Med Image Anal. 2024 Mar 29;94:103157. doi: 10.1016/j.media.2024.103157. Online ahead of print.

ABSTRACT

Computer-aided detection and diagnosis systems (CADe/CADx) in endoscopy are commonly trained using high-quality imagery, which is not representative for the heterogeneous input typically encountered in clinical practice. In endoscopy, the image quality heavily relies on both the skills and experience of the endoscopist and the specifications of the system used for screening. Factors such as poor illumination, motion blur, and specific post-processing settings can significantly alter the quality and general appearance of these images. This so-called domain gap between the data used for developing the system and the data it encounters after deployment, and the impact it has on the performance of deep neural networks (DNNs) supportive endoscopic CAD systems remains largely unexplored. As many of such systems, for e.g. polyp detection, are already being rolled out in clinical practice, this poses severe patient risks in particularly community hospitals, where both the imaging equipment and experience are subject to considerable variation. Therefore, this study aims to evaluate the impact of this domain gap on the clinical performance of CADe/CADx for various endoscopic applications. For this, we leverage two publicly available data sets (KVASIR-SEG and GIANA) and two in-house data sets. We investigate the performance of commonly-used DNN architectures under synthetic, clinically calibrated image degradations and on a prospectively collected dataset including 342 endoscopic images of lower subjective quality. Additionally, we assess the influence of DNN architecture and complexity, data augmentation, and pretraining techniques for improved robustness. The results reveal a considerable decline in performance of 11.6% (±1.5) as compared to the reference, within the clinically calibrated boundaries of image degradations. Nevertheless, employing more advanced DNN architectures and self-supervised in-domain pre-training effectively mitigate this drop to 7.7% (±2.03). Additionally, these enhancements yield the highest performance on the manually collected test set including images with lower subjective quality. By comprehensively assessing the robustness of popular DNN architectures and training strategies across multiple datasets, this study provides valuable insights into their performance and limitations for endoscopic applications. The findings highlight the importance of including robustness evaluation when developing DNNs for endoscopy applications and propose strategies to mitigate performance loss.

PMID:38574544 | DOI:10.1016/j.media.2024.103157

Comput Biol Med. 2024 Mar 20;173:108293. doi: 10.1016/j.compbiomed.2024.108293. Online ahead of print.

ABSTRACT

Accurately identifying the Kirsten rat sarcoma virus (KRAS) gene mutation status in colorectal cancer (CRC) patients can assist doctors in deciding whether to use specific targeted drugs for treatment. Although deep learning methods are popular, they are often affected by redundant features from non-lesion areas. Moreover, existing methods commonly extract spatial features from imaging data, which neglect important frequency domain features and may degrade the performance of KRAS gene mutation status identification. To address this deficiency, we propose a segmentation-guided Transformer U-Net (SG-Transunet) model for KRAS gene mutation status identification in CRC. Integrating the strength of convolutional neural networks (CNNs) and Transformers, SG-Transunet offers a unique approach for both lesion segmentation and KRAS mutation status identification. Specifically, for precise lesion localization, we employ an encoder-decoder to obtain segmentation results and guide the KRAS gene mutation status identification task. Subsequently, a frequency domain supplement block is designed to capture frequency domain features, integrating it with high-level spatial features extracted in the encoding path to derive advanced spatial-frequency domain features. Furthermore, we introduce a pre-trained Xception block to mitigate the risk of overfitting associated with small-scale datasets. Following this, an aggregate attention module is devised to consolidate spatial-frequency domain features with global information extracted by the Transformer at shallow and deep levels, thereby enhancing feature discriminability. Finally, we propose a mutual-constrained loss function that simultaneously constrains the segmentation mask acquisition and gene status identification process. Experimental results demonstrate the superior performance of SG-Transunet over state-of-the-art methods in discriminating KRAS gene mutation status.

PMID:38574528 | DOI:10.1016/j.compbiomed.2024.108293

Comput Methods Programs Biomed. 2024 Mar 25;249:108141. doi: 10.1016/j.cmpb.2024.108141. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Lung tumor annotation is a key upstream task for further diagnosis and prognosis. Although deep learning techniques have promoted automation of lung tumor segmentation, there remain challenges impeding its application in clinical practice, such as a lack of prior annotation for model training and data-sharing among centers.

METHODS: In this paper, we use data from six centers to design a novel federated semi-supervised learning (FSSL) framework with dynamic model aggregation and improve segmentation performance for lung tumors. To be specific, we propose a dynamically updated algorithm to deal with model parameter aggregation in FSSL, which takes advantage of both the quality and quantity of client data. Moreover, to increase the accessibility of data in the federated learning (FL) network, we explore the FAIR data principle while the previous federated methods never involve.

RESULT: The experimental results show that the segmentation performance of our model in six centers is 0.9348, 0.8436, 0.8328, 0.7776, 0.8870 and 0.8460 respectively, which is superior to traditional deep learning methods and recent federated semi-supervised learning methods.

CONCLUSION: The experimental results demonstrate that our method is superior to the existing FSSL methods. In addition, our proposed dynamic update strategy effectively utilizes the quality and quantity information of client data and shows efficiency in lung tumor segmentation. The source code is released on (https://github.com/GDPHMediaLab/FedDUS).

PMID:38574423 | DOI:10.1016/j.cmpb.2024.108141

Cancer Imaging. 2024 Apr 5;24(1):48. doi: 10.1186/s40644-024-00691-x.

ABSTRACT

BACKGROUND: Ductal Carcinoma In Situ (DCIS) can progress to invasive breast cancer, but most DCIS lesions never will. Therefore, four clinical trials (COMET, LORIS, LORETTA, AND LORD) test whether active surveillance for women with low-risk Ductal carcinoma In Situ is safe (E. S. Hwang et al., BMJ Open, 9: e026797, 2019, A. Francis et al., Eur J Cancer. 51: 2296-2303, 2015, Chizuko Kanbayashi et al. The international collaboration of active surveillance trials for low-risk DCIS (LORIS, LORD, COMET, LORETTA), L. E. Elshof et al., Eur J Cancer, 51, 1497-510, 2015). Low-risk is defined as grade I or II DCIS. Because DCIS grade is a major eligibility criteria in these trials, it would be very helpful to assess DCIS grade on mammography, informed by grade assessed on DCIS histopathology in pre-surgery biopsies, since surgery will not be performed on a significant number of patients participating in these trials.

OBJECTIVE: To assess the performance and clinical utility of a convolutional neural network (CNN) in discriminating high-risk (grade III) DCIS and/or Invasive Breast Cancer (IBC) from low-risk (grade I/II) DCIS based on mammographic features. We explored whether the CNN could be used as a decision support tool, from excluding high-risk patients for active surveillance.

METHODS: In this single centre retrospective study, 464 patients diagnosed with DCIS based on pre-surgery biopsy between 2000 and 2014 were included. The collection of mammography images was partitioned on a patient-level into two subsets, one for training containing 80% of cases (371 cases, 681 images) and 20% (93 cases, 173 images) for testing. A deep learning model based on the U-Net CNN was trained and validated on 681 two-dimensional mammograms. Classification performance was assessed with the Area Under the Curve (AUC) receiver operating characteristic and predictive values on the test set for predicting high risk DCIS-and high-risk DCIS and/ or IBC from low-risk DCIS.

RESULTS: When classifying DCIS as high-risk, the deep learning network achieved a Positive Predictive Value (PPV) of 0.40, Negative Predictive Value (NPV) of 0.91 and an AUC of 0.72 on the test dataset. For distinguishing high-risk and/or upstaged DCIS (occult invasive breast cancer) from low-risk DCIS a PPV of 0.80, a NPV of 0.84 and an AUC of 0.76 were achieved.

CONCLUSION: For both scenarios (DCIS grade I/II vs. III, DCIS grade I/II vs. III and/or IBC) AUCs were high, 0.72 and 0.76, respectively, concluding that our convolutional neural network can discriminate low-grade from high-grade DCIS.

PMID:38576031 | DOI:10.1186/s40644-024-00691-x

Med Biol Eng Comput. 2024 Apr 5. doi: 10.1007/s11517-024-03057-4. Online ahead of print.

ABSTRACT

The most fatal disease affecting women worldwide now is breast cancer. Early detection of breast cancer enhances the likelihood of a full recovery and lowers mortality. Based on medical imaging, researchers from all around the world are developing breast cancer screening technologies. Due to their rapid progress, deep learning algorithms have caught the interest of many in the field of medical imaging. This research proposes a novel method in mammogram image feature extraction with classification and optimization using machine learning in breast cancer detection. The input image has been processed for noise removal, smoothening, and normalization. The input image features were extracted using probabilistic principal component analysis for detecting the presence of tumors in mammogram images. The extracted tumor region is classified using the Naïve Bayes classifier and transfer integrated convolution neural networks. The classified output has been optimized using firefly binary grey optimization and metaheuristic moth flame lion optimization. The experimental analysis has been carried out in terms of different parameters based on datasets. The proposed framework used an ensemble model for breast cancer that made use of the proposed Bayes + FBGO and TCNN + MMFLO classifier and optimizer for diverse mammography image datasets. The INbreast dataset was evaluated using the proposed Bayes + FBGO and TCNN + MMFLO classifiers, which achieved 95% and 98% accuracy, respectively.

PMID:38575824 | DOI:10.1007/s11517-024-03057-4

NPJ Digit Med. 2024 Apr 4;7(1):85. doi: 10.1038/s41746-024-01086-9.

NO ABSTRACT

PMID:38575794 | DOI:10.1038/s41746-024-01086-9

Sci Rep. 2024 Apr 4;14(1):7974. doi: 10.1038/s41598-024-58750-z.

ABSTRACT

Every nation treasures its handloom heritage, and in India, the handloom industry safeguards cultural traditions, sustains millions of artisans, and preserves ancient weaving techniques. To protect this legacy, a critical need arises to distinguish genuine handloom products, exemplified by the renowned "gamucha" from India's northeast, from counterfeit powerloom imitations. Our study's objective is to create an AI tool for effortless detection of authentic handloom items amidst a sea of fakes. Six deep learning architectures-VGG16, VGG19, ResNet50, InceptionV3, InceptionResNetV2, and DenseNet201-were trained on annotated image repositories of handloom and powerloom towels (17,484 images in total, with 14,020 for training and 3464 for validation). A novel deep learning model was also proposed. Despite respectable training accuracies, the pre-trained models exhibited lower performance on the validation dataset compared to our novel model. The proposed model outperformed pre-trained models, demonstrating superior validation accuracy, lower validation loss, computational efficiency, and adaptability to the specific classification problem. Notably, the existing models showed challenges in generalizing to unseen data and raised concerns about practical deployment due to computational expenses. This study pioneers a computer-assisted approach for automated differentiation between authentic handwoven "gamucha"s and counterfeit powerloom imitations-a groundbreaking recognition method. The methodology presented not only holds scalability potential and opportunities for accuracy improvement but also suggests broader applications across diverse fabric products.

PMID:38575749 | DOI:10.1038/s41598-024-58750-z

Chaos. 2024 Apr 1;34(4):043115. doi: 10.1063/5.0201557.

ABSTRACT

Reconstructing complex networks and predicting the dynamics are particularly challenging in real-world applications because the available information and data are incomplete. We develop a unified collaborative deep-learning framework consisting of three modules: network inference, state estimation, and dynamical learning. The complete network structure is first inferred and the states of the unobserved nodes are estimated, based on which the dynamical learning module is activated to determine the dynamical evolution rules. An alternating parameter updating strategy is deployed to improve the inference and prediction accuracy. Our framework outperforms baseline methods for synthetic and empirical networks hosting a variety of dynamical processes. A reciprocity emerges between network inference and dynamical prediction: better inference of network structure improves the accuracy of dynamical prediction, and vice versa. We demonstrate the superior performance of our framework on an influenza dataset consisting of 37 US States and a PM2.5 dataset covering 184 cities in China.

PMID:38574280 | DOI:10.1063/5.0201557

PLoS One. 2024 Apr 4;19(4):e0301019. doi: 10.1371/journal.pone.0301019. eCollection 2024.

ABSTRACT

Automatic and accurate segmentation of medical images plays an essential role in disease diagnosis and treatment planning. Convolution neural networks have achieved remarkable results in medical image segmentation in the past decade. Meanwhile, deep learning models based on Transformer architecture also succeeded tremendously in this domain. However, due to the ambiguity of the medical image boundary and the high complexity of physical organization structures, implementing effective structure extraction and accurate segmentation remains a problem requiring a solution. In this paper, we propose a novel Dual Encoder Network named DECTNet to alleviate this problem. Specifically, the DECTNet embraces four components, which are a convolution-based encoder, a Transformer-based encoder, a feature fusion decoder, and a deep supervision module. The convolutional structure encoder can extract fine spatial contextual details in images. Meanwhile, the Transformer structure encoder is designed using a hierarchical Swin Transformer architecture to model global contextual information. The novel feature fusion decoder integrates the multi-scale representation from two encoders and selects features that focus on segmentation tasks by channel attention mechanism. Further, a deep supervision module is used to accelerate the convergence of the proposed method. Extensive experiments demonstrate that, compared to the other seven models, the proposed method achieves state-of-the-art results on four segmentation tasks: skin lesion segmentation, polyp segmentation, Covid-19 lesion segmentation, and MRI cardiac segmentation.

PMID:38573957 | DOI:10.1371/journal.pone.0301019

J Int Med Res. 2024 Apr;52(4):3000605241232519. doi: 10.1177/03000605241232519.

ABSTRACT

OBJECTIVE: To develop and evaluate a novel feature selection technique, using photoplethysmography (PPG) sensors, for enhancing the performance of deep learning models in classifying vascular access quality in hemodialysis patients.

METHODS: This cross-sectional study involved creating a novel feature selection method based on SelectKBest principles, specifically designed to optimize deep learning models for PPG sensor data, in hemodialysis patients. The method effectiveness was assessed by comparing the performance of multiple deep learning models using the feature selection approach versus complete feature set. The model with the highest accuracy was then trained and tested using a 70:30 approach, respectively, with the full dataset and the SelectKBest dataset. Performance results were compared using Student's paired t-test.

RESULTS: Data from 398 hemodialysis patients were included. The 1-dimensional convolutional neural network (CNN1D) displayed the highest accuracy among different models. Implementation of the SelectKBest-based feature selection technique resulted in a statistically significant improvement in the CNN1D model's performance, achieving an accuracy of 92.05% (with feature selection) versus 90.79% (with full feature set).

CONCLUSION: These findings suggest that the newly developed feature selection approach might aid in accurately predicting vascular access quality in hemodialysis patients. This advancement may contribute to the development of reliable diagnostic tools for identifying vascular complications, such as stenosis, potentially improving patient outcomes and their quality of life.

PMID:38573764 | DOI:10.1177/03000605241232519

Int J Comput Assist Radiol Surg. 2024 Apr 4. doi: 10.1007/s11548-024-03110-5. Online ahead of print.

ABSTRACT

PURPOSE: Three-dimensional (3D) preoperative planning has become the gold standard for orthopedic surgeries, primarily relying on CT-reconstructed 3D models. However, in contrast to standing radiographs, a CT scan is not part of the standard protocol but is usually acquired for preoperative planning purposes only. Additionally, it is costly, exposes the patients to high doses of radiation and is acquired in a non-weight-bearing position.

METHODS: In this study, we develop a deep-learning based pipeline to facilitate 3D preoperative planning for high tibial osteotomies, based on 3D models reconstructed from low-dose biplanar standing EOS radiographs. Using digitally reconstructed radiographs, we train networks to localize the clinically required landmarks, separate the two legs in the sagittal radiograph and finally reconstruct the 3D bone model. Finally, we evaluate the accuracy of the reconstructed 3D models for the particular application case of preoperative planning, with the aim of eliminating the need for a CT scan in specific cases, such as high tibial osteotomies.

RESULTS: The mean Dice coefficients for the tibial reconstructions were 0.92 and 0.89 for the right and left tibia, respectively. The reconstructed models were successfully used for clinical-grade preoperative planning in a real patient series of 52 cases. The mean differences to ground truth values for mechanical axis and tibial slope were 0.52° and 4.33°, respectively.

CONCLUSIONS: We contribute a novel framework for the 2D-3D reconstruction of bone models from biplanar standing EOS radiographs and successfully use them in automated clinical-grade preoperative planning of high tibial osteotomies. However, achieving precise reconstruction and automated measurement of tibial slope remains a significant challenge.

PMID:38573567 | DOI:10.1007/s11548-024-03110-5

Int J Comput Assist Radiol Surg. 2024 Apr 4. doi: 10.1007/s11548-024-03100-7. Online ahead of print.

ABSTRACT

PURPOSE: Cancer confirmation in the operating room (OR) is crucial to improve local control in cancer therapies. Histopathological analysis remains the gold standard, but there is a lack of real-time in situ cancer confirmation to support margin confirmation or remnant tissue. Raman spectroscopy (RS), as a label-free optical technique, has proven its power in cancer detection and, when integrated into a robotic assistance system, can positively impact the efficiency of procedures and the quality of life of patients, avoiding potential recurrence.

METHODS: A workflow is proposed where a 6-DOF robotic system (optical camera + MECA500 robotic arm) assists the characterization of fresh tissue samples using RS. Three calibration methods are compared for the robot, and the temporal efficiency is compared with standard hand-held analysis. For healthy/cancerous tissue discrimination, a 1D-convolutional neural network is proposed and tested on three ex vivo datasets (brain, breast, and prostate) containing processed RS and histopathology ground truth.

RESULTS: The robot achieves a minimum error of 0.20 mm (0.12) on a set of 30 test landmarks and demonstrates significant time reduction in 4 of the 5 proposed tasks. The proposed classification model can identify brain, breast, and prostate cancer with an accuracy of 0.83 (0.02), 0.93 (0.01), and 0.71 (0.01), respectively.

CONCLUSION: Automated RS analysis with deep learning demonstrates promising classification performance compared to commonly used support vector machines. Robotic assistance in tissue characterization can contribute to highly accurate, rapid, and robust biopsy analysis in the OR. These two elements are an important step toward real-time cancer confirmation using RS and OR integration.

PMID:38573566 | DOI:10.1007/s11548-024-03100-7

Int J Comput Assist Radiol Surg. 2024 Apr 4. doi: 10.1007/s11548-024-03098-y. Online ahead of print.

ABSTRACT

PURPOSE: In medical research, deep learning models rely on high-quality annotated data, a process often laborious and time-consuming. This is particularly true for detection tasks where bounding box annotations are required. The need to adjust two corners makes the process inherently frame-by-frame. Given the scarcity of experts' time, efficient annotation methods suitable for clinicians are needed.

METHODS: We propose an on-the-fly method for live video annotation to enhance the annotation efficiency. In this approach, a continuous single-point annotation is maintained by keeping the cursor on the object in a live video, mitigating the need for tedious pausing and repetitive navigation inherent in traditional annotation methods. This novel annotation paradigm inherits the point annotation's ability to generate pseudo-labels using a point-to-box teacher model. We empirically evaluate this approach by developing a dataset and comparing on-the-fly annotation time against traditional annotation method.

RESULTS: Using our method, annotation speed was 3.2 × faster than the traditional annotation technique. We achieved a mean improvement of 6.51 ± 0.98 AP@50 over conventional method at equivalent annotation budgets on the developed dataset.

CONCLUSION: Without bells and whistles, our approach offers a significant speed-up in annotation tasks. It can be easily implemented on any annotation platform to accelerate the integration of deep learning in video-based medical research.

PMID:38573565 | DOI:10.1007/s11548-024-03098-y

Phys Eng Sci Med. 2024 Apr 4. doi: 10.1007/s13246-024-01419-8. Online ahead of print.

ABSTRACT

Following the great success of various deep learning methods in image and object classification, the biomedical image processing society is also overwhelmed with their applications to various automatic diagnosis cases. Unfortunately, most of the deep learning-based classification attempts in the literature solely focus on the aim of extreme accuracy scores, without considering interpretability, or patient-wise separation of training and test data. For example, most lung nodule classification papers using deep learning randomly shuffle data and split it into training, validation, and test sets, causing certain images from the Computed Tomography (CT) scan of a person to be in the training set, while other images of the same person to be in the validation or testing image sets. This can result in reporting misleading accuracy rates and the learning of irrelevant features, ultimately reducing the real-life usability of these models. When the deep neural networks trained on the traditional, unfair data shuffling method are challenged with new patient images, it is observed that the trained models perform poorly. In contrast, deep neural networks trained with strict patient-level separation maintain their accuracy rates even when new patient images are tested. Heat map visualizations of the activations of the deep neural networks trained with strict patient-level separation indicate a higher degree of focus on the relevant nodules. We argue that the research question posed in the title has a positive answer only if the deep neural networks are trained with images of patients that are strictly isolated from the validation and testing patient sets.

PMID:38573489 | DOI:10.1007/s13246-024-01419-8

Sci China Life Sci. 2024 Apr 2. doi: 10.1007/s11427-023-2518-8. Online ahead of print.

ABSTRACT

The human face is a valuable biomarker of aging, but the collection and use of its image raise significant privacy concerns. Here we present an approach for facial data masking that preserves age-related features using coordinate-wise monotonic transformations. We first develop a deep learning model that estimates age directly from non-registered face point clouds with high accuracy and generalizability. We show that the model learns a highly indistinguishable mapping using faces treated with coordinate-wise monotonic transformations, indicating that the relative positioning of facial information is a low-level biomarker of facial aging. Through visual perception tests and computational 3D face verification experiments, we demonstrate that transformed faces are significantly more difficult to perceive for human but not for machines, except when only the face shape information is accessible. Our study leads to a facial data protection guideline that has the potential to broaden public access to face datasets with minimized privacy risks.

PMID:38573362 | DOI:10.1007/s11427-023-2518-8

Int J Surg. 2024 Apr 3. doi: 10.1097/JS9.0000000000001358. Online ahead of print.

ABSTRACT

OBJECTIVES: Accurate preoperative prediction of the pathological grade of clear cell renal cell carcinoma (ccRCC) is crucial for optimal treatment planning and patient outcomes. This study aims to develop and validate a deep-learning (DL) algorithm to automatically segment renal tumours, kidneys, and perirenal adipose tissue (PRAT) from computed tomography (CT) images and extract radiomics features to predict the pathological grade of ccRCC.

METHODS: In this cross-ethnic retrospective study, a total of 614 patients were divided into a training set (383 patients from the local hospital), an internal validation set (88 patients from the local hospital), and an external validation set (143 patients from the public dataset). A two-dimensional TransUNet-based DL model combined with the train-while-annotation method was trained for automatic volumetric segmentation of renal tumours, kidneys, and visceral adipose tissue (VAT) on images from two groups of datasets. PRAT was extracted using a dilation algorithm by calculating voxels of VAT surrounding the kidneys. Radiomics features were subsequently extracted from three regions of interest of CT images, adopting multiple filtering strategies. The least absolute shrinkage and selection operator (LASSO) regression was used for feature selection, and the support vector machine (SVM) for developing the pathological grading model. Ensemble learning was used for imbalanced data classification. Performance evaluation included the Dice coefficient for segmentation and metrics such as accuracy and area under curve (AUC) for classification. The WHO/International Society of Urological Pathology (ISUP) grading models were finally interpreted and visualized using the SHapley Additive exPlanations (SHAP) method.

RESULTS: For automatic segmentation, the mean Dice coefficient achieved 0.836 for renal tumours and 0.967 for VAT on the internal validation dataset. For WHO/ISUP grading, a model built with features of PRAT achieved a moderate AUC of 0.711 (95% CI, 0.604-0.802) in the internal validation set, coupled with a sensitivity of 0.400 and a specificity of 0.781. While model built with combination features of the renal tumour, kidney, and PRAT showed an AUC of 0.814 (95% CI, 0.717-0.889) in the internal validation set, with a sensitivity of 0.800 and a specificity of 0.753, significantly higher than the model built with features solely from tumour lesion (0.760; 95% CI, 0.657-0.845), with a sensitivity of 0.533 and a specificity of 0.767.

CONCLUSION: Automated segmentation of kidneys and visceral adipose tissue (VAT) through TransUNet combined with a conventional image morphology processing algorithm offers a standardized approach to extract PRAT with high reproducibility. The radiomics features of PRAT and tumour lesions, along with machine learning, accurately predict the pathological grade of ccRCC and reveal the incremental significance of PRAT in this prediction.

PMID:38573065 | DOI:10.1097/JS9.0000000000001358

J Chem Inf Model. 2024 Apr 4. doi: 10.1021/acs.jcim.4c00058. Online ahead of print.

ABSTRACT

Rapidly predicting enzyme properties for catalyzing specific substrates is essential for identifying potential enzymes for industrial transformations. The demand for sustainable production of valuable industry chemicals utilizing biological resources raised a pressing need to speed up biocatalyst screening using machine learning techniques. In this research, we developed an all-purpose deep-learning-based multiple-toolkit (ALDELE) workflow for screening enzyme catalysts. ALDELE incorporates both structural and sequence representations of proteins, alongside representations of ligands by subgraphs and overall physicochemical properties. Comprehensive evaluation demonstrated that ALDELE can predict the catalytic activities of enzymes, and particularly, it identifies residue-based hotspots to guide enzyme engineering and generates substrate heat maps to explore the substrate scope for a given biocatalyst. Moreover, our models notably match empirical data, reinforcing the practicality and reliability of our approach through the alignment with confirmed mutation sites. ALDELE offers a facile and comprehensive solution by integrating different toolkits tailored for different purposes at affordable computational cost and therefore would be valuable to speed up the discovery of new functional enzymes for their exploitation by the industry.

PMID:38573056 | DOI:10.1021/acs.jcim.4c00058

Chaos. 2024 Apr 1;34(4):043112. doi: 10.1063/5.0181791.

ABSTRACT

Making accurate forecasts for a complex system is a challenge in various practical applications. The major difficulty in solving such a problem concerns nonlinear spatiotemporal dynamics with time-varying characteristics. Takens' delay embedding theory provides a way to transform high-dimensional spatial information into temporal information. In this work, by combining delay embedding theory and deep learning techniques, we propose a novel framework, delay-embedding-based forecast Machine (DEFM), to predict the future values of a target variable in a self-supervised and multistep-ahead manner based on high-dimensional observations. With a three-module spatiotemporal architecture, the DEFM leverages deep neural networks to effectively extract both the spatially and temporally associated information from the observed time series even with time-varying parameters or additive noise. The DEFM can accurately predict future information by transforming spatiotemporal information to the delay embeddings of a target variable. The efficacy and precision of the DEFM are substantiated through applications in three spatiotemporally chaotic systems: a 90-dimensional (90D) coupled Lorenz system, the Lorenz 96 system, and the Kuramoto-Sivashinsky equation with inhomogeneity. Additionally, the performance of the DEFM is evaluated on six real-world datasets spanning various fields. Comparative experiments with five prediction methods illustrate the superiority and robustness of the DEFM and show the great potential of the DEFM in temporal information mining and forecasting.

PMID:38572943 | DOI:10.1063/5.0181791

J Forensic Sci. 2024 Apr 4. doi: 10.1111/1556-4029.15516. Online ahead of print.

ABSTRACT

Videos are considered as most trustworthy means of communication in the present digital era. The advancement in multimedia technology has made video content sharing and manipulation very easy. Hence, the video authenticity is a challenging task for the research community. Video forensics refer to uncovering the forgery traces. The detection of spatiotemporal object-removal forgery in surveillance videos is crucial for judicial forensics, as the presence of objects in the video has significant information as legal evidence. The author proposes a passive max-median averaging motion residual algorithm for revealing the forgery traces, successfully giving visible object-removal traces followed by a deep learning approach, YOLO-V8, for forged region localization. YOLO-V8 is the latest deep learning model, which has a wide scope for real-time application. The proposed method utilizes YOLO-V8 for object-removal forgery in surveillance videos. The network is trained on the SYSU-OBJFORG dataset for object-removal forged region localization in videos. The fine-tuned YOLO-V8 successfully classifies and localizes the object-removal tampered region with an F1-score of 0.99 and a precision of 0.99. The observed high confidence score of the bounding box around the forged region makes the model reliable. This fine-tuned YOLO-V8 would be a better choice in real-time applications as it solves the complex object-based forgery detection in videos. The performance of the proposed system is far better than the existing deep learning approach.

PMID:38572826 | DOI:10.1111/1556-4029.15516

Heliyon. 2024 Mar 21;10(7):e28538. doi: 10.1016/j.heliyon.2024.e28538. eCollection 2024 Apr 15.

ABSTRACT

Liver tumors are one of the most aggressive malignancies in the human body. Computer-aided technology and liver interventional surgery are effective in the prediction, identification and management of liver neoplasms. One of the important processes is to accurately grasp the morphological structure of the liver and liver blood vessels. However, accurate identification and segmentation of hepatic blood vessels in CT images poses a formidable challenge. Manually locating and segmenting liver vessels in CT images is time-consuming and impractical. There is an imperative clinical requirement for a precise and effective algorithm to segment liver vessels. In response to this demand, the current paper advocates a liver vessel segmentation approach that employs an enhanced 3D fully convolutional neural network V-Net. The network model improves the basic network structure according to the characteristics of liver vessels. First, a pyramidal convolution block is introduced between the encoder and decoder of the network to improve the network localization ability. Then, multi-resolution deep supervision is introduced in the network, resulting in more robust segmentation. Finally, by fusing feature maps of different resolutions, the overall segmentation result is predicted. Evaluation experiments on public datasets demonstrate that our improved scheme can increase the segmentation ability of existing network models for liver vessels. Compared with the existing work, the experimental outcomes demonstrate that the technique presented in this manuscript has attained superior performance on the Dice Coefficient index, which can promote the treatment of liver tumors.

PMID:38571625 | PMC:PMC10988037 | DOI:10.1016/j.heliyon.2024.e28538