This website uses a security service to protect against malicious bots. This page is displayed while the website verifies you are not a bot.
Category: robotics/AI – Page 15
Phosphoinositide Depletion and Compensatory Phospho-Signaling in Angiotensin II-Induced Heart Disease
Westhoff & colleagues found that PTEN inhibition reduces cardiac fibrosis caused by the high blood pressure hormone AngII. Learn how to fight fibrosis from hypertension at.
This website uses a security service to protect against malicious bots. This page is displayed while the website verifies you are not a bot.
Clinical Utility of Deep Learning–based Multiple Arterial Phase MRI in Hepatocellular Carcinoma
Hepatocellular carcinoma (HCC) diagnosis relies heavily on well‑timed arterial phase MRI, yet single arterial phase scans often miss the optimal late arterial phase, especially with hepatobiliary contrast agents that are prone to motion artifacts and narrow timing windows. These limitations can compromise image quality and reduce detection of key features such as arterial phase hyperenhancement.
In a study recently published in Radiology: Imaging Cancer, researchers led by Kai Liu, BS, Zhongshan Hospital at Fudan University in Shanghai, compared conventional single phase imaging with an ultrafast, deep learning-based multiphase MRI technique, which can rapidly acquire six high-resolution arterial phases in a single breath hold.
In a cohort of 236 participants, the deep learning–based multiphase MRI technique markedly improved late arterial capture, boosted overall image quality and enhanced detection of lesions and HCC for both extracellular and hepatobiliary agents. The method achieved a late arterial capture rate of 98% (vs. 81% to 85% with single phase imaging) and showed strong performance in identifying small tumors.
“These findings support the potential of deep learning-based multiphase arterial MRI to streamline HCC diagnosis,” the authors conclude.
Read the full article, “Clinical Utility of Deep Learning–based Multiple Arterial Phase MRI in Hepatocellular Carcinoma.”
The AI Paradox: Cure or Poison?
Technology promised simplicity. It delivered complexity.
AI promised resolution. It is delivering acceleration.
The paradox is not a bug. It is the feature. And the question is what we choose to do about it.
This week I published a new essay, It is the argument I have been circling for a decade, finally in one place.
The short version: as AI’s capabilities grow, so do the risks. They are not separate variables. They climb the same curve. A more powerful model can cure more diseases and design more weapons. A smarter agent can book your travel and drain your bank account. Capability is leverage. Leverage is indifferent to ethics.
Every time we raise the ceiling of what AI can do, we raise the floor of what can go wrong.
We still have the how. We are drowning in the what. What we have neglected, almost completely, is the why.
Natural-language AI helps chemists design molecules step by step
Designing molecules is one of chemistry’s most complex challenges. From life-saving drugs to advanced materials, each compound requires a precise sequence of reactions. Planning these steps demands both technical knowledge and strategic insight, making it a task that often relies on years of experience.
Two problems plague much of modern chemistry. The first is retrosynthesis: Chemists start from a target molecule and work backward to identify simpler building blocks and viable reaction pathways. Retrosynthesis involves countless decisions, from choosing starting materials to determining when to form rings or protect sensitive functional groups. While computers can explore vast “chemical spaces,” they often struggle to capture the strategic reasoning used by human experts.
The second problem is reaction mechanisms. These describe how chemical reactions unfold step by step through the movements of electrons. Mechanistic insight helps scientists predict new reactions, improve efficiency, and reduce costly trial and error. Existing computational methods can generate many possible pathways, but often lack the chemical intuition needed to identify the most plausible ones.
Bridging structure and function: artificial intelligence-based modelling of kidney proteins
Advances in artificial intelligence-driven algorithms and experimental technologies have revolutionized the field of protein modelling. This Review describes how these developments have provided unprecedented insights into the structure of key proteins within the kidney, improved understanding of the relationships between protein structure and stability, and enabled mechanistic interpretation of variants that underlie a variety of kidney pathologies.
Nvidia becomes first company to cross $5 trillion in market value
Nvidia has achieved a historic milestone. The chipmaker is now the world’s most valuable listed company. Its market capitalization has surpassed five trillion dollars. This surge places Nvidia ahead of tech giants like Alphabet and Apple. The company’s success is driven by its crucial role in supplying GPUs for artificial intelligence models. Nvidia’s stock performance reflects its strong market position.
Machine learning identifies catalyst ‘sweet spot’ for greener urea from waste gases
Urea is an extremely important chemical, especially for fertilizers. But, making urea is energy intensive and relies heavily on fossil fuels. However, new findings from Griffith University and the Queensland University of Technology have highlighted new ways to produce urea electrochemically, using electricity and waste gases such as carbon monoxide (CO) and nitrogen oxides (NO) instead.
The paper, “Machine Learning-Assisted Design Framework of Carbon Edge-Dominated Dual-Atom Catalysts for Urea Electrosynthesis,” has been published in ASC Nano.
“The challenge is that when CO and NO react on a catalyst, they usually don’t form urea,” said co-lead author Professor Qin Li from Griffith University.
