An artificial intelligence (AI)-based model accurately classified paediatric sarcomas using digital pathology images alone, according to results presented at the American Association for Cancer Research (AACR) Annual Meeting, held April 25-30.
Paediatric sarcomas are rare and diverse tumours that can form in various types of soft tissue, including muscle, tendons, fat, blood or lymphatic vessels, nerves, or the tissue surrounding joints.
Sarcomas are classified into subtypes based on several factors, including the tissue of origin and various molecular features.
“Accurate classification of a patient’s sarcoma subtype is an important step that helps guide and optimise treatment,” said Adam Thiesen, an MD/PhD candidate at UConn Health and The Jackson Laboratory in the lab of Jeffrey Chuang, PhD.
“Unfortunately, the heterogeneity of sarcomas makes them particularly difficult to classify, often requiring complex molecular and genetic testing, as well as external review by highly specialised pathologists who use pattern recognition skills honed through years of training to arrive at a diagnosis—resources that are not readily available in many health care settings.”
In this study, Thiesen and colleagues examined the potential of AI to accurately identify paediatric sarcoma subtypes.
They used 691 digital images of pathology slides from collaborators at Massachusetts General Hospital, Yale New Haven Children’s Hospital, St. Jude Children’s Hospital, and the Children’s Oncology Group, representing nine sarcoma subtypes to train AI algorithms to recognise patterns associated with each subtype.
“By digitising tissue pathology slides, we translated the visual data a pathologist normally studies into numerical data that a computer can analyse,” Thiesen explained.
“Much like our cell phones can recognise a person’s face in photos and automatically generate an album of photos of that person, our AI-based models recognise certain tumour morphology patterns in the digitised slides and group them into diagnostic categories associated with specific sarcoma subtypes.”
Briefly, the researchers developed and applied open-source software to harmonise the images collected from different institutions to account for variation in format, staining, and magnification, among other factors.
The harmonised images were then converted into small tiles before being fed into deep learning models that extracted numerical data for analysis by a novel statistical method.
The statistical method generated summaries of each slide’s features, which were evaluated by the trained AI algorithms to categorise each slide as a specific subtype.
In validation experiments, the AI algorithms identified sarcoma subtypes with high accuracy, Thiesen reported.
Specifically, the AI-driven models correctly distinguished between:
“Our findings demonstrate that AI-based models can accurately diagnose various subtypes of paediatric sarcoma using only routine pathology images,” said Thiesen.
“This AI-driven model could help provide more paediatric patients access to quick, streamlined, and highly accurate cancer diagnoses regardless of their geographic location or health care setting.
“Our models are built in such a way that new images can be added and trained with minimal computational equipment,” he added.
“After the standard data processing, clinicians could theoretically use our models on their own laptops, which could vastly increase accessibility even in under-resourced settings.”
A limitation of the study was that the number of available pathology images was smaller than the researchers would have wanted for training AI algorithms.
However, Thiesen noted that, given the rarity of paediatric sarcomas, their imaging dataset may be the largest multicenter collection of paediatric sarcomas to date, representing multiple subtypes, anatomical locations, and patient demographics.
“We hope that, over time, additional groups will work with us to further increase the size of this dataset,” said Thiesen.
The study was organised by surgical oncologist Jill Rubinstein, MD, PhD, senior research scientist at The Jackson Laboratory, and utilised software created by Sergii Domanskyi, PhD, associate computational scientist at The Jackson Laboratory.
This research was supported by the National Institutes of Health, The Jackson Laboratory, and Hartford Hospital.
Thiesen declares no conflicts of interest.
We are an independent charity and are not backed by a large company or society. We raise every penny ourselves to improve the standards of cancer care through education. You can help us continue our work to address inequalities in cancer care by making a donation.
Any donation, however small, contributes directly towards the costs of creating and sharing free oncology education.
Together we can get better outcomes for patients by tackling global inequalities in access to the results of cancer research.
Thank you for your support.