RESUMEN

Background: The growing demand for genomic testing and limited access to experts necessitate innovative service models. While chatbots have shown promise in supporting genomic services like pre-test counseling, their use in returning positive genetic results, especially using the more recent large language models (LLMs) remains unexplored. Objective: This study reports the prompt engineering process and intrinsic evaluation of the LLM component of a chatbot designed to support returning positive population-wide genomic screening results. Methods: We used a three-step prompt engineering process, including Retrieval-Augmented Generation (RAG) and few-shot techniques to develop an open-response chatbot. This was then evaluated using two hypothetical scenarios, with experts rating its performance using a 5-point Likert scale across eight criteria: tone, clarity, program accuracy, domain accuracy, robustness, efficiency, boundaries, and usability. Results: The chatbot achieved an overall score of 3.88 out of 5 across all criteria and scenarios. The highest ratings were in Tone (4.25), Usability (4.25), and Boundary management (4.0), followed by Efficiency (3.88), Clarity and Robustness (3.81), and Domain Accuracy (3.63). The lowest-rated criterion was Program Accuracy, which scored 3.25. Discussion: The LLM handled open-ended queries and maintained boundaries, while the lower Program Accuracy rating indicates areas for improvement. Future work will focus on refining prompts, expanding evaluations, and exploring optimal hybrid chatbot designs that integrate LLM components with rule-based chatbot components to enhance genomic service delivery.

RESUMEN

Developmental toxicity (DevTox) tests evaluate the adverse effects of chemical exposures on an organism's development. While large animal tests are currently heavily relied on, the development of new approach methodologies (NAMs) is encouraging industries and regulatory agencies to evaluate these novel assays. Several practical advantages have made C. elegansa useful model for rapid toxicity testing and studying developmental biology. Although the potential to study DevTox is promising, current low-resolution and labor-intensive methodologies prohibit the use of C. elegans for sub-lethal DevTox studies at high throughputs. With the recent availability of a large-scale microfluidic device, vivoChip, we can now rapidly collect 3D high-resolution images of ~ 1,000 C. elegans from 24 different populations. In this paper, we demonstrate DevTox studies using a 2.5D U-Net architecture (vivoBodySeg) that can precisely segment C. elegans in images obtained from vivoChip devices, achieving an average Dice score of 97.80. The fully automated platform can analyze 36 GB data from each device to phenotype multiple body parameters within 35 min on a desktop PC at speeds ~ 140x faster than the manual analysis. Highly reproducible DevTox parameters (4-8% CV) and additional autofluorescence-based phenotypes allow us to assess the toxicity of chemicals with high statistical power.

RESUMEN

OBJECTIVE: We developed a few-shot learning (FSL) framework for the diagnosis of osteopenia and osteoporosis in knee X-ray images. METHODS: Computer vision models containing deep convolutional neural networks were fine-tuned to enable generalization from natural images (ImageNet) to chest X-ray images (normal vs. pneumonia, base images). Then, a series of automated machine learning classifiers based on the Euclidean distances of base images were developed to make predictions for novel images (normal vs. osteopenia vs. osteoporosis). The performance of the FSL framework was compared with that of junior and senior radiologists. In addition, the gradient-weighted class activation mapping algorithm was used for visual interpretation. RESULTS: In Cohort #1, the mean accuracy (0.728) and sensitivity (0.774) of the FSL models were higher than those of the radiologists (0.512 and 0.448). A diagnostic pipeline of FSL model (first)-radiologists (second) achieved better performance (0.653 accuracy, 0.582 sensitivity, and 0.816 specificity) than radiologists alone. In Cohort #2, the diagnostic pipeline also showed improved performance. CONCLUSIONS: The FSL framework yielded practical performance with respect to the diagnosis of osteopenia and osteoporosis in comparison with radiologists. This retrospective study supports the use of promising FSL methods in computer-aided diagnosis tasks involving limited samples.

Asunto(s)

RESUMEN

Metric-based meta-learning methods have demonstrated remarkable success in the domain of few-shot image classification. However, their performance is significantly contingent upon the choice of metric and the feature representation for the support classes. Current approaches, which predominantly rely on holistic image features, may inadvertently disregard critical details necessary for novel tasks, a phenomenon known as "supervision collapse". Moreover, relying solely on visual features to characterize support classes can prove to be insufficient, particularly in scenarios involving limited sample sizes. In this paper, we introduce an innovative framework named Patch Matching Metric-based Semantic Interaction Meta-Learning (PatSiML), designed to overcome these challenges. To counteract supervision collapse, we have developed a patch matching metric strategy based on the Transformer architecture to transform input images into a set of distinct patch embeddings. This approach dynamically creates task-specific embeddings, facilitated by a graph convolutional network, to formulate precise matching metrics between the support classes and the query image patches. To enhance the integration of semantic knowledge, we have also integrated a label-assisted channel semantic interaction strategy. This strategy merges word embeddings with patch-level visual features across the channel dimension, utilizing a sophisticated language model to combine semantic understanding with visual information. Our empirical findings across four diverse datasets reveal that the PatSiML method achieves a classification accuracy improvement of 0.65% to 21.15% over existing methodologies, underscoring its robustness and efficacy.

RESUMEN

N-terminal coding sequence (NCS) influences gene expression by impacting the translation initiation rate. The NCS optimization problem is to find an NCS that maximizes gene expression. The problem is important in genetic engineering. However, current methods for NCS optimization such as rational design and statistics-guided approaches are labor-intensive yield only relatively small improvements. This paper introduces a deep learning/synthetic biology codesigned few-shot training workflow for NCS optimization. Our method utilizes k-nearest encoding followed by word2vec to encode the NCS, then performs feature extraction using attention mechanisms, before constructing a time-series network for predicting gene expression intensity, and finally a direct search algorithm identifies the optimal NCS with limited training data. We took green fluorescent protein (GFP) expressed by Bacillus subtilis as a reporting protein of NCSs, and employed the fluorescence enhancement factor as the metric of NCS optimization. Within just six iterative experiments, our model generated an NCS (MLD62) that increased average GFP expression by 5.41-fold, outperforming the state-of-the-art NCS designs. Extending our findings beyond GFP, we showed that our engineered NCS (MLD62) can effectively boost the production of N-acetylneuraminic acid by enhancing the expression of the crucial rate-limiting GNA1 gene, demonstrating its practical utility. We have open-sourced our NCS expression database and experimental procedures for public use.

Asunto(s)

RESUMEN

Introduction: Recently, Google introduced Pathways as its next-generation AI architecture. Pathways must address three critical challenges: learning one general model for several continuous tasks, ensuring tasks can leverage each other without forgetting old tasks, and learning from multi-modal data such as images and audio. Additionally, Pathways must maintain sparsity in both learning and deployment. Current lifelong multi-task learning approaches are inadequate in addressing these challenges. Methods: To address these challenges, we propose SEN, a Sparse and Expandable Network. SEN is designed to handle multiple tasks concurrently by maintaining sparsity and enabling expansion when new tasks are introduced. The network leverages multi-modal data, integrating information from different sources while preventing interference between tasks. Results: The proposed SEN model demonstrates significant improvements in multi-task learning, successfully managing task interference and forgetting. It effectively integrates data from various modalities and maintains efficiency through sparsity during both the learning and deployment phases. Discussion: SEN offers a straightforward yet effective solution to the limitations of current lifelong multi-task learning methods. By addressing the challenges identified in the Pathways architecture, SEN provides a promising approach for developing AI systems capable of learning and adapting over time without sacrificing performance or efficiency.

RESUMEN

Objective: It is challenging to accurately distinguish atypical endometrial hyperplasia (AEH) and endometrial cancer (EC) under routine transvaginal ultrasonic (TVU) detection. Our research aims to use the few-shot learning (FSL) method to identify non-atypical endometrial hyperplasia (NAEH), AEH, and EC based on limited TVU images. Methods: The TVU images of pathologically confirmed NAEH, AEH, and EC patients (n = 33 per class) were split into the support set (SS, n = 3 per class) and the query set (QS, n = 30 per class). Next, we used dual pretrained ResNet50 V2 which pretrained on ImageNet first and then on extra collected TVU images to extract 1*64 eigenvectors from the TVU images in SS and QS. Then, the Euclidean distances were calculated between each TVU image in QS and nine TVU images of SS. Finally, the k-nearest neighbor (KNN) algorithm was used to diagnose the TVU images in QS. Results: The overall accuracy and macro precision of the proposed FSL model in QS were 0.878 and 0.882 respectively, superior to the automated machine learning models, traditional ResNet50 V2 model, junior sonographer, and senior sonographer. When identifying EC, the proposed FSL model achieved the highest precision of 0.964, the highest recall of 0.900, and the highest F1-score of 0.931. Conclusions: The proposed FSL model combining dual pretrained ResNet50 V2 eigenvectors extractor and KNN classifier presented well in identifying NAEH, AEH, and EC patients with limited TVU images, showing potential in the application of computer-aided disease diagnosis.

RESUMEN

The lack of annotated medical images limits the performance of deep learning models, which usually need large-scale labelled datasets. Few-shot learning techniques can reduce data scarcity issues and enhance medical image analysis speed and robustness. This systematic review gives a comprehensive overview of few-shot learning methods for medical image analysis, aiming to establish a standard methodological pipeline for future research reference. With a particular emphasis on the role of meta-learning, we analysed 80 relevant articles published from 2018 to 2023, conducting a risk of bias assessment and extracting relevant information, especially regarding the employed learning techniques. From this, we delineated a comprehensive methodological pipeline shared among all studies. In addition, we performed a statistical analysis of the studies' results concerning the clinical task and the meta-learning method employed while also presenting supplemental information such as imaging modalities and model robustness evaluation techniques. We discussed the findings of our analysis, providing a deep insight into the limitations of the state-of-the-art methods and the most promising approaches. Drawing on our investigation, we yielded recommendations on potential future research directions aiming to bridge the gap between research and clinical practice.

Asunto(s)

RESUMEN

Accurate segmentation of the left atrium (LA) from late gadolinium-enhanced cardiac magnetic resonance (LGE CMR) images is crucial for aiding the treatment of patients with atrial fibrillation. Few-shot learning holds significant potential for achieving accurate LA segmentation with low demand on high-cost labeled LGE CMR data and fast generalization across different centers. However, accurate LA segmentation with few-shot learning is a challenging task due to the low-intensity contrast between the LA and other neighboring organs in LGE CMR images. To address this issue, we propose an Adaptive Dynamic Inference Network (ADINet) that explicitly models the differences between the foreground and background. Specifically, ADINet leverages dynamic collaborative inference (DCI) and dynamic reverse inference (DRI) to adaptively allocate semantic-aware and spatial-specific convolution weights and indication information. These allocations are conditioned on the support foreground and background knowledge, utilizing pixel-wise correlations, for different spatial positions of query images. The convolution weights adapt to different visual patterns based on spatial positions, enabling effective encoding of differences between foreground and background regions. Meanwhile, the indication information adapts to the background visual pattern to reversely decode foreground LA regions, leveraging their spatial complementarity. To promote the learning of ADINet, we propose hierarchical supervision, which enforces spatial consistency and differences between the background and foreground regions through pixel-wise semantic supervision and pixel-pixel correlation supervision. We demonstrated the performance of ADINet on three LGE CMR datasets from different centers. Compared to state-of-the-art methods with ten available samples, ADINet yielded better segmentation performance in terms of four metrics.

Asunto(s)

RESUMEN

The molecular property prediction (MPP) plays a crucial role in the drug discovery process, providing valuable insights for molecule evaluation and screening. Although deep learning has achieved numerous advances in this area, its success often depends on the availability of substantial labeled data. The few-shot MPP is a more challenging scenario, which aims to identify unseen property with only few available molecules. In this paper, we propose an attribute-guided prototype network (APN) to address the challenge. APN first introduces an molecular attribute extractor, which can not only extract three different types of fingerprint attributes (single fingerprint attributes, dual fingerprint attributes, triplet fingerprint attributes) by considering seven circular-based, five path-based, and two substructure-based fingerprints, but also automatically extract deep attributes from self-supervised learning methods. Furthermore, APN designs the Attribute-Guided Dual-channel Attention module to learn the relationship between the molecular graphs and attributes and refine the local and global representation of the molecules. Compared with existing works, APN leverages high-level human-defined attributes and helps the model to explicitly generalize knowledge in molecular graphs. Experiments on benchmark datasets show that APN can achieve state-of-the-art performance in most cases and demonstrate that the attributes are effective for improving few-shot MPP performance. In addition, the strong generalization ability of APN is verified by conducting experiments on data from different domains.

Asunto(s)

RESUMEN

Few-shot learning is often challenged by low generalization performance due to the model is mostly learned with the base classes only. To mitigate the above issues, a few-shot learning method with representative global prototype is proposed in this paper. Specifically, to enhance generalization to novel class, we propose a strategy for jointly training base and novel classes. This process produces prototypes characterizing the class information called representative global prototypes. Additionally, to avoid the problem of data imbalance and prototype bias caused by newly added categories of sparse samples, a novel sample synthesis method is proposed for augmenting more representative samples of novel class. Finally, representative samples and non-representative samples with high uncertainty are selected to enhance the representational and discriminative abilities of the global prototype. Intensive experiments have been conducted on two popular benchmark datasets, and the experimental results show that this method significantly improves the classification ability of few-shot learning tasks and achieves state-of-the-art performance.

RESUMEN

With the advancement of deep learning, related networks have shown strong performance for Hyperspectral Image (HSI) classification. However, these methods face two main challenges in HSI classification: (1) the inability to capture global information of HSI due to the restriction of patch input and (2) insufficient utilization of information from limited labeled samples. To overcome these challenges, we propose an Advanced Global Prototypical Segmentation (AGPS) framework. Within the AGPS framework, we design a patch-free feature extractor segmentation network (SegNet) based on a fully convolutional network (FCN), which processes the entire HSI to capture global information. To enrich the global information extracted by SegNet, we propose a Fusion of Lateral Connection (FLC) structure that fuses the low-level detailed features of the encoder output with the high-level features of the decoder output. Additionally, we propose an Atrous Spatial Pyramid Pooling-Position Attention (ASPP-PA) module to capture multi-scale spatial positional information. Finally, to explore more valuable information from limited labeled samples, we propose an advanced global prototypical representation learning strategy. Building upon the dual constraints of the global prototypical representation learning strategy, we introduce supervised contrastive learning (CL), which optimizes our network with three different constraints. The experimental results of three public datasets demonstrate that our method outperforms the existing state-of-the-art methods.

RESUMEN

Ternary content-addressable memory (TCAM) is promising for data-intensive artificial intelligence applications due to its large-scale parallel in-memory computing capabilities. However, it is still challenging to build a reliable TCAM cell from a single circuit component. Here, we demonstrate a single transistor TCAM based on a floating-gate two-dimensional (2D) ambipolar MoTe2 field-effect transistor with graphene contacts. Our bottom graphene contacts scheme enables gate modulation of the contact Schottky barrier heights, facilitating carrier injection for both electrons and holes. The 2D nature of our channel and contact materials provides device scaling potentials beyond silicon. By integration with a floating-gate stack, a highly reliable nonvolatile memory is achieved. Our TCAM cell exhibits a resistance ratio larger than 1000 and symmetrical complementary states, allowing the implementation of large-scale TCAM arrays. Finally, we show through circuit simulations that in-memory Hamming distance computation is readily achievable based on our TCAM with array sizes up to 128 cells.

RESUMEN

Plant diseases pose significant threats to agriculture, impacting both food safety and public health. Traditional plant disease detection systems are typically limited to recognizing disease categories included in the training dataset, rendering them ineffective against new disease types. Although out-of-distribution (OOD) detection methods have been proposed to address this issue, the impact of fine-tuning paradigms on these methods has been overlooked. This paper focuses on studying the impact of fine-tuning paradigms on the performance of detecting unknown plant diseases. Currently, fine-tuning on visual tasks is mainly divided into visual-based models and visual-language-based models. We first discuss the limitations of large-scale visual language models in this task: textual prompts are difficult to design. To avoid the side effects of textual prompts, we futher explore the effectiveness of purely visual pre-trained models for OOD detection in plant disease tasks. Specifically, we employed five publicly accessible datasets to establish benchmarks for open-set recognition, OOD detection, and few-shot learning in plant disease recognition. Additionally, we comprehensively compared various OOD detection methods, fine-tuning paradigms, and factors affecting OOD detection performance, such as sample quantity. The results show that visual prompt tuning outperforms fully fine-tuning and linear probe tuning in out-of-distribution detection performance, especially in the few-shot scenarios. Notably, the max-logit-based on visual prompt tuning achieves an AUROC score of 94.8 % in the 8-shot setting, which is nearly comparable to the method of fully fine-tuning on the full dataset (95.2 % ), which implies that an appropriate fine-tuning paradigm can directly improve OOD detection performance. Finally, we visualized the prediction distributions of different OOD detection methods and discussed the selection of thresholds. Overall, this work lays the foundation for unknown plant disease recognition, providing strong support for the security and reliability of plant disease recognition systems. We will release our code at https://github.com/JiuqingDong/PDOOD to further advance this field.

Asunto(s)

RESUMEN

Large language models (LLMs) are sophisticated AI-driven models trained on vast sources of natural language data. They are adept at generating responses that closely mimic human conversational patterns. One of the most notable examples is OpenAI's ChatGPT, which has been extensively used across diverse sectors. Despite their flexibility, a significant challenge arises as most users must transmit their data to the servers of companies operating these models. Utilizing ChatGPT or similar models online may inadvertently expose sensitive information to the risk of data breaches. Therefore, implementing LLMs that are open source and smaller in scale within a secure local network becomes a crucial step for organizations where ensuring data privacy and protection has the highest priority, such as regulatory agencies. As a feasibility evaluation, we implemented a series of open-source LLMs within a regulatory agency's local network and assessed their performance on specific tasks involving extracting relevant clinical pharmacology information from regulatory drug labels. Our research shows that some models work well in the context of few- or zero-shot learning, achieving performance comparable, or even better than, neural network models that needed thousands of training samples. One of the models was selected to address a real-world issue of finding intrinsic factors that affect drugs' clinical exposure without any training or fine-tuning. In a dataset of over 700 000 sentences, the model showed a 78.5% accuracy rate. Our work pointed to the possibility of implementing open-source LLMs within a secure local network and using these models to perform various natural language processing tasks when large numbers of training examples are unavailable.

Asunto(s)

RESUMEN

Accurately assigning standardized diagnosis and procedure codes from clinical text is crucial for healthcare applications. However, this remains challenging due to the complexity of medical language. This paper proposes a novel model that incorporates extreme multi-label classification tasks to enhance International Classification of Diseases (ICD) coding. The model utilizes deformable convolutional neural networks to fuse representations from hidden layer outputs of pre-trained language models and external medical knowledge embeddings fused using a multimodal approach to provide rich semantic encodings for each code. A probabilistic label tree is constructed based on the hierarchical structure existing in ICD labels to incorporate ontological relationships between ICD codes and enable structured output prediction. Experiments on medical code prediction on the MIMIC-III database demonstrate competitive performance, highlighting the benefits of this technique for robust clinical code assignment.

Asunto(s)

RESUMEN

Background: The automated classification of histological images is crucial for the diagnosis of cancer. The limited availability of well-annotated datasets, especially for rare cancers, poses a significant challenge for deep learning methods due to the small number of relevant images. This has led to the development of few-shot learning approaches, which bear considerable clinical importance, as they are designed to overcome the challenges of data scarcity in deep learning for histological image classification. Traditional methods often ignore the challenges of intraclass diversity and interclass similarities in histological images. To address this, we propose a novel mutual reconstruction network model, aimed at meeting these challenges and improving the few-shot classification performance of histological images. Methods: The key to our approach is the extraction of subtle and discriminative features. We introduce a feature enhancement module (FEM) and a mutual reconstruction module to increase differences between classes while reducing variance within classes. First, we extract features of support and query images using a feature extractor. These features are then processed by the FEM, which uses a self-attention mechanism for self-reconstruction of features, enhancing the learning of detailed features. These enhanced features are then input into the mutual reconstruction module. This module uses enhanced support features to reconstruct enhanced query features and vice versa. The classification of query samples is based on weighted calculations of the distances between query features and reconstructed query features and between support features and reconstructed support features. Results: We extensively evaluated our model using a specially created few-shot histological image dataset. The results showed that in a 5-way 10-shot setup, our model achieved an impressive accuracy of 92.09%. This is a 23.59% improvement in accuracy compared to the model-agnostic meta-learning (MAML) method, which does not focus on fine-grained attributes. In the more challenging, 5-way 1-shot setting, our model also performed well, demonstrating a 18.52% improvement over the ProtoNet, which does not address this challenge. Additional ablation studies indicated the effectiveness and complementary nature of each module and confirmed our method's ability to parse small differences between classes and large variations within classes in histological images. These findings strongly support the superiority of our proposed method in the few-shot classification of histological images. Conclusions: The mutual reconstruction network provides outstanding performance in the few-shot classification of histological images, successfully overcoming the challenges of similarities between classes and diversity within classes. This marks a significant advancement in the automated classification of histological images.

RESUMEN

Cross-domain few-shot Learning (CDFSL) is proposed to first pre-train deep models on a source domain dataset where sufficient data is available, and then generalize models to target domains to learn from only limited data. However, the gap between the source and target domains greatly hampers the generalization and target-domain few-shot finetuning. To address this problem, we analyze the domain gap from the aspect of frequency-domain analysis. We find the domain gap could be reflected by the compositions of source-domain spectra, and the lack of compositions in the source datasets limits the generalization. Therefore, we aim to expand the coverage of spectra composition in the source datasets to help the source domain cover a larger range of possible target-domain information, to mitigate the domain gap. To achieve this goal, we propose the Spectral Decomposition and Transformation (SDT) method, which first randomly decomposes the spectrogram of the source datasets into orthogonal bases, and then randomly samples different coordinates in the space formed by these bases. We integrate the above process into a data augmentation module, and further design a two-stream network to handle augmented images and original images respectively. Experimental results show that our method achieves state-of-the-art performance in the CDFSL benchmark dataset.

Asunto(s)

RESUMEN

AIMS: Recent advances in artificial intelligence, particularly with large language models like GPT-4Vision (GPT-4V)-a derivative feature of ChatGPT-have expanded the potential for medical image interpretation. This study evaluates the accuracy of GPT-4V in image classification tasks of histopathological images and compares its performance with a traditional convolutional neural network (CNN). METHODS: We utilised 1520 images, including haematoxylin and eosin staining and tau immunohistochemistry, from patients with various neurodegenerative diseases, such as Alzheimer's disease (AD), progressive supranuclear palsy (PSP) and corticobasal degeneration (CBD). We assessed GPT-4V's performance using multi-step prompts to determine how textual context influences image interpretation. We also employed few-shot learning to enhance improvements in GPT-4V's diagnostic performance in classifying three specific tau lesions-astrocytic plaques, neuritic plaques and tufted astrocytes-and compared the outcomes with the CNN model YOLOv8. RESULTS: GPT-4V accurately recognised staining techniques and tissue origin but struggled with specific lesion identification. The interpretation of images was notably influenced by the provided textual context, which sometimes led to diagnostic inaccuracies. For instance, when presented with images of the motor cortex, the diagnosis shifted inappropriately from AD to CBD or PSP. However, few-shot learning markedly improved GPT-4V's diagnostic capabilities, enhancing accuracy from 40% in zero-shot learning to 90% with 20-shot learning, matching the performance of YOLOv8, which required 100-shot learning to achieve the same accuracy. CONCLUSIONS: Although GPT-4V faces challenges in independently interpreting histopathological images, few-shot learning significantly improves its performance. This approach is especially promising for neuropathology, where acquiring extensive labelled datasets is often challenging.

Asunto(s)