In this paper we perform an empirical evaluation of variants of deep learning methods to automatically localize anatomical landmarks in bioimages of fishes acquired using different imaging modalities (microscopy and radiography). We compare two methodologies namely heatmap based regression and multivariate direct regression, and evaluate them in combination with several Convolutional Neural Network (CNN) architectures. Heatmap based regression approaches employ Gaussian or Exponential heatmap generation functions combined with CNNs to output the heatmaps corresponding to landmark locations whereas direct regression approaches output directly the (x, y) coordinates corresponding to landmark locations. In our experiments, we use two microscopy datasets of Zebrafish and Medaka fish and one radiography dataset of gilthead Seabream. On our three datasets, the heatmap approach with Exponential function and U-Net architecture performs better. Datasets and open-source code for training and prediction are made available to ease future landmark detection research and bioimaging applications.

Kumar, N., Biagio, C.d., Dellacqua, Z., Raman, R., Martini, A., Boglione, C., et al. (2023). Empirical Evaluation of Deep Learning Approaches for Landmark Detection in Fish Bioimages. In Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13804. Springer, Cham. (pp.470-486). Cham : Springer Nature [10.1007/978-3-031-25069-9_31].

Empirical Evaluation of Deep Learning Approaches for Landmark Detection in Fish Bioimages

Kumar N.
Methodology
;
Boglione C.
Conceptualization
;
2023-02-14

Abstract

In this paper we perform an empirical evaluation of variants of deep learning methods to automatically localize anatomical landmarks in bioimages of fishes acquired using different imaging modalities (microscopy and radiography). We compare two methodologies namely heatmap based regression and multivariate direct regression, and evaluate them in combination with several Convolutional Neural Network (CNN) architectures. Heatmap based regression approaches employ Gaussian or Exponential heatmap generation functions combined with CNNs to output the heatmaps corresponding to landmark locations whereas direct regression approaches output directly the (x, y) coordinates corresponding to landmark locations. In our experiments, we use two microscopy datasets of Zebrafish and Medaka fish and one radiography dataset of gilthead Seabream. On our three datasets, the heatmap approach with Exponential function and U-Net architecture performs better. Datasets and open-source code for training and prediction are made available to ease future landmark detection research and bioimaging applications.
Workshop on BioImage Computing BIC 2022
Tel Aviv, Israel
2022
European Conference on Computer Vision (ECCV)
Rilevanza internazionale
contributo
14-feb-2023
Settore ING-INF/05 - SISTEMI DI ELABORAZIONE DELLE INFORMAZIONI
English
Deep learning; Bioimages; Landmark detection; Heatmap; Multi-variate regression
https://link.springer.com/chapter/10.1007/978-3-031-25069-9_31#citeas
Intervento a convegno
Kumar, N., Biagio, C.d., Dellacqua, Z., Raman, R., Martini, A., Boglione, C., et al. (2023). Empirical Evaluation of Deep Learning Approaches for Landmark Detection in Fish Bioimages. In Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13804. Springer, Cham. (pp.470-486). Cham : Springer Nature [10.1007/978-3-031-25069-9_31].
Kumar, N; Biagio, Cd; Dellacqua, Z; Raman, R; Martini, A; Boglione, C; Muller, M; Geurts, P; Maree, R
File in questo prodotto:
File Dimensione Formato  
lavoro Navdeep.pdf

accesso aperto

Tipologia: Versione Editoriale (PDF)
Licenza: Creative commons
Dimensione 2.6 MB
Formato Adobe PDF
2.6 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2108/326983
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact