A Spatial Regulated Patch-Wise Approach for Cervical Dysplasia Diagnosis


  • Ying Zhang National University of Singapore Northwestern Polytechnical University
  • Yifang Yin National University of Singapore
  • Zhenguang Liu Zhejiang Gongshang University
  • Roger Zimmermann National University of Singapore




Healthcare, Medicine & Wellness


Cervical dysplasia diagnosis via visual investigation is a challenging problem. Recent approaches use deep learning techniques to extract features and require the downsampling of high-resolution cervical screening images to smaller sizes for training. Such a reduction may result in the loss of visual details that appear weakly and locally within a cervical image. To overcome this challenge, our work divides an image into patches and then represents it from patch features. We aggregate patch patterns into an image feature in a weighted manner by considering the patch--image label relation. The weights are visualized as a heatmap to explain where the diagnosis results come from. We further introduce a spatial regulator to guide the classifier to focus on the cervix region and to adjust the weight distribution, without requiring any manual annotations of the cervix region. A novel iterative algorithm is designed to refine the regulator, which is able to capture the variations in cervix center locations and shapes. Experiments on an 18-year real-world dataset indicate a minimal of 3.47%, 4.59%, 8.54% improvements over the state-of-the-art in accuracy, F1, and recall measures, respectively.




How to Cite

Zhang, Y., Yin, Y., Liu, Z., & Zimmermann, R. (2021). A Spatial Regulated Patch-Wise Approach for Cervical Dysplasia Diagnosis. Proceedings of the AAAI Conference on Artificial Intelligence, 35(1), 733-740. https://doi.org/10.1609/aaai.v35i1.16154



AAAI Technical Track on Application Domains