Search

The increasing incidence and mortality of breast cancer pose significant global challenges for women. Deep learning (DL) has shown superior diagnostic performance in breast cancer classification compared to human experts. However, most DL methods have relied on unimodal features, which may limit the performance of diagnostic models. Recent studies focus on multimodal data along with multiple views of mammograms, typically two: Cranio-Caudal (CC) and Medio-Lateral-Oblique (MLO). Combining multimodal data has shown improvements in classification effectiveness over single-modal systems. In this study, we compiled a multimodal dataset comprising imaging and textual data (combination of clinical and radiological features). We propose a DL-based multiview multimodal feature fusion (MMFF) strategy for breast cancer classification that utilizes images (four views of mammograms) and tabular data (extracted from radiological reports) from our newly developed in-house dataset. Various augmentation techniques are applied to both imaging and textual data to expand the training dataset size. Imaging features were extracted using a Squeeze-and-Excitation (SE) network-based ResNet50 model, while textual features were extracted using an artificial neural network (ANN). Afterwards, extracted features from both modalities were fused using a late feature fusion strategy. Finally, fused features were fed into the ANN for the final classification of breast cancer. In our study, we compared the performance of our proposed MMFF model with single-modal models (image only) and models built on textual data. The performance was evaluated using accuracy, precision, sensitivity, F1 score and area under the receiver operating characteristic curve (AUC) metrics. Our model MMFF achieved an AUC of 0.965 for benign vs malignant classification as compared to image-only (ResNet $50=0.545$ ), text-only (ANN =0.688, SVM =0.842) and other multimodal approaches (ResNet50+ANN =0.748, EfficientNetb7+ANN =0.874).

Abstract Background Recently, machine learning (ML), deep learning (DL), and natural language processing (NLP) have provided promising results in the free-form radiological reports’ classification in the respective medical domain. In order to classify radiological reports properly, a high-quality annotated and curated dataset is required. Currently, no publicly available breast imaging-based radiological dataset exists for the classification of Breast Imaging Reporting and Data System (BI-RADS) categories and breast density scores, as characterized by the American College of Radiology (ACR). To tackle this problem, we construct and annotate a breast imaging-based radiological reports dataset and its benchmark results. The dataset was originally in Spanish. Board-certified radiologists collected and annotated it according to the BI-RADS lexicon and categories at the Breast Radiology department, TecSalud Hospitals Monterrey, Mexico. Initially, it was translated into English language using Google Translate. Afterwards, it was preprocessed by removing duplicates and missing values. After preprocessing, the final dataset consists of 5046 unique reports from 5046 patients with an average age of 53 years and 100% women. Furthermore, we used word-level NLP-based embedding techniques, term frequency-inverse document frequency (TF-IDF) and word2vec to extract semantic and syntactic information. We also compared the performance of ML, DL and large language models (LLMs) classifiers for BI-RADS category classification. Results The final breast imaging-based radiological reports dataset contains 5046 unique reports. We compared K-Nearest Neighbour (KNN), Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient-Boosting (GB), Extreme Gradient Boosting (XGB), Long Short-Term Memory (LSTM), Bidirectional Encoder Representations from Transformers (BERT) and Biomedical Generative Pre-trained Transformer (BioGPT) classifiers. It is observed that the BioGPT classifier with preprocessed data performed 6% better with a mean sensitivity of 0.60 (95% confidence interval (CI), 0.391-0.812) compared to the second best performing classifier BERT, which achieved mean sensitivity of 0.54 (95% CI, 0.477-0.607). Conclusion In this work, we propose a curated and annotated benchmark dataset that can be used for BI-RADS and breast density category classification. We also provide baseline results of most ML, DL and LLMs models for BI-RADS classification that can be used as a starting point for future investigation. The main objective of this investigation is to provide a repository for the investigators who wish to enter the field to push the boundaries further.

BackgroundMedical image analysis, particularly in the context of visual question answering (VQA) and image captioning, is crucial for accurate diagnosis and educational purposes. ObjectiveOur study aims to introduce BioMedBLIP models, fine-tuned for VQA tasks using specialized medical data sets such as Radiology Objects in Context and Medical Information Mart for Intensive Care-Chest X-ray, and evaluate their performance in comparison to the state of the art (SOTA) original Bootstrapping Language-Image Pretraining (BLIP) model. MethodsWe present 9 versions of BioMedBLIP across 3 downstream tasks in various data sets. The models are trained on a varying number of epochs. The findings indicate the strong overall performance of our models. We proposed BioMedBLIP for the VQA generation model, VQA classification model, and BioMedBLIP image caption model. We conducted pretraining in BLIP using medical data sets, producing an adapted BLIP model tailored for medical applications. ResultsIn VQA generation tasks, BioMedBLIP models outperformed the SOTA on the Semantically-Labeled Knowledge-Enhanced (SLAKE) data set, VQA in Radiology (VQA-RAD), and Image Cross-Language Evaluation Forum data sets. In VQA classification, our models consistently surpassed the SOTA on the SLAKE data set. Our models also showed competitive performance on the VQA-RAD and PathVQA data sets. Similarly, in image captioning tasks, our model beat the SOTA, suggesting the importance of pretraining with medical data sets. Overall, in 20 different data sets and task combinations, our BioMedBLIP excelled in 15 (75%) out of 20 tasks. BioMedBLIP represents a new SOTA in 15 (75%) out of 20 tasks, and our responses were rated higher in all 20 tasks (P

Abstract Background Recent advancements in computing power and state-of-the-art algorithms have helped in more accessible and accurate diagnosis of numerous diseases. In addition, the development of de novo areas in imaging science, such as radiomics and radiogenomics, have been adding more to personalize healthcare to stratify patients better. These techniques associate imaging phenotypes with the related disease genes. Various imaging modalities have been used for years to diagnose breast cancer. Nonetheless, digital breast tomosynthesis (DBT), a state-of-the-art technique, has produced promising results comparatively. DBT, a 3D mammography, is replacing conventional 2D mammography rapidly. This technological advancement is key to AI algorithms for accurately interpreting medical images. Objective and methods This paper presents a comprehensive review of deep learning (DL), radiomics and radiogenomics in breast image analysis. This review focuses on DBT, its extracted synthetic mammography (SM), and full-field digital mammography (FFDM). Furthermore, this survey provides systematic knowledge about DL, radiomics, and radiogenomics for beginners and advanced-level researchers. Results A total of 500 articles were identified, with 30 studies included as the set criteria. Parallel benchmarking of radiomics, radiogenomics, and DL models applied to the DBT images could allow clinicians and researchers alike to have greater awareness as they consider clinical deployment or development of new models. This review provides a comprehensive guide to understanding the current state of early breast cancer detection using DBT images. Conclusion Using this survey, investigators with various backgrounds can easily seek interdisciplinary science and new DL, radiomics, and radiogenomics directions towards DBT.

BackgroundBreast cancer is the leading cause of cancer-related fatalities among women worldwide. Conventional screening and risk prediction models primarily rely on demographic and patient clinical history to devise policies and estimate likelihood. However, recent advancements in artificial intelligence (AI) techniques, particularly deep learning (DL), have shown promise in the development of personalized risk models. These models leverage individual patient information obtained from medical imaging and associated reports. In this systematic review, we thoroughly investigated the existing literature on the application of DL to digital mammography, radiomics, genomics, and clinical information for breast cancer risk assessment. We critically analyzed these studies and discussed their findings, highlighting the promising prospects of DL techniques for breast cancer risk prediction. Additionally, we explored ongoing research initiatives and potential future applications of AI-driven approaches to further improve breast cancer risk prediction, thereby facilitating more effective screening and personalized risk management strategies.Objective and methodsThis study presents a comprehensive overview of imaging and non-imaging features used in breast cancer risk prediction using traditional and AI models. The features reviewed in this study included imaging, radiomics, genomics, and clinical features. Furthermore, this survey systematically presented DL methods developed for breast cancer risk prediction, aiming to be useful for both beginners and advanced-level researchers.ResultsA total of 600 articles were identified, 20 of which met the set criteria and were selected. Parallel benchmarking of DL models, along with natural language processing (NLP) applied to imaging and non-imaging features, could allow clinicians and researchers to gain greater awareness as they consider the clinical deployment or development of new models. This review provides a comprehensive guide for understanding the current status of breast cancer risk assessment using AI.ConclusionThis study offers investigators a different perspective on the use of AI for breast cancer risk prediction, incorporating numerous imaging and non-imaging features.

In today’s social media-dominated landscape, digital platforms wield substantial influence over public opinion, particularly during crucial political events such as electoral processes. These platforms become hubs for diverse discussions, encompassing topics, reforms, and desired changes. Notably, in times of government dissatisfaction, they serve as arenas for anti-establishment discourse, highlighting the need to analyze public sentiment in these conversations. However, the analysis of such discourse is notably scarce, even in high-resource languages, and entirely non-existent in the context of the Nepali language. To address this critical gap, we present Nepal Anti Establishment discourse Tweets (NAET), a novel dataset comprising 4,445 multi-aspect annotated Nepali tweets, facilitating a comprehensive understanding of political conversations. Our contributions encompass evaluating tweet relevance, sentiment, and satire, while also exploring the presence of hate speech, identifying its targets, and distinguishing directed and non-directed expressions. Additionally, we investigate hope speech, an underexplored aspect crucial in the context of anti-establishment discourse, as it reflects the aspirations and expectations from new political figures and parties. Furthermore, we set NLP-based baselines for all these tasks. To ensure a holistic analysis, we also employ topic modeling, a powerful technique that helps us identify and understand the prevalent themes and patterns emerging from the discourse. Our research thus presents a comprehensive and multi-faceted perspective on anti-establishment election discourse in a low-resource language setting. The dataset is publicly available, facilitating in-depth analysis of political tweets in Nepali discourse and further advancing NLP research for the Nepali language through labeled data and baselines for various NLP tasks. The dataset for this work is made available at https://github.com/rkritesh210/NAET.

Abstract Background Text mining in the biomedical field has received much attention and regarded as the important research area since a lot of biomedical data is in text format. Topic modeling is one of the popular methods among text mining techniques used to discover hidden semantic structures, so called topics. However, discovering topics from biomedical data is a challenging task due to the sparsity, redundancy, and unstructured format. Methods In this paper, we proposed a novel multiple kernel fuzzy topic modeling (MKFTM) technique using fusion probabilistic inverse document frequency and multiple kernel fuzzy c-means clustering algorithm for biomedical text mining. In detail, the proposed fusion probabilistic inverse document frequency method is used to estimate the weights of global terms while MKFTM generates frequencies of local and global terms with bag-of-words. In addition, the principal component analysis is applied to eliminate higher-order negative effects for term weights. Results Extensive experiments are conducted on six biomedical datasets. MKFTM achieved the highest classification accuracy 99.04%, 99.62%, 99.69%, 99.61% in the Muchmore Springer dataset and 94.10%, 89.45%, 92.91%, 90.35% in the Ohsumed dataset. The CH index value of MKFTM is higher, which shows that its clustering performance is better than state-of-the-art topic models. Conclusion We have confirmed from results that proposed MKFTM approach is very efficient to handles to sparsity and redundancy problem in biomedical text documents. MKFTM discovers semantically relevant topics with high accuracy for biomedical documents. Its gives better results for classification and clustering in biomedical documents. MKFTM is a new approach to topic modeling, which has the flexibility to work with a variety of clustering methods.

Abstract Background The abundance of biomedical text data coupled with advances in natural language processing (NLP) is resulting in novel biomedical NLP (BioNLP) applications. These NLP applications, or tasks, are reliant on the availability of domain-specific language models (LMs) that are trained on a massive amount of data. Most of the existing domain-specific LMs adopted bidirectional encoder representations from transformers (BERT) architecture which has limitations, and their generalizability is unproven as there is an absence of baseline results among common BioNLP tasks. Results We present 8 variants of BioALBERT, a domain-specific adaptation of a lite bidirectional encoder representations from transformers (ALBERT), trained on biomedical (PubMed and PubMed Central) and clinical (MIMIC-III) corpora and fine-tuned for 6 different tasks across 20 benchmark datasets. Experiments show that a large variant of BioALBERT trained on PubMed outperforms the state-of-the-art on named-entity recognition (+ 11.09% BLURB score improvement), relation extraction (+ 0.80% BLURB score), sentence similarity (+ 1.05% BLURB score), document classification (+ 0.62% F1-score), and question answering (+ 2.83% BLURB score). It represents a new state-of-the-art in 5 out of 6 benchmark BioNLP tasks. Conclusions The large variant of BioALBERT trained on PubMed achieved a higher BLURB score than previous state-of-the-art models on 5 of the 6 benchmark BioNLP tasks. Depending on the task, 5 different variants of BioALBERT outperformed previous state-of-the-art models on 17 of the 20 benchmark datasets, showing that our model is robust and generalizable in the common BioNLP tasks. We have made BioALBERT freely available which will help the BioNLP community avoid computational cost of training and establish a new set of baselines for future efforts across a broad range of BioNLP tasks.

Breast cancer (BC) is the second most prevalent type of cancer among women leading to death, and its rate of mortality is very high. Its effects will be reduced if diagnosed early. BC’s early detection will greatly boost the prognosis and likelihood of recovery, as it may encourage prompt surgical care for patients. It is therefore vital to have a system enabling the healthcare industry to detect breast cancer quickly and accurately. Machine learning (ML) is widely used in breast cancer (BC) pattern classification due to its advantages in modelling a critical feature detection from complex BC datasets. In this paper, we propose a system for automatic detection of BC diagnosis and prognosis using ensemble of classifiers. First, we review various machine learning (ML) algorithms and ensemble of different ML algorithms. We present an overview of ML algorithms including ANN, and ensemble of different classifiers for automatic BC diagnosis and prognosis detection. We also present and compare various ensemble models and other variants of tested ML based models with and without up-sampling technique on two benchmark datasets. We also studied the effects of using balanced class weight on prognosis dataset and compared its performance with others. The results showed that the ensemble method outperformed other state-of-the-art methods and achieved 98.83% accuracy. Because of high performance, the proposed system is of great importance to the medical industry and relevant research community. The comparison shows that the proposed method outperformed other state-of-the-art methods.

Reading newly-published papers in time is important for researchers since these papers provide the latest research findings. However, it is challenging to retrieve newly-published papers through common query-based search engines because the papers lacking sufficient citations and links are usually ranked too low in the search list. To this end, we design a time-aware joint model to infer users’ preference for the newly-published papers with the help of subsidiary relations of social and article linkages. The temporal preference of researchers for articles is jointly modeled with social and article relations by a group of matrices sharing common dimensions of researchers and articles. A joint multi-relational factorization algorithm is devised to approximate the latent factor matrices along with a temporal recommendation algorithm to predict the personalized new referential papers based on the factor matrices. The experimental results on real-world datasets show that the proposed model outperforms the state-of-the-art methods.

The fuzzy graph is the foundation of many actual structures such as networking, picture planning, and so on. Generalized fuzzy graphs (GFG) are ideal for avoiding certain constraints of fuzzy graphs. Social networks are a useful and powerful way to link citizens worldwide. A central person in a social network is to deny the leading people in it. Different centrality steps have also been established over the years. We evaluated the centrality of the social network through a general fuzzy graph in this article. An application to detect the central person in any online group like WhatsApp is described in this study by using generalized fuzzy graphs. Also, a few important results are established in this study.

An enormous amount of clinical free-text information, such as pathology reports, progress reports, clinical notes and discharge summaries have been collected at hospitals and medical care clinics. These data provide an opportunity of developing many useful machine learning applications if the data could be transferred into a learn-able structure with appropriate labels for supervised learning. The annotation of this data has to be performed by qualified clinical experts, hence, limiting the use of this data due to the high cost of annotation. An underutilised technique of machine learning that can label new data called active learning (AL) is a promising candidate to address the high cost of the label the data. AL has been successfully applied to labelling speech recognition and text classification, however, there is a lack of literature investigating its use for clinical purposes. We performed a comparative investigation of various AL techniques using ML and deep learning (DL)-based strategies on three unique biomedical datasets. We investigated random sampling (RS), least confidence (LC), informative diversity and density (IDD), margin and maximum representativeness-diversity (MRD) AL query strategies. Our experiments show that AL has the potential to significantly reducing the cost of manual labelling. Furthermore, pre-labelling performed using AL expediates the labelling process by reducing the time required for labelling.

Stock price prediction can be made more efficient by considering the price fluctuations and understanding people’s sentiments. A limited number of models understand financial jargon or have labelled datasets concerning stock price change. To overcome this challenge, we introduced FinALBERT, an ALBERT based model trained to handle financial domain text classification tasks by labelling Stocktwits text data based on stock price change. We collected Stocktwits data for over ten years for 25 different companies, including the major five FAANG (Facebook, Amazon, Apple, Netflix, Google). These datasets were labelled with three labelling techniques based on stock price changes. Our proposed model FinALBERT is fine-tuned with these labels to achieve optimal results. We experimented with the labelled dataset by training it on traditional machine learning, BERT, and FinBERT models, which helped us understand how these labels behaved with different model architectures. Our labelling method’s competitive advantage is that it can help analyse the historical data effectively, and the mathematical function can be easily customised to predict stock movement.