AUTHOR=Yang Min , Liu Huan , Dai Qingli , Yao Ling , Zhang Shun , Wang Zhihong , Li Jing , Duan Qinghong 

TITLE=Treatment Response Prediction Using Ultrasound-Based Pre-, Post-Early, and Delta Radiomics in Neoadjuvant Chemotherapy in Breast Cancer

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.748008

DOI=10.3389/fonc.2022.748008

ISSN=2234-943X

ABSTRACT=Objective To develop and validate a radiomics nomogram based on pre-treatment, early treatment ultrasound (US) radiomics features combined with clinical characteristics for early predicting response to neoadjuvant chemotherapy (NAC) in breast cancer.
Method A total of 217 patients with histological results of breast cancer receiving NAC 4-8 cycles before surgery were enrolled from January 2018 to December 2020. Patients from the study population were randomly separated into a training set(n=152) and a validation set(n=65) with a ratio of 7:3. A total of 788 radiomics features were extracted from each region of interest in US image at pre-treatment baseline (radiomic signature, RS1) , early treatment (after completion of the two cycle of NAC, RS2) and Delta-radiomics (calculated between the pre-treatment and post-treatment features, Delta RS). The Max-Relevance and Min-Redundancy (mRMR) and the least absolute shrinkage and selection operator (LASSO) regression were applied for feature selection. The predictive nomogram was built based on the radiomics signature combined with clinicopathological risk factors. Discrimination, calibration and prediction performance was further evaluated in the validation set. 
Result Of 217 breast masses, 127 (58.5 %) were response to NAC and 90 (41.5 %) were non-response to NAC. Following the features selection, 9 features in RS1, 11 features in RS2 and 8 features in Delta RS were remained, respectively. With multivariate analysis, the RS1, RS2, Delta RS and Ki-67 expression were independently associated with breast NAC response. But the performance of the Delta RS (AUCDelta RS =0.743) was not higher than the RS1 (AUCRS1=0.722, PDelta vs RS1 =0.086) and RS2 (AUCRS2=0.811, PDelta vs RS2 =0.173) with the delong test. The nomogram incorporating RS1, RS2 and Ki-67 expression showed better predictive ability for NAC response with an area under the curve (AUC) of 0.866 in validation cohorts than either the single RS1 (AUC 0.725) or RS2 (AUC 0.793) or the Ki-67 (AUC 0.643). 
Conclusion The nomogram incorporating pre-treatment and early-treatment US radiomics features and Ki-67 expression had good performance for NAC response in breast cancer, which could provide valuable information for individual treatment and timely adjustment of chemotherapy regimens.