Recent statistics report that more than 3.7 million new cases of cancer occur in Europe yearly, and according to the WHO the disease accounts for approximately 20% of all deaths. Cancer places enormous economic and psychological strains on the population. High throughput drug screening of cancer cell cultures has dominated the research screening for novel, effective anticancer therapies in the past decades. Recently, 3D organoid cultures from the patient’s own cancer cells gain importance in the development of precision therapies. The drug responses can be measured ex vivo in organoids. This, in combination with the patient’s clinical data and genetic information is used to define more effective personalised cancer therapies.There is an urgent need for the development of technologies gearing the drug screening of organoids. We recently evaluated the major advancements and needs of 3D organoid screening field. Our findings show that strictly standardised sample preparation and more complex data analysis solutions are the most desired developments.

Here we propose an artificial intelligence guided low-cost organoid delivery system. It consists of a light microscope, a micro-manipulator and a pressure controller. The device is driven by a deep learning software. The system performs initial viability and morphology-based feature checks on spheroids and transports most appropriate ones between various sample holders throughout the sample preparation phase. This leads to highly controlled experimental conditions of cancer cell organoids treated with various drugs and eliminates a non-trivial side effect of sample variability resulting a step towards the next-generation precision medicine.