Joshua Millward

Joshua Millward

Auto-generated profile, based on publicly available information

Joshua Millward

La Trobe University

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 March 2025 in Journal of Translational Medicine
Verified
Journal Article
Open access
PDF file
JMJoshua Millward
Joshua Millward
ZHZhen He
Zhen He
ANAiden Nibali
Aiden Nibali
DMDmitri Mouradov
Dmitri Mouradov
LMLisa A Mielke
Lisa A Mielke
DWDavid S Williams
David S Williams
Background: The presence of tumour-infiltrating lymphocytes (TILs) is a well-established prognostic biomarker across multiple cancer types, with higher TIL counts being associated with lower recurrence rates and improved patient survival. We aimed to examine whether an automated intraepithelial TIL (iTIL) assessment could stratify patients by risk, with the ability to generalise across independent patient cohorts, using routine H&E slides of colorectal cancer (CRC). To our knowledge, no other existing fully automated iTIL system has demonstrated this capability. Methods: An automated method employing deep neural networks was developed to enumerate iTILs in H&E slides of CRC. The method was applied to a Stage III discovery cohort (n = 353) to identify an optimal threshold of 17 iTILs per-mm2 tumour for stratifying relapse-free survival. Using this threshold, patients from two independent Stage II-III validation cohorts (n = 1070, n = 885) were classified as “TIL-High” or “TIL-Low”. Results: Significant stratification was observed in terms of overall survival for a combined validation cohort univariate (HR 1.67, 95%CI 1.39–2.00; p < 0.001) and multivariate (HR 1.37, 95%CI 1.13–1.66; p = 0.001) analysis. Our iTIL classifier was an independent prognostic factor within proficient DNA mismatch repair (pMMR) Stage II CRC cases with clinical high-risk features. Of these, those classified as TIL-High had outcomes similar to pMMR clinical low risk cases, and those classified TIL-Low had significantly poorer outcomes (univariate HR 2.38, 95%CI 1.57–3.61; p < 0.001, multivariate HR 2.17, 95%CI 1.42–3.33; p < 0.001). Conclusions: Our deep learning method is the first fully automated system to stratify patient outcome by analysing TILs in H&E slides of CRC, that has shown generalisation capabilities across multiple independent cohorts.

1 April 2026 in Psychological Methods
Verified
Journal Article
Open access
BRBen Riordan
Ben Riordan
JMJoshua Millward
Joshua Millward
ZHZhen He
Zhen He
DADan Anderson-Luxford
Dan Anderson-Luxford
SSSamatha Pararath Salim
Samatha Pararath Salim
EKEmmanuel Kuntsche
Emmanuel Kuntsche
Thanks to the popularity of smartphones with high-quality cameras and social media platforms, an exceptional amount of image data is generated and shared daily. This visual data can provide unprecedented insights into daily life and can be used to help answer research questions in psychology. However, the traditional methods used to analyze visual data are burdensome and are either time-intensive (e.g., content analysis) or require technical training (e.g., developing and training deep learning models). Zero-shot learning, where a pretrained model is used without any additional training, requires less technical expertise and may be a particularly attractive method for psychology researchers aiming to analyze image data. In this tutorial, we aim to provide an overview and step-by-step guide on how to analyze visual data with zero-shot learning. Specifically, we demonstrate how to use two popular models (Contrastive Language-Image Pretraining and Large Language and Vision Assistant) to identify a beverage in an image from a data set where we manipulated the type of beverage present, the setting, and the prominence of the beverage in the image (foreground, midground, background). To guide researchers through this process, we provide open code and data on GitHub and as a Google Colab notebook. Finally, we discuss how to interpret and report accuracy, how to create a validation data set, what steps need to be taken to implement the models with new data, and discuss future challenges and limitations of the method. To conclude, zero-shot learning requires less technical expertise and may be a particularly attractive method for psychology researchers aiming to analyze image data. (PsycInfo Database Record (c) 2025 APA, all rights reserved).


26 January 2026 in Addiction
Verified
Journal Article
Closed access
SSSamatha Pararath Salim
Samatha Pararath Salim
ZHZhen He
Zhen He
JMJoshua Millward
Joshua Millward
EKEmmanuel Kuntsche
Emmanuel Kuntsche
BRBen Riordan
Ben Riordan

18 January 2026 in Drug and Alcohol Review
Verified
Journal Article
Closed access
SSSamatha Pararath Salim
Samatha Pararath Salim
ZHZhen He
Zhen He
EKEmmanuel Kuntsche
Emmanuel Kuntsche
JMJoshua Millward
Joshua Millward
BRBen Riordan
Ben Riordan

1 February 2026 in Disease Models & Mechanisms
Verified
Journal Article
Open access
SMSarah Mele
Sarah Mele
JMJoshua Millward
Joshua Millward
LNLong Nguyen
Long Nguyen
NRNatasha Ruth
Natasha Ruth
JGJemma Gasperoni
Jemma Gasperoni
TJTravis Johnson
Travis Johnson
Quantitative behavioural analysis is a powerful approach for linking genotype to phenotype, but many existing tools require specialised hardware, extensive preprocessing or coding expertise. We present Segment Anything Model for Behavioural Analysis (SAMBA), an open-access, Google Colab-based pipeline that harnesses the Segment Anything Model 2 (SAM2) for accurate, semi-automated tracking without thresholding or background subtraction. With minimal user input, SAMBA extracts movement parameters, detects behavioural states and supports batch processing. Validating SAMBA in three Drosophila melanogaster models of human neurological disease revealed impaired locomotion, reduced speed and altered decision-making. We further demonstrated adaptability to adult Drosophila and larval zebrafish, underscoring its cross-species utility. By combining foundation-model segmentation with an accessible interface, SAMBA lowers technical barriers to analysing motor pattern defects and is readily extendable to diverse model organisms, life stages and experimental paradigms. This flexibility positions SAMBA as a valuable platform for accelerating disease mechanism studies, genetic screens and preclinical testing.