Click here to

Session: Education General ePoster Viewing [Return to Session]

A Multi-Modal Deep Learning-Based Decision Support System for Individualized Radiotherapy of Non-Small Cell Lung Cancer

A Niecikowski1, S Gupta2, G Suarez3, J Kim4, H Chen5, F Guo6, W Long7, J Deng8*, (1) Yale University, New Haven, CT (2) Delhi Technological University, India,(3) University of Puerto Rico, Mayaguez, Puerto Rico, (4) Yale University, New Haven, CT (5) Yale New Haven Hospital, New Haven, CT, (6) Yale New Haven Hospital, New Haven, CT, (7) Yale University School of Medicine, New Haven, CT, (8) Yale University School of Medicine, New Haven, CT


PO-GePV-E-7 (Sunday, 7/10/2022)   [Eastern Time (GMT-4)]

ePoster Forums

Purpose: In cancer, interactions between the tumor and host can exist in multiple modalities across scales such as clinical, genomic, molecular, pathological, and radiological imaging, which poses a challenge to clinicians in making treatment decisions. AI can explore potential care paths to generate the best treatment option for a patient while maximizing benefits and minimizing toxicities. In this work, we aim to develop a multi-modal, AI-empowered, clinical decision support system for personalized radiotherapy of non-small cell lung cancer patients.

Methods: With IRB approval, data of 217 non-small cell lung cancer patients was obtained, which included treatment planning data, images, and clinical notes. Treatment planning factors were focused on clinical, demographic, and dose-volume indexes, radiomic features were extracted using 3D Slicer, and the clinical notes were analyzed using natural language processing. Patient toxicities were ranked on a RTOG scale of 0-5 on radiation pneumonitis severity, while the outcomes were ranked on from 0-3 based on tumor reduction over 3 years per RECIST 1.1 guidelines. The consolidated data was input into a deep neural network with five hidden layers. Using 5-fold cross validation testing, an optimal set of weights was determined.

Results: The accuracy of the model was 89.4% for predicting whether radiation pneumonitis was severe (RTOG >=2) and was 71.0% in predicting whether the treatment was successful after 3 years. This approach was superior to traditional approaches focusing on a single datatype. The model performed well with up to 5% of the training data missing, reflecting real clinical challenges.

Conclusion: In this work, we’ve developed a multi-modality-based decision support system for radiation therapy and demonstrated its efficacy in predicting radiation-induced pneumonitis and patient outcome. Future work will be on automating the curation of patient data to achieve adaptive personalized radiotherapy for more robust clinical decision support in the clinic.

Funding Support, Disclosures, and Conflict of Interest: NSF Funding


Not Applicable / None Entered.


Not Applicable / None Entered.

Contact Email