The most widely used technology to identify the proteins present in a complex biological sample is tandem mass spectrometry, which quickly produces a large collection of spectra representative of the peptides (i.e., protein subsequences) present in the original sample.

The most widely used technology to identify the proteins present in a complex biological sample is tandem mass spectrometry, which quickly produces a large collection of spectra representative of the peptides (i.e., protein subsequences) present in the original sample.

Characterizing the cellular properties of neurons is fundamental to understanding their function in the brain. In this quest, the generation of bio-realistic models is central towards integrating multimodal cellular data sets and establishing causal relationships. However, current modeling approaches remain constrained by the limited availability and intrinsic variability of experimental neuronal data. The deterministic formalism of bio-realistic models currently precludes accounting for the natural variability observed experimentally. While deep learning is becoming increasingly relevant in this space, it fails to capture the full biophysical complexity of neurons, their nonlinear voltage dynamics, and variability. To address these shortcomings, we introduce NOBLE, a neural operator framework that learns a mapping from a continuous frequency-modulated embedding of interpretable neuron features to the somatic voltage response induced by current injection. Trained on synthetic data generated from bio-realistic neuron models, NOBLE predicts distributions of neural dynamics accounting for the intrinsic experimental variability. Unlike conventional bio-realistic neuron models, interpolating within the embedding space offers models whose dynamics are consistent with experimentally observed responses. NOBLE enables the efficient generation of synthetic neurons that closely resemble experimental data and exhibit trial-to-trial variability, offering a $4200\times$ speedup over the numerical solver. NOBLE is the first scaled-up deep learning framework that validates its generalization with real experimental data. To this end, NOBLE captures fundamental neural properties in a unique and emergent manner that opens the door to a better understanding of cellular composition and computations, neuromorphic architectures, large-scale brain circuits, and general neuroAI applications.

Accurate standard plane acquisition in fetal ultrasound (US) videos is crucial for fetal growth assessment, anomaly detection, and adherence to clinical guidelines. However, manually selecting standard frames is time-consuming and prone to intra-and inter-sonographer variability. Existing methods primarily rely on image-based approaches that capture standard frames and then classify the input frames across different anatomies. This ignores the dynamic nature of video acquisition and its interpretation. To address these challenges, we introduce Multi-Tier Class-A ware Token Transformer (MCA T); a visual query-based video clip localization (VQ-VCL) method to assist sonographers by enabling them to capture a quick US sweep. By then providing a visual query of the anatomy they wish to analyze, MCA T returns the video clip containing the standard frames for that anatomy, facilitating thorough screening for potential anomalies. We evaluate MCA T on two ultrasound video datasets and a natural image VQ-VCL dataset based on Ego4D. Our model outperforms state-of-the-art methods by 10% and 13% mtIoU on the ultrasound datasets and by 5.35% mtIoU on the Ego4D dataset, using 96% fewer tokens. MCA T's efficiency and accuracy have significant potential implications for public health, especially in low-and middle-income countries (LMICs), where it may enhance prenatal care by streamlining standard plane acquisition, simplifying US based screening, diagnosis and allowing sonographers to examine more patients.

The biggest news this week is inarguably the Trump administration's baffling tariffs, which have rattled the global economy, impacting everything from the US tech industry to literal penguins, leaving most of the world wondering what comes next. But if you're looking for a mystery that doesn't feel quite so, well, existential, look no further than Indiana University. On March 18, the FBI raided the homes of Xiaofeng Wang, a data privacy professor and researcher who worked at the IU for more than 20 years. The same day, according to a termination email viewed by WIRED, Wang was fired from his job, and people soon noticed that he and his wife seemed to have disappeared. A WIRED investigation found that the university was looking into whether Wang received unreported research funding from China prior to his position being terminated.

"Any sufficiently advanced technology is indistinguishable from magic," Arthur C Clarke famously said. And this could certainly be said of the impressive OpenAI update to ChatGPT, called GPT-4o, which was released on Monday. With the slight caveat that it felt a lot like the magician was a horny 12-year-old boy who had just watched the Spike Jonze movie Her. If you aren't up to speed on GPT-4o (the o stands for "omni") it's basically an all-singing, all-dancing, all-seeing version of the original chatbot. It can give you advice, it can rate your jokes, it can describe your surroundings, it can banter with you.

Is there a right way for Google's generative AI to create fake images of Nazis? Gemini, Google's answer to ChatGPT, was shown last week to generate an absurd range of racially and gender-diverse German soldiers styled in Wehrmacht garb. It was, understandably, ridiculed for not generating any images of Nazis who were actually white. Prodded further, it seemed to actively resist generating images of white people altogether. The company ultimately apologized for "inaccuracies in some historical image generation depictions" and paused Gemini's ability to generate images featuring people.

Cochlear implants (CIs) are neural prosthetics used to treat patients with severe-to-profound hearing loss. Patient-specific modeling of CI stimulation of the auditory nerve fiber (ANFs) can help audiologists improve the CI programming. These models require localization of the ANFs relative to surrounding anatomy and the CI. Localization is challenging because the ANFs are so small they are not directly visible in clinical imaging. In this work, we hypothesize the position of the ANFs can be accurately inferred from the location of the internal auditory canal (IAC), which has high contrast in CT, since the ANFs pass through this canal between the cochlea and the brain. Inspired by VoxelMorph, in this paper we propose a deep atlas-based IAC segmentation network. We create a single atlas in which the IAC and ANFs are pre-localized. Our network is trained to produce deformation fields (DFs) mapping coordinates from the atlas to new target volumes and that accurately segment the IAC. We hypothesize that DFs that accurately segment the IAC in target images will also facilitate accurate atlas-based localization of the ANFs. As opposed to VoxelMorph, which aims to produce DFs that accurately register the entire volume, our novel contribution is an entirely self-supervised training scheme that aims to produce DFs that accurately segment the target structure. This self-supervision is facilitated using a regional level set (LS) inspired loss function. We call our method Deep Atlas Based Segmentation using Level Sets (DABS-LS). Results show that DABS-LS outperforms VoxelMorph for IAC segmentation. Tests with publicly available datasets for trachea and kidney segmentation also show significant improvement in segmentation accuracy, demonstrating the generalizability of the method.

Within the walls of a 19th-century chapel on the outskirts of Barcelona, a heart starts to slowly contract. This is not a real heart but a virtual copy of one that still pounds inside a patient's chest. With its 100 million patches of simulated cells, the digital twin--a fully functional simulation of human anatomy-- pumps at a leisurely pace as it tests treatments, from drugs to implants. This digital twin pulses within MareNostrum, a supercomputer used by scientists to simulate features of the real world. These simulations can look just like the real thing, but they are vastly more sophisticated than Hollywood visual effects because they behave like the real thing--from how the heart moves to the charged atoms that zip in and out of its cells.

Did you miss a session from the Future of Work Summit? Managing supply chains was challenging before the pandemic, but the health crises headwinds ramped up the pressure. In a 2021 survey from the Institute for Supply Management, 42% of organizations said that increased cost to supply management due to the pandemic was one of their top concerns. A separate poll from BluJay found that outdated IT systems have become a growing barrier to supply chain innovation. One of the major blockers that organizations face when it comes to the supply chain is reconciling -- and analyzing -- information from an array of different sources. Data including images, paperwork, recordings of customer calls, and raw sensor readings are often spread across disparate systems, apps, and services that don't communicate with each other.