Segmentation is manually performed by physicians, which takes considerable time and may be subject to observers. Automating this task can increase efficiency and consistency. Existing studies on meningioma segmentatio...
详细信息
Segmentation is manually performed by physicians, which takes considerable time and may be subject to observers. Automating this task can increase efficiency and consistency. Existing studies on meningioma segmentation used data from limited study centers, indicating the need for research on multi-center data to assess generalizability. In this work, two semi-automated methods with bounding box priors, LiteMedSAM and BBU-Net, are evaluated on the brain tumor segmentation (BraTS) 2023 meningioma dataset collected from five study-centers. Preprocessing included exclusion of small tumors, z-score normalization, and extraction of slices that contain tumors, generating 25,602 2D axial magnetic resonance imaging (MRI) scans. A fine-tuning strategy is adopted for LiteMedSAM while BBU-Net is trained from scratch. The models are evaluated using a five-fold cross-validation, with data split at the case level. Results show that while U-Net models can achieve performance close to LiteMedSAM, the foundation model has overall better performance, with more than 90% in all evaluation scores.
The growing number of medical images has led to radiologist burnout, which seriously impacts the radiologist's performance. To address the previously mentioned issue, an Auxiliary Signal Guided Knowledge (ASGK) mu...
详细信息
The growing number of medical images has led to radiologist burnout, which seriously impacts the radiologist's performance. To address the previously mentioned issue, an Auxiliary Signal Guided Knowledge (ASGK) multimodal encoder-decoder framework was designed to automatically generate the medical report based on the proposed medical graph and natural language decoder. It utilizes DenseNet-121 as the image encoder. With DenseNet-121 lack of computational and memory efficiency, this study aims to explore the potential of EfficientNetB0 to EfficientNetB4 as an ASGK image encoder substitute. The framework is trained with IU X-Ray dataset for 30 epochs, with Adam optimizer, a learning rate of 0.01 with 0.8 decay rate, binary cross entropy loss for the medical tags, and cross-entropy loss for the generated medical captions. During the framework training process with each image encoder, the parameter that achieves the highest CIDEr score on the validation set is considered the best image encoder parameter and will be used on the test set. On the test set, EfficientNetB3 as an ASGK image encoder has been shown to increase the CIDEr score to 0.35, a significant increase from the 0.28 CIDEr score obtained by the ASGK using DenseNet-121. This score is only a 1% decrease from the best validation score. It suggests that not only EfficientNetB3 increases the framework's performance, it is also less prone to overfitting. This study has demonstrated that EfficientNetB3 is a potential image encoder substitute for DenseNet-121 in the ASGK framework.
A wide variety of disciplines contribute to bioinformatics research, including computer science, biology, chemistry, mathematics, and physics. This study determines the number of research articles published on arXiv c...
详细信息
A wide variety of disciplines contribute to bioinformatics research, including computer science, biology, chemistry, mathematics, and physics. This study determines the number of research articles published on arXiv classified as bioinformatics topics and the most frequently used bioinformatics terms using topic modeling, Latent Dirichlet Allocation (LDA). An algorithm based on LDA is used to discover topics hidden within large collections of documents through the use of statistical analysis. Our research examined 226453 articles on arXiv between January 2023 and January 2024. As a result, there are more than 10521 articles categorized into bioinformatics topics. Most commonly, 6352 documents are in the "Mathematical Physics" category. The second most popular category is "Computer science," with 2950 documents. Accordingly, the terms 'RNA,' 'sequence,' 'tree,' and 'homology' are the three most commonly used terms in bioinformatics. The study of RNA plays a vital role in molecular biology; thus, the study of RNA is prevalent in bioinformatics. Sequential data refer to the order in which nucleotides or amino acids can be found in a DNA molecule or a protein.
The delineation of Lymph Nodes (LNs) is pivotal in pinpointing therapeutic targets for radiotherapy in head and neck malignancies. Nevertheless, this endeavor poses a formidable challenge, primarily stemming from the ...
详细信息
The growing hype surrounding GPT models has generated both fear and excitement, with concerns about job replacement and admiration for its capabilities. This study investigated the prevailing sentiments within the aca...
The growing hype surrounding GPT models has generated both fear and excitement, with concerns about job replacement and admiration for its capabilities. This study investigated the prevailing sentiments within the academic field. The paper aimed to conduct a more comprehensive and objective analysis focusing on academia. We conducted sentiment analysis on a corpus of both peer-reviewed and preprinted article abstracts published between January 2022 and March 2023 to determine the early prevailing sentiments toward GPT models. We collected and processed 400+academic papers on GPT models, extracting the abstracts and keywords to gain insights into authors' perspectives. The study focused on identifying these articles' positive, negative, and neutral sentiments. The study considered various approaches, including RoBERTa, and traditional Machine Learning models such as Naïve Bayes, Random Forest, and Support Vector Machine, to analyze the collected data and compare performance results. The results demonstrated that the predominant sentiments expressed in scholarly paper abstracts toward GPT models are neutral (60.2% of the sample), instead of polarized. This observation holds even when the confidence score of the model output is limited to $\gt0.5$. The significance of this study lies in its novelty, as limited articles have examined these sentiments. Understanding the various sentiments expressed in scholarly discourse on GPT models can contribute to further research on the ethical implications of generative AI.
With the growing demands for Precision Agriculture (PA) in Indonesia, researchers have evaluated the utilization of Machine Learning for predicting oil palm yields and determining variables affecting them. Previous st...
详细信息
Recent advances in deep learning not only facilitate the implementation of zero-shot singing voice synthesis (SVS) and singing voice conversion (SVC) tasks but also provide the opportunity to unify these two tasks int...
详细信息
One way to save time and resources in the human recruitment and hiring process is to post open job positions on the Internet, but the overload of applications creates challenges for hiring managers and companies to se...
详细信息
The process of using ICT to provide services to the public is known as the Indonesian e-Government system, or Sistem Pemerintahan Berbasis Elektronik (SPBE). The e-Government initiative in Jakarta Provincial Health Of...
详细信息
Human activity recognition (HAR) is the process of using mobile sensor data to determine the physical activities performed by individuals. HAR is the backbone of many mobile healthcare applications, such as passive he...
详细信息
暂无评论