Researchers at the UCLA Health Jonsson Comprehensive Cancer Centre have developed a new platform that combines 3D bioprinting, advanced imaging and artificial intelligence to better monitor how cancer responds to treatment.

The technology could help researchers identify promising cancer therapies more rapidly and provide a way to test treatments on a patient's own tumour cells, helping guide more personalised treatment decisions.

Described in Nature Protocols, the approach uses cancer cells from patients to create tiny, lab-grown replicas of tumours, known as organoids, and continuously tracks their response to different drugs.

Artificial intelligence then analyses the resulting data, helping scientists evaluate hundreds of potential therapies simultaneously to uncover patterns in drug responses that could inform treatment strategies for cancers with few effective options.

Why it matters 

Tumour organoids have become powerful tools for cancer research because they more closely resemble patient tumours than traditional laboratory models.

However, many current systems still struggle to combine biological accuracy with the speed, consistency, and scale needed for larger studies or clinical use.

This study addresses that challenge by creating a platform that can generate and analyse large numbers of patient-derived tumour organoids while capturing detailed information about how they respond to treatment.

What the study did

The researchers developed a unified workflow that uses extrusion bioprinting to generate three-dimensional tumour organoids embedded in extracellular matrix constructs designed for high-throughput multiwell formats.

These organoids were then continuously monitored using high-speed, label-free quantitative phase imaging, which tracks changes in biomass and growth dynamics to measure tumour fitness over time.

The approach does not require dyes or destructive assays, which can alter cell behaviour and limit how long cells can be observed.

To analyse the resulting datasets, the platform incorporates automated image reconstruction, deep learning-based segmentation, and machine learning-based tracking of individual organoid responses to therapy.

This allows researchers to quantify drug responses at single-organoid resolution across thousands of samples, providing a detailed view of tumour heterogeneity and differences in how tumours respond to therapy.

What they found

The platform successfully measured how tumour organoids responded to drug treatment over time, both in established cancer cell lines and in a patient-derived tumour sample.

Advanced imaging allowed researchers to continuously monitor organoid growth changes in response to a range of drugs, while artificial intelligence helped analyse large amounts of data and track responses at the level of individual organoids.

“Instead of asking whether a drug works on average for a large number of tumour cells, we can now determine which specific organoids respond and which do not, and, ultimately, have an approach to determine the underlying reasons for unique response profiles,” said Dr. Michael Teitell, director of the UCLA Health Jonsson Comprehensive Cancer Centre, professor of pathology and laboratory medicine and co-senior author of the study.

“This allows us to measure drug responses across thousands of individual organoids, detect rare resistant tumour populations, track growth and treatment responses over time, and better predict which therapies may work for a particular patient.”

What this means for patients

The technology points to a potential approach in which doctors could test cancer drugs on a patient’s own tumour cells before treatment begins.

By helping researchers identify which therapies are most likely to work for a particular tumour, the method could support more personalised treatment decisions, particularly for patients with rare and hard-to-treat cancers.

Source: University of California - Los Angeles Health Sciences