Artificial intelligence-based morphologic classification and molecular characterization of neuroblastic tumors from digital histopathology

Siddhi Ramesh; Emma Dyer; Monica Pomaville; Kristina Doytcheva; James Dolezal; Sara Kochanny; Rachel Terhaar; Casey J Mehrhoff; Kritika Patel; Jacob Brewer; Benjamin Kusswurm; Arlene Naranjo; Hiroyuki Shimada; Nicole A Cipriani; Aliya N Husain; Peter Pytel; Elizabeth A Sokol; Susan L Cohn; Rani E George; Alexander T Pearson; Mark A Applebaum

doi:10.1038/s41698-024-00745-0

Artificial intelligence-based morphologic classification and molecular characterization of neuroblastic tumors from digital histopathology

NPJ Precis Oncol. 2024 Nov 8;8(1):255. doi: 10.1038/s41698-024-00745-0.

Authors

Siddhi Ramesh¹, Emma Dyer¹, Monica Pomaville², Kristina Doytcheva³, James Dolezal⁴, Sara Kochanny¹, Rachel Terhaar⁵, Casey J Mehrhoff⁶, Kritika Patel^{7

8}, Jacob Brewer⁹, Benjamin Kusswurm⁹, Arlene Naranjo¹⁰, Hiroyuki Shimada¹¹, Nicole A Cipriani¹², Aliya N Husain¹², Peter Pytel¹², Elizabeth A Sokol¹³, Susan L Cohn¹⁴, Rani E George^{15

16}, Alexander T Pearson¹, Mark A Applebaum¹⁷

Affiliations

¹ Department of Medicine, University of Chicago, Chicago, IL, USA.
² Department of Pediatrics, The Children's Hospital of Philadelphia, Philadelphia, PA, USA.
³ Anatomic Pathology Department of Oklahoma University Medical Center, Oklahoma City, OK, USA.
⁴ Geisinger Cancer Institute, Danville, PA, USA.
⁵ Pritzker School of Medicine, University of Chicago, Chicago, IL, USA.
⁶ Intermountain Primary Children's Hospital, Huntsman Cancer Institute, Spencer Fox Eccles School of Medicine at the University of Utah, Salt Lake City, UT, USA.
⁷ Cancer and Blood Disorders Center, Seattle Children's Hospital, Seattle, WA, USA.
⁸ Division of Hematology/Oncology and Bone Marrow Transplant, Department of Pediatrics, University of Washington, Seattle, WA, USA.
⁹ Applied Data Science Program, University of Chicago, Chicago, IL, USA.
¹⁰ Children's Oncology Group Statistics and Data Center, Department of Biostatistics, University of Florida, Gainesville, FL, USA.
¹¹ Department of Pathology and Pediatrics, Stanford University, Stanford, CA, USA.
¹² Department of Pathology, University of Chicago, Chicago, IL, USA.
¹³ Division of Hematology, Oncology, and Stem Cell Transplantation, Ann & Robert H. Lurie Children's Hospital of Chicago, Northwestern University Feinberg School of Medicine, Chicago, IL, USA.
¹⁴ Department of Pediatrics, University of Chicago, Chicago, IL, USA.
¹⁵ Department of Pediatric Hematology/Oncology, Dana-Farber Cancer Institute and Boston Children's Hospital, Boston, MA, USA.
¹⁶ Department of Pediatrics, Harvard Medical School, Boston, MA, USA.
¹⁷ Department of Pediatrics, University of Chicago, Chicago, IL, USA. mapplebaum@bsd.uchicago.edu.

Abstract

A deep learning model using attention-based multiple instance learning (aMIL) and self-supervised learning (SSL) was developed to perform pathologic classification of neuroblastic tumors and assess MYCN-amplification status using H&E-stained whole slide images from the largest reported cohort to date. The model showed promising performance in identifying diagnostic category, grade, mitosis-karyorrhexis index (MKI), and MYCN-amplification with validation on an external test dataset, suggesting potential for AI-assisted neuroblastoma classification.

Abstract

Grants and funding