Multi-center evaluation of artificial intelligent imaging and clinical models for predicting neoadjuvant chemotherapy response in breast cancer

• Main Authors: Tan, Hong Qi, Ong, Hiok Hian, Kumaran, Arjunan Muthu, Tan, Tira J., Tan, Ryan Ying Cong, Lee, Ghislaine Su-Xin, Lim, Elaine Hsuen, Ng, Raymond, Yeo, Richard Ming Chert, Lim, Faye Lynette Tching Wei, Zhang, Zewen, Yang, Christina Shi Hui, Wong, Ru Xin, Ooi, Gideon Su Kai, Chee, Lester Hao Leong, Tan, Su Ming, Preetha, Madhukumar, Sim, Yirong, Tan, Veronique Kiak Mien, Yeong, Joe, Wong, Fuh Yong, Cai, Yiyu, Nei, Wen Long, JBCR, Ai3
• Other Authors: School of Mechanical and Aerospace Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Computer science and engineering; Engineering::Mechanical engineering; Neoadjuvant Chemotherapy; Breast Cancer
• Online Access: https://hdl.handle.net/10356/163001
• Institution: Nanyang Technological University

Background: Neoadjuvant chemotherapy (NAC) plays an important role in the management of locally advanced breast cancer. It allows for downstaging of tumors, potentially allowing for breast conservation. NAC also allows for in-vivo testing of the tumors’ response to chemotherapy and provides important prognostic information. There are currently no clearly defined clinical models that incorporate imaging with clinical data to predict response to NAC. Thus, the aim of this work is to develop a predictive AI model based on routine CT imaging and clinical parameters to predict response to NAC. Methods: The CT scans of 324 patients with NAC from multiple centers in Singapore were used in this study. Four different radiomics models were built for predicting pathological complete response (pCR): first two were based on textural features extracted from peri-tumoral and tumoral regions, the third model based on novel space-resolved radiomics which extract feature maps using voxel-based radiomics and the fourth model based on deep learning (DL). Clinical parameters were included to build a final prognostic model. Results: The best performing models were based on space-resolved and DL approaches. Space-resolved radiomics improves the clinical AUCs of pCR prediction from 0.743 (0.650 to 0.831) to 0.775 (0.685 to 0.860) and our DL model improved it from 0.743 (0.650 to 0.831) to 0.772 (0.685 to 0.853). The tumoral radiomics model performs the worst with no improvement of the AUC from the clinical model. The peri-tumoral combined model gives moderate performance with an AUC of 0.765 (0.671 to 0.855). Conclusions: Radiomics features extracted from diagnostic CT augment the predictive ability of pCR when combined with clinical features. The novel space-resolved radiomics and DL radiomics approaches outperformed conventional radiomics techniques.