Early Changes in Quantitative Ultrasound Imaging Parameters during Neoadjuvant Chemotherapy to Predict Recurrence in Patients with Locally Advanced Breast Cancer

Abstract

Background: This study was conducted to explore the use of quantitative ultrasound (QUS) in predicting recurrence for patients with locally advanced breast cancer (LABC) early during neoadjuvant chemotherapy (NAC). Methods: Eighty-three patients with LABC were scanned with 7 MHz ultrasound before starting NAC (week 0) and during treatment (week 4). Spectral parametric maps were generated corresponding to tumor volume. Twenty-four textural features (QUS-Tex1) were determined from parametric maps acquired using grey-level co-occurrence matrices (GLCM) for each patient, which were further processed to generate 64 texture derivatives (QUS-Tex1-Tex2), leading to a total of 95 features from each time point. Analysis was carried out on week 4 data and compared to baseline (week 0) data. ∆Week 4 data was obtained from the difference in QUS parameters, texture features (QUS-Tex1), and texture derivatives (QUS-Tex1-Tex2) of week 4 data and week 0 data. Patients were divided into two groups: recurrence and non-recurrence. Machine learning algorithms using k-nearest neighbor (k-NN) and support vector machines (SVMs) were used to generate radiomic models. Internal validation was undertaken using leave-one patient out cross-validation method. Results: With a median follow up of 69 months (range 7–118 months), 28 patients had disease recurrence. The k-NN classifier was the best performing algorithm at week 4 with sensitivity, specificity, accuracy, and area under curve (AUC) of 87%, 75%, 81%, and 0.83, respectively. The inclusion of texture derivatives (QUS-Tex1-Tex2) in week 4 QUS data analysis led to the improvement of the classifier performances. The AUC increased from 0.70 (0.59 to 0.79, 95% confidence interval) without texture derivatives to 0.83 (0.73 to 0.92) with texture derivatives. The most relevant features separating the two groups were higher-order texture derivatives obtained from scatterer diameter and acoustic concentration-related parametric images. Conclusions: This is the first study highlighting the utility of QUS radiomics in the prediction of recurrence during the treatment of LABC. It reflects that the ongoing treatment-related changes can predict clinical outcomes with higher accuracy as compared to pretreatment features alone.

Clinical-radiomics models based on plain X-rays for prediction of lung metastasis in patients with osteosarcoma

“…KNN is a conceptually simple but powerful algorithm that is easy to use, interpret and implement [28]. It has been widely used in previous studies [29][30][31]. Furthermore, we found that XGBoost had the highest ACC in the training group.…”

Artificial intelligence assists precision medicine in cancer treatment

“…ML and DL can also assist in post-radiotherapy management, such as distinguishing between the true and false progression of the tumor, radiation necrosis and tumor recurrence, and promoting clinical medical decision-making, thus improving PM ( 171 – 174 ). In addition, the image-based AI model can also assist radiologists in treatment evaluation, including predicting the response of individual cancer patients to chemotherapy or immunotherapy, and monitoring recurrence and metastasis ( 175 – 177 ). Several radiomics-based ML and DL models can predict patient prognosis, such as recrudesce-free and progression-free survival, survival rate, mortality, surgical results, postoperative metastasis and recurrence.…”

Implementation of Non-Invasive Quantitative Ultrasound in Clinical Cancer Imaging

“…Bhardwaj et al developed a classification model for predicting disease relapses in a cohort of 83 patients with LABC (28 recurrences and 55 non-recurrence) treated with NAC [ 60 ]. The pool of radiomics features included first-order statistical mean-value, GLCM-based textures, and GLCM-based higher-order textures from QUS spectral parametric images.…”

“…The pool of radiomics features included first-order statistical mean-value, GLCM-based textures, and GLCM-based higher-order textures from QUS spectral parametric images. They reported the best model from baseline and changes in week 4 features, achieving 87% sensitivity, 75% specificity, 81% accuracy, and 0.83 AUC [ 60 ].…”