Improved cell segmentation using deep learning in label-free optical microscopy images


Ayanzadeh A., Ozuysal O. Y., Okvur D. P., Onal S., Töreyin B. U., Unay D.

TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, cilt.29, ss.2855-2868, 2021 (SCI-Expanded) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 29
  • Basım Tarihi: 2021
  • Doi Numarası: 10.3906/elk-2105-244
  • Dergi Adı: TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Applied Science & Technology Source, Compendex, Computer & Applied Sciences, INSPEC, TR DİZİN (ULAKBİM)
  • Sayfa Sayıları: ss.2855-2868
  • Anahtar Kelimeler: Segmentation, breast cancer, convolutional neural networks, optical microscopy, phase-contrast, brightfield, CONTRAST, TRACKING
  • İstanbul Teknik Üniversitesi Adresli: Evet

Özet

The recently popular deep neural networks (DNNs) have a significant effect on the improvement of segmentation accuracy from various perspectives, including robustness and completeness in comparison to conventional methods. We determined that the naive U-Net has some lacks in specific perspectives and there is high potential for further enhancements on the model. Therefore, we employed some modifications in different folds of the U-Net to overcome this problem. Based on the probable opportunity for improvement, we develop a novel architecture by using an alternative feature extractor in the encoder of U-Net and replacing the plain blocks with residual blocks in the decoder. This alteration makes the model superconvergent yielding improved performance results on two challenging optical microscopy image series: a phase-contrast dataset of our own (MDA-MB-231) and a brightfield dataset from a well-known challenge (DSB2018). We utilized the U-Net with pretrained ResNet-18 as the encoder for the segmentation task. Hence, following the modifications, we redesign a novel skip-connection to reduce the semantic gap between the encoder and the decoder. The proposed skip-connection increases the accuracy of the model on both datasets. The proposed segmentation approach results in Jaccard Index values of 85.0% and 89.2% on the DSB2018 and MDA-MB-231 datasets, respectively. The results reveal that our method achieves competitive results compared to the state-of-the-art approaches and surpasses the performance of baseline approaches.