Fig 1.
Left: The Orbit user interface: Image browser on the left, tasks are on top grouped in tabs; properties and working results are on the right. Image viewer in the centre. Right: The architecture of Orbit Image Analysis.
Fig 2.
The integrated script editor allows the execution of Groovy scripts which can access the Orbit API. Results can be visualized as a mark-up on open image frames.
Fig 3.
Upper image: After an object segmentation the user can define object classes (1), use the object marker tool (2) and mark segmented objects (3). Orbit computes features for each object and uses a SVM to classify the objects. Lower image: Results of the object classification.
Fig 4.
Idiopathic Pulmonary Fibrosis Quantification (IPF).
IPF quantification: Treated/unhealthy (left) and control/healthy (right). (A,C) and (B,D) shows how the exclusion model works. (E,G) and (F,H) shows the fine-grained collagen quantification.
Fig 5.
Intraepidermal nerve fibre detection.
Nerve fibre image (A) and annotated automatically detected nerves (B) on a bright-field image. Only nerve fibres close to or crossing the manually annotated junction line are detected.
Fig 6.
Glomeruli detection on kidney slides using deep learning.
Manually annotated glomeruli outlines (ground truth) in yellow, detected glomeruli outlines in green.
Fig 7.
Deep-learning object detection.
Top: Annotated objects on the left side, generated segmentation map which is used as training input on the right side. Bottom: The ResNet-101 based encoder-decoder network takes a tile image as input and outputs the tile mask.
Table 1.
Evaluation results of the glomeruli segmentation for each group and total.
Samples of each staining type are illustrated in Fig 6.