Front Med (Lausanne). 2024 Jun 20;11:1418800. doi: 10.3389/fmed.2024.1418800. eCollection 2024.

ABSTRACT

BACKGROUND: Potential uncertainties and overtreatment exist in adjuvant chemotherapy for triple-negative breast cancer (TNBC) patients.

OBJECTIVES: This study aims to explore the performance of deep learning (DL) models in personalized chemotherapy selection and quantify the impact of baseline characteristics on treatment efficacy.

METHODS: Patients who received treatment recommended by models were compared to those who did not. Overall survival for treatment according to model recommendations was the primary outcome. To mitigate bias, inverse probability treatment weighting (IPTW) was employed. A mixed-effect multivariate linear regression was employed to visualize the influence of certain baseline features of patients on chemotherapy selection.

RESULTS: A total of 10,070 female TNBC patients met the inclusion criteria. Treatment according to Self-Normalizing Balanced (SNB) individual treatment effect for survival data model recommendations was associated with a survival benefit (IPTW-adjusted hazard ratio: 0.53, 95% CI, 0.32-8.60; IPTW-adjusted risk difference: 12.90, 95% CI, 6.99-19.01; IPTW-adjusted the difference in restricted mean survival time: 5.54, 95% CI, 1.36-8.61), which surpassed other models and the National Comprehensive Cancer Network guidelines. No survival benefit for chemotherapy was seen for patients not recommended to receive this treatment. SNB predicted older patients with larger tumors and more positive lymph nodes are the optimal candidates for chemotherapy.

CONCLUSION: These findings suggest that the SNB model may identify patients with TNBC who could benefit from chemotherapy. This novel analytical approach may provide debiased individual survival information and treatment recommendations. Further research is required to validate these models in clinical settings with more features and outcome measurements.

PMID:38966532 | PMC:PMC11222643 | DOI:10.3389/fmed.2024.1418800

Front Cell Infect Microbiol. 2024 Jun 20;14:1429197. doi: 10.3389/fcimb.2024.1429197. eCollection 2024.

NO ABSTRACT

PMID:38966252 | PMC:PMC11223062 | DOI:10.3389/fcimb.2024.1429197

Front Plant Sci. 2024 Jun 20;15:1381367. doi: 10.3389/fpls.2024.1381367. eCollection 2024.

ABSTRACT

INTRODUCTION: Pine wilt disease spreads rapidly, leading to the death of a large number of pine trees. Exploring the corresponding prevention and control measures for different stages of pine wilt disease is of great significance for its prevention and control.

METHODS: To address the issue of rapid detection of pine wilt in a large field of view, we used a drone to collect multiple sets of diseased tree samples at different times of the year, which made the model trained by deep learning more generalizable. This research improved the YOLO v4(You Only Look Once version 4) network for detecting pine wilt disease, and the channel attention mechanism module was used to improve the learning ability of the neural network.

RESULTS: The ablation experiment found that adding the attention mechanism SENet module combined with the self-designed feature enhancement module based on the feature pyramid had the best improvement effect, and the mAP of the improved model was 79.91%.

DISCUSSION: Comparing the improved YOLO v4 model with SSD, Faster RCNN, YOLO v3, and YOLO v5, it was found that the mAP of the improved YOLO v4 model was significantly higher than the other four models, which provided an efficient solution for intelligent diagnosis of pine wood nematode disease. The improved YOLO v4 model enables precise location and identification of pine wilt trees under changing light conditions. Deployment of the model on a UAV enables large-scale detection of pine wilt disease and helps to solve the challenges of rapid detection and prevention of pine wilt disease.

PMID:38966144 | PMC:PMC11222607 | DOI:10.3389/fpls.2024.1381367

Front Oncol. 2024 Jun 20;14:1423774. doi: 10.3389/fonc.2024.1423774. eCollection 2024.

ABSTRACT

PURPOSE: Addressing the challenges of unclear tumor boundaries and the confusion between cysts and tumors in liver tumor segmentation, this study aims to develop an auto-segmentation method utilizing Gaussian filter with the nnUNet architecture to effectively distinguish between tumors and cysts, enhancing the accuracy of liver tumor auto-segmentation.

METHODS: Firstly, 130 cases of liver tumorsegmentation challenge 2017 (LiTS2017) were used for training and validating nnU-Net-based auto-segmentation model. Then, 14 cases of 3D-IRCADb dataset and 25 liver cancer cases retrospectively collected in our hospital were used for testing. The dice similarity coefficient (DSC) was used to evaluate the accuracy of auto-segmentation model by comparing with manual contours.

RESULTS: The nnU-Net achieved an average DSC value of 0.86 for validation set (20 LiTS cases) and 0.82 for public testing set (14 3D-IRCADb cases). For clinical testing set, the standalone nnU-Net model achieved an average DSC value of 0.75, which increased to 0.81 after post-processing with the Gaussian filter (P<0.05), demonstrating its effectiveness in mitigating the influence of liver cysts on liver tumor segmentation.

CONCLUSION: Experiments show that Gaussian filter is beneficial to improve the accuracy of liver tumor segmentation in clinic.

PMID:38966060 | PMC:PMC11222586 | DOI:10.3389/fonc.2024.1423774

Asia Pac J Clin Nutr. 2024 Sep;33(3):348-361. doi: 10.6133/apjcn.202409_33(3).0005.

ABSTRACT

BACKGROUND AND OBJECTIVES: We aim to establish deep learning models to optimize the individualized energy delivery for septic patients.

METHODS AND STUDY DESIGN: We conducted a study of adult septic patients in ICU, collecting 47 indicators for 14 days. We filtered out nutrition-related features and divided the data into datasets according to the three metabolic phases proposed by ESPEN: acute early, acute late, and rehabilitation. We then established optimal energy target models for each phase using deep learning and conducted external validation.

RESULTS: A total of 179 patients in training dataset and 98 patients in external validation dataset were included in this study, and total data size was 3115 elements. The age, weight and BMI of the patients were 63.05 (95%CI 60.42-65.68), 61.31(95%CI 59.62-63.00) and 22.70 (95%CI 22.21-23.19), respectively. And 26.0% (72) of the patients were female. The models indicated that the optimal energy targets in the three phases were 900kcal/d, 2300kcal/d, and 2000kcal/d, respectively. Excessive energy intake increased mortality rapidly in the early period of the acute phase. Insufficient energy in the late period of the acute phase significantly raised the mortality as well. For the rehabilitation phase, too much or too little energy delivery were both associated with elevated death risk.

CONCLUSIONS: Our study established time-series prediction models for septic patients to optimize energy delivery in the ICU. We recommended permissive underfeeding only in the early acute phase. Later, increased energy intake may improve survival and settle energy debts caused by underfeeding.

PMID:38965722 | DOI:10.6133/apjcn.202409_33(3).0005

Mol Phylogenet Evol. 2024 Jul 2:108142. doi: 10.1016/j.ympev.2024.108142. Online ahead of print.

ABSTRACT

Assigning a query individual animal or plant to its derived population is a prime task in diverse applications related to organismal genealogy. Such endeavors have conventionally relied on short DNA sequences under a phylogenetic framework. These methods naturally show constraints when the inferred population sources are ambiguously phylogenetically structured, a scenario demanding substantially more informative genetic signals. Recent advances in cost-effective production of whole-genome sequences and artificial intelligence have created an unprecedented opportunity to trace the population origin for essentially any given individual, as long as the genome reference data are comprehensive and standardized. Here, we developed a convolutional neural network method to identify population origins using genomic SNPs. Three empirical datasets (an Asian honeybee, a red fire ant, and a chicken datasets) and two simulated populations are used for the proof of concepts. The performance tests indicate that our method can accurately identify the genealogy origin of query individuals, with success rates ranging from > 93 % to 100 %. We further showed that the accuracy of the model can be significantly increased by refining the informative sites through FST filtering. Our method is robust to configurations related to batch sizes and epochs, whereas model learning benefits from the setting of a proper preset learning rate. Moreover, we explained the importance score of key sites for algorithm interpretability and credibility, which has been largely ignored. We anticipate that by coupling genomics and deep learning, our method will see broad potential in conservation and management applications that involve natural resources, invasive pests and weeds, and illegal trades of wildlife products.

PMID:38964594 | DOI:10.1016/j.ympev.2024.108142

J Proteomics. 2024 Jul 2:105246. doi: 10.1016/j.jprot.2024.105246. Online ahead of print.

ABSTRACT

The 2023 European Bioinformatics Community for Mass Spectrometry (EuBIC-MS) Developers Meeting was held from January 15th to January 20th, 2023, in Congressi Stefano Franscin at Monte Verità in Ticino, Switzerland. The participants were scientists and developers working in computational mass spectrometry (MS), metabolomics, and proteomics. The 5-day program was split between introductory keynote lectures and parallel hackathon sessions focusing on "Artificial Intelligence in proteomics" to stimulate future directions in the MS-driven omics areas. During the latter, the participants developed bioinformatics tools and resources addressing outstanding needs in the community. The hackathons allowed less experienced participants to learn from more advanced computational MS experts and actively contribute to highly relevant research projects. We successfully produced several new tools applicable to the proteomics community by improving data analysis and facilitating future research.

PMID:38964537 | DOI:10.1016/j.jprot.2024.105246

Int J Radiat Oncol Biol Phys. 2024 Jul 2:S0360-3016(24)00750-8. doi: 10.1016/j.ijrobp.2024.06.015. Online ahead of print.

ABSTRACT

PURPOSE: To investigate the potential of virtual contrast-enhanced MRI (VCE-MRI) for gross-tumor-volume (GTV) delineation of nasopharyngeal carcinoma (NPC) using multi-institutional data.

METHODS AND MATERIALS: This study retrospectively retrieved T1-weighted (T1w), T2-weighted (T2w) MRI, gadolinium-based contrast-enhanced MRI (CE-MRI) and planning CT of 348 biopsy-proven NPC patients from three oncology centers. A multimodality-guided synergistic neural network (MMgSN-Net) was trained using 288 patients to leverage complementary features in T1w and T2w MRI for VCE-MRI synthesis, which was independently evaluated using 60 patients. Three board-certified radiation oncologists and two medical physicists participated in clinical evaluations in three aspects: image quality assessment of the synthetic VCE-MRI, VCE-MRI in assisting target volume delineation, and effectiveness of VCE-MRI-based contours in treatment planning. The image quality assessment includes distinguishability between VCE-MRI and CE-MRI, clarity of tumor-to-normal tissue interface and veracity of contrast enhancement in tumor invasion risk areas. Primary tumor delineation and treatment planning were manually performed by radiation oncologists and medical physicists, respectively.

RESULTS: The mean accuracy to distinguish VCE-MRI from CE-MRI was 31.67%; no significant difference was observed in the clarity of tumor-to-normal tissue interface between VCE-MRI and CE-MRI; for the veracity of contrast enhancement in tumor invasion risk areas, an accuracy of 85.8% was obtained. The image quality assessment results suggest that the image quality of VCE-MRI is highly similar to real CE-MRI. The mean dosimetric difference of planning target volumes were less than 1Gy.

CONCLUSIONS: The VCE-MRI is highly promising to replace the use of gadolinium-based CE-MRI in tumor delineation of NPC patients.

PMID:38964419 | DOI:10.1016/j.ijrobp.2024.06.015

Comput Biol Med. 2024 Jul 3;179:108743. doi: 10.1016/j.compbiomed.2024.108743. Online ahead of print.

ABSTRACT

Abdominal tumor segmentation is a crucial yet challenging step during the screening and diagnosis of tumors. While 3D segmentation models provide powerful performance, they demand substantial computational resources. Additionally, in 3D data, tumors often represent a small portion, leading to imbalanced data and potentially overlooking crucial information. Conversely, 2D segmentation models have a lightweight structure, but disregard the inter-slice correlation, risking the loss of tumor in edge slices. To address these challenges, this paper proposes a novel Position-Aware and Key Slice Feature Sharing 2D tumor segmentation model (PAKS-Net). Leveraging the Swin-Transformer, we effectively model the global features within each slice, facilitating essential information extraction. Furthermore, we introduce a Position-Aware module to capture the spatial relationship between tumors and their corresponding organs, mitigating noise and interference from surrounding organ tissues. To enhance the edge slice segmentation accuracy, we employ key slices to assist in the segmentation of other slices to prioritize tumor regions. Through extensive experiments on three abdominal tumor segmentation CT datasets and a lung tumor segmentation CT dataset, PAKS-Net demonstrates superior performance, reaching 0.893, 0.769, 0.598 and 0.738 tumor DSC on the KiTS19, LiTS17, pancreas and LOTUS datasets, surpassing 3D segmentation models, while remaining computationally efficient with fewer parameters.

PMID:38964246 | DOI:10.1016/j.compbiomed.2024.108743

Comput Biol Med. 2024 Jul 3;179:108734. doi: 10.1016/j.compbiomed.2024.108734. Online ahead of print.

ABSTRACT

Artificial intelligence (AI) has played a vital role in computer-aided drug design (CADD). This development has been further accelerated with the increasing use of machine learning (ML), mainly deep learning (DL), and computing hardware and software advancements. As a result, initial doubts about the application of AI in drug discovery have been dispelled, leading to significant benefits in medicinal chemistry. At the same time, it is crucial to recognize that AI is still in its infancy and faces a few limitations that need to be addressed to harness its full potential in drug discovery. Some notable limitations are insufficient, unlabeled, and non-uniform data, the resemblance of some AI-generated molecules with existing molecules, unavailability of inadequate benchmarks, intellectual property rights (IPRs) related hurdles in data sharing, poor understanding of biology, focus on proxy data and ligands, lack of holistic methods to represent input (molecular structures) to prevent pre-processing of input molecules (feature engineering), etc. The major component in AI infrastructure is input data, as most of the successes of AI-driven efforts to improve drug discovery depend on the quality and quantity of data, used to train and test AI algorithms, besides a few other factors. Additionally, data-gulping DL approaches, without sufficient data, may collapse to live up to their promise. Current literature suggests a few methods, to certain extent, effectively handle low data for better output from the AI models in the context of drug discovery. These are transferring learning (TL), active learning (AL), single or one-shot learning (OSL), multi-task learning (MTL), data augmentation (DA), data synthesis (DS), etc. One different method, which enables sharing of proprietary data on a common platform (without compromising data privacy) to train ML model, is federated learning (FL). In this review, we compare and discuss these methods, their recent applications, and limitations while modeling small molecule data to get the improved output of AI methods in drug discovery. Article also sums up some other novel methods to handle inadequate data.

PMID:38964243 | DOI:10.1016/j.compbiomed.2024.108734

Comput Biol Med. 2024 Jul 3;179:108792. doi: 10.1016/j.compbiomed.2024.108792. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Concerns about patient privacy issues have limited the application of medical deep learning models in certain real-world scenarios. Differential privacy (DP) can alleviate this problem by injecting random noise into the model. However, naively applying DP to medical models will not achieve a satisfactory balance between privacy and utility due to the high dimensionality of medical models and the limited labeled samples.

METHODS: This work proposed the DP-SSLoRA model, a privacy-preserving classification model for medical images combining differential privacy with self-supervised low-rank adaptation. In this work, a self-supervised pre-training method is used to obtain enhanced representations from unlabeled publicly available medical data. Then, a low-rank decomposition method is employed to mitigate the impact of differentially private noise and combined with pre-trained features to conduct the classification task on private datasets.

RESULTS: In the classification experiments using three real chest-X ray datasets, DP-SSLoRA achieves good performance with strong privacy guarantees. Under the premise of ɛ=2, with the AUC of 0.942 in RSNA, the AUC of 0.9658 in Covid-QU-mini, and the AUC of 0.9886 in Chest X-ray 15k.

CONCLUSION: Extensive experiments on real chest X-ray datasets show that DP-SSLoRA can achieve satisfactory performance with stronger privacy guarantees. This study provides guidance for studying privacy-preserving in the medical field. Source code is publicly available online. https://github.com/oneheartforone/DP-SSLoRA.

PMID:38964242 | DOI:10.1016/j.compbiomed.2024.108792

Epilepsy Behav. 2024 Jul 3;158:109908. doi: 10.1016/j.yebeh.2024.109908. Online ahead of print.

ABSTRACT

OBJECTIVE: Evaluate the performance of a custom application developed for tonic-clonic seizure (TCS) monitoring on a consumer-wearable (Apple Watch) device.

METHODS: Participants with a history of convulsive epileptic seizures were recruited for either Epilepsy Monitoring Unit (EMU) or ambulatory (AMB) monitoring; participants without epilepsy (normal controls [NC]) were also enrolled in the AMB group. Both EMU and AMB participants wore an Apple Watch with a research app that continuously recorded accelerometer and photoplethysmography (PPG) signals, and ran a fixed-and-frozen tonic-clonic seizure detection algorithm during the testing period. This algorithm had been previously developed and validated using a separate training dataset. All EMU convulsive events were validated by video-electroencephalography (video-EEG); AMB events were validated by caregiver reporting and follow-ups. Device performance was characterized and compared to prior monitoring devices through sensitivity, false alarm rate (FAR; false-alarms per 24 h), precision, and detection delay (latency).

RESULTS: The EMU group had 85 participants (4,279 h, 19 TCS from 15 participants) enrolled across four EMUs; the AMB group had 21 participants (13 outpatient, 8 NC, 6,735 h, 10 TCS from 3 participants). All but one AMB participant completed the study. Device performance in the EMU group included a sensitivity of 100 % [95 % confidence interval (CI) 79-100 %]; an FAR of 0.05 [0.02, 0.08] per 24 h; a precision of 68 % [48 %, 83 %]; and a latency of 32.07 s [standard deviation (std) 10.22 s]. The AMB group had a sensitivity of 100 % [66-100 %]; an FAR of 0.13 [0.08, 0.24] per 24 h; a precision of 22 % [11 %, 37 %]; and a latency of 37.38 s [13.24 s]. Notably, a single AMB participant was responsible for 8 of 31 false alarms. The AMB FAR excluding this participant was 0.10 [0.07, 0.14] per 24 h.

DISCUSSION: This study demonstrates the practicability of TCS monitoring on a popular consumer wearable (Apple Watch) in daily use for people with epilepsy. The monitoring app had a high sensitivity and a substantially lower FAR than previously reported in both EMU and AMB environments.

PMID:38964183 | DOI:10.1016/j.yebeh.2024.109908

Schizophr Res. 2024 Jul 3;270:323-324. doi: 10.1016/j.schres.2024.06.052. Online ahead of print.

NO ABSTRACT

PMID:38964077 | DOI:10.1016/j.schres.2024.06.052

Leg Med (Tokyo). 2024 Jun 23;70:102476. doi: 10.1016/j.legalmed.2024.102476. Online ahead of print.

ABSTRACT

Sex estimation is a necessary part of forensic and osteological analyses of skeletal human remains in the construction of a biological profile. Several skeletal traits are sexually dimorphic and used for skeletal sex estimation. The human mandible and morphological traits therein have been long used for sex estimation, but the validity of using the mandible in this purpose has become a concern. In this study, we examined the potential of artificial intelligence (AI) and especially deep learning (DL) to provide accurate sex estimations from the mandible. We used 193 modern South African mandibles from the Human Osteological Research Collection (HORC) in the Sefako Makgatho Health Sciences university with known sex to conduct our study. All mandibles were photographed from the same angle and the photographs were analyzed with an open-source DL software. The best-performing DL algorithm estimated the sex of males with 100% accuracy and females with 76.9% accuracy. However, further studies with a higher number of specimens could provide more reliable validity for using AI when building the biological profile from skeletal remains.

PMID:38964075 | DOI:10.1016/j.legalmed.2024.102476

Pneumonia (Nathan). 2024 Jul 5;16(1):11. doi: 10.1186/s41479-024-00133-z.

ABSTRACT

Tuberculosis remains a significant global health challenge. Tuberculosis affects millions of individuals worldwide. Early detection of tuberculosis plays a relevant role in the management of treatment of tuberculosis. This systematic review will analyze the findings of several published studies on the topic of the early detection of tuberculosis. This systematic review highlights their methodologies and limitations as well as their contributions to our understanding of this pressing issue. Early detection of tuberculosis can be achieved through tuberculosis screening for contacts. Comprehensive health education for household contacts can be used as early detection. The in-house deep learning models can be used in the X-ray used for automatic detection of tuberculosis. Interferon gamma release assay, routine passive and active case detection, portable X-ray and nucleic acid amplification testing, and highly sensitive enzyme-linked immunosorbent assay tests play critical roles in improving tuberculosis detection.

PMID:38965640 | DOI:10.1186/s41479-024-00133-z

Cancer Imaging. 2024 Jul 4;24(1):85. doi: 10.1186/s40644-024-00737-0.

ABSTRACT

BACKGROUND: Recently, the application of deep learning (DL) has made great progress in various fields, especially in cancer research. However, to date, the bibliometric analysis of the application of DL in cancer is scarce. Therefore, this study aimed to explore the research status and hotspots of the application of DL in cancer.

METHODS: We retrieved all articles on the application of DL in cancer from the Web of Science database Core Collection database. Biblioshiny, VOSviewer and CiteSpace were used to perform the bibliometric analysis through analyzing the numbers, citations, countries, institutions, authors, journals, references, and keywords.

RESULTS: We found 6,016 original articles on the application of DL in cancer. The number of annual publications and total citations were uptrend in general. China published the greatest number of articles, USA had the highest total citations, and Saudi Arabia had the highest centrality. Chinese Academy of Sciences was the most productive institution. Tian, Jie published the greatest number of articles, while He Kaiming was the most co-cited author. IEEE Access was the most popular journal. The analysis of references and keywords showed that DL was mainly used for the prediction, detection, classification and diagnosis of breast cancer, lung cancer, and skin cancer.

CONCLUSIONS: Overall, the number of articles on the application of DL in cancer is gradually increasing. In the future, further expanding and improving the application scope and accuracy of DL applications, and integrating DL with protein prediction, genomics and cancer research may be the research trends.

PMID:38965599 | DOI:10.1186/s40644-024-00737-0

Sci Rep. 2024 Jul 4;14(1):15433. doi: 10.1038/s41598-024-65845-0.

ABSTRACT

The COVID-19 pandemic continues to challenge healthcare systems globally, necessitating advanced tools for clinical decision support. Amidst the complexity of COVID-19 symptomatology and disease severity prediction, there is a critical need for robust decision support systems to aid healthcare professionals in timely and informed decision-making. In response to this pressing demand, we introduce BayesCovid, a novel decision support system integrating Bayesian network models and deep learning techniques. BayesCovid automates data preprocessing and leverages advanced computational methods to unravel intricate patterns in COVID-19 symptom dynamics. By combining Bayesian networks and Bayesian deep learning models, BayesCovid offers a comprehensive solution for uncovering hidden relationships between symptoms and predicting disease severity. Experimental validation demonstrates BayesCovid 's high prediction accuracy (83.52-98.97%). Our work represents a significant stride in addressing the urgent need for clinical decision support systems tailored to the complexities of managing COVID-19 cases. By providing healthcare professionals with actionable insights derived from sophisticated computational analysis, BayesCovid aims to enhance clinical decision-making, optimise resource allocation, and improve patient outcomes in the ongoing battle against the COVID-19 pandemic.

PMID:38965354 | DOI:10.1038/s41598-024-65845-0

Sci Rep. 2024 Jul 5;14(1):15463. doi: 10.1038/s41598-024-64209-y.

ABSTRACT

Hepatitis C virus (HCV) is a major global health concern, affecting millions of individuals worldwide. While existing literature predominantly focuses on disease classification using clinical data, there exists a critical research gap concerning HCV genotyping based on genomic sequences. Accurate HCV genotyping is essential for patient management and treatment decisions. While the neural models excel at capturing complex patterns, they still face challenges, such as data scarcity, that exist a lot in computational genomics. To overcome this challenges, this paper introduces an advanced deep learning approach for HCV genotyping based on the graphical representation of nucleotide sequences that outperforms classical approaches. Notably, it is effective for both partial and complete HCV genomes and addresses challenges associated with imbalanced datasets. In this work, ten HCV genotypes: 1a, 1b, 2a, 2b, 2c, 3a, 3b, 4, 5, and 6 were used in the analysis. This study utilizes Chaos Game Representation for 2D mapping of genomic sequences, employing self-supervised learning using convolutional autoencoder for deep feature extraction, resulting in an outstanding performance for HCV genotyping compared to various machine learning and deep learning models. This baseline provides a benchmark against which the performance of the proposed approach and other models can be evaluated. The experimental results showcase a remarkable classification accuracy of over 99%, outperforming traditional deep learning models. This performance demonstrates the capability of the proposed model to accurately identify HCV genotypes in both partial and complete sequences and in dealing with data scarcity for certain genotypes. The results of the proposed model are compared to NCBI genotyping tool.

PMID:38965254 | DOI:10.1038/s41598-024-64209-y

Sci Rep. 2024 Jul 4;14(1):15432. doi: 10.1038/s41598-024-59263-5.

ABSTRACT

Previous research has primarily employed deep learning models such as Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs) for decoding imagined character signals. These approaches have treated the temporal and spatial features of the signals in a sequential, parallel, or single-feature manner. However, there has been limited research on the cross-relationships between temporal and spatial features, despite the inherent association between channels and sampling points in Brain-Computer Interface (BCI) signal acquisition, which holds significant information about brain activity. To address the limited research on the relationships between temporal and spatial features, we proposed a Temporal-Spatial Cross-Attention Network model, named TSCA-Net. The TSCA-Net is comprised of four modules: the Temporal Feature (TF), the Spatial Feature (SF), the Temporal-Spatial Cross (TSCross), and the Classifier. The TF combines LSTM and Transformer to extract temporal features from BCI signals, while the SF captures spatial features. The TSCross is introduced to learn the correlations between the temporal and spatial features. The Classifier predicts the label of BCI data based on its characteristics. We validated the TSCA-Net model using publicly available datasets of handwritten characters, which recorded the spiking activity from two micro-electrode arrays (MEAs). The results showed that our proposed TSCA-Net outperformed other comparison models (EEG-Net, EEG-TCNet, S3T, GRU, LSTM, R-Transformer, and ViT) in terms of accuracy, precision, recall, and F1 score, achieving 92.66 % , 92.77 % , 92.70 % , and 92.58 % , respectively. The TSCA-Net model demonstrated a 3.65 % to 7.49 % improvement in accuracy over the comparison models.

PMID:38965248 | DOI:10.1038/s41598-024-59263-5

Int J Comput Assist Radiol Surg. 2024 Jul 4. doi: 10.1007/s11548-024-03217-9. Online ahead of print.

ABSTRACT

PURPOSE: Most recently transformer models became the state of the art in various medical image segmentation tasks and challenges, outperforming most of the conventional deep learning approaches. Picking up on that trend, this study aims at applying various transformer models to the highly challenging task of colorectal cancer (CRC) segmentation in CT imaging and assessing how they hold up to the current state-of-the-art convolutional neural network (CNN), the nnUnet. Furthermore, we wanted to investigate the impact of the network size on the resulting accuracies, since transformer models tend to be significantly larger than conventional network architectures.

METHODS: For this purpose, six different transformer models, with specific architectural advancements and network sizes were implemented alongside the aforementioned nnUnet and were applied to the CRC segmentation task of the medical segmentation decathlon.

RESULTS: The best results were achieved with the Swin-UNETR, D-Former, and VT-Unet, each transformer models, with a Dice similarity coefficient (DSC) of 0.60, 0.59 and 0.59, respectively. Therefore, the current state-of-the-art CNN, the nnUnet could be outperformed by transformer architectures regarding this task. Furthermore, a comparison with the inter-observer variability (IOV) of approx. 0.64 DSC indicates almost expert-level accuracy. The comparatively low IOV emphasizes the complexity and challenge of CRC segmentation, as well as indicating limitations regarding the achievable segmentation accuracy.

CONCLUSION: As a result of this study, transformer models underline their current upward trend in producing state-of-the-art results also for the challenging task of CRC segmentation. However, with ever smaller advances in total accuracies, as demonstrated in this study by the on par performances of multiple network variants, other advantages like efficiency, low computation demands, or ease of adaption to new tasks become more and more relevant.

PMID:38965166 | DOI:10.1007/s11548-024-03217-9