (GSCNet) for the CGI diagnosis from endoscopic images of three dominant gastric sections, the antrum, body and cardia. The proposed network consists of two dominant modules including the scaling feature fusion module and section correlation module. The front one aims to extract scaling fusion features which can effectively represent the mucosa under variant viewing angles and scale changes for each gastric section. The latter one aims to apply the medical prior knowledge with three section correlation losses to model the correlations of different gastric sections for the CGI diagnosis. Results: The proposed method outperforms competing deep learning methods and achieves high testing accuracy, sensitivity, and specificity of 0.957, 0.938 and 0.962, respectively. Conclusions: The proposed method is the first method to identify high gastric cancer risk patients with CGI from endoscopic images without invasive biopsies and time-consuming pathological analysis.

PMID:38899022 | PMC:PMC11186652 | DOI:10.1109/OJEMB.2023.3277219

IEEE Open J Eng Med Biol. 2024 May 23;5:393-395. doi: 10.1109/OJEMB.2024.3404653. eCollection 2024.

ABSTRACT

Researchers in biomedical engineering are increasingly turning to weakly-supervised deep learning (WSDL) techniques [1] to tackle challenges in biomedical data analysis, which often involves noisy, limited, or imprecise expert annotations [2]. WSDL methods have emerged as a solution to alleviate the manual annotation burden for structured biomedical data like signals, images, and videos [3] while enabling deep neural network models to learn from larger-scale datasets at a reduced annotation cost. With the proliferation of advanced deep learning techniques such as generative adversarial networks (GANs), graph neural networks (GNNs) [4], vision transformers (ViTs) [5], and deep reinforcement learning (DRL) models [6], research endeavors are focused on solving WSDL problems and applying these techniques to various biomedical analysis tasks.

PMID:38899020 | PMC:PMC11186656 | DOI:10.1109/OJEMB.2024.3404653

IEEE Open J Eng Med Biol. 2024 May 15;5:345-352. doi: 10.1109/OJEMB.2024.3401571. eCollection 2024.

ABSTRACT

Goal: Auscultation for neonates is a simple and non-invasive method of diagnosing cardiovascular and respiratory disease. However, obtaining high-quality chest sounds containing only heart or lung sounds is non-trivial. Hence, this study introduces a new deep-learning model named NeoSSNet and evaluates its performance in neonatal chest sound separation with previous methods. Methods: We propose a masked-based architecture similar to Conv-TasNet. The encoder and decoder consist of 1D convolution and 1D transposed convolution, while the mask generator consists of a convolution and transformer architecture. The input chest sounds were first encoded as a sequence of tokens using 1D convolution. The tokens were then passed to the mask generator to generate two masks, one for heart sounds and one for lung sounds. Each mask is then applied to the input token sequence. Lastly, the tokens are converted back to waveforms using 1D transposed convolution. Results: Our proposed model showed superior results compared to the previous methods based on objective distortion measures, ranging from a 2.01 dB improvement to a 5.06 dB improvement. The proposed model is also significantly faster than the previous methods, with at least a 17-time improvement. Conclusions: The proposed model could be a suitable preprocessing step for any health monitoring system where only the heart sound or lung sound is desired.

PMID:38899018 | PMC:PMC11186644 | DOI:10.1109/OJEMB.2024.3401571

IEEE Open J Eng Med Biol. 2023 Jan 27;5:396-403. doi: 10.1109/OJEMB.2023.3240280. eCollection 2024.

ABSTRACT

Goal: As an essential human-machine interactive task, emotion recognition has become an emerging area over the decades. Although previous attempts to classify emotions have achieved high performance, several challenges remain open: 1) How to effectively recognize emotions using different modalities remains challenging. 2) Due to the increasing amount of computing power required for deep learning, how to provide real-time detection and improve the robustness of deep neural networks is important. Method: In this paper, we propose a deep learning-based multimodal emotion recognition (MER) called Deep-Emotion, which can adaptively integrate the most discriminating features from facial expressions, speech, and electroencephalogram (EEG) to improve the performance of the MER. Specifically, the proposed Deep-Emotion framework consists of three branches, i.e., the facial branch, speech branch, and EEG branch. Correspondingly, the facial branch uses the improved GhostNet neural network proposed in this paper for feature extraction, which effectively alleviates the overfitting phenomenon in the training process and improves the classification accuracy compared with the original GhostNet network. For work on the speech branch, this paper proposes a lightweight fully convolutional neural network (LFCNN) for the efficient extraction of speech emotion features. Regarding the study of EEG branches, we proposed a tree-like LSTM (tLSTM) model capable of fusing multi-stage features for EEG emotion feature extraction. Finally, we adopted the strategy of decision-level fusion to integrate the recognition results of the above three modes, resulting in more comprehensive and accurate performance. Result and Conclusions: Extensive experiments on the CK+, EMO-DB, and MAHNOB-HCI datasets have demonstrated the advanced nature of the Deep-Emotion method proposed in this paper, as well as the feasibility and superiority of the MER approach.

PMID:38899017 | PMC:PMC11186647 | DOI:10.1109/OJEMB.2023.3240280

IEEE Open J Eng Med Biol. 2023 Aug 15;5:459-466. doi: 10.1109/OJEMB.2023.3305190. eCollection 2024.

ABSTRACT

Goal: Deep learning techniques have made significant progress in medical image analysis. However, obtaining ground truth labels for unlabeled medical images is challenging as they often outnumber labeled images. Thus, training a high-performance model with limited labeled data has become a crucial challenge. Methods: This study introduces an underlying knowledge-based semi-supervised framework called UKSSL, consisting of two components: MedCLR extracts feature representations from the unlabeled dataset; UKMLP utilizes the representation and fine-tunes it with the limited labeled dataset to classify the medical images. Results: UKSSL evaluates on the LC25000 and BCCD datasets, using only 50% labeled data. It gets precision, recall, F1-score, and accuracy of 98.9% on LC25000 and 94.3%, 94.5%, 94.3%, and 94.1% on BCCD, respectively. These results outperform other supervised-learning methods using 100% labeled data. Conclusions: The UKSSL can efficiently extract underlying knowledge from the unlabeled dataset and perform better using limited labeled medical images.

PMID:38899016 | PMC:PMC11186655 | DOI:10.1109/OJEMB.2023.3305190

IEEE Open J Eng Med Biol. 2024 Feb 13;5:467-475. doi: 10.1109/OJEMB.2024.3365290. eCollection 2024.

ABSTRACT

Accurate short- and mid-term blood glucose predictions are crucial for patients with diabetes struggling to maintain healthy glucose levels, as well as for individuals at risk of developing the disease. Consequently, numerous efforts from the scientific community have focused on developing predictive models for glucose levels. This study harnesses physiological data collected from wearable sensors to construct a series of data-driven models based on deep learning approaches. We systematically compare these models to offer insights for practitioners and researchers venturing into glucose prediction using deep learning techniques. Key questions addressed in this work encompass the comparison of various deep learning architectures for this task, determining the optimal set of input variables for accurate glucose prediction, comparing population-wide, fine-tuned, and personalized models, and assessing the impact of an individual's data volume on model performance. Additionally, as part of our outcomes, we introduce a meticulously curated dataset inclusive of data from both healthy individuals and those with diabetes, recorded in free-living conditions. This dataset aims to foster research in this domain and facilitate equitable comparisons among researchers.

PMID:38899015 | PMC:PMC11186642 | DOI:10.1109/OJEMB.2024.3365290

Acad Radiol. 2024 Jun 18:S1076-6332(24)00368-4. doi: 10.1016/j.acra.2024.06.010. Online ahead of print.

ABSTRACT

RATIONALE AND OBJECTIVES: To determine if super-resolution deep learning reconstruction (SR-DLR) improves the depiction of cranial nerves and interobserver agreement when assessing neurovascular conflict in 3D fast asymmetric spin echo (3D FASE) brain MR images, as compared to deep learning reconstruction (DLR).

MATERIALS AND METHODS: This retrospective study involved reconstructing 3D FASE MR images of the brain for 37 patients using SR-DLR and DLR. Three blinded readers conducted qualitative image analyses, evaluating the degree of neurovascular conflict, structure depiction, sharpness, noise, and diagnostic acceptability. Quantitative analyses included measuring edge rise distance (ERD), edge rise slope (ERS), and full width at half maximum (FWHM) using the signal intensity profile along a linear region of interest across the center of the basilar artery.

RESULTS: Interobserver agreement on the degree of neurovascular conflict of the facial nerve was generally higher with SR-DLR (0.429-0.923) compared to DLR (0.175-0.689). SR-DLR exhibited increased subjective image noise compared to DLR (p ≥ 0.008). However, all three readers found SR-DLR significantly superior in terms of sharpness (p < 0.001); cranial nerve depiction, particularly of facial and acoustic nerves, as well as the osseous spiral lamina (p < 0.001); and diagnostic acceptability (p ≤ 0.002). The FWHM (mm)/ERD (mm)/ERS (mm-1) for SR-DLR and DLR was 3.1-4.3/0.9-1.1/8795.5-10,703.5 and 3.3-4.8/1.4-2.1/5157.9-7705.8, respectively, with SR-DLR's image sharpness being significantly superior (p ≤ 0.001).

CONCLUSION: SR-DLR enhances image sharpness, leading to improved cranial nerve depiction and a tendency for greater interobserver agreement regarding facial nerve neurovascular conflict.

PMID:38897913 | DOI:10.1016/j.acra.2024.06.010

Am J Pathol. 2024 Jun 17:S0002-9440(24)00210-4. doi: 10.1016/j.ajpath.2024.05.011. Online ahead of print.

ABSTRACT

Lung cancer is an increasingly serious health problem worldwide, and early detection and diagnosis are crucial for successful treatment. With the development of artificial intelligence and the growth of data volume, machine learning techniques can play a significant role in improving the accuracy of early detection in lung cancer.This study proposes a deep learning-based segmentation algorithm for rapid on-site cytopathological evaluation (ROSE) to enhance the diagnostic efficiency of endobronchial ultrasoundguided transbronchial needle aspiration biopsy (EBUS-TBNA) during surgery. By utilizing the CUNet3+ network model, cell clusters, including cancer cell clusters, can be accurately segmented in ROSE-stained pathological sections. The model demonstrated high accuracy, with an F1-score of 0.9604, recall of 0.9609, precision of 0.9654, and accuracy of 0.9834 on the internal testing dataset. It also achieved an AUC of 0.9972 for cancer identification. The proposed algorithm provides time savings for on-site diagnosis, improves EBUS-TBNA efficiency, and outperforms classical segmentation algorithms in accurately identifying lung cancer cell clusters in ROSE-stained images. It effectively reduces over-segmentation, decreases network parameters, and enhances computational efficiency, making it suitable for real-time patient evaluation during surgical procedures.

PMID:38897537 | DOI:10.1016/j.ajpath.2024.05.011