Unsupervised Domain Adaptation with Contrastive Learning for OCT Segmentation

Accurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment of eye diseases. While deep learning has been successful at this task, trained supervised models often fail for images that do not resemble labeled examples, e.g. for images acquired using different devices. We hereby propose a novel semi-supervised learning framework for segmentation of volumetric images from new unlabeled domains. We jointly use supervised and contrastive learning, also introducing a contrastive pairing scheme that leverages similarity between nearby slices in 3D. In addition, we propose channel-wise aggregation as an alternative to conventional spatial-pooling aggregation for contrastive feature map projection. We evaluate our methods for domain adaptation from a (labeled) source domain to an (unlabeled) target domain, each containing images acquired with different acquisition devices. In the target domain, our method achieves a Dice coefficient 13.8% higher than SimCLR (a state-of-the-art contrastive framework), and leads to results comparable to an upper bound with supervised training in that domain. In the source domain, our model also improves the results by 5.4% Dice, by successfully leveraging information from many unlabeled images.

Lu, HuanxiangF Hoffmann La Roche & Cie AG, Basel, Switzerland. (författare)
Li, Yun YvonnaF Hoffmann La Roche & Cie AG, Basel, Switzerland. (författare)
Albrecht, ThomasF Hoffmann La Roche & Cie AG, Basel, Switzerland. (författare)
Maunz, AndreasF Hoffmann La Roche & Cie AG, Basel, Switzerland. (författare)
Benmansour, FethallahF Hoffmann La Roche & Cie AG, Basel, Switzerland. (författare)
Valcarcel, Alessandra M.Genentech Inc, South San Francisco, CA USA. (författare)
Luu, JenniferGenentech Inc, South San Francisco, CA USA. (författare)
Ferrara, DanielaGenentech Inc, South San Francisco, CA USA. (författare)
Göksel, OrcunUppsala universitet,Avdelningen Vi3,Bildanalys och människa-datorinteraktion,Swiss Fed Inst Technol, Comp Assisted Applicat Med, Zurich, Switzerland.(Swepub:uu)orcgo786 (författare)
F Hoffmann La Roche & Cie AG, Basel, Switzerland.Genentech Inc, South San Francisco, CA USA. (creator_code:org_t)

Ingår i:Medical Image Computing and Computer Assisted Intervention, MICCAI 2022, pt viiiCham : Springer Nature, s. 351-36197830311645219783031164514

Av författaren/redakt...: Gomariz, Alvaro; Lu, Huanxiang; Li, Yun Yvonna; Albrecht, Thomas; Maunz, Andreas; Benmansour, Feth ...; visa fler...; Valcarcel, Aless ...; Luu, Jennifer; Ferrara, Daniela; Göksel, Orcun; visa färre...

Om ämnet

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.