A priori prediction of tumour response to neoadjuvant chemotherapy in breast cancer patients using quantitative CT and machine learning
| Autor: | Hadi Moghadas-Dastjerdi, Ali Sadeghi-Naini, Gregory J. Czarnota, Hira Rahman Sha-E-Tallat, Lakshmanan Sannachi |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Receptor
ErbB-2 lcsh:Medicine 030218 nuclear medicine & medical imaging Correlation Machine Learning Tumour biomarkers 0302 clinical medicine Breast cancer Antineoplastic Combined Chemotherapy Protocols AdaBoost Quantitative computed tomography lcsh:Science Mathematics Aged 80 and over Multidisciplinary medicine.diagnostic_test Carcinoma Ductal Breast Middle Aged Prognosis Neoadjuvant Therapy 3. Good health Receptors Estrogen Feature (computer vision) 030220 oncology & carcinogenesis Female Receptors Progesterone Biomedical engineering Adult Adolescent Tumour heterogeneity Feature selection Breast Neoplasms Article 03 medical and health sciences Young Adult medicine Humans Sensitivity (control systems) Aged Receiver operating characteristic business.industry lcsh:R medicine.disease Computer science Carcinoma Lobular ROC Curve lcsh:Q Nuclear medicine business Tomography X-Ray Computed Follow-Up Studies |
| Zdroj: | Scientific Reports Scientific Reports, Vol 10, Iss 1, Pp 1-11 (2020) |
| ISSN: | 2045-2322 |
| Popis: | Response to Neoadjuvant chemotherapy (NAC) has demonstrated a high correlation to survival in locally advanced breast cancer (LABC) patients. An early prediction of responsiveness to NAC could facilitate treatment adjustments on an individual patient basis that would be expected to improve treatment outcomes and patient survival. This study investigated, for the first time, the efficacy of quantitative computed tomography (qCT) parametric imaging to characterize intra-tumour heterogeneity and its application in predicting tumour response to NAC in LABC patients. Textural analyses were performed on CT images acquired from 72 patients before the start of chemotherapy to determine quantitative features of intra-tumour heterogeneity. The best feature subset for response prediction was selected through a sequential feature selection with bootstrap 0.632 + area under the receiver operating characteristic (ROC) curve ($${\mathrm{A}\mathrm{U}\mathrm{C}}_{0.632+}$$ A U C 0.632 + ) as a performance criterion. Several classifiers were evaluated for response prediction using the selected feature subset. Amongst the applied classifiers an Adaboost decision tree provided the best results with cross-validated $${\mathrm{A}\mathrm{U}\mathrm{C}}_{0.632+}$$ A U C 0.632 + , accuracy, sensitivity and specificity of 0.89, 84%, 80% and 88%, respectively. The promising results obtained in this study demonstrate the potential of the proposed biomarkers to be used as predictors of LABC tumour response to NAC prior to the start of treatment. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|