AACR 2025: An Artificial Intelligence-based Model may help Improve Pediatric Sarcoma Subtyping

Results from a study presented at the annual meeting of the American Association for Cancer Research (AACR), held April 25-30, 2025, in Chicago, Illinois, suggests that an artificial intelligence (AI)-based model accurately classified pediatric sarcomas using digital pathology images alone. [1]

Pediatric sarcomas are a heterogeneous group of tumors accounting for approximately 10% of childhood solid tumors. This is a rare type of diverse tumors 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. [2]

Pediatric sarcomas are divided into soft tissue sarcomas and osseous tumors. Soft tissue sarcomas are further delineated into rhabdomyosarcomas, which affect young children and non-rhabdomyosarcomas, which are more common in adolescents. The most common bone sarcomas are osteosarcomas and Ewing sarcoma. [2]

Treatment of pediatric sarcoma typically involves a combination of surgery, chemotherapy, and radiation therapy. The specific treatment plan is tailored to the type and stage of the sarcoma, as well as the child’s individual needs and overall health, hence accurate classification is essential.

Accurate classification
“Accurate classification of a patient’s sarcoma subtype is an important step that helps guide and optimize 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 specialized 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.” Thiesen noted.

Deep neural network models (DNNs) trained on histopathology slides may help reduce the time and cost to diagnosis and attenuate disparities in care based on geographical location and socioeconomic status.

In their study, Thiesen and colleagues examined the potential of AI to accurately identify pediatric sarcoma subtypes.

They demonstrated the efficacy of automated image analysis for assigning sarcoma diagnoses across centers by identifying Ewing Sarcoma, distinguishing rhabdomyosarcoma vs non-rhabdomyosarcoma soft tissue sarcomas, as well as classifying alveolar, embryonal, and spindle cell RMS subtypes.

As part of the study, 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 recognize patterns associated with each subtype.

Numerical data
“By digitizing tissue pathology slides, we translated the visual data a pathologist normally studies into numerical data that a computer can analyze,” Thiesen explained.

“Much like our cell phones can recognize a person’s face in photos and automatically generate an album of photos of that person, our AI-based models recognize certain tumor morphology patterns in the digitized slides and group them into diagnostic categories associated with specific sarcoma subtypes,” Thiesen added.

Briefly, the researchers developed and applied open-source software to harmonize the images collected from different institutions to account for variation in format, staining, and magnification, among other factors. The harmonized 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 categorize each slide as a specific subtype.

Validation Experiments
In validation experiments, the AI algorithms identified sarcoma subtypes with high accuracy, Thiesen reported. Specifically, the AI-driven models correctly distinguished between:

• Ewing sarcoma and other sarcoma types in 92.2% of cases;
• Non-rhabdomyosarcoma soft tissue sarcomas and rhabdomyosarcoma soft tissue sarcomas in 93.8% of cases;
• Alveolar rhabdomyosarcoma and embryonal rhabdomyosarcoma in 95.1% of cases; and
• Alveolar rhabdomyosarcoma, embryonal rhabdomyosarcoma, and spindle cell rhabdomyosarcoma in 87.3% of cases.

“Our findings demonstrate that AI-based models can accurately diagnose various subtypes of pediatric sarcoma using only routine pathology images,” Thiesen explained.

“This AI-driven model could help provide more pediatric patients access to quick, streamlined, and highly accurate cancer diagnoses regardless of their geographic location or health care setting,” he added.

“Our models are built in such a way that new images can be added and trained with minimal computational equipment,” Thiesen further noted.

“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.”

Study limitations
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 pediatric sarcomas, their imaging dataset may be the largest multicenter collection of pediatric 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,” Thiesen concluded.

The study was organized by surgical oncologist Jill Rubinstein, MD, PhD, senior research scientist at The Jackson Laboratory, and utilized 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.

Reference
[1] Thiesen A, Domanskyi S, Foroughi pour A, Zhang J, Sheridan TB, Neuhauser SB, Stetson A, Dannheim K, Cameron DB, Ahn S, Wu H, Christison-Lagay ER, Bult CJ, Chuang JH, Rubinstein JC. Automated classification of pediatric sarcoma using digital histopathology. In: Proceedings of the 116th Annual Meeting of the American Association for Cancer Research; 2025 April 25-30; Chicago, IL.: AACR; 2025. Abstract nr 2423 / 8
[2] Williams RF, Fernandez-Pineda I, Gosain A. Pediatric Sarcomas. Surg Clin North Am. 2016 Oct;96(5):1107-25. doi: 10.1016/j.suc.2016.05.012. PMID: 27542645.

Featured image: Young Girl Receiving Chemotherapy. © 2020 – 2025 National Cancer Institute (NCI). Use under the Unsplash License.

DOI