Hyperspectral placenta dataset: Hyperspectral image acquisition, annotations, and processing of biological tissues in microsurgical training

Sami Puustinen; Joni Hyttinen; Antti-Pekka Elomaa; Hana Vrzáková

doi:10.1016/j.dib.2023.109526

Hyperspectral placenta dataset: Hyperspectral image acquisition, annotations, and processing of biological tissues in microsurgical training

Data Brief. 2023 Aug 28:50:109526. doi: 10.1016/j.dib.2023.109526. eCollection 2023 Oct.

Authors

Sami Puustinen¹, Joni Hyttinen², Antti-Pekka Elomaa³, Hana Vrzáková²

Affiliations

¹ Microsurgery Center of Eastern Finland, Kuopio University Hospital, Puijonlaaksontie 2, Kuopio 70210, Finland.
² Faculty of Science, Forestry and Technology, University of Eastern Finland, Yliopistokatu 2, Joensuu 80100, Finland.
³ Department of Neurosurgery, Kuopio University Hospital, Puijonlaaksontie 2, Kuopio 70210, Finland.

Abstract

The dataset consists of 101 hyperspectral images of four human placentas and six hyperspectral images of contrast dyes (i.e., indocyanine green and red and blue food colorant) that were captured in the range 515-900 nm, step = 5 nm. The hyperspectral images were manually annotated, delineating the key anatomical structures: arteries, veins, stroma, and the umbilical cord. Standard reference materials were used for flat-field correction. The dataset is instrumental for advancing machine-learning algorithms and automated classification of anatomical structures, particularly the classification of superficial and deep vessels and transparent tissue layers.

Keywords: Medical hyperspectral imaging; Microsurgical training; Tissue classification.