Automated classification of focal breast lesions according to S-detect: validation and role as a clinical and teaching tool

• Published in: Journal of ultrasound 2018-06, Vol.21 (2), p.105-118
• Main Authors: Di Segni, Mattia, de Soccio, Valeria, Cantisani, Vito, Bonito, Giacomo, Rubini, Antonello, Di Segni, Gabriele, Lamorte, Sveva, Magri, Valentina, De Vito, Corrado, Migliara, Giuseppe, Bartolotta, Tommaso Vincenzo, Metere, Alessio, Giacomelli, Laura, de Felice, Carlo, D’Ambrosio, Ferdinando
• Format: Article
• Language: English
• Subjects: Adult; Aged; Aged, 80 and over; Biopsy; Breast; Breast - diagnostic imaging; Breast Neoplasms - diagnostic imaging; Contingency; Diagnostic software; Diagnostic systems; Education, Medical; Elasticity Imaging Techniques; Feasibility Studies; Follow-Up Studies; Humans; Image Interpretation, Computer-Assisted - methods; Lesions; Medicine; Medicine & Public Health; Middle Aged; Operators; Original; Original Article; Pattern Recognition, Automated - methods; Prospective Studies; Radiology; Retrospective Studies; Sensitivity; Sensitivity and Specificity; Ultrasonography, Mammary - methods; Ultrasound; Young Adult
• ISSN: 1876-7931; 1971-3495; 1876-7931
• DOI: 10.1007/s40477-018-0297-2

Purpose To assess the diagnostic performance and the potential as a teaching tool of S-detect in the assessment of focal breast lesions. Methods 61 patients (age 21–84 years) with benign breast lesions in follow-up or candidate to pathological sampling or with suspicious lesions candidate to biopsy were enrolled. The study was based on a prospective and on a retrospective phase. In the prospective phase, after completion of baseline US by an experienced breast radiologist and S-detect assessment, 5 operators with different experience and dedication to breast radiology performed elastographic exams. In the retrospective phase, the 5 operators performed a retrospective assessment and categorized lesions with BI-RADS 2013 lexicon. Integration of S-detect to in-training operators evaluations was performed by giving priority to S-detect analysis in case of disagreement. 2 × 2 contingency tables and ROC analysis were used to assess the diagnostic performances; inter-rater agreement was measured with Cohen’s k ; Bonferroni’s test was used to compare performances. A significance threshold of p  = 0.05 was adopted. Results All operators showed sensitivity > 90% and varying specificity (50–75%); S-detect showed sensitivity > 90 and 70.8% specificity, with inter-rater agreement ranging from moderate to good. Lower specificities were improved by the addition of S-detect. The addition of elastography did not lead to any improvement of the diagnostic performance. Conclusions S-detect is a feasible tool for the characterization of breast lesions; it has a potential as a teaching tool for the less experienced operators.