Every story in this issue with a short summary, so you can decide what to read before leaving the site. Summaries are written by AI (Claude) only from each publisher's own description and checked by Jev for anything not in that description. They are not full translations. Follow "Read the original" for the full story.
The digital slide scanners market is set for steady growth through 2035. The growth is driven by expanding telepathology adoption and AI integration in clinical pathology workflows.
Read the original →A new deep learning network grades the gain quality of automated breast ultrasound images with 95.49 percent accuracy. It outperforms standard models while using fewer computational resources.
Read the original →A new asymmetric AI fusion framework treats dermoscopic images as the primary representation and clinical photos as a corrective signal. It consistently outperformed naive fusion across nine skin datasets.
Read the original →A French research team combined time-domain reflectometry with temporal convolutional networks to detect, locate, and characterize wiring faults. They achieved perfect accuracy on a Y-shaped network.
Read the original →A systematic review of 123 studies maps how artificial intelligence is transforming brain imaging and computer-aided diagnosis of neurological diseases. It warns that clinical maturity depends on further factors.
Read the original →A new study shows that AI models trained on routine pathology slides can predict BRAF mutation status in melanoma patients with accuracy approaching molecular sequencing. This could potentially speed up targeted therapy triage.
Read the original →Researchers in China have developed an internally validated machine learning model. It predicts long-term post-stroke disability from routine blood tests taken at admission.
Read the original →A new critical review finds that AI-enabled ECG has reached clinical maturity in STEMI triage and reduced ejection fraction screening. For most other cardiovascular uses it remains at the validation stage.
Read the original →A new evidence-guided framework called E-MDD combines deep EEG representations, neurophysiological biomarkers and a constrained large language model. It is designed to detect depression with high accuracy.
Read the original →A Texas couple used AI to organize medication instructions while they were sick. The story shows how ChatGPT can assist patients without replacing doctors.
Read the original →A new review maps how artificial intelligence is transforming RNA-targeted drug discovery. It covers both small molecules and oligonucleotide therapeutics.
Read the original →MarketsandMarkets projects the global AI in drug discovery market will grow from USD 5.09 billion in 2026 to USD 17.56 billion by 2031, a CAGR of 28.1%. Growth is attributed to pharmaceutical demand to cut drug discovery timelines and R&D costs, wider adoption of generative AI and foundation models, and more multi-omics datasets.
Read the original →A former medical journal editor says his team was made redundant after executives chose an AI publishing platform. The account highlights the uneven and human cost of automation.
Read the original →The Armed Forces of Ukraine and NATO's Allied Command Transformation developed two AI-supported tools. The tools are for predicting enemy unmanned aerial vehicle strikes.
Read the original →China's Ministry of Commerce and Ministry of Science and Technology announced on the 16th that they will tighten export controls on 40 technologies covering AI, biopharmaceuticals and solar power. Fourteen items, including AI generation technology for programs that could be misused in cyberattacks, will be banned from export.
Read the original →