Marie-Christine Fluet

A Year of Journal Articles (Day 262/365) Wang, Junze, Wenjun Zhang, Dandan Li, Chao Li, and Weipeng Jing. "HGSNet: A hypergraph network for subtle lesions segmentation in medical imaging." IET Image Processing (2024). Summary: Problem: - Lesion segmentation in medical images is crucial, especially for hard-to-detect subtle lesions. - Convolutional Neural Networks (CNNs), a popular method, often struggle to capture the relationships between lesions, leading to errors in their spatial arrangement (topology) during training. Proposed Solution: The paper introduces a novel method that shifts from using pixel-level information to a representation called a hypergraph. - In a hypergraph, lesions are represented as vertices (points), and their connections are represented by hyperedges. This allows the model to capture the topological relationships between lesions. - A new strategy called Dynamic Hypergraph Learning Strategy (DHLS) is proposed. DHLS can dynamically construct hypergraphs based on the specific variations present in the input lesions. - The core network, called HGSNet (Hypergraph Global-aware Segmentation Network), is built upon this concept. HGSNet can capture the high-level structural information of the lesions, improving the overall understanding of their topology. - To further enhance performance, a composite loss function is introduced. This function focuses on both the global aspects of the segmentation and the accuracy of the boundaries around the lesions. Evaluation: - The paper compares HGSNet with other advanced models on publicly available medical image datasets from various organs. - The results demonstrate that HGSNet outperforms existing methods and achieves state-of-the-art performance in lesion segmentation. - Overall, this approach presents a promising technique for accurate lesion segmentation in medical images, particularly for subtle lesions where traditional CNN methods might struggle.

🌟🌟🌟Highly Cited Paper🌟🌟🌟 Comprehensive Analysis of Feature Extraction Methods for Emotion Recognition from Multichannel EEG Recordings https://lnkd.in/d6knXbf5 #EEG #EmotionRecognition #FeatureExtraction #Valence #Arousal #PatternRecognition

📃Scientific paper: Machine learning and EEG can classify passive viewing of discrete categories of visual stimuli but not the observation of pain Abstract: Previous studies have demonstrated the potential of machine learning (ML) in classifying physical pain from non-pain states using electroencephalographic (EEG) data. However, the application of ML to EEG data to categorise the observation of pain versus non-pain images of human facial expressions or scenes depicting pain being inflicted has not been explored. The present study aimed to address this by training Random Forest (RF) models on cortical event-related potentials (ERPs) recorded while participants passively viewed faces displaying either pain or neutral expressions, as well as action scenes depicting pain or matched non-pain (neutral) scenarios. Ninety-one participants were recruited across three samples, which included a model development group (n = 40) and a cross-subject validation group (n = 51). Additionally, 25 participants from the model development group completed a second experimental session, providing a within-subject temporal validation sample. The analysis of ERPs revealed an enhanced N170 component in response to faces compared to action scenes. Moreover, an increased late positive potential (LPP) was observed during the viewing of pain scenes compared to neutral scenes. Additionally, an enhanced P3 response was found when participants viewed faces displaying pain expressions compared to neutral expressions. Subsequently, three RF models were developed to classify images into faces and scenes, neutral and pain scenes, and neutral and pain expr... Continued on ES/IODE ➡️ https://etcse.fr/QRS ------- If you find this interesting, feel free to follow, comment and share. We need your help to enhance our visibility, so that our platform continues to serve you.