Suzanne L. van Winkel

Mrs. Suzanne L. van Winkel

Department of Medical Imaging, Radboud university medical center, Nijmegen, The Netherlands
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 May 2021 in European Radiology
Verified
Journal Article
Open access
PDF file
Suzanne L. van WinkelSuzanne L. van Winkel
Suzanne L. van Winkel
ARAlejandro Rodríguez-Ruiz
Alejandro Rodríguez-Ruiz
LALinda Appelman
Linda Appelman
AGAlbert Gubern-Mérida
Albert Gubern-Mérida
NKNico Karssemeijer
Nico Karssemeijer
RMRitse M Mann
Ritse M Mann
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.

14 August 2025 in The Lancet Digital Health
Verified
Journal Article
Open access
Suzanne L. van WinkelSuzanne L. van Winkel
Suzanne L. van Winkel
JPJim Peters
Jim Peters
NJNatasja Janssen
Natasja Janssen
JKJaap Kroes
Jaap Kroes
ELElizabeth A Loehrer
Elizabeth A Loehrer
RMRitse M Mann
Ritse M Mann
Breast cancer screening programmes have shown to reduce mortality, but current methods face challenges such as limited mammographic sensitivity, limited resources, and variability in radiologist expertise. Artificial intelligence (AI) offers potential to improve screening accuracy and efficiency. This study simulated different screening scenarios, evaluating the performance of population-based breast cancer screening when using an AI system as a stand-alone reader or second reader. In this retrospective cohort study, 42 236 consecutive 2D mammograms from 42 100 women attending the Dutch population-based breast cancer screening between Sept 1, 2016, and Aug 31, 2018 were processed by an AI-based cancer detection system (Transpara version 1.7.0, ScreenPoint Medical). Verified outcomes from the Netherlands Cancer Registry on screen-detected cancers, interval cancers, and later-in-future-detected breast cancers were available with 4-year follow-up. We compared sensitivity, specificity, and recall-rate between single human reading, double human reading, stand-alone AI reading, and combined single human reading with AI. Furthermore, we assessed potential differences in performance regarding breast density, tumour size, lymph-node positivity, and invasiveness between cancers identified by single human readers and AI alone. After follow-up, 580 mammograms (579 woman) were labelled positive: 291 screen-detected cancers, 102 interval cancers, and 187 future breast cancers. Double human reading recalled 1244 mammograms (2·9%, 291 screen-detected cancers) and combined single human reading with AI recalled 2112 mammograms (5·0%, 282 screen-detected cancers, 29 interval cancers, 38 future breast cancers), improving the sensitivity by 8·4% (95% CI 5·7-11·2, p<0·0001). No significant difference in performance between combined single human reading with AI across density categories was found. AI-detected future breast cancers and interval cancers missed by human readers were more often invasive cancers (26·7%) or tumours larger than 20 mm in diameter (16·6%) by the time of eventual detection compared with the average screen-detected cancers. Evaluating screening mammograms with one human reader and AI leads to increased breast cancer detection compared with double human reading, independent of breast density. However, an effective arbitration process is needed as the recall rate increases. AI-identified breast cancers that are missed by human readers seem larger and more often invasive by the time they are eventually detected, confirming the clinical relevance of these cases, recognisable by AI at an earlier stage. MARBLE.

1 February 2025 in Radiology
Verified
Journal Article
Closed access
Suzanne L. van WinkelSuzanne L. van Winkel
Suzanne L. van Winkel
Riccardo SampernaRiccardo Samperna
Riccardo Samperna
ELElizabeth A. Loehrer
Elizabeth A. Loehrer
JKJaap Kroes
Jaap Kroes
ARAlejandro Rodriguez-Ruiz
Alejandro Rodriguez-Ruiz
RMRitse M. Mann
Ritse M. Mann
An artificial intelligence system at mammography effectively selected women with intermediate risk for breast cancer development (up to 50% lifetime risk) for supplemental MRI screening.

19 June 2025 in Diagnostics
Verified
Journal Article
Open access
PDF file
Suzanne L. van WinkelSuzanne L. van Winkel
Suzanne L. van Winkel
ISIoannis Sechopoulos
Ioannis Sechopoulos
ARAlejandro Rodríguez-Ruiz
Alejandro Rodríguez-Ruiz
WVWouter Jan Hendrik Veldkamp
Wouter Jan Hendrik Veldkamp
GGGisella Gennaro
Gisella Gennaro
RMRitse M. Mann
Ritse M. Mann
Background: The integration of artificial intelligence (AI) in digital mammography (DM) screening holds promise for early breast cancer detection, potentially enhancing accuracy and efficiency. However, AI performance is not identical to that of human observers. We aimed to identify common morphological image characteristics of true cancers that are missed by either AI or human screening when their interpretations are discrepant. Methods: Twenty-six breast cancer-positive cases, identified from a large retrospective multi-institutional digital mammography dataset based on discrepant AI and human interpretations, were included in a reader study. Ground truth was confirmed by histopathology or ≥1-year follow-up. Fourteen radiologists assessed lesion visibility, morphological features, and likelihood of malignancy. AI performance was evaluated using receiver operating characteristic (ROC) analysis and area under the curve (AUC). The reader study results were analyzed using interobserver agreement measures and descriptive statistics. Results: AI demonstrated high discriminative capability in the full dataset, with AUCs ranging from 0.903 (95% CI: 0.862–0.944) to 0.946 (95% CI: 0.896–0.996). Cancers missed by AI had a significantly smaller median size (9.0 mm, IQR 6.5–12.0) compared to those missed by human readers (21.0 mm, IQR 10.5–41.0) (p = 0.0014). Cancers in discrepant cases were often described as having ‘low visibility’, ‘indistinct margins’, or ‘irregular shape’. Calcifications were observed in 27% of human-missed cancers (42/154) versus 18% of AI-missed cancers (38/210). A very high likelihood of malignancy was assigned in 32.5% (50/154) of human-missed cancers compared to 19.5% (41/210) of AI-missed cancers. Overall inter-rater agreement was poor to fair (<0.40), indicating interpretation challenges of the selected images. Among the human-missed cancers, calcifications were more frequent (42/154; 27%) than among the AI-missed cancers (38/210; 18%) (p = 0.396). Furthermore, 50/154 (32.5%) human-missed cancers were deemed to have a very high likelihood of malignancy, compared to 41/210 (19.5%) AI-missed cancers (p = 0.8). Overall inter-rater agreement on the items assessed during the reader study was poor to fair (<0.40), suggesting that interpretation of the selected images was challenging. Conclusions: Lesions missed by AI were smaller and less often calcified than cancers missed by human readers. Cancers missed by AI tended to show lower levels of suspicion than those missed by human readers. While definitive conclusions are premature, the findings highlight the complementary roles of AI and human readers in mammographic interpretation.

12 June 2025 in European Radiology
Verified
Journal Article
Open access
PDF file
Suzanne L. van WinkelSuzanne L. van Winkel
Suzanne L. van Winkel
RSRiccardo Samperna
Riccardo Samperna
ELElizabeth A. Loehrer
Elizabeth A. Loehrer
CDCaroline A. Drukker
Caroline A. Drukker
KSKelly Sessink
Kelly Sessink
RMRitse M. Mann
Ritse M. Mann
Objective: This study evaluates breast cancer (BC) detection in women with ≥ 20% lifetime risk who discontinued annual breast MRI screening surveillance. Materials and methods: This retrospective single screening cohort (2003–2019) study included 3308 women who received at least one breast MRI. After verifying with the Netherlands Comprehensive Cancer Organization (IKNL), a sub-population of women who developed BC after discontinuation was identified. Screening indications, BC incidence rates, tumor characteristics, and reasons for MRI screening discontinuation were compared between women who continued and those who discontinued MRI screening using descriptive and inferential methods. Results: Among 3308 participants, 2647 discontinued MRI screening. After discontinuation, 58/2647 (2.2%) developed BC (43 invasive, 13 DCIS, 2 NA). Initial screening indications included: personal (26/58, 44.8%) or family history (17/58, 29.3%) of BC, BRCA1 (3/58, 5.2%), BRCA2 (1/58, 1.7%), chest irradiation (1/58, 1.7%), other mutations (2/58, 3.4%) and other (8/58, 13.8%). Of these, 27 continued mammography screening, detecting 23 BC-cases. Discontinuation was mainly physician-driven. Invasive tumor size after cessation of MRI screening tended to be larger compared to tumors detected while participating in MRI screening (median difference: 7.0 mm, 95% CI: 4.0–10.0, p < 0.001). Mean age at diagnosis was 58. Median time from last MRI to diagnosis was 5.9 years. Conclusion: Women with a personal or family history of BC commonly discontinued MRI screening, often influenced by referring physicians. However, after cessation of MRI screening, a substantial number of these women are still diagnosed with BC, challenging current MRI screening regulations. Although a last negative MRI appears to reduce the subsequent decade’s likelihood of BC, post-MRI discontinuation detected tumors are prognostically worse, highlighting the need for more personalized, extended screening. Key Points: Question Current regulations and duration of MRI screening do not suit the entire increased-risk population . Findings Early discontinuation disproportionately affects women with a personal or family history. Cancers detected after cessation of MRI screening seem larger and more often invasive . Clinical relevance Because certain women with a personal or family risk indication could benefit from a longer duration of MRI screening, extended, personalized screening beyond current guidelines is suggested . Graphical