Placenta accreta spectrum (PAS) is a severe obstetric complication characterized by abnormal placental villous invasion into the myometrium, serving as a primary driver of life-threatening postpartum hemorrhage. Prenatal diagnosis currently depends on operator-dependent ultrasonography and adjunctive magnetic resonance imaging, both of which exhibit limited sensitivity in early gestation. Consequently, many cases remain undiagnosed until delivery, highlighting the need for objective, non-invasive biomarkers.

A moth-shaped robot used an artificial circulatory system to deliver chemical building blocks through its body and grow a light sensor where UV light struck.

This review provides a clinically grounded and translationally oriented synthesis of artificial intelligence (AI) in ophthalmology, covering methodological foundations, ophthalmic imaging modalities, public datasets, disease-specific applications, evaluation metrics, deployment barriers, and future directions. It argues that the next phase of ophthalmic AI should move beyond high accuracy toward prospective validation, external generalization, clinician-centered design, calibrated uncertainty, and accountable integration into real-world eye-care pathways.

The Mollisols in Northeast China are a precious arable land resource in China and a core base for safeguarding national food security. Long-term intensive tillage can readily cause soil degradation, compaction, and declines in soil fertility. As a mainstream conservation tillage practice, no-tillage with straw mulching (NTSM) has been widely promoted in Northeast China; this practice can stabilize soil, conserve water, and increase soil organic matter content.

Chromatin is not static inside the cell nucleus. Using machine learning-assisted Repli-Histo labeling and single-nucleosome imaging, researchers examined how transcription influences different chromatin classes in living human cells. RNA polymerase II transcription constrains nucleosome motion in euchromatin and in heterochromatin around nucleoli, whereas RNA polymerase I transcription specifically constrains late-replicating Class III heterochromatin around nucleoli. The findings show that transcription shapes chromatin behavior differently depending on both chromatin type and nuclear location.

3D µ-printing is an established technique for printing micro-optical components from the meso down to the sub-micron scale. As the involved optical and photo-chemical processes are affected by many parameters, deviations between initial design and printed structure are unavoidable and have not yet been predicted accurately due to their complexity.  This work demonstrates that machine learning can be used to account for those deviations and improve fabrication quality.