Cureus. 2024 Feb 19;16(2):e54467. doi: 10.7759/cureus.54467. eCollection 2024 Feb.

ABSTRACT

This comprehensive review explores the transformative role of artificial intelligence (AI) in the realm of gastrointestinal cancer. Gastrointestinal cancers present unique challenges, necessitating precise diagnostic tools and personalized treatment strategies. Leveraging AI, particularly machine learning and deep learning algorithms, has demonstrated remarkable potential in revolutionizing early detection, treatment planning, prognosis, and drug development. The analysis of current research and technological advancements underscores the capacity of AI to unravel intricate patterns within extensive datasets, providing actionable insights that enhance diagnostic accuracy and treatment efficacy. The transformative impact of AI on the landscape of gastrointestinal cancer is emphasized, signaling a paradigm shift towards more precise and targeted cancer care. The conclusion emphasizes the need for sustained research efforts and collaborative initiatives among AI researchers, healthcare professionals, and policymakers. By fostering interdisciplinary collaboration, we can navigate the evolving field of gastrointestinal cancer care, embracing the potential of AI to improve patient outcomes and contribute to a more effective and personalized approach to cancer management.

PMID:38510911 | PMC:PMC10953838 | DOI:10.7759/cureus.54467

Brain Spine. 2023 Dec 23;4:102738. doi: 10.1016/j.bas.2023.102738. eCollection 2024.

ABSTRACT

INTRODUCTION: Modic Changes (MCs) are MRI alterations in spine vertebrae's signal intensity. This study introduces an end-to-end model to automatically detect and classify MCs in lumbar MRIs. The model's two-step process involves locating intervertebral regions and then categorizing MC types (MC0, MC1, MC2) using paired T1-and T2-weighted images. This approach offers a promising solution for efficient and standardized MC assessment.

RESEARCH QUESTION: The aim is to investigate how different MRI normalization techniques affect MCs classification and how the model can be used in a clinical setting.

MATERIAL AND METHODS: A combination of Faster R-CNN and a 3D Convolutional Neural Network (CNN) is employed. The model first identifies intervertebral regions and then classifies MC types (MC0, MC1, MC2) using paired T1-and T2-weighted lumbar MRIs. Two datasets are used for model development and evaluation.

RESULTS: The detection model achieves high accuracy in identifying intervertebral areas, with Intersection over Union (IoU) values above 0.7, indicating strong localization alignment. Confidence scores above 0.9 demonstrate the model's accurate levels identification. In the classification task, standardization proves the best performances for MC type assessment, achieving mean sensitivities of 0.83 for MC0, 0.85 for MC1, and 0.78 for MC2, along with balanced accuracy of 0.80 and F1 score of 0.88.

DISCUSSION AND CONCLUSION: The study's end-to-end model shows promise in automating MC assessment, contributing to standardized diagnostics and treatment planning. Limitations include dataset size, class imbalance, and lack of external validation. Future research should focus on external validation, refining model generalization, and improving clinical applicability.

PMID:38510635 | PMC:PMC10951698 | DOI:10.1016/j.bas.2023.102738

J Med Imaging (Bellingham). 2024 Mar;11(2):024502. doi: 10.1117/1.JMI.11.2.024502. Epub 2024 Mar 19.

ABSTRACT

PURPOSE: The diagnosis of primary bone tumors is challenging as the initial complaints are often non-specific. The early detection of bone cancer is crucial for a favorable prognosis. Incidentally, lesions may be found on radiographs obtained for other reasons. However, these early indications are often missed. We propose an automatic algorithm to detect bone lesions in conventional radiographs to facilitate early diagnosis. Detecting lesions in such radiographs is challenging. First, the prevalence of bone cancer is very low; any method must show high precision to avoid a prohibitive number of false alarms. Second, radiographs taken in health maintenance organizations (HMOs) or emergency departments (EDs) suffer from inherent diversity due to different X-ray machines, technicians, and imaging protocols. This diversity poses a major challenge to any automatic analysis method.

APPROACH: We propose training an off-the-shelf object detection algorithm to detect lesions in radiographs. The novelty of our approach stems from a dedicated preprocessing stage that directly addresses the diversity of the data. The preprocessing consists of self-supervised region-of-interest detection using vision transformer (ViT), and a foreground-based histogram equalization for contrast enhancement to relevant regions only.

RESULTS: We evaluate our method via a retrospective study that analyzes bone tumors on radiographs acquired from January 2003 to December 2018 under diverse acquisition protocols. Our method obtains 82.43% sensitivity at a 1.5% false-positive rate and surpasses existing preprocessing methods. For lesion detection, our method achieves 82.5% accuracy and an IoU of 0.69.

CONCLUSIONS: The proposed preprocessing method enables effectively coping with the inherent diversity of radiographs acquired in HMOs and EDs.

PMID:38510544 | PMC:PMC10950029 | DOI:10.1117/1.JMI.11.2.024502

J Med Imaging (Bellingham). 2024 Mar;11(2):024003. doi: 10.1117/1.JMI.11.2.024003. Epub 2024 Mar 19.

ABSTRACT

Purpose: The goal of this study was to develop a fully convolutional network (FCN) tool to automatedly segment the left-ventricular (LV) myocardium in displacement encoding with stimulated echoes MRI. The segmentation results are used for LV chamber quantification and strain analyses in breast cancer patients susceptible to cancer therapy-related cardiac dysfunction (CTRCD). Approach: A DeepLabV3+ FCN with a ResNet-101 backbone was custom-designed to conduct chamber quantification on 45 female breast cancer datasets (23 training, 11 validation, and 11 test sets). LV structural parameters and LV ejection fraction (LVEF) were measured, and myocardial strains estimated with the radial point interpolation method. Myocardial classification validation was against quantization-based ground-truth with computations of accuracy, Dice score, average perpendicular distance (APD), Hausdorff-distance, and others. Additional validations were conducted with equivalence tests and Cronbach's alpha (C-α) intraclass correlation coefficients between the FCN and a vendor tool on chamber quantification and myocardial strain computations. Results: Myocardial classification results against ground-truth were Dice=0.89, APD=2.4 mm, and accuracy=97% for the validation set and Dice=0.90, APD=2.5 mm, and accuracy=97% for the test set. The confidence intervals (CI) and two one-sided t-test results of equivalence tests between the FCN and vendor-tool were CI=-1.36% to 2.42%, p-value < 0.001 for LVEF (58±5% versus 57±6%), and CI=-0.71% to 0.63%, p-value < 0.001 for longitudinal strain (-15±2% versus -15±3%). Conclusions: The validation results were found equivalent to the vendor tool-based parameter estimates, which show that accurate LV chamber quantification followed by strain analysis for CTRCD investigation can be achieved with our proposed FCN methodology.

PMID:38510543 | PMC:PMC10950093 | DOI:10.1117/1.JMI.11.2.024003

Comput Struct Biotechnol J. 2024 Mar 11;24:205-212. doi: 10.1016/j.csbj.2024.03.007. eCollection 2024 Dec.

ABSTRACT

The diagnosis of cancer is typically based on histopathological sections or biopsies on glass slides. Artificial intelligence (AI) approaches have greatly enhanced our ability to extract quantitative information from digital histopathology images as a rapid growth in oncology data. Gynecological cancers are major diseases affecting women's health worldwide. They are characterized by high mortality and poor prognosis, underscoring the critical importance of early detection, treatment, and identification of prognostic factors. This review highlights the various clinical applications of AI in gynecological cancers using digitized histopathology slides. Particularly, deep learning models have shown promise in accurately diagnosing, classifying histopathological subtypes, and predicting treatment response and prognosis. Furthermore, the integration with transcriptomics, proteomics, and other multi-omics techniques can provide valuable insights into the molecular features of diseases. Despite the considerable potential of AI, substantial challenges remain. Further improvements in data acquisition and model optimization are required, and the exploration of broader clinical applications, such as the biomarker discovery, need to be explored.

PMID:38510535 | PMC:PMC10951449 | DOI:10.1016/j.csbj.2024.03.007

Front Artif Intell. 2024 Mar 6;7:1269366. doi: 10.3389/frai.2024.1269366. eCollection 2024.

ABSTRACT

The emergence of social media has given rise to a variety of networking and communication opportunities, as well as the well-known issue of cyberbullying, which is continuously on the rise in the current world. Researchers have been actively addressing cyberbullying for a long time by applying machine learning and deep learning techniques. However, although these algorithms have performed well on artificial datasets, they do not provide similar results when applied to real-time datasets with high levels of noise and imbalance. Consequently, finding generic algorithms that can work on dynamic data available across several platforms is critical. This study used a unique hybrid random forest-based CNN model for text classification, combining the strengths of both approaches. Real-time datasets from Twitter and Instagram were collected and annotated to demonstrate the effectiveness of the proposed technique. The performance of various ML and DL algorithms was compared, and the RF-based CNN model outperformed them in accuracy and execution speed. This is particularly important for timely detection of bullying episodes and providing assistance to victims. The model achieved an accuracy of 96% and delivered results 3.4 seconds faster than standard CNN models.

PMID:38510470 | PMC:PMC10950905 | DOI:10.3389/frai.2024.1269366

Front Med (Lausanne). 2024 Mar 6;11:1356752. doi: 10.3389/fmed.2024.1356752. eCollection 2024.

ABSTRACT

BACKGROUND: Esophageal cancer is the seventh most frequently diagnosed cancer with a high mortality rate and the sixth leading cause of cancer deaths in the world. Early detection of esophageal cancer is very vital for the patients. Traditionally, contrast computed tomography (CT) was used to detect esophageal carcinomas, but with the development of deep learning (DL) technology, it may now be possible for non-contrast CT to detect esophageal carcinomas. In this study, we aimed to establish a DL-based diagnostic system to stage esophageal cancer from non-contrast chest CT images.

METHODS: In this retrospective dual-center study, we included 397 primary esophageal cancer patients with pathologically confirmed non-contrast chest CT images, as well as 250 healthy individuals without esophageal tumors, confirmed through endoscopic examination. The images of these participants were treated as the training data. Additionally, images from 100 esophageal cancer patients and 100 healthy individuals were enrolled for model validation. The esophagus segmentation was performed using the no-new-Net (nnU-Net) model; based on the segmentation result and feature extraction, a decision tree was employed to classify whether cancer is present or not. We compared the diagnostic efficacy of the DL-based method with the performance of radiologists with various levels of experience. Meanwhile, a diagnostic performance comparison of radiologists with and without the aid of the DL-based method was also conducted.

RESULTS: In this study, the DL-based method demonstrated a high level of diagnostic efficacy in the detection of esophageal cancer, with a performance of AUC of 0.890, sensitivity of 0.900, specificity of 0.880, accuracy of 0.882, and F-score of 0.891. Furthermore, the incorporation of the DL-based method resulted in a significant improvement of the AUC values w.r.t. of three radiologists from 0.855/0.820/0.930 to 0.910/0.955/0.965 (p = 0.0004/<0.0001/0.0068, with DeLong's test).

CONCLUSION: The DL-based method shows a satisfactory performance of sensitivity and specificity for detecting esophageal cancers from non-contrast chest CT images. With the aid of the DL-based method, radiologists can attain better diagnostic workup for esophageal cancer and minimize the chance of missing esophageal cancers in reading the CT scans acquired for health check-up purposes.

PMID:38510455 | PMC:PMC10953501 | DOI:10.3389/fmed.2024.1356752

Front Med (Lausanne). 2024 Mar 6;11:1335958. doi: 10.3389/fmed.2024.1335958. eCollection 2024.

ABSTRACT

INTRODUCTION: Physical measurements of expiratory flow volume and speed can be obtained using spirometry. These measurements have been used for the diagnosis and risk assessment of chronic obstructive pulmonary disease and play a crucial role in delivering early care. However, spirometry is not performed frequently in routine clinical practice, thereby hindering the early detection of pulmonary function impairment. Chest radiographs (CXRs), though acquired frequently, are not used to measure pulmonary functional information. This study aimed to evaluate whether spirometry parameters can be estimated accurately from single frontal CXR without image findings using deep learning.

METHODS: Forced vital capacity (FVC), forced expiratory volume in 1 s (FEV1), and FEV1/FVC as spirometry measurements as well as the corresponding chest radiographs of 11,837 participants were used in this study. The data were randomly allocated to the training, validation, and evaluation datasets at an 8:1:1 ratio. A deep learning network was pretrained using ImageNet. The input and output information were CXRs and spirometry test values, respectively. The training and evaluation of the deep learning network were performed separately for each parameter. The mean absolute error rate (MAPE) and Pearson's correlation coefficient (r) were used as the evaluation indices.

RESULTS: The MAPEs between the spirometry measurements and AI estimates for FVC, FEV1 and FEV1/FVC were 7.59% (r = 0.910), 9.06% (r = 0.879) and 5.21% (r = 0.522), respectively. A strong positive correlation was observed between the measured and predicted indices of FVC and FEV1. The average accuracy of >90% was obtained in each estimation of spirometry indices. Bland-Altman analysis revealed good agreement between the estimated and measured values for FVC and FEV1.

DISCUSSION: Frontal CXRs contain information related to pulmonary function, and AI estimation performed using frontal CXRs without image findings could accurately estimate spirometry values. The network proposed for estimating pulmonary function in this study could serve as a recommendation for performing spirometry or as an alternative method, suggesting its utility.

PMID:38510449 | PMC:PMC10953498 | DOI:10.3389/fmed.2024.1335958

Comput Methods Programs Biomed. 2024 Mar 15;248:108122. doi: 10.1016/j.cmpb.2024.108122. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Most of the existing machine learning-based heart sound classification methods achieve limited accuracy. Since they primarily depend on single domain feature information and tend to focus equally on each part of the signal rather than employing a selective attention mechanism. In addition, they fail to exploit convolutional neural network (CNN) - based features with an effective fusion strategy.

METHODS: In order to overcome these limitations, a novel multimodal attention convolutional neural network (MACNN) with a feature-level fusion strategy, in which Mel-cepstral domain as well as general frequency domain features are incorporated to increase the diversity of the features, is proposed in this paper. In the proposed method, DilationAttenNet is first utilized to construct attention-based CNN feature extractors and then these feature extractors are jointly optimized in MACNN at the feature-level. The attention mechanism aims to suppress irrelevant information and focus on crucial diverse features extracted from the CNN.

RESULTS: Extensive experiments are carried out to study the efficacy of the feature level fusion in comparison to that with early fusion. The results show that the proposed MACNN method significantly outperforms the state-of-the-art approaches in terms of accuracy and score for the two publicly available Github and Physionet datasets.

CONCLUSION: The findings of our experiments demonstrated the high performance for heart sound classification based on the proposed MACNN, and hence have potential clinical usefulness in the identification of heart diseases. This technique can assist cardiologists and researchers in the design and development of heart sound classification methods.

PMID:38507960 | DOI:10.1016/j.cmpb.2024.108122

Med Image Anal. 2024 Mar 16;94:103143. doi: 10.1016/j.media.2024.103143. Online ahead of print.

ABSTRACT

Nuclei detection and segmentation in hematoxylin and eosin-stained (H&E) tissue images are important clinical tasks and crucial for a wide range of applications. However, it is a challenging task due to nuclei variances in staining and size, overlapping boundaries, and nuclei clustering. While convolutional neural networks have been extensively used for this task, we explore the potential of Transformer-based networks in combination with large scale pre-training in this domain. Therefore, we introduce a new method for automated instance segmentation of cell nuclei in digitized tissue samples using a deep learning architecture based on Vision Transformer called CellViT. CellViT is trained and evaluated on the PanNuke dataset, which is one of the most challenging nuclei instance segmentation datasets, consisting of nearly 200,000 annotated nuclei into 5 clinically important classes in 19 tissue types. We demonstrate the superiority of large-scale in-domain and out-of-domain pre-trained Vision Transformers by leveraging the recently published Segment Anything Model and a ViT-encoder pre-trained on 104 million histological image patches - achieving state-of-the-art nuclei detection and instance segmentation performance on the PanNuke dataset with a mean panoptic quality of 0.50 and an F1-detection score of 0.83. The code is publicly available at https://github.com/TIO-IKIM/CellViT.

PMID:38507894 | DOI:10.1016/j.media.2024.103143

Med Image Anal. 2024 Mar 11;94:103137. doi: 10.1016/j.media.2024.103137. Online ahead of print.

ABSTRACT

Analyzing functional brain networks (FBN) with deep learning has demonstrated great potential for brain disorder diagnosis. The conventional construction of FBN is typically conducted at a single scale with a predefined brain region atlas. However, numerous studies have identified that the structure and function of the brain are hierarchically organized in nature. This urges the need of representing FBN in a hierarchical manner for more effective analysis of the complementary diagnostic insights at different scales. To this end, this paper proposes to build hierarchical FBNs adaptively within the Transformer framework. Specifically, a sparse attention-based node-merging module is designed to work alongside the conventional network feature extraction modules in each layer. The proposed module generates coarser nodes for further FBN construction and analysis by combining fine-grained nodes. By stacking multiple such layers, a hierarchical representation of FBN can be adaptively learned in an end-to-end manner. The hierarchical structure can not only integrate the complementary information from multiscale FBN for joint analysis, but also reduce the model complexity due to decreasing node sizes. Moreover, this paper argues that the nodes defined by the existing atlases are not necessarily the optimal starting level to build FBN hierarchy and exploring finer nodes may further enrich the FBN representation. In this regard, each predefined node in an atlas is split into multiple sub-nodes, overcoming the scale limitation of the existing atlases. Extensive experiments conducted on various data sets consistently demonstrate the superior performance of the proposed method over the competing methods.

PMID:38507893 | DOI:10.1016/j.media.2024.103137

Med Eng Phys. 2024 Mar;125:104118. doi: 10.1016/j.medengphy.2024.104118. Epub 2024 Feb 15.

ABSTRACT

In terms of speed and accuracy, the deep learning-based polyp segmentation method is superior. It is essential for the early detection and treatment of colorectal cancer and has the potential to greatly reduce the disease's overall prevalence. Due to the various forms and sizes of polyps, as well as the blurring of the boundaries between the polyp region and the surrounding mucus, most existing algorithms are unable to provide highly accurate colorectal polyp segmentation. Therefore, to overcome these obstacles, we propose an adaptive feature aggregation network (AFANet). It contains two main modules: the Multi-modal Balancing Attention Module (MMBA) and the Global Context Module (GCM). The MMBA extracts improved local characteristics for inference by integrating local contextual information while paying attention to them in three regions: foreground, background, and border. The GCM takes global information from the top of the encoder and sends it to the decoder layer in order to further investigate global contextual feature information in the pathologic picture. Dice of 92.11 % and 94.76 % and MIoU of 91.07 % and 94.54 %, respectively, are achieved by comprehensive experimental validation of our proposed technique on two benchmark datasets, Kvasir-SEG and CVCClinicDB. The experimental results demonstrate that the strategy outperforms other cutting-edge approaches.

PMID:38508807 | DOI:10.1016/j.medengphy.2024.104118

Med Eng Phys. 2024 Mar;125:104131. doi: 10.1016/j.medengphy.2024.104131. Epub 2024 Feb 28.

ABSTRACT

Variations in muscular contraction are known to significantly impact the quality of the generated EMG signal and the output decision of a proposed classifier. This is an issue when the classifier is further implemented in prosthetic hand design. Therefore, this study aims to develop a deep learning classifier to improve the classification of hand motion gestures and investigate the effect of force variations on their accuracy on amputees. The contribution of this study showed that the resulting deep learning architecture based on DNN (deep neural network) could recognize the six gestures and robust against different force levels (18 combinations). Additionally, this study recommended several channels that most contribute to the classifier's accuracy. Also, the selected time domain features were used for a classifier to recognize 18 combinations of EMG signal patterns (6 gestures and three forces). The average accuracy of the proposed method (DNN) was also observed at 92.0 ± 6.1 %. Moreover, several other classifiers were used as comparisons, such as support vector machine (SVM), decision tree (DT), K-nearest neighbors, and Linear Discriminant Analysis (LDA). The increase in the mean accuracy of the proposed method compared to other conventional classifiers (SVM, DT, KNN, and LDA), was 17.86 %. Also, the study's implication stated that the proposed method should be applied to developing prosthetic hands for amputees that recognize multi-force gestures.

PMID:38508805 | DOI:10.1016/j.medengphy.2024.104131

Med Eng Phys. 2024 Mar;125:104111. doi: 10.1016/j.medengphy.2024.104111. Epub 2024 Jan 18.

ABSTRACT

Cardiovascular diseases, often asymptomatic until severe, pose a significant challenge in medical diagnosis. Despite individuals' normal outward appearance and routine activities, subtle indications of these diseases can manifest in the electrocardiogram (ECG) signals, often overlooked by standard interpretation. Current machine learning models have been ineffective in discerning these minor variations due to the irregular and subtle nature of changes in the ECG patterns. This paper uses a novel deep-learning approach to predict slight variations in ECG signals by fine-tuning the learning rate of a deep convolutional neural network. The strategy involves segmenting ECG signals into separate data sequences, each evaluated for unique centroid points. Utilizing a clustering approach, this technique efficiently recognizes minute yet significant variations in the ECG signal characteristics. This method is estimated using a specific dataset from SRM College Hospital and Research Centre, Kattankulathur, Chennai, India, focusing on patients' ECG signals. The model aims to predict the ordinary and subtle variations in ECG signal patterns, which were subsequently mapped to a pre-trained feature set of cardiovascular diseases. The results suggest that the proposed method outperforms existing state-of-the-art approaches in detecting minor and irregular ECG signal variations. This advancement could significantly enhance the early detection of cardiovascular diseases, offering a promising new tool in predictive medical diagnostics.

PMID:38508789 | DOI:10.1016/j.medengphy.2024.104111

Nihon Hoshasen Gijutsu Gakkai Zasshi. 2024 Mar 21. doi: 10.6009/jjrt.2024-1353. Online ahead of print.

ABSTRACT

PURPOSE: To verify the optimal imaging conditions for coronary computed tomography angiography (CCTA) examinations when using high-definition (HD) mode and deep learning image reconstruction (DLIR) in combination.

METHOD: A chest phantom and an in-house phantom using 3D printer were scanned with a 256-row detector CT scanner. The scan parameters were as follows - acquisition mode: ON (HD mode) and OFF (normal resolution [NR] mode), rotation time: 0.28 s/rotation, beam coverage width: 160 mm, and the radiation dose was adjusted based on CT-AEC. Image reconstruction was performed using ASiR-V (Hybrid-IR), TrueFidelity Image (DLIR), and HD-Standard (HD mode) and Standard (NR mode) reconstruction kernels. The task-based transfer function (TTF) and noise power spectrum (NPS) were measured for image evaluation, and the detectability index (d') was calculated. Visual evaluation was also performed on an in-house coronary phantom.

RESULT: The in-plane TTF was better for the HD mode than for the NR mode, while the z-axis TTF was lower for DLIR than for Hybrid-IR. The NPS values in the high-frequency region were higher for the HD mode compared to those for the NR mode, and the NPS was lower for DLIR than for Hybrid-IR. The combination of HD mode and DLIR showed the best value for in-plane d', whereas the combination of NR mode and DLIR showed the best value for z-axis d'. In the visual evaluation, the combination of NR mode and DLIR showed the best values from a noise index of 45 HU.

CONCLUSION: The optimal combination of HD mode and DLIR depends on the image noise level, and the combination of NR mode and DLIR was the best imaging condition under noisy conditions.

PMID:38508756 | DOI:10.6009/jjrt.2024-1353

Neuroimage. 2024 Mar 18:120580. doi: 10.1016/j.neuroimage.2024.120580. Online ahead of print.

ABSTRACT

Diagnosis of disorders of consciousness (DOC) remains a formidable challenge. Deep learning methods have been widely applied in general neurological and psychiatry disorders, while limited in DOC domain. Considering the successful use of resting-state functional MRI (rs-fMRI) for evaluating patients with DOC, this study seeks to explore the conjunction of deep learning techniques and rs-fMRI in precisely detecting awareness in DOC. We initiated our research with a benchmark dataset comprising 140 participants, including 76 unresponsive wakefulness syndrome (UWS), 25 minimally conscious state (MCS), and 39 Controls, from three independent sites. We developed a cascade 3D EfficientNet-B3-based deep learning framework tailored for discriminating MCS from UWS patients, referred to as "DeepDOC", and compared its performance against five state-of-the-art machine learning models. We also included an independent dataset consists of 11 DOC patients to test whether our model could identify patients with cognitive motor dissociation (CMD), in which DOC patients were behaviorally diagnosed unconscious but could be detected conscious by brain computer interface (BCI) method. Our results demonstrate that DeepDOC outperforms the five machine learning models, achieving an area under curve (AUC) value of 0.927 and accuracy of 0.861 for distinguishing MCS from UWS patients. More importantly, DeepDOC excels in CMD identification, achieving an AUC of 1 and accuracy of 0.909. Using gradient-weighted class activation mapping algorithm, we found that the posterior cortex, encompassing the visual cortex, posterior middle temporal gyrus, posterior cingulate cortex, precuneus, and cerebellum, as making a more substantial contribution to classification compared to other brain regions. This research offers a convenient and accurate method for detecting covert awareness in patients with MCS and CMD using rs-fMRI data.

PMID:38508294 | DOI:10.1016/j.neuroimage.2024.120580

Magn Reson Imaging. 2024 Mar 18:S0730-725X(24)00077-8. doi: 10.1016/j.mri.2024.03.021. Online ahead of print.

ABSTRACT

Accurate and efficient segmenting of vertebral bodies, muscles, and discs is crucial for analyzing various spinal diseases. However, traditional methods are either laborious and time-consuming (manual segmentation) or require extensive training data (fully automatic segmentation). FastCleverSeg, our proposed semi-automatic segmentation approach, addresses those limitations by significantly reducing user interaction while maintaining high accuracy. First, we reduce user interaction by requiring the manual annotation of only two or three slices. Next, we automatically Estimate the Annotation on Intermediary Slices (EANIS) using traditional computer vision/graphics concepts. Finally, our proposed method leverages improved voxel weight balancing to achieve fast and precise volumetric segmentation in the segmentation process. Experimental evaluations on our assembled diverse MRI databases comprising 179 patients (60 male, 119 female), demonstrate a remarkable 25 ms (30 ms standard deviation) processing time and a significant reduction in user interaction compared to existing approaches. Importantly, FastCleverSeg maintains or surpasses the segmentation quality of competing methods, achieving a Dice score of 94%. This invaluable tool empowers physicians to efficiently generate reliable ground truths, expediting the segmentation process and paving the way for future integration with deep learning approaches. In turn, this opens exciting possibilities for future fully automated spine segmentation.

PMID:38508290 | DOI:10.1016/j.mri.2024.03.021

Comput Biol Med. 2024 Mar 13;172:108251. doi: 10.1016/j.compbiomed.2024.108251. Online ahead of print.

ABSTRACT

This paper proposes a deep learning algorithm named CoGSPro for classifying lung cancer-related proteins. CoGSPro combines graph neural networks and attention mechanisms to extract key features from protein data and accurately classify proteins. It utilizes large-scale protein expression datasets to train and validate the model, enabling it to identify subtle patterns related to lung cancer. CoGSPro integrates protein-protein interaction network information to improve its predictive accuracy. The experimental results indicate that CoGSPro achieves cutting-edge performance, attaining an accuracy of 96.60% in the classification of lung cancer proteins, surpassing other baseline methods. Additionally, CoGSPro has uncovered new biomarkers for lung cancer, offering potential targets for early detection and treatment.

PMID:38508055 | DOI:10.1016/j.compbiomed.2024.108251

Comput Biol Med. 2024 Mar 16;172:108324. doi: 10.1016/j.compbiomed.2024.108324. Online ahead of print.

ABSTRACT

Early detection is crucial for lung cancer to prolong the patient's survival. Existing model architectures used in such systems have shown promising results. However, they lack reliability and robustness in their predictions and the models are typically evaluated on a single dataset, making them overconfident when a new class is present. With the existence of uncertainty, uncertain images can be referred to medical experts for a second opinion. Thus, we propose an uncertainty-aware framework that includes three phases: data preprocessing and model selection and evaluation, uncertainty quantification (UQ), and uncertainty measurement and data referral for the classification of benign and malignant nodules using 3D CT images. To quantify the uncertainty, we employed three approaches; Monte Carlo Dropout (MCD), Deep Ensemble (DE), and Ensemble Monte Carlo Dropout (EMCD). We evaluated eight different deep learning models consisting of ResNet, DenseNet, and the Inception network family, all of which achieved average F1 scores above 0.832, and the highest average value of 0.845 was obtained using InceptionResNetV2. Furthermore, incorporating the UQ demonstrated significant improvement in the overall model performance. Upon evaluation of the uncertainty estimate, MCD outperforms the other UQ models except for the metric, URecall, where DE and EMCD excel, implying that they are better at identifying incorrect predictions with higher uncertainty levels, which is vital in the medical field. Finally, we show that using a threshold for data referral can greatly improve the performance further, increasing the accuracy up to 0.959.

PMID:38508053 | DOI:10.1016/j.compbiomed.2024.108324

Neural Netw. 2024 Mar 16;174:106241. doi: 10.1016/j.neunet.2024.106241. Online ahead of print.

ABSTRACT

Remarkable achievements have been made in the field of remote sensing cross-scene classification in recent years. However, most methods directly align the entire image features for cross-scene knowledge transfer. They usually ignore the high background complexity and low category consistency of remote sensing images, which can significantly impair the performance of distribution alignment. Besides, shortcomings of the adversarial training paradigm and the inability to guarantee the prediction discriminability and diversity can also hinder cross-scene classification performance. To alleviate the above problems, we propose a novel cross-scene classification framework in a discriminator-free adversarial paradigm, called Adversarial Pair-wise Distribution Matching (APDM), to avoid irrelevant knowledge transfer and enable effective cross-domain modeling. Specifically, we propose the pair-wise cosine discrepancy for both inter-domain and intra-domain prediction measurements to fully leverage the prediction information, which can suppress negative semantic features and implicitly align the cross-scene distributions. Nuclear-norm maximization and minimization are introduced to enhance the target prediction quality and increase the applicability of the source knowledge, respectively. As a general cross-scene framework, APDM can be easily embedded with existing methods to boost the performance. Experimental results and analyses demonstrate that APDM can achieve competitive and effective performance on cross-scene classification tasks.

PMID:38508050 | DOI:10.1016/j.neunet.2024.106241