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

Autor: Qi TH; Division of Radiation Oncology, National Cancer Centre Singapore, Singapore, Singapore., Hian OH; School of Computer Science and Engineering, Nanyang Technological University Singapore, Singapore, Singapore., Kumaran AM; Division of Radiation Oncology, National Cancer Centre Singapore, Singapore, Singapore., Tan TJ; Division of Medical Oncology, National Cancer Center Singapore, Singapore, Singapore.; Oncology Academic Programme, Duke-NUS Medical School, Singapore, Singapore., Cong TRY; Division of Medical Oncology, National Cancer Center Singapore, Singapore, Singapore.; Oncology Academic Programme, Duke-NUS Medical School, Singapore, Singapore., Su-Xin GL; Division of Radiation Oncology, National Cancer Centre Singapore, Singapore, Singapore., Lim EH; Division of Medical Oncology, National Cancer Center Singapore, Singapore, Singapore., Ng R; Division of Medical Oncology, National Cancer Center Singapore, Singapore, Singapore.; Oncology Academic Programme, Duke-NUS Medical School, Singapore, Singapore., Yeo MCR; Division of Radiation Oncology, National Cancer Centre Singapore, Singapore, Singapore.; Oncology Academic Programme, Duke-NUS Medical School, Singapore, Singapore., Tching FLLW; Division of Radiation Oncology, National Cancer Centre Singapore, Singapore, Singapore.; Oncology Academic Programme, Duke-NUS Medical School, Singapore, Singapore., Zewen Z; Division of Medical Oncology, National Cancer Center Singapore, Singapore, Singapore.; Oncology Academic Programme, Duke-NUS Medical School, Singapore, Singapore., Hui CYS; Division of Surgery and Surgical Oncology, National Cancer Center Singapore, Singapore, Singapore.; Department of Breast Surgery, Singapore General Hospital, Singapore, Singapore., Xin WR; Division of Radiation Oncology, National Cancer Centre Singapore, Singapore, Singapore.; Oncology Academic Programme, Duke-NUS Medical School, Singapore, Singapore., Ooi SKG; Division of Oncologic Imaging, National Cancer Center Singapore, Singapore, Singapore.; Oncology Academic Programme, Duke-NUS Medical School, Singapore, Singapore., Leong LCH; Department of Diagnostic Radiology, Singapore General Hospital, Singapore, Singapore., Tan SM; Division of Breast Surgery, Changi General Hospital, Singapore, Singapore., Preetha M; Division of Surgery and Surgical Oncology, National Cancer Center Singapore, Singapore, Singapore.; Department of Breast Surgery, Singapore General Hospital, Singapore, Singapore., Sim Y; Division of Surgery and Surgical Oncology, National Cancer Center Singapore, Singapore, Singapore.; Department of Breast Surgery, Singapore General Hospital, Singapore, Singapore., Tan VKM; Division of Surgery and Surgical Oncology, National Cancer Center Singapore, Singapore, Singapore.; Department of Breast Surgery, Singapore General Hospital, Singapore, Singapore., Yeong J; Division of Pathology, Singapore General Hospital, Singapore, Singapore.; Institute of Molecular and Cell Biology, Agency for Science Technology and Research, Singapore, Singapore., Yong WF; Division of Radiation Oncology, National Cancer Centre Singapore, Singapore, Singapore. wong.fuh.yong@singhealth.com.sg.; Oncology Academic Programme, Duke-NUS Medical School, Singapore, Singapore. wong.fuh.yong@singhealth.com.sg., Cai Y; School of Mechanical & Aerospace Engineering, Nanyang Technological University Singapore, Singapore, Singapore. MYYCai@ntu.edu.sg., Nei WL; Division of Radiation Oncology, National Cancer Centre Singapore, Singapore, Singapore. nei.wen.long@singhealth.com.sg.; Oncology Academic Programme, Duke-NUS Medical School, Singapore, Singapore. nei.wen.long@singhealth.com.sg.
Jazyk: angličtina
Zdroj: Breast cancer research and treatment [Breast Cancer Res Treat] 2022 May; Vol. 193 (1), pp. 121-138. Date of Electronic Publication: 2022 Mar 09.
DOI: 10.1007/s10549-022-06521-7
Abstrakt: 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.
(© 2022. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)
Databáze: MEDLINE