AUTHOR=Wang Liping , Wang Yuan , Lu Wenliang , Xu Dong , Yao Jincao , Wang Lijing , Xu Lei 

TITLE=Differential regional importance mapping for thyroid nodule malignancy prediction with potential to improve needle aspiration biopsy sampling reliability

JOURNAL=Frontiers in Oncology

VOLUME=Volume 13 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1136922

DOI=10.3389/fonc.2023.1136922

ISSN=2234-943X

ABSTRACT=Objective: Existing guidelines for ultrasound-guided fine needle aspiration biopsy lack specifications on sampling sites but number of biopsies to improve diagnostic reliability. We propose the use of Class Activation Maps (CAMs) and our modified malignancy-specific heat maps that locate important deep representations of thyroid nodules for class predictions. 
Methods: We applied adversarial noise perturbations to the segmented concentric “hot” nodular regions of equal sizes to differentiate regional importance for the malignancy diagnostic performances of an accurate ultrasound-based Artificial Intelligent Computer-Aided Diagnosis System (AI-CADx) using retrospectively collected 2602 thyroid nodules with known histopathological diagnosis. 
Results: The AI system demonstrated high diagnostic performance with the AUC value of 0.9302 and good nodule identification capability with a median dice coefficient >0.9 compared to radiologists’ segmentations. Experiments confirmed that the CAM-based heat maps reflect differentiable importance of different nodular regions for an AI-CADx system to make its predictions. No less importantly, the hot regions in malignancy heatmaps of ultrasound images in comparison with the inactivated regions of the same 100 malignant nodules randomly selected from the dataset had higher summed frequency-weighted feature scores of 6.04 versus 4.96 rated by radiologists with more than 15 years of ultrasound examination experiences according to widely used ultrasound-based risk stratification ACR Thyroid Imaging, Reporting and Data System (TI-RADS) in terms of nodule composition, echogenicity and echogenic foci, excluding shape and margin attributes which could only be evaluated on the whole rather than on the sub-nodular component levels. In addition, we show examples demonstrating good spatial correspondence of highlighted regions of malignancy heat map to malignant tumor cell-rich regions in hematoxylin and eosin-stained histopathological images.
Conclusion: Our proposed CAM-based ultrasonographic malignancy heat map provides quantitative visualization of malignancy heterogeneity within a tumor and it is of clinical interests to investigate in the future its usefulness to improve FNAB sampling reliability by targeting potentially more suspicious sub-nodular regions.