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

A. Pfob, C. Sidey-Gibbons, R. Barr, V. Duda, Z. Alwafai, C. Balleyguier, D. Clevert, S. Fastner, C. Gomez, M. Goncalo, I. Gruber, M. Hahn, A. Hennigs, P. Kapetas, S. Lu, J. Nees, R. Ohlinger, F. Riedel, M. Rutten, B. Schaefgen, M. Schuessler, A. Stieber, R. Togawa, M. Tozaki, S. Wojcinski, C. Xu, G. Rauch, J. Heil and M. Golatta

European Radiology 2022;32:4101-4115.

DOI PMID Cited by ~9

Abstract 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.