Clinically grounded computational science

Statistical and machine learning systems for clinically grounded translational research.

The Knowlton Lab develops interpretable analytics, evaluation workflows, and decision support methods for breast imaging, reproductive biology, and biomedical discovery in real clinical settings.

4
Selected recent publications
6
Current PhD students
2
Institutional homes

Research programmes

Research programmes

Method development connected to translational use cases, not benchmark theatre.

Explore all

Supervision

Supervision

PhD and Masters training across imaging, machine learning, and biomedical data science.

Explore all

Teaching

Teaching

Practical statistics and data science courses with direct links to hosted materials.

Explore all

Selected work

Publications are now part of the site, not hidden behind a profile link.

2026 Journal of Medical Imaging and Radiation Oncology

Improving Breast Cancer Detection in Higher Risk Women: A Multi-Modality Imaging Evaluation in a Private Screening Clinic

Evaluates tomosynthesis, ultrasound, and MRI in a risk-stratified breast screening workflow for women with dense breasts and elevated risk.

Breast imagingClinical translationRisk stratification
Read abstract
2025 Journal of Assisted Reproduction and Genetics

Accurate machine learning model for human embryo morphokinetic stage detection

Describes a machine learning pipeline for identifying 17 morphokinetic stages in pre-implantation embryo development from time-lapse imagery.

EmbryologyComputer visionMachine learning
Read abstract
2024 Cancers

Analysis of HER2-Low Breast Cancer in Aotearoa New Zealand: A Nationwide Retrospective Cohort Study

National cohort analysis of HER2-positive, HER2-low, and HER2-zero invasive breast cancers in Aotearoa New Zealand.

Breast cancerPopulation studyAotearoa
Read abstract

Profiles and contact

Cross-institutional work, one cleaner front door.

The site now brings research themes, publications, teaching resources, and supervision into one cohesive experience while keeping external profile links easy to reach.