Lesion Classification by Model-Based Feature Extraction: A Differential Affine Invariant Model of Soft Tissue Elasticity in CT Images

• Published in: Journal of imaging informatics in medicine 2024-08
• Main Authors: Cao, Weiguo, Pomeroy, Marc J, Liang, Zhengrong, Gao, Yongfeng, Shi, Yongyi, Tan, Jiaxing, Han, Fangfang, Wang, Jing, Ma, Jianhua, Lu, Hongbin, Abbasi, Almas F, Pickhardt, Perry J
• Format: Article
• Language: English
• ISSN: 2948-2933; 2948-2933
• DOI: 10.1007/s10278-024-01178-8

The elasticity of soft tissues has been widely considered a characteristic property for differentiation of healthy and lesions and, therefore, motivated the development of several elasticity imaging modalities, for example, ultrasound elastography, magnetic resonance elastography, and optical coherence elastography to directly measure the tissue elasticity. This paper proposes an alternative approach of modeling the elasticity for prior knowledge-based extraction of tissue elastic characteristic features for machine learning (ML) lesion classification using computed tomography (CT) imaging modality. The model describes a dynamic non-rigid (or elastic) soft tissue deformation in differential manifold to mimic the tissues' elasticity under wave fluctuation in vivo. Based on the model, a local deformation invariant is formulated using the 1 and 2 order derivatives of the lesion volumetric CT image and used to generate elastic feature map of the lesion volume. From the feature map, tissue elastic features are extracted and fed to ML to perform lesion classification. Two pathologically proven image datasets of colon polyps and lung nodules were used to test the modeling strategy. The outcomes reached the score of area under the curve of receiver operating characteristics of 94.2% for the polyps and 87.4% for the nodules, resulting in an average gain of 5 to 20% over several existing state-of-the-art image feature-based lesion classification methods. The gain demonstrates the importance of extracting tissue characteristic features for lesion classification, instead of extracting image features, which can include various image artifacts and may vary for different protocols in image acquisition and different imaging modalities.