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

2021 ◽  
Author(s):  
Tao Jiang ◽  
Wenyan Jiang ◽  
Shijie Chang ◽  
Hongbo Wang ◽  
Shuxian Niu ◽  
...  
2021 ◽  
Vol In Press (In Press) ◽  
Author(s):  
Aysegul Altunkeser ◽  
Zeynep Fatma Arslan ◽  
Mehmet Ali Eryilmaz ◽  
Muslu Kazım Korez ◽  
Zeynep Bayramoğlu

Background: Digital mammography (DM) and digital breast tomosynthesis (DBT) are important radiological modalities, which increase the survival of breast cancer patients. Breast cancer is a morphologically heterogeneous disease with various histopathological parameters and multiple receptors in its biological profile. Objectives: This study aimed to analyze the morphological features of invasive breast cancer on DM and DBT, to investigate the contribution of DBT to DM, to examine the association of DBT findings with pathological molecular subtypes, Bloom-Richardson grade, and Ki-67 index, and to determine the effect of breast parenchyma density on the relationship between DBT findings and hormone receptors. Patients and Methods: A total of 36 patients with malignant lesions were evaluated in this study. According to the American College of Radiology (ACR) classification, the lesion features were divided into subgroups based on DM and DBT, and the findings were compared. The relationships between DBT findings and the hormone receptor status, molecular classification, and Bloom-Richardson grade were also investigated, and the effect of density on these relationships was assessed. Results: The mean age of the patients (n = 36) was 53 years. Based on the comparison of DM and DBT findings, spiculated margins, mass density, architectural distortion, and microcalcifications were significantly more frequent in DBT. Lesions with indistinct margins on DM were observed as mass lesions with spiculated margins on DBT (P < 0.001). Regarding the relationship between DBT findings and hormone receptor status and Ki-67 proliferation index, in PR-positive patients, an irregular tumor shape was more common (89.7%). In PR-negative patients, skin changes and nipple retraction were more frequently seen (P = 0.03 for skin changes, and P = 0.049 for nipple retraction). Regarding the association between Bloom-Richardson grade and DBT findings, tumors with a higher grade were more likely to be associated with a high tumor density (P = 0.032). Also, considering the relationship between molecular classification and DBT findings, skin changes and nipple retraction were significantly more frequent in triple-negative masses compared to other subtypes (P = 0.011 for skin changes and P = 0.016 for nipple retraction). Conclusions: DBT is superior to DM, as it reveals the lesion margins, density, and architectural distortion more accurately. The majority of PR-positive tumors were irregular, while most PR-negative cases were round. The mass density also increased as the tumor grade increased. Skin change and nipple retraction were frequently seen in triple-negative tumors compared to other subtypes. Therefore, DBT is a promising diagnostic tool for showing molecular subtypes in dense breasts.


2019 ◽  
Vol 3 (1) ◽  
Author(s):  
Alberto Stefano Tagliafico ◽  
Bianca Bignotti ◽  
Federica Rossi ◽  
Joao Matos ◽  
Massimo Calabrese ◽  
...  

Author(s):  
Suzanne L. van Winkel ◽  
Alejandro Rodríguez-Ruiz ◽  
Linda Appelman ◽  
Albert Gubern-Mérida ◽  
Nico Karssemeijer ◽  
...  

Abstract Objectives Digital breast tomosynthesis (DBT) increases sensitivity of mammography and is increasingly implemented in breast cancer screening. However, the large volume of images increases the risk of reading errors and reading time. This study aims to investigate whether the accuracy of breast radiologists reading wide-angle DBT increases with the aid of an artificial intelligence (AI) support system. Also, the impact on reading time was assessed and the stand-alone performance of the AI system in the detection of malignancies was compared to the average radiologist. Methods A multi-reader multi-case study was performed with 240 bilateral DBT exams (71 breasts with cancer lesions, 70 breasts with benign findings, 339 normal breasts). Exams were interpreted by 18 radiologists, with and without AI support, providing cancer suspicion scores per breast. Using AI support, radiologists were shown examination-based and region-based cancer likelihood scores. Area under the receiver operating characteristic curve (AUC) and reading time per exam were compared between reading conditions using mixed-models analysis of variance. Results On average, the AUC was higher using AI support (0.863 vs 0.833; p = 0.0025). Using AI support, reading time per DBT exam was reduced (p < 0.001) from 41 (95% CI = 39–42 s) to 36 s (95% CI = 35– 37 s). The AUC of the stand-alone AI system was non-inferior to the AUC of the average radiologist (+0.007, p = 0.8115). Conclusions Radiologists improved their cancer detection and reduced reading time when evaluating DBT examinations using an AI reading support system. Key Points • Radiologists improved their cancer detection accuracy in digital breast tomosynthesis (DBT) when using an AI system for support, while simultaneously reducing reading time. • The stand-alone breast cancer detection performance of an AI system is non-inferior to the average performance of radiologists for reading digital breast tomosynthesis exams. • The use of an AI support system could make advanced and more reliable imaging techniques more accessible and could allow for more cost-effective breast screening programs with DBT.


Sign in / Sign up

Export Citation Format

Share Document