Comput Biol Med. 2024 Jul 21;179:108902. doi: 10.1016/j.compbiomed.2024.108902. Online ahead of print.

ABSTRACT

In the field of histopathology, many studies on the classification of whole slide images (WSIs) using artificial intelligence (AI) technology have been reported. We have studied the disease progression assessment of glioma. Adult-type diffuse gliomas, a type of brain tumor, are classified into astrocytoma, oligodendroglioma, and glioblastoma. Astrocytoma and oligodendroglioma are also called low grade glioma (LGG), and glioblastoma is also called glioblastoma multiforme (GBM). LGG patients frequently have isocitrate dehydrogenase (IDH) mutations. Patients with IDH mutations have been reported to have a better prognosis than patients without IDH mutations. Therefore, IDH mutations are an essential indicator for the classification of glioma. That is why we focused on the IDH1 mutation. In this paper, we aimed to classify the presence or absence of the IDH1 mutation using WSIs and clinical data of glioma patients. Ensemble learning between the WSIs model and the clinical data model is used to classify the presence or absence of IDH1 mutation. By using slide level labels, we combined patch-based imaging information from hematoxylin and eosin (H & E) stained WSIs, along with clinical data using deep image feature extraction and machine learning classifier for predicting IDH1 gene mutation prediction versus wild-type across cohort of 546 patients. We experimented with different deep learning (DL) models including attention-based multiple instance learning (ABMIL) models on imaging data along with gradient boosting machine (LightGBM) for the clinical variables. Further, we used hyperparameter optimization to find the best overall model in terms of classification accuracy. We obtained the highest area under the curve (AUC) of 0.823 for WSIs, 0.782 for clinical data, and 0.852 for ensemble results using MaxViT and LightGBM combination, respectively. Our experimental results indicate that the overall accuracy of the AI models can be improved by using both clinical data and images.

PMID:39038392 | DOI:10.1016/j.compbiomed.2024.108902

Comput Biol Med. 2024 Jul 21;179:108926. doi: 10.1016/j.compbiomed.2024.108926. Online ahead of print.

ABSTRACT

Toxicity emerges as a prominent challenge in the design of therapeutic peptides, causing the failure of numerous peptides during clinical trials. In 2013, our group developed ToxinPred, a computational method that has been extensively adopted by the scientific community for predicting peptide toxicity. In this paper, we propose a refined variant of ToxinPred that showcases improved reliability and accuracy in predicting peptide toxicity. Initially, we utilized a similarity/alignment-based approach employing BLAST to predict toxic peptides, which yielded satisfactory accuracy; however, the method suffered from inadequate coverage. Subsequently, we employed a motif-based approach using MERCI software to uncover specific patterns or motifs that are exclusively observed in toxic peptides. The search for these motifs in peptides allowed us to predict toxic peptides with a high level of specificity with poor sensitivity. To overcome the coverage limitations, we developed alignment-free methods using machine/deep learning techniques to balance sensitivity and specificity of prediction. Deep learning model (ANN - LSTM with fixed sequence length) developed using one-hot encoding achieved a maximum AUROC of 0.93 with MCC of 0.71 on an independent dataset. Machine learning model (extra tree) developed using compositional features of peptides achieved a maximum AUROC of 0.95 with MCC of 0.78. We also developed large language models and achieved maximum AUC of 0.93 using ESM2-t33. Finally, we developed hybrid or ensemble methods combining two or more methods to enhance performance. Our specific hybrid method, which combines a motif-based approach with a machine learning-based model, achieved a maximum AUROC of 0.98 with MCC 0.81 on an independent dataset. In this study, all models were trained and tested on 80 % of data using five-fold cross-validation and evaluated on the remaining 20 % of data called independent dataset. The evaluation of all methods on an independent dataset revealed that the method proposed in this study exhibited better performance than existing methods. To cater to the needs of the scientific community, we have developed a standalone software, pip package and web-based server ToxinPred3 (https://github.com/raghavagps/toxinpred3 and https://webs.iiitd.edu.in/raghava/toxinpred3/).

PMID:39038391 | DOI:10.1016/j.compbiomed.2024.108926

J Phys Chem Lett. 2024 Jul 22:7681-7693. doi: 10.1021/acs.jpclett.4c01509. Online ahead of print.

ABSTRACT

Accurate prediction of Drug-Target Interactions (DTI) is crucial for drug development. Current state-of-the-art deep learning methods have significantly advanced the field; however, these methods exhibit limitations in predictive performance and the propensity for false negatives. Therefore, we propose EADTN, a simple and efficient ensemble model. We have designed an innovative feature adaptation technique to automatically extract local weights of drugs and targets, and we utilize clustering-enhanced parameter fine-tuning to overcome the issue of false negatives, thereby enhancing its reliability in drug discovery. Based on EADTN, we also propose a Shapley value-based method for identifying key drug substructures, effectively enhancing the model's interpretability. Additionally, we utilized EADTN to reveal potential interactions between NQO1 targets and the drugs SIRT-IN-1 and LY2183240, which were subsequently validated through wet-lab experiments. Experimental evidence demonstrates that EADTN consistently outperforms existing best-performing models across various data sets, promising significant benefits in fields such as drug repositioning.

PMID:39038219 | DOI:10.1021/acs.jpclett.4c01509

PLoS One. 2024 Jul 22;19(7):e0305857. doi: 10.1371/journal.pone.0305857. eCollection 2024.

ABSTRACT

Traditional differential expression genes (DEGs) identification models have limitations in small sample size datasets because they require meeting distribution assumptions, otherwise resulting high false positive/negative rates due to sample variation. In contrast, tabular data model based on deep learning (DL) frameworks do not need to consider the data distribution types and sample variation. However, applying DL to RNA-Seq data is still a challenge due to the lack of proper labeling and the small sample size compared to the number of genes. Data augmentation (DA) extracts data features using different methods and procedures, which can significantly increase complementary pseudo-values from limited data without significant additional cost. Based on this, we combine DA and DL framework-based tabular data model, propose a model TabDEG, to predict DEGs and their up-regulation/down-regulation directions from gene expression data obtained from the Cancer Genome Atlas database. Compared to five counterpart methods, TabDEG has high sensitivity and low misclassification rates. Experiment shows that TabDEG is robust and effective in enhancing data features to facilitate classification of high-dimensional small sample size datasets and validates that TabDEG-predicted DEGs are mapped to important gene ontology terms and pathways associated with cancer.

PMID:39037985 | DOI:10.1371/journal.pone.0305857

J Chem Inf Model. 2024 Jul 22. doi: 10.1021/acs.jcim.4c00481. Online ahead of print.

ABSTRACT

We propose HydraScreen, a deep-learning framework for safe and robust accelerated drug discovery. HydraScreen utilizes a state-of-the-art 3D convolutional neural network designed for the effective representation of molecular structures and interactions in protein-ligand binding. We designed an end-to-end pipeline for high-throughput screening and lead optimization, targeting applications in structure-based drug design. We assessed our approach using established public benchmarks based on the CASF-2016 core set, achieving top-tier results in affinity and pose prediction (Pearson's r = 0.86, RMSE = 1.15, Top-1 = 0.95). We introduced a novel approach for interaction profiling, aimed at detecting potential biases within both the model and data sets. This approach not only enhanced interpretability but also reinforced the impartiality of our methodology. Finally, we demonstrated HydraScreen's ability to generalize effectively across novel proteins and ligands through a temporal split. We also provide insights into potential avenues for future development aimed at enhancing the robustness of machine learning scoring functions. HydraScreen (accessible at http://hydrascreen.ro5.ai/paper) provides a user-friendly GUI and a public API, facilitating the easy-access assessment of protein-ligand complexes.

PMID:39037942 | DOI:10.1021/acs.jcim.4c00481

IEEE/ACM Trans Comput Biol Bioinform. 2024 Jul 22;PP. doi: 10.1109/TCBB.2024.3431688. Online ahead of print.

ABSTRACT

The virus poses a longstanding and enduring danger to various forms of life. Despite the ongoing endeavors to combat viral diseases, there exists a necessity to explore and develop novel therapeutic options. Antiviral peptides are bioactive molecules with a favorable toxicity profile, making them promising alternatives for viral infection treatment. Therefore, this article employed a generative adversarial network for antiviral peptide augmentation and a novel two-step authentication process for augmented synthetic peptides to enhance antiviral activity prediction. Additionally, five widely utilized deep learning models were employed for classification purposes. Initially, a GAN was used to augment the antiviral peptide. In a two-step authentication process, the NCBI-BLAST was utilized to identify the antiviral activity resemblance between the synthetic and real peptide. Subsequently, the hydrophobicity, hydrophilicity, hydroxylic nature, positive charge, and negative charge of synthetic and authentic antiviral peptides were compared before their utilization. Later, to examine the impact of authenticated peptide augmentation in the prediction of antiviral peptides, a comparison is conducted with the outcomes of non-peptide augmented prediction. The study demonstrates that the 1-D convolution neural network with augmented peptide exhibits superior performance compared to other employed classifiers and state-of-the-art models. The network attains a mean classification accuracy of 95.41%, an AUC value of 0.95, and an MCC value of 0.90 on the benchmark antiviral and anti-corona peptides dataset. Thus, the performance of the proposed model indicates its efficacy in predicting the antiviral activity of peptides.

PMID:39037884 | DOI:10.1109/TCBB.2024.3431688

IEEE Trans Med Imaging. 2024 Jul 22;PP. doi: 10.1109/TMI.2024.3432388. Online ahead of print.

ABSTRACT

Heterogeneous data captured by different scanning devices and imaging protocols can affect the generalization performance of the deep learning magnetic resonance (MR) reconstruction model. While a centralized training model is effective in mitigating this problem, it raises concerns about privacy protection. Federated learning is a distributed training paradigm that can utilize multi-institutional data for collaborative training without sharing data. However, existing federated learning MR image reconstruction methods rely on models designed manually by experts, which are complex and computationally expensive, suffering from performance degradation when facing heterogeneous data distributions. In addition, these methods give inadequate consideration to fairness issues, namely ensuring that the model's training does not introduce bias towards any specific dataset's distribution. To this end, this paper proposes a generalizable federated neural architecture search framework for accelerating MR imaging (GAutoMRI). Specifically, automatic neural architecture search is investigated for effective and efficient neural network representation learning of MR images from different centers. Furthermore, we design a fairness adjustment approach that can enable the model to learn features fairly from inconsistent distributions of different devices and centers, and thus facilitate the model to generalize well to the unseen center. Extensive experiments show that our proposed GAutoMRI has better performances and generalization ability compared with seven state-of-the-art federated learning methods. Moreover, the GAutoMRI model is significantly more lightweight, making it an efficient choice for MR image reconstruction tasks. The code will be made available at https://github.com/ternencewu123/GAutoMRI.

PMID:39037877 | DOI:10.1109/TMI.2024.3432388

J Imaging Inform Med. 2024 Jul 22. doi: 10.1007/s10278-024-01195-7. Online ahead of print.

ABSTRACT

Adenomatous polyps, a common premalignant lesion, are often classified into villous adenoma (VA) and tubular adenoma (TA). VA has a higher risk of malignancy, whereas TA typically grows slowly and has a lower likelihood of cancerous transformation. Accurate classification is essential for tailored treatment. In this study, we develop a deep learning-based approach for the localization and classification of adenomatous polyps using endoscopic images. Specifically, a pre-trained EGE-UNet is first adopted to extract regions of interest from original images. Multi-level feature maps are then extracted by the feature extraction pipeline (FEP). The deep-level features are fed into the Pyramid Pooling Module (PPM) to capture global contextual information, and the squeeze body edge (SBE) module is then used to decouple the body and edge parts of features, enabling separate analysis of their distinct characteristics. The Group Aggregation Bridge (GAB) and Boundary Enhancement Module (BEM) are then applied to enhance the body features and edge features, respectively, emphasizing their structural and morphological characteristics. By combining the features of the body and edge parts, the final output can be obtained. Experiments show the proposed method achieved promising results on two private datasets. For adenoma vs. non-adenoma classification, It achieved a mIoU of 91.41%, mPA of 96.33%, mHD of 11.63, and mASD of 2.33. For adenoma subclassification (non-adenomas vs. villous adenomas vs. tubular adenomas), it achieved a mIoU of 91.21%, mPA of 94.83%, mHD of 13.75, and mASD of 2.56. These results demonstrate the potential of our approach for precise adenomatous polyp classification.

PMID:39037669 | DOI:10.1007/s10278-024-01195-7

Development. 2024 Jul 15;151(14):dev202800. doi: 10.1242/dev.202800. Epub 2024 Jul 18.

ABSTRACT

We present a new set of computational tools that enable accurate and widely applicable 3D segmentation of nuclei in various 3D digital organs. We have developed an approach for ground truth generation and iterative training of 3D nuclear segmentation models, which we applied to popular CellPose, PlantSeg and StarDist algorithms. We provide two high-quality models trained on plant nuclei that enable 3D segmentation of nuclei in datasets obtained from fixed or live samples, acquired from different plant and animal tissues, and stained with various nuclear stains or fluorescent protein-based nuclear reporters. We also share a diverse high-quality training dataset of about 10,000 nuclei. Furthermore, we advanced the MorphoGraphX analysis and visualization software by, among other things, providing a method for linking 3D segmented nuclei to their surrounding cells in 3D digital organs. We found that the nuclear-to-cell volume ratio varies between different ovule tissues and during the development of a tissue. Finally, we extended the PlantSeg 3D segmentation pipeline with a proofreading tool that uses 3D segmented nuclei as seeds to correct cell segmentation errors in difficult-to-segment tissues.

PMID:39036998 | DOI:10.1242/dev.202800

Nucleic Acids Res. 2024 Jul 22:gkae623. doi: 10.1093/nar/gkae623. Online ahead of print.

ABSTRACT

Nucleosomes represent elementary building units of eukaryotic chromosomes and consist of DNA wrapped around a histone octamer flanked by linker DNA segments. Nucleosomes are central in epigenetic pathways and their genomic positioning is associated with regulation of gene expression, DNA replication, DNA methylation and DNA repair, among other functions. Building on prior discoveries that DNA sequences noticeably affect nucleosome positioning, our objective is to identify nucleosome positions and related features across entire genome. Here, we introduce an interpretable framework based on the concepts of deep residual networks (NuPoSe). Trained on high-coverage human experimental MNase-seq data, NuPoSe is able to learn sequence and structural patterns associated with nucleosome organization in human genome. NuPoSe can be also applied to unseen data from different organisms and cell types. Our findings point to 43 informative features, most of them constitute tri-nucleotides, di-nucleotides and one tetra-nucleotide. Most features are significantly associated with the nucleosomal structural characteristics, namely, periodicity of nucleosomal DNA and its location with respect to a histone octamer. Importantly, we show that features derived from the 27 bp linker DNA flanking nucleosomes contribute up to 10% to the quality of the prediction model. This, along with the comprehensive training sets, deep-learning architecture, and feature selection method, may contribute to the NuPoSe's 80-89% classification accuracy on different independent datasets.

PMID:39036965 | DOI:10.1093/nar/gkae623

Antib Ther. 2024 May 30;7(3):199-208. doi: 10.1093/abt/tbae012. eCollection 2024 Jul.

ABSTRACT

BACKGROUND: Early assessment of antibody off-target binding is essential for mitigating developability risks such as fast clearance, reduced efficacy, toxicity, and immunogenicity. The baculovirus particle (BVP) binding assay has been widely utilized to evaluate polyreactivity of antibodies. As a complementary approach, computational prediction of polyreactivity is desirable for counter-screening antibodies from in silico discovery campaigns. However, there is a lack of such models.

METHODS: Herein, we present the development of an ensemble of three deep learning models based on two pan-protein foundational protein language models (ESM2 and ProtT5) and an antibody-specific protein language model (PLM) (Antiberty). These models were trained in a transfer learning network to predict the outcomes in the BVP assay and the bovine serum albumin binding assay, which was developed as a complement to the BVP assay. The training was conducted on a large dataset of antibody sequences augmented with experimental conditions, which were collected through a highly efficient application system.

RESULTS: The resulting models demonstrated robust performance on canonical mAbs (monospecific with heavy and light chain), bispecific Abs, and single-domain Fc (VHH-Fc). PLMs outperformed a model built using molecular descriptors calculated from AlphaFold 2 predicted structures. Embeddings from the antibody-specific and foundational PLMs resulted in similar performance.

CONCLUSION: To our knowledge, this represents the first application of PLMs to predict assay data on bispecifics and VHH-Fcs.

PMID:39036071 | PMC:PMC11259759 | DOI:10.1093/abt/tbae012

Data Brief. 2024 Jun 17;55:110633. doi: 10.1016/j.dib.2024.110633. eCollection 2024 Aug.

ABSTRACT

This data article presents a comprehensive dataset comprising breast cancer images collected from patients, encompassing two distinct sets: one from individuals diagnosed with breast cancer and another from those without the condition. Expert physicians carefully select, verify, and categorize the dataset to guarantee its quality and dependability for use in research and teaching. The dataset, which originates from Sulaymaniyah, Iraq, provides a distinctive viewpoint on the frequency and features of breast cancer in the area. This dataset offers a wealth of information for developing and testing deep learning algorithms for identifying breast cancer, with 745 original images and 9,685 augmented images. The addition of augmented X-rays to the dataset increases its adaptability for algorithm development and instructional projects. This dataset holds immense potential for advancing medical research, aiding in the development of innovative diagnostic tools, and fostering educational opportunities for medical students interested in breast cancer detection and diagnosis.

PMID:39035836 | PMC:PMC11259914 | DOI:10.1016/j.dib.2024.110633

Comput Struct Biotechnol J. 2024 Jun 20;23:2708-2716. doi: 10.1016/j.csbj.2024.06.019. eCollection 2024 Dec.

ABSTRACT

In the field of computational oncology, patient status is often assessed using radiology-genomics, which includes two key technologies and data, such as radiology and genomics. Recent advances in deep learning have facilitated the integration of radiology-genomics data, and even new omics data, significantly improving the robustness and accuracy of clinical predictions. These factors are driving artificial intelligence (AI) closer to practical clinical applications. In particular, deep learning models are crucial in identifying new radiology-genomics biomarkers and therapeutic targets, supported by explainable AI (xAI) methods. This review focuses on recent developments in deep learning for radiology-genomics integration, highlights current challenges, and outlines some research directions for multimodal integration and biomarker discovery of radiology-genomics or radiology-omics that are urgently needed in computational oncology.

PMID:39035833 | PMC:PMC11260400 | DOI:10.1016/j.csbj.2024.06.019

J Bioinform Comput Biol. 2024 Jul 20:2450016. doi: 10.1142/S0219720024500161. Online ahead of print.

ABSTRACT

The Qingfei Paidu decoction (QFPDD) is a widely acclaimed therapeutic formula employed nationwide for the clinical management of coronavirus disease 2019 (COVID-19). QFPDD exerts a synergistic therapeutic effect, characterized by its multi-component, multi-target, and multi-pathway action. However, the intricate interactions among the ingredients and targets within QFPDD and their systematic effects in multiple tissues remain undetermined. To address this, we qualitatively characterized the chemical components of QFPDD. We integrated multi-tissue transcriptomic analysis with GraphDTA, a deep learning model, to screen for potential compound-target interactions of QFPDD in multiple tissues. We predicted 13 key active compounds, 127 potential targets and 27 pathways associated with QFPDD across six different tissues. Notably, oleanolic acid-AXL exhibited leading affinity in the heart, blood, and liver. Molecular docking and molecular dynamics simulation confirmed their strong binding affinity. The robust interaction between oleanolic acid and the AXL receptor suggests that AXL is a promising target for developing clinical intervention strategies. Through the construction of a multi-tissue compound-target interaction network, our study further elucidated the mechanisms through which QFPDD effectively combats COVID-19 in multiple tissues. Our work also establishes a framework for future investigations into the systemic effects of other Traditional Chinese Medicine (TCM) formulas in disease treatment.

PMID:39036847 | DOI:10.1142/S0219720024500161

J Bioinform Comput Biol. 2024 Jul 20:2450015. doi: 10.1142/S021972002450015X. Online ahead of print.

ABSTRACT

The rapid development of single-cell RNA sequencing (scRNA-seq) technology has generated vast amounts of data. However, these data often exhibit batch effects due to various factors such as different time points, experimental personnel, and instruments used, which can obscure the biological differences in the data itself. Based on the characteristics of scRNA-seq data, we designed a dense deep residual network model, referred to as NDnetwork. Subsequently, we combined the NDnetwork model with the MNN method to correct batch effects in scRNA-seq data, and named it the NDMNN method. Comprehensive experimental results demonstrate that the NDMNN method outperforms existing commonly used methods for correcting batch effects in scRNA-seq data. As the scale of single-cell sequencing continues to expand, we believe that NDMNN will be a valuable tool for researchers in the biological community for correcting batch effects in their studies. The source code and experimental results of the NDMNN method can be found at https://github.com/mustang-hub/NDMNN.

PMID:39036845 | DOI:10.1142/S021972002450015X

Osteoarthr Imaging. 2023 Mar;3(1):100087. doi: 10.1016/j.ostima.2023.100087. Epub 2023 Feb 10.

ABSTRACT

OBJECTIVE: To evaluate whether the deep learning (DL) segmentation methods from the six teams that participated in the IWOAI 2019 Knee Cartilage Segmentation Challenge are appropriate for quantifying cartilage loss in longitudinal clinical trials.

DESIGN: We included 556 subjects from the Osteoarthritis Initiative study with manually read cartilage volume scores for the baseline and 1-year visits. The teams used their methods originally trained for the IWOAI 2019 challenge to segment the 1130 knee MRIs. These scans were anonymized and the teams were blinded to any subject or visit identifiers. Two teams also submitted updated methods. The resulting 9,040 segmentations are available online.The segmentations included tibial, femoral, and patellar compartments. In post-processing, we extracted medial and lateral tibial compartments and geometrically defined central medial and lateral femoral sub-compartments. The primary study outcome was the sensitivity to measure cartilage loss as defined by the standardized response mean (SRM).

RESULTS: For the tibial compartments, several of the DL segmentation methods had SRMs similar to the gold standard manual method. The highest DL SRM was for the lateral tibial compartment at 0.38 (the gold standard had 0.34). For the femoral compartments, the gold standard had higher SRMs than the automatic methods at 0.31/0.30 for medial/lateral compartments.

CONCLUSION: The lower SRMs for the DL methods in the femoral compartments at 0.2 were possibly due to the simple sub-compartment extraction done during post-processing. The study demonstrated that state-of-the-art DL segmentation methods may be used in standardized longitudinal single-scanner clinical trials for well-defined cartilage compartments.

PMID:39036792 | PMC:PMC11258861 | DOI:10.1016/j.ostima.2023.100087

J Community Hosp Intern Med Perspect. 2024 May 7;14(3):37-43. doi: 10.55729/2000-9666.1341. eCollection 2024.

ABSTRACT

Gastrointestinal diseases are increasing in global prevalence. As a result, the contribution to both mortality and healthcare costs is increasing. While interventions utilizing scoping techniques or ultrasound are crucial to both the timely diagnosis and management of illness, a few limitations are associated with these techniques. Artificial intelligence, using computerized diagnoses, deep learning systems, or neural networks, is increasingly being employed in multiple aspects of medicine to improve the characteristics and outcomes of these tools. Therefore, this review aims to discuss applications of artificial intelligence in endoscopy, colonoscopy, and endoscopic ultrasound.

PMID:39036586 | PMC:PMC11259475 | DOI:10.55729/2000-9666.1341

J Natl Cancer Cent. 2022 Oct 11;2(4):306-313. doi: 10.1016/j.jncc.2022.09.003. eCollection 2022 Dec.

ABSTRACT

Precision radiotherapy is a critical and indispensable cancer treatment means in the modern clinical workflow with the goal of achieving "quality-up and cost-down" in patient care. The challenge of this therapy lies in developing computerized clinical-assistant solutions with precision, automation, and reproducibility built-in to deliver it at scale. In this work, we provide a comprehensive yet ongoing, incomplete survey of and discussions on the recent progress of utilizing advanced deep learning, semantic organ parsing, multimodal imaging fusion, neural architecture search and medical image analytical techniques to address four corner-stone problems or sub-problems required by all precision radiotherapy workflows, namely, organs at risk (OARs) segmentation, gross tumor volume (GTV) segmentation, metastasized lymph node (LN) detection, and clinical tumor volume (CTV) segmentation. Without loss of generality, we mainly focus on using esophageal and head-and-neck cancers as examples, but the methods can be extrapolated to other types of cancers. High-precision, automated and highly reproducible OAR/GTV/LN/CTV auto-delineation techniques have demonstrated their effectiveness in reducing the inter-practitioner variabilities and the time cost to permit rapid treatment planning and adaptive replanning for the benefit of patients. Through the presentation of the achievements and limitations of these techniques in this review, we hope to encourage more collective multidisciplinary precision radiotherapy workflows to transpire.

PMID:39036546 | PMC:PMC11256697 | DOI:10.1016/j.jncc.2022.09.003

Front Plant Sci. 2024 Jul 5;15:1412988. doi: 10.3389/fpls.2024.1412988. eCollection 2024.

ABSTRACT

Plant diseases significantly impact crop productivity and quality, posing a serious threat to global agriculture. The process of identifying and categorizing these diseases is often time-consuming and prone to errors. This research addresses this issue by employing a convolutional neural network and support vector machine (CNN-SVM) hybrid model to classify diseases in four economically important crops: strawberries, peaches, cherries, and soybeans. The objective is to categorize 10 classes of diseases, with six diseased classes and four healthy classes, for these crops using the deep learning-based CNN-SVM model. Several pre-trained models, including VGG16, VGG19, DenseNet, Inception, MobileNetV2, MobileNet, Xception, and ShuffleNet, were also trained, achieving accuracy ranges from 53.82% to 98.8%. The proposed model, however, achieved an average accuracy of 99.09%. While the proposed model's accuracy is comparable to that of the VGG16 pre-trained model, its significantly lower number of trainable parameters makes it more efficient and distinctive. This research demonstrates the potential of the CNN-SVM model in enhancing the accuracy and efficiency of plant disease classification. The CNN-SVM model was selected over VGG16 and other models due to its superior performance metrics. The proposed model achieved a 99% F1-score, a 99.98% Area Under the Curve (AUC), and a 99% precision value, demonstrating its efficacy. Additionally, class activation maps were generated using the Gradient Weighted Class Activation Mapping (Grad-CAM) technique to provide a visual explanation of the detected diseases. A heatmap was created to highlight the regions requiring classification, further validating the model's accuracy and interpretability.

PMID:39036360 | PMC:PMC11257924 | DOI:10.3389/fpls.2024.1412988

Front Plant Sci. 2024 Jul 5;15:1415297. doi: 10.3389/fpls.2024.1415297. eCollection 2024.

ABSTRACT

Tomatoes, widely cherished for their high nutritional value, necessitate precise ripeness identification and selective harvesting of mature fruits to significantly enhance the efficiency and economic benefits of tomato harvesting management. Previous studies on intelligent harvesting often focused solely on identifying tomatoes as the target, lacking fine-grained detection of tomato ripeness. This deficiency leads to the inadvertent harvesting of immature and rotten fruits, resulting in economic losses. Moreover, in natural settings, uneven illumination, occlusion by leaves, and fruit overlap hinder the precise assessment of tomato ripeness by robotic systems. Simultaneously, the demand for high accuracy and rapid response in tomato ripeness detection is compounded by the need for making the model lightweight to mitigate hardware costs. This study proposes a lightweight model named PDSI-RTDETR to address these challenges. Initially, the PConv_Block module, integrating partial convolution with residual blocks, replaces the Basic_Block structure in the legacy backbone to alleviate computing load and enhance feature extraction efficiency. Subsequently, a deformable attention module is amalgamated with intra-scale feature interaction structure, bolstering the capability to extract detailed features for fine-grained classification. Additionally, the proposed slimneck-SSFF feature fusion structure, merging the Scale Sequence Feature Fusion framework with a slim-neck design utilizing GSConv and VoVGSCSP modules, aims to reduce volume of computation and inference latency. Lastly, by amalgamating Inner-IoU with EIoU to formulate Inner-EIoU, replacing the original GIoU to expedite convergence while utilizing auxiliary frames enhances small object detection capabilities. Comprehensive assessments validate that the PDSI-RTDETR model achieves an average precision mAP50 of 86.8%, marking a 3.9% enhancement over the original RT-DETR model, and a 38.7% increase in FPS. Furthermore, the GFLOPs of PDSI-RTDETR have been diminished by 17.6%. Surpassing the baseline RT-DETR and other prevalent methods regarding precision and speed, it unveils its considerable potential for detecting tomato ripeness. When applied to intelligent harvesting robots in the future, this approach can improve the quality of tomato harvesting by reducing the collection of immature and spoiled fruits.

PMID:39036358 | PMC:PMC11257922 | DOI:10.3389/fpls.2024.1415297