Intratumoral analysis of digital breast tomosynthesis for predicting the Ki‐67 level in breast cancer: A multi‐center radiomics study

Abstract

Purpose To non‐invasively evaluate the Ki‐67 level in digital breast tomosynthesis (DBT) images of breast cancer (BC) patients based on subregional radiomics. Methods A total of 266 patients who underwent DBT scans were consecutively enrolled at two centers, between September 2017 and September 2021. The whole tumor region was partitioned into various intratumoral subregions, based on individual‐ and population‐level clustering. Handcrafted radiomics and deep learning‐based features were extracted from the subregions and from the whole tumor region, and were selected by least absolute shrinkage and selection operator (LASSO) regression, yielding radiomics signatures (RSs). The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to assess the developed RSs. Results Each breast tumor region was partitioned into an inner subregion (S1) and a marginal subregion (S2). The RSs derived from S1 always generated higher AUCs compared with those from S2 or from the whole tumor region (W), for the external validation cohort (AUCs, S1 vs. W, handcrafted RSs: 0.583 [95% CI, 0.429–0.727] vs. 0.559 [95% CI, 0.405–0.705], p‐value: 0.920; deep RSs: 0.670 [95% CI, 0.516–0.802] vs. 0.551 [95% CI, 0.397–0.698], p‐value: 0.776). The fusion RSs, combining handcrafted and deep learning‐based features derived from S1, yielded the highest AUCs of 0.820 (95% CI, 0.714–0.900) and 0.792 (95% CI, 0.647–0.897) for the internal and external validation cohorts, respectively. Conclusions The subregional radiomics approach can accurately predict the Ki‐67 level based on DBT data; thus, it may be used as a potential non‐invasive tool for preoperative treatment planning in BC.

MRI‐based radiomics nomogram for the preoperative prediction of deep myometrial invasion of FIGO stage I endometrial carcinoma

“…The U-LASSO-AIC method used in this study has been useful in many previous reports. [40][41][42][43][44][45] The AUC, p, and radiomics model in this study are good, which shows that the screening method is indeed reliable. The four most predictive features from CE-T1W were included in the final combined radiomics signature, including one first-order statistical feature, two GLCM features, and one GLRLM feature.…”

“…At present, there is no unified fixed standard for combining different feature screening methods, and different studies have adopted different methods. The U‐LASSO‐AIC method used in this study has been useful in many previous reports 40–45 . The AUC, p , and radiomics model in this study are good, which shows that the screening method is indeed reliable.…”

Development and validation of combined Ki67 status prediction model for intrahepatic cholangiocarcinoma based on clinicoradiological features and MRI radiomics

“…Currently, radiomics is defined as a high-throughput extraction of numerous image features from medical images, and independent features are applied to the construction of diagnostic, predictive and prognostic models [16]. Several studies have achieved good predictive efficiency in the Ki67 prediction of several malignant cancers, including HCC [17], breast cancer [18] and lung cancer [19]. However, the development and validation of Ki67 status prediction model for ICC lesions based on radiomics features has not yet been studied.…”

Development and verification of radiomics framework for computed tomography image segmentation

“…Subregional radiomic features have been proposed to capture QII of subvolumes created by the clustering method (c‐subvolume). 17 Subregional features extracted from magnetic resonance imaging (MRI) and CT images could capture QII differences between c‐subvolumes. 18 , 19 For example, the lung tumor was classified into three c‐subvolumes (i.e., marginal subregion, fragmental subregion, and inner subregion) to detect the epidermal growth factor receptor mutation using MRI images, 19 among which inner subregion features displayed the optimum predictive performance.…”

“…Subregional radiomic features have been proposed to capture QII of subvolumes created by the clustering method (c‐subvolume) 17 . Subregional features extracted from magnetic resonance imaging (MRI) and CT images could capture QII differences between c‐subvolumes 18,19 .…”