Nucleus Segmentation and Classification using Residual SE-UNet and Feature Concatenation Approach in Cervical Cytopathology Cell images

Jignesh Chowdary, Suganya G, Premalatha M, Pratheepan Yogarajah

Research output: Contribution to journalReview articlepeer-review

18 Downloads (Pure)


Introduction: Pap smear is considered to be the primary examination for the diagnosis of cervical cancer. But the analysis of pap smear slides is a time-consuming task and tedious as it requires manual intervention. The diagnostic efficiency depends on the medical expertise of the pathologist, and human error often hinders the diagnosis. Automated segmentation and classification of cervical nuclei will help diagnose cervical cancer in earlier stages. Materials and Methods: The proposed work first segments the data, and then utilizes the segmented data for classification. The proposed methodology includes three models: a deep learning-based segmentation model, a fusion-based feature extraction model and a classification model. In this work, a Residual-Squeeze-and-Excitation-module is proposed for efficient cervical nuclei segmentation. Classification is performed using the Multi-layer Perceptron. Three sets of deep features are extracted from these segmented nuclei using the pre-trained and fine-tuned VGG19, VGG-F, and CaffeNet models, and two hand-crafted descriptors, Bag-of-Features and Linear-Binary-Patterns, are extracted for each image. These feature sets are processed using the principal component analysis method and concatenated for classification. For this work, Herlev, SIPaKMeD, and ISBI2014 datasets are used for evaluation. The Herlev dataset is used for evaluating both segmentation, and classification models. Whereas the SIPaKMeD is used for evaluating the classification model, and the ISBI2014 is used for evaluating the segmentation model. Results The segmentation network enhanced the precision and ZSI by 2.04%, and 2.00% on the Herlev dataset, and the precision and recall by 0.68%, and 2.59% on the ISBI2014 dataset. The classification approach enhanced the accuracy, recall, and specificity by 0.59%, 0.47%, and 1.15% on the Herlev dataset, and by 0.02%, 0.15%, and 0.22% on the SIPaKMed dataset. Conclusion: The experiments demonstrate that the proposed work achieves promising performance on segmentation and classification in cervical cytopathology cell images.
Original languageEnglish
Pages (from-to)1-13
Number of pages13
JournalTechnology in Cancer Research and Treatment
Publication statusAccepted/In press - 30 Sep 2022


  • Cervical cancer
  • pap smear
  • deep learning
  • segmentation
  • transfer learning


Dive into the research topics of 'Nucleus Segmentation and Classification using Residual SE-UNet and Feature Concatenation Approach in Cervical Cytopathology Cell images'. Together they form a unique fingerprint.

Cite this