Molt contents d'haver estat un dels projectes mereixedors d'una ajuda de @la_marato. Un projecte molt ambiciós, liderat per #DanielVegaMoreno, conjuntament amb #MarinaLópezSolà, #AzucenaGarcíaPalacios i #JordiSoléCasals.

Code available: #DeepLearning #ECG #SignalProcessing #CardiacHealth #AIinHealthcare #Research #Collaboration.

This research was conducted in collaboration with the University of Science and Technology of China, @juntendo_univ, Hefei University of Technology, @CONICETLaPlata, @Cambridge_Uni and @uvic_ucc.

Our proposed model, ECGDenoiser, significantly outperforms traditional and state-of-the-art denoising techniques across multiple datasets and noise types — a promising step toward more accurate and reliable cardiac diagnostics.

In this work, we introduce a novel deep learning method that enhances ECG signals by combining magnitude-aware analysis and phase retrieval in the time-frequency domain.

Excited to share our latest publication: "ECGDenoiser: A Magnitude-Aware Deep Learning Framework with Phase Retrieval for Electrocardiogram Signal Enhancement" in Circuits, Systems, and Signal Processing. Read more:

RT @AI4Pathology: I shared my thoughts in a @NatureMedicine comment on the urgent need for more standardized benchmarks in #AI for biomedic….

We participate at the 35th Annual Cambridge Neuroscience Seminar – #CNS2025: "Expanding the Horizons of Brain Research", presenting @ShuningHan’s poster (see image below). #Neuroscience #giftedness #MRI #connectivity @uvic_ucc @Cambridge_Uni @nankai @juntendo_univ @CONICETLaPlata

Congrats to all the coauthors!.

A frequency enhancement module with hard attention refines artifact removal, while a time-domain compensation module preserves global information. Experiments show A²DM outperforms CNN-based methods, improving correlation coefficient (CC) metrics by 12%.

In this paper ee propose an artifact-aware EEG denoising model (A²DM) to remove various artifacts effectively. A²DM integrates a pre-trained artifact classification model to identify and remove artifacts in the time-frequency domain.

This work is a joint collaboration between @nankai @Tsinghua_Uni, @juntendo_univ, The 903Rd Hospital of PLA (Hangzhou), and the Weifang Hospital Of Traditional Chinese Medicine (Shandong) and @uvic_DSP.

Check the new paper published today in @CognComput, part of the PhD work of Haoran Li, from @nankai: .#EEG #artifactRemoval #time_frequency #AI

We thank the organising committee for the excellent talks and the atmosphere during the conference, and @hgamboa especially, for his dedication and kindness. Congratulations to all! .#biosignals #machinelearning #deeplearning #AI.

Additionally, Dr. @jsolec delivered the invited talk "Crossing Borders: My Research Journey from Theory to Applications in Biomedical Signal Processing", sharing his research experience and the international collaborations over the past 25 years.

Meanwhile, PhD student Mr. #XavierSànchezCorrales presented the poster "Analyzing Male Depression Using Empirical Mode Decomposition", also as part of his doctoral research in the Bioinformatics PhD program.

PhD student Ms. @ShuningHan presented the paper "Analyzing Cognitive Patterns in Gifted Children Using MRI and Morphometric Similarity Networks", which is part of her doctoral thesis within the PhD program in Experimental Sciences and Technology.

Members of our group participated last week in the 18th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSIGNALS), held in Porto (Portugal) .

Another paper published thanks to our collaboration with the College of Artificial Intelligence and the Tianjin Key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation at @nankai University. Congrats to all coauthors!.

A paper from our group, featured by @Applsci .Congrats, @CusidoJordi @Le_Lluc @pmartipuig @jsolec @uvic_ucc .#LLM @AI #medicine #symptomRecognition #ArtificialIntelligence