Biomedical Tasks Research Articles

Context Prior Guided Semantic Modeling for Biomedical Image Segmentation

Most state-of-the-art deep networks proposed for biomedical image segmentation are developed based on U-Net. While remarkable success has been achieved, its inherent limitations hinder it from yielding more precise segmentation. First, its receptive field is limited due to the fixed kernel size, which prevents the network from modeling global context information. Second, when spatial information captured by shallower layer is directly transmitted to higher layers by skip connections, the process inevitably introduces noise and irrelevant information to feature maps and blurs their semantic meanings. In this article, we propose a novel segmentation network equipped with a new context prior guidance (CPG) module to overcome these limitations for biomedical image segmentation, namely context prior guidance network (CPG-Net). Specifically, we first extract a set of context priors under the supervision of a coarse segmentation and then employ these context priors to model the global context information and bridge the spatial-semantic gap between high-level features and low-level features. The CPG module contains two major components: context prior representation (CPR) and semantic complement flow (SCF). CPR is used to extract pixels belonging to the same objects and hence produce more discriminative features to distinguish different objects. We further introduce deep semantic information for each CPR by the SCF mechanism to compensate the semantic information diluted during the decoding. We extensively evaluate the proposed CPG-Net on three famous biomedical image segmentation tasks with diverse imaging modalities and semantic environments. Experimental results demonstrate the effectiveness of our network, consistently outperforming state-of-the-art segmentation networks in all the three tasks. Codes are available at https://github.com/zzw-szu/CPGNet .

Multi-View Graph Neural Architecture Search for Biomedical Entity and Relation Extraction.

Recently, graph neural architecture search (GNAS) frameworks have been successfully used to automatically design the optimal neural architectures for many problems such as node classification and graph classification. In the existing GNAS frameworks, the designed graph neural network (GNN) architectures learn the representation of homogenous graphs with one type of relationship connecting two nodes. However, multi-view graphs, where each view represents a type of relationship among nodes, are ubiquitous in the real world. The traditional GNAS frameworks learn the graph representation without considering the interactions between nodes and multiple relationships, so they fail to solve multi-view graph-based problems, such as multi-view graphs modelling the biomedical entity and relation extraction tasks. In this paper, we propose MVGNAS, a multi-view graph neural network automatic modelling framework for biomedical entity and relation extraction, to resolve this challenge. In MVGNAS, we propose an automatic multi-view representation learning to learn low-dimensional representations of nodes that capture multiple relationships in a multi-view graph, representing the first research work in literature to solve the problem of multi-view graph representation learning architecture search for biomedical entity and relation extraction tasks. The experimental results demonstrate that MVGNAS can achieve the best performance in biomedical entity and relation extraction tasks against the state-of-the-art baseline methods.

On the effectiveness of compact biomedical transformers.

Language models pre-trained on biomedical corpora, such as BioBERT, have recently shown promising results on downstream biomedical tasks. Many existing pre-trained models, on the other hand, are resource-intensive and computationally heavy owing to factors such as embedding size, hidden dimension and number of layers. The natural language processing community has developed numerous strategies to compress these models utilizing techniques such as pruning, quantization and knowledge distillation, resulting in models that are considerably faster, smaller and subsequently easier to use in practice. By the same token, in this article, we introduce six lightweight models, namely, BioDistilBERT, BioTinyBERT, BioMobileBERT, DistilBioBERT, TinyBioBERT and CompactBioBERT which are obtained either by knowledge distillation from a biomedical teacher or continual learning on the Pubmed dataset. We evaluate all of our models on three biomedical tasks and compare them with BioBERT-v1.1 to create the best efficient lightweight models that perform on par with their larger counterparts. We trained six different models in total, with the largest model having 65 million in parameters and the smallest having 15 million; a far lower range of parameters compared with BioBERT's 110M. Based on our experiments on three different biomedical tasks, we found that models distilled from a biomedical teacher and models that have been additionally pre-trained on the PubMed dataset can retain up to 98.8% and 98.6% of the performance of the BioBERT-v1.1, respectively. Overall, our best model below 30 M parameters is BioMobileBERT, while our best models over 30 M parameters are DistilBioBERT and CompactBioBERT, which can keep up to 98.2% and 98.8% of the performance of the BioBERT-v1.1, respectively. Codes are available at: https://github.com/nlpie-research/Compact-Biomedical-Transformers. Trained models can be accessed at: https://huggingface.co/nlpie.

Efficacy improvement in searching MEDLINE database using a novel PubMed visual analytic system: EEEvis.

PubMed is the most extensively used database and search engine in the biomedical and healthcare fields. However, users could experience several difficulties in acquiring their target papers facing massive numbers of search results, especially in their unfamiliar fields. Therefore, we developed a novel user interface for PubMed and conducted three steps of study: step A, a preliminary user survey with 76 medical experts regarding the current usability for the biomedical literature search task at PubMed; step B is implementing EEEvis, a novel interactive visual analytic system for the search task; step C, a randomized user study comparing PubMed and EEEvis. First, we conducted a Google survey of 76 medical experts regarding the unmet needs of PubMed and the user requirements for a novel search interface. According to the data of preliminary Google survey, we implemented a novel interactive visual analytic system for biomedical literature search. This EEEvis provides enhanced literature data analysis functions including (1) an overview of the bibliographic features including publication date, citation count, and impact factors, (2) an overview of the co-authorship network, and (3) interactive sorting, filtering, and highlighting. In the randomized user study of 24 medical experts, the search speed of EEEvis was not inferior to PubMed in the time to reach the first article (median difference 3 sec, 95% CI -2.1 to 8.5, P = 0.535) nor in the search completion time (median difference 8 sec, 95% CI -4.7 to 19.1, P = 0.771). However, 22 participants (91.7%) responded that they are willing to use EEEvis as their first choice for a biomedical literature search task, and 21 participants (87.5%) answered the bibliographic sorting and filtering functionalities of EEEvis as a major advantage. EEEvis could be a supplementary interface for PubMed that can enhance the user experience in the search for biomedical literature.

Modified Double U-Net Architecture for Medical Image Segmentation

Semantic segmentation is the process of labeling each pixel of an input image with its appropriate class. In biomedical image processing, semantic segmentation is a critical preprocessing step. After the evolution of deep learning, specifically, the U-Net, which is based on the encoder–decoder model, researchers have extensively used several modified versions of U-Net for semantic segmentation. This manuscript presents a novel architecture called modified Double U-Net for various biomedical image segmentation tasks. The modified Double U-Net takes full advantage of Double U-Net and ensemble learning. It is the combination of two U-Net architectures stacked on top of each other. The first U-Net uses an ensemble of pretrained Xception, DenseNet, and VGG-19. We have deliberately used a pretrained model so that the features learned from the ImageNet classification task can be reused for our semantic segmentation task. Another U-Net is stacked at the bottom to capture more information that can be used in our semantic segmentation task. The performance of our proposed model has been evaluated on five different medical datasets, namely, the Data Science Bowl Challenge-2018, the CVC-ClinicDB dataset, which has complex images, such as smaller and flat polyps, the ISIC-2018 challenge dataset, the Kvasir-Instrument dataset, and the INBreast dataset achieving state-of-the-art performance. Conducting fivefold cross-validation on the five datasets mentioned above intersection over union of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$89.13~\pm ~2.88$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$85.22~\pm ~1.26$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$83.13~\pm ~3.56$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$85.22~\pm ~1.26$ </tex-math></inline-formula> , and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$95.22~\pm ~2.56$ </tex-math></inline-formula> were obtained.

Attention Mechanism Trained with Small Datasets for Biomedical Image Segmentation

The understanding of long-range pixel–pixel dependencies plays a vital role in image segmentation. The use of a CNN plus an attention mechanism still has room for improvement, since existing transformer-based architectures require many thousands of annotated training samples to model long-range spatial dependencies. This paper presents a smooth attention branch (SAB), a novel architecture that simplifies the understanding of long-range pixel–pixel dependencies for biomedical image segmentation in small datasets. The SAB is essentially a modified attention operation that implements a subnetwork via reshaped feature maps instead of directly calculating a softmax value over the attention score for each input. The SAB fuses multilayer attentive feature maps to learn visual attention in multilevel features. We also introduce position blurring and inner cropping specifically for small-scale datasets to prevent overfitting. Furthermore, we redesign the skip pathway for the reduction of the semantic gap between every captured feature of the contracting and expansive path. We evaluate the architecture of U-Net with the SAB (SAB-Net) by comparing it with the original U-Net and widely used transformer-based models across multiple biomedical image segmentation tasks related to the Brain MRI, Heart MRI, Liver CT, Spleen CT, and Colonoscopy datasets. Our training set was made of random 100 images of the original training set, since our goal was to adopt attention mechanisms for biomedical image segmentation tasks with small-scale labeled data. An ablation study conducted on the brain MRI test set demonstrated that every proposed method achieved an improvement in biomedical image segmentation. Integrating the proposed methods helped the resulting models consistently achieve outstanding performance on the above five biomedical segmentation tasks. In particular, the proposed method with U-Net improved its segmentation performance over that of the original U-Net by 13.76% on the Brain MRI dataset. We proposed several novel methods to address the need for modeling long-range pixel–pixel dependencies in small-scale biomedical image segmentation. The experimental results illustrated that each method could improve the medical image segmentation accuracy to various degrees. Moreover, SAB-Net, which integrated all proposed methods, consistently achieved outstanding performance on the five biomedical segmentation tasks.

Negation-based transfer learning for improving biomedical Named Entity Recognition and Relation Extraction

Background and Objectives:Named Entity Recognition (NER) and Relation Extraction (RE) are two of the most studied tasks in biomedical Natural Language Processing (NLP). The detection of specific terms and entities and the relationships between them are key aspects for the development of more complex automatic systems in the biomedical field. In this work, we explore transfer learning techniques for incorporating information about negation into systems performing NER and RE. The main purpose of this research is to analyse to what extent the successful detection of negated entities in separate tasks helps in the detection of biomedical entities and their relationships. Methods:Three neural architectures are proposed in this work, all of them mainly based on Bidirectional Long Short-Term Memory (Bi-LSTM) networks and Conditional Random Fields (CRFs). While the first architecture is devoted to detecting triggers and scopes of negated entities in any domain, two specific models are developed for performing isolated NER tasks and joint NER and RE tasks in the biomedical domain. Then, weights related to negation detection learned by the first architecture are incorporated into those last models. Two different languages, Spanish and English, are taken into account in the experiments. Results:Performance of the biomedical models is analysed both when the weights of the neural networks are randomly initialized, and when weights from the negation detection model are incorporated into them. Improvements of around 3.5% of F-Measure in the English language and more than 7% in the Spanish language are achieved in the NER task, while the NER+RE task increases F-Measure scores by more than 13% for the NER submodel and around 2% for the RE submodel. Conclusions:The obtained results allow us to conclude that negation-based transfer learning techniques are appropriate for performing biomedical NER and RE tasks. These results highlight the importance of detecting negation for improving the identification of biomedical entities and their relationships. The explored techniques show robustness by maintaining consistent results and improvements across different tasks and languages.

Functional Annotation and Analysis of Genetic Variants

The process of functional annotation of human genetic variants is important for some significant biomedical tasks like understanding functional genomics and gene-disease associations. Moreover, genetic variants that lead to pathogenic mutations can have harmful consequences which may lead to certain medical conditions or diseases. This paper investigates and presents two methodologies utilizing the Gene Ontology (GO) for functional annotation of genetic variants (and human gene mutations): (1) using the concept of term enrichment from the biological process taxonomy in the gene ontology, and (2) using the concept of least common subsumer (LCS) within the gene ontology tree. The second methodology induces the most significant and accurate functions for a given set of variants having one common aspect, e.g. specific disease. This method is based on the structure of the directed acyclic graph of GO to induce and identify the most significant LCS’s to be used for functionally annotating the variants under investigation. We applied the methods on a large sets of genetic variants causing mutations. Our method can determine important functions and with significance level of p<0.02, the outcomes and results of the method are biologically significant. We found that certain ontology annotations are more related to mutations through certain genes compared with normal bp functions (biological process terms) in GO; for example, one of these bp functions is {GO:0031325; positive regulation of cellular metabolic process}. The results are basically important and suggest that a mutation can be annotated with functions from the gene ontology, e.g. biological process aspect, just like the genes. This outcome may contribute into a more complete understanding of mutation-gene-disease relationships, mutation pathogenicity, and understanding disease mechanisms..

A new hybrid framework based on deep neural networks and JAYA optimization algorithm for feature selection using SVM applied to classification of acute lymphoblastic Leukaemia

ABSTRACT Identification of Acute lymphoblastic leukemia (ALL) in microscopic images is one of the most challenging tasks in medical image analysis. Despite a wide variety of image processing and deep learning techniques, the task of extracting features from ALL images and selecting the proper features from these redundant and high-dimensional feature space set, and then detecting ALL cells is still a complex issue. In this study, we present a new hybrid two-layer framework to construct an appropriate subset of features. In the first layer of the proposed method, image segmentation is implemented using an improved modified First-Spike-based approach integrated with a Gaussian function. Then a developed deep residual architecture is employed to extract the features. In the second layer, a powerful and reliable meta-heuristic algorithm known as the JAYA optimization algorithm is adopted for feature selection due to its computational efficiency. Finally, a support vector machine (SVM) is used to classify ALL images. To show the effectiveness of the proposed model, it is applied on microscopic images of blood samples from ALL images (ALL-IDB) and ISBI-2019 C-NMC dataset. The results show the superiority of the model to be an appropriate choice for future biomedical imaging tasks.

Predicting drug characteristics using biomedical text embedding

BackgroundDrug–drug interactions (DDIs) are preventable causes of medical injuries and often result in doctor and emergency room visits. Previous research demonstrates the effectiveness of using matrix completion approaches based on known drug interactions to predict unknown Drug–drug interactions. However, in the case of a new drug, where there is limited or no knowledge regarding the drug’s existing interactions, such an approach is unsuitable, and other drug’s preferences can be used to accurately predict new Drug–drug interactions.MethodsWe propose adjacency biomedical text embedding (ABTE) to address this limitation by using a hybrid approach which combines known drugs’ interactions and the drug’s biomedical text embeddings to predict the DDIs of both new and well known drugs.ResultsOur evaluation demonstrates the superiority of this approach compared to recently published DDI prediction models and matrix factorization-based approaches. Furthermore, we compared the use of different text embedding methods in ABTE, and found that the concept embedding approach, which involves biomedical information in the embedding process, provides the highest performance for this task. Additionally, we demonstrate the effectiveness of leveraging biomedical text embedding for additional drugs’ biomedical prediction task by presenting text embedding’s contribution to a multi-modal pregnancy drug safety classification.ConclusionText and concept embeddings created by analyzing a domain-specific large-scale biomedical corpora can be used for predicting drug-related properties such as Drug–drug interactions and drug safety prediction. Prediction models based on the embeddings resulted in comparable results to hand-crafted features, however text embeddings do not require manual categorization or data collection and rely solely on the published literature.

Calibrating the Dice Loss to Handle Neural Network Overconfidence for Biomedical Image Segmentation

The Dice similarity coefficient (DSC) is both a widely used metric and loss function for biomedical image segmentation due to its robustness to class imbalance. However, it is well known that the DSC loss is poorly calibrated, resulting in overconfident predictions that cannot be usefully interpreted in biomedical and clinical practice. Performance is often the only metric used to evaluate segmentations produced by deep neural networks, and calibration is often neglected. However, calibration is important for translation into biomedical and clinical practice, providing crucial contextual information to model predictions for interpretation by scientists and clinicians. In this study, we provide a simple yet effective extension of the DSC loss, named the DSC++ loss, that selectively modulates the penalty associated with overconfident, incorrect predictions. As a standalone loss function, the DSC++ loss achieves significantly improved calibration over the conventional DSC loss across six well-validated open-source biomedical imaging datasets, including both 2D binary and 3D multi-class segmentation tasks. Similarly, we observe significantly improved calibration when integrating the DSC++ loss into four DSC-based loss functions. Finally, we use softmax thresholding to illustrate that well calibrated outputs enable tailoring of recall-precision bias, which is an important post-processing technique to adapt the model predictions to suit the biomedical or clinical task. The DSC++ loss overcomes the major limitation of the DSC loss, providing a suitable loss function for training deep learning segmentation models for use in biomedical and clinical practice. Source code is available at https://github.com/mlyg/DicePlusPlus.

AID-U-Net: An Innovative Deep Convolutional Architecture for Semantic Segmentation of Biomedical Images.

Semantic segmentation of biomedical images found its niche in screening and diagnostic applications. Recent methods based on deep learning convolutional neural networks have been very effective, since they are readily adaptive to biomedical applications and outperform other competitive segmentation methods. Inspired by the U-Net, we designed a deep learning network with an innovative architecture, hereafter referred to as AID-U-Net. Our network consists of direct contracting and expansive paths, as well as a distinguishing feature of containing sub-contracting and sub-expansive paths. The implementation results on seven totally different databases of medical images demonstrated that our proposed network outperforms the state-of-the-art solutions with no specific pre-trained backbones for both 2D and 3D biomedical image segmentation tasks. Furthermore, we showed that AID-U-Net dramatically reduces time inference and computational complexity in terms of the number of learnable parameters. The results further show that the proposed AID-U-Net can segment different medical objects, achieving an improved 2D F1-score and 3D mean BF-score of 3.82% and 2.99%, respectively.

Participation and chronic illness: Nurses’ perceptions in primary care in Brazil, Germany, and Spain

Abstract Background Many chronically ill persons are challenged by integrating the illness in everyday life and making ‘competent’ decisions on their life and care. In multiprofessional primary care, promoting clients’ self-management and strengthening their abilities to participate in everyday life is increasingly recognized as a nursing task. This study investigates facilitating and inhibiting conditions that nurses experience when exercising this task. Methods Drawing upon a phenomenological approach, we conducted guided interviews with 34 practicing nurses and 23 key informants with advanced knowledge of primary health care nursing practice in Brazil, Germany, and Spain. The interviews were analysed using structuring content analysis. Results The interviewees see competencies of nurses to establish trusting relationships with chronically ill clients as key to greater client participation. Nurses, however, state that bonding with clients can be time-consuming and exhausting. They consider it fundamental that physicians and other professionals value nurses’ efforts towards stronger client participation as a way forward to reach for person-oriented primary care. They criticize that especially physicians value biomedical tasks more than enabling participation. Referring to primary health care organisation, nurses experience that pressure of time through a growing number of routine and administrative tasks inhibits their efforts to strengthen clients’ participation. Conclusions To promote the participation of clients with chronic illnesses in their everyday life and in care, relationship building with clients and self-management support needs to be acknowledged as an important scope of practice approached by nurses. To be able to unfold the potentials nurses need to be equipped with sufficient time and skills.

Critical assessment of transformer-based AI models for German clinical notes

Healthcare data such as clinical notes are primarily recorded in an unstructured manner. If adequately translated into structured data, they can be utilized for health economics and set the groundwork for better individualized patient care. To structure clinical notes, deep-learning methods, particularly transformer-based models like Bidirectional Encoder Representations from Transformers (BERT), have recently received much attention. Currently, biomedical applications are primarily focused on the English language. While general-purpose German-language models such as GermanBERT and GottBERT have been published, adaptations for biomedical data are unavailable. This study evaluated the suitability of existing and novel transformer-based models for the German biomedical and clinical domain. We used 8 transformer-based models and pre-trained 3 new models on a newly generated biomedical corpus, and systematically compared them with each other. We annotated a new dataset of clinical notes and used it with 4 other corpora (BRONCO150, CLEF eHealth 2019 Task 1, GGPONC, and JSynCC) to perform named entity recognition (NER) and document classification tasks. General-purpose language models can be used effectively for biomedical and clinical natural language processing (NLP) tasks, still, our newly trained BioGottBERT model outperformed GottBERT on both clinical NER tasks. However, training new biomedical models from scratch proved ineffective. The domain-adaptation strategy's potential is currently limited due to a lack of pre-training data. Since general-purpose language models are only marginally inferior to domain-specific models, both options are suitable for developing German-language biomedical applications. General-purpose language models perform remarkably well on biomedical and clinical NLP tasks. If larger corpora become available in the future, domain-adapting these models may improve performances.

BioGPT: generative pre-trained transformer for biomedical text generation and mining.

Pre-trained language models have attracted increasing attention in the biomedical domain, inspired by their great success in the general natural language domain. Among the two main branches of pre-trained language models in the general language domain, i.e. BERT (and its variants) and GPT (and its variants), the first one has been extensively studied in the biomedical domain, such as BioBERT and PubMedBERT. While they have achieved great success on a variety of discriminative downstream biomedical tasks, the lack of generation ability constrains their application scope. In this paper, we propose BioGPT, a domain-specific generative Transformer language model pre-trained on large-scale biomedical literature. We evaluate BioGPT on six biomedical natural language processing tasks and demonstrate that our model outperforms previous models on most tasks. Especially, we get 44.98%, 38.42% and 40.76% F1 score on BC5CDR, KD-DTI and DDI end-to-end relation extraction tasks, respectively, and 78.2% accuracy on PubMedQA, creating a new record. Our case study on text generation further demonstrates the advantage of BioGPT on biomedical literature to generate fluent descriptions for biomedical terms.

Light‐Induced Cold Marangoni Flow for Microswarm Actuation: From Intelligent Behaviors to Collective Drug Delivery

AbstractMicroswarms have shown great potential in biomedical applications at small scales due to their features of wireless actuation and collective microrobotic behaviors. However, actuation of microswarms with strong universality and intelligent biomimetic behaviors is always a great challenge. Here, photothermal damage‐free actuation of an intelligent microswarm based on light‐induced cold Marangoni flow (CMF) is reported, along with collective drug delivery and targeted cell chemotherapy. This microswarm actuation shows strong universality and high controllability for both abiotic particles and living materials. Importantly, this microswarm exhibits intelligent biomimetic behaviors, such as collective migration, size‐based self‐organization, and group rejection, due to the synergy between cold flow with individual agents. The distinctive photothermal isolation capability of CMF ensures the microswarm to perform photothermal damage‐free biomedical tasks such as collective gene delivery and targeted single‐cell chemotherapy. This light‐induced CMF provides an optical strategy for photothermal damage‐free actuation of intelligent biomimetic microswarm robots, with great promises to perform many collective and cognitive tasks in biomedical applications such as cooperative grasping, collective drug delivery, and precise chemotherapy.

OAU-net: Outlined Attention U-net for biomedical image segmentation

In this paper, we propose an Outlined Attention U-network (OAU-net) with bypass branching strategy to solve biomedical image segmentation tasks, which is capable of sensing shallow and deep features. Unlike previous studies, we use residual convolution and res2convolution as encoders. In particular, the outline filter and attention module are embedded in the skip connection part, respectively. Shallow features will enhance the edge information after being processed by the outline filter. Meanwhile, in the depths of the network, to better realize feature fusion, our attention module will simultaneously emphasize the independence between feature map channels (channel attention module) and each position information (spatial attention module), that is, the hybrid domain attention module. Finally, we conducted ablation experiments and comparative experiments according to three public data sets (pulmonary CT lesions, Kaggle 2018 data science bowl, skin lesions), and analyzed them with classical evaluation indexes. Experimental results show that our proposed method improves segmentation accuracy effectively. Our code is public at https://github.com/YF-W/OAU-net.

BioADAPT-MRC: adversarial learning-based domain adaptation improves biomedical machine reading comprehension task.

ABSTRACTMotivationBiomedical machine reading comprehension (biomedical-MRC) aims to comprehend complex biomedical narratives and assist healthcare professionals in retrieving information from them. The high performance of modern neural network-based MRC systems depends on high-quality, large-scale, human-annotated training datasets. In the biomedical domain, a crucial challenge in creating such datasets is the requirement for domain knowledge, inducing the scarcity of labeled data and the need for transfer learning from the labeled general-purpose (source) domain to the biomedical (target) domain. However, there is a discrepancy in marginal distributions between the general-purpose and biomedical domains due to the variances in topics. Therefore, direct-transferring of learned representations from a model trained on a general-purpose domain to the biomedical domain can hurt the model’s performance.ResultsWe present an adversarial learning-based domain adaptation framework for the biomedical machine reading comprehension task (BioADAPT-MRC), a neural network-based method to address the discrepancies in the marginal distributions between the general and biomedical domain datasets. BioADAPT-MRC relaxes the need for generating pseudo labels for training a well-performing biomedical-MRC model. We extensively evaluate the performance of BioADAPT-MRC by comparing it with the best existing methods on three widely used benchmark biomedical-MRC datasets—BioASQ-7b, BioASQ-8b and BioASQ-9b. Our results suggest that without using any synthetic or human-annotated data from the biomedical domain, BioADAPT-MRC can achieve state-of-the-art performance on these datasets.Availability and implementationBioADAPT-MRC is freely available as an open-source project at https://github.com/mmahbub/BioADAPT-MRC.Supplementary information Supplementary data are available at Bioinformatics online.

Pre-trained language models with domain knowledge for biomedical extractive summarization

Biomedical text summarization is a critical task for comprehension of an ever-growing amount of biomedical literature. Pre-trained language models (PLMs) with transformer-based architectures have been shown to greatly improve performance in biomedical text mining tasks. However, existing methods for text summarization generally fine-tune PLMs on the target corpora directly and do not consider how fine-grained domain knowledge, such as PICO elements used in evidence-based medicine, can help to identify the context needed for generating coherent summaries. To fill the gap, we propose KeBioSum, a novel knowledge infusion training framework, and experiment using a number of PLMs as bases, for the task of extractive summarization on biomedical literature. We investigate generative and discriminative training techniques to fuse domain knowledge (i.e., PICO elements) into knowledge adapters and apply adapter fusion to efficiently inject the knowledge adapters into the basic PLMs for fine-tuning the extractive summarization task. Experimental results from the extractive summarization task on three biomedical literature datasets show that existing PLMs (BERT, RoBERTa, BioBERT, and PubMedBERT) are improved by incorporating the KeBioSum knowledge adapters, and our model outperforms the strong baselines.

Generative adversarial networks and its applications in the biomedical image segmentation: a comprehensive survey.

Recent advancements with deep generative models have proven significant potential in the task of image synthesis, detection, segmentation, and classification. Segmenting the medical images is considered a primary challenge in the biomedical imaging field. There have been various GANs-based models proposed in the literature to resolve medical segmentation challenges. Our research outcome has identified 151 papers; after the twofold screening, 138 papers are selected for the final survey. A comprehensive survey is conducted on GANs network application to medical image segmentation, primarily focused on various GANs-based models, performance metrics, loss function, datasets, augmentation methods, paper implementation, and source codes. Secondly, this paper provides a detailed overview of GANs network application in different human diseases segmentation. We conclude our research with critical discussion, limitations of GANs, and suggestions for future directions. We hope this survey is beneficial and increases awareness of GANs network implementations for biomedical image segmentation tasks.