The Potential of Shear Wave Elastography to Reduce Unnecessary Biopsies in Breast Cancer Diagnosis: An International, Diagnostic, Multicenter Trial

Golatta, Michael; Pfob, André; Büsch, Christopher; Brückner, Thomas; Alwafai, Zaher; Balleyguier, Corinne; Clevert, Dirk-André; Duda, Volker; Gonçalo, Manuela; Gruber, Ines; Hahn, Markus; Kapetas, Panagiotis; Öhlinger, R.; Rutten, M.J.C.M.; Tozaki, Mitsuhiro; Wojcinski, Sebastian; Rauch, Geraldine; Heil, Jörg; Barr, Richard G.

doi:10.1055/a-1543-6156

Cited by 13 publications

(25 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Guidelines for multivariable risk prediction models recommend validation of such a model in a dataset of at least 100 events [ 11 ]. Only one trial site had at least 100 events and was thus used as validation set (study site 1 of the parental trial) [ 8 ]. The other 11 trial sites were used as a development set.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

The importance of multi-modal imaging and clinical information for humans and AI-based algorithms to classify breast masses (INSPiRED 003): an international, multicenter analysis

et al. 2022

Self Cite

View full text Add to dashboard Cite

Objectives AI-based algorithms for medical image analysis showed comparable performance to human image readers. However, in practice, diagnoses are made using multiple imaging modalities alongside other data sources. We determined the importance of this multi-modal information and compared the diagnostic performance of routine breast cancer diagnosis to breast ultrasound interpretations by humans or AI-based algorithms. Methods Patients were recruited as part of a multicenter trial (NCT02638935). The trial enrolled 1288 women undergoing routine breast cancer diagnosis (multi-modal imaging, demographic, and clinical information). Three physicians specialized in ultrasound diagnosis performed a second read of all ultrasound images. We used data from 11 of 12 study sites to develop two machine learning (ML) algorithms using unimodal information (ultrasound features generated by the ultrasound experts) to classify breast masses which were validated on the remaining study site. The same ML algorithms were subsequently developed and validated on multi-modal information (clinical and demographic information plus ultrasound features). We assessed performance using area under the curve (AUC). Results Of 1288 breast masses, 368 (28.6%) were histopathologically malignant. In the external validation set (n = 373), the performance of the two unimodal ultrasound ML algorithms (AUC 0.83 and 0.82) was commensurate with performance of the human ultrasound experts (AUC 0.82 to 0.84; p for all comparisons > 0.05). The multi-modal ultrasound ML algorithms performed significantly better (AUC 0.90 and 0.89) but were statistically inferior to routine breast cancer diagnosis (AUC 0.95, p for all comparisons ≤ 0.05). Conclusions The performance of humans and AI-based algorithms improves with multi-modal information. Key Points • The performance of humans and AI-based algorithms improves with multi-modal information. • Multimodal AI-based algorithms do not necessarily outperform expert humans. • Unimodal AI-based algorithms do not represent optimal performance to classify breast masses.

show abstract

Section: Methodsmentioning

confidence: 99%

“…We hypothesized that both humans and AI-based algorithms can improve their performance when considering multi-modal instead of unimodal information. For our analysis, we used data of an international multicenter trial that evaluated the use of a new ultrasound technique compared to traditional B-mode breast ultrasound [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

The importance of multi-modal imaging and clinical information for humans and AI-based algorithms to classify breast masses (INSPiRED 003): an international, multicenter analysis

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Die bisher größte prospektive, multizentrische, internationale Studie konnte die explorativen Cut-Off-Werte vorhergehender Studien nicht bestätigen, da die Rate an falsch-positiven Befunden zwar reduziert wurde, allerdings auf Kosten einer erhöhten Rate an übersehenen Karzinomen. Sekundäre Analysen deuten darauf hin, dass insbesondere die Herabstufung von US-Kategorie 4(a) Läsionen mit SWE 2,55 m/s oder weniger zu einer Reduktion falsch-positiver Befunde (und damit unnötiger Biopsien) um 24 %, bei gleichzeitig leitliniengemäßer Detektionsrate an Karzinomen führen könnte [35]. Bei der Anwendung des Verfahrens ist zu berücksichtigen, dass der optimale Grenzwert, um maligne von benignen Läsionen zu unterscheiden, noch nicht abschließend geklärt ist.…”

Section: Shear-wave-elastografie (Scherwellenelastografie)unclassified

Best Practice Guideline – Empfehlungen der DEGUM zur Durchführung und Beurteilung der Mammasonografie

Vogel-Minea¹,

Bader

Blohmer

et al. 2023

Ultraschall Med

Self Cite

View full text Add to dashboard Cite

ZusammenfassungDie Mammasonografie hat sich seit vielen Jahren neben der Mammografie als wichtige Methode zur Abklärung von Brustbefunden etabliert.Der Arbeitskreis Mammasonografie der DEGUM beabsichtigt mit der „Best Practice Guideline“ den senologisch tätigen Kolleginnen und Kollegen neben dem in Teil I publizierten aktuellen Dignitätskriterien- und Befundungskatalog in dem vorliegenden Teil II die additiven und fakultativen Anwendungsmodalitäten zur Abklärung von Brustbefunden zu beschreiben und dazu DEGUM-Empfehlungen zu äußern, um die Differenzialdiagnose von unklaren Läsionen zu erleichtern.Die vorliegende „Best Practice Guideline“ hat sich zum Ziel gesetzt, den Anforderungen zur Qualitätssicherung und der Gewährleistung einer qualitätskontrollierten Durchführung der Mammasonografie nachzukommen. Die wichtigsten Aspekte der Qualitätssicherung werden in diesem Teil II der Best Practice Guideline erläutert.

show abstract

“…The classification of the lesions was made by experienced radiologists according to the BI-RADS fifth edition of the American College of Radiology and based on the above information combined with relevant medical history. For SWE, the regions of interest (ROIs) were manually depicted at the highest SWE velocity point within the lesion as previously described (19). Effective images were then captured in SWE, and the maximum and average elasticity values of the lesions were generated using the built-in quantitative analysis software "Q-boxTM Ratio".…”

Section: Ultrasound Examinationmentioning

confidence: 99%

Machine learning–based diagnostic evaluation of shear-wave elastography in BI-RADS category 4 breast cancer screening: a multicenter, retrospective study

Tang¹,

Liang²,

Li³

et al. 2022

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: Ultrasound is commonly used in breast cancer screening but lacks quantification ability and diagnostic power due to its low specificity, which can lead to overdiagnosis and unnecessary biopsies. This study evaluated the diagnostic efficacy and clinical utility of adding shear-wave elastography (SWE) to the screening of the Breast Imaging Reporting and Data System (BI-RADS) category 4 breast cancer.Methods: A machine learning-based diagnostic model was constructed using data retrospectively collected from 3 independent cohorts with features selected using lasso regression and support vector machine-recursive feature elimination algorithms. Propensity score matching (PSM) was used to preclude confounding baseline characteristics between malignant and benign lesions. A decision curve analysis (DCA) was used to evaluate the clinical benefit of the diagnostic model in identifying high-risk tumor patients for intervention while simultaneously avoiding overtreatment of low-risk patients with integrative evaluation using a net benefit value and treatment reduction rate.Results: In our training center, a total of 122 patients were enrolled, and 577 breast tumors were collected.The comparison between malignant and benign lesions revealed significant differences in patient age, tumor size, resistance index (RI), and elasticity values. The maximum elasticity value (Emax) was identified as an independent diagnostic feature and was included in the diagnostic model. The combination of Emax with BI-RADS category 4 demonstrated a significantly better diagnostic efficacy than the BI-RADS category alone [BI-RADS+Emax: AUC: 0.908, 95% confidence interval (CI), 0.842−0.974; BI-RADS: AUC =0.862, 95% CI, 0.784−0.94; P=0.024] and significantly increased the clinical benefit for patients and policy makers by effectively reducing overdiagnosis and biopsy rates. In the BI-RADS category 4A subgroup, adding Emax to breast cancer screening benefited patients and showed a greater absolute benefit than did the BI-RADS category alone when used for patients with a higher probability of cancer (>0.403), demonstrating a 50% overtreatment reduction.Conclusions: Adding Emax to BI-RADS category 4 breast cancer screening using SWE significantly reduced overdiagnosis and biopsy rates compared with the BI-RADS category alone, especially for BI-RADS 4A patients. 2 Tang et al. SWE for BI-RADS 4 breast cancer screening

show abstract

The Potential of Shear Wave Elastography to Reduce Unnecessary Biopsies in Breast Cancer Diagnosis: An International, Diagnostic, Multicenter Trial

Cited by 13 publications

References 30 publications

The importance of multi-modal imaging and clinical information for humans and AI-based algorithms to classify breast masses (INSPiRED 003): an international, multicenter analysis

The importance of multi-modal imaging and clinical information for humans and AI-based algorithms to classify breast masses (INSPiRED 003): an international, multicenter analysis

Best Practice Guideline – Empfehlungen der DEGUM zur Durchführung und Beurteilung der Mammasonografie

Machine learning–based diagnostic evaluation of shear-wave elastography in BI-RADS category 4 breast cancer screening: a multicenter, retrospective study

Contact Info

Product

Resources

About