Dataset of sodium chloride sterile liquid in bottles for intravenous administration and fill level monitoring

Abstract

We propose a dataset to investigate the relationship between the fill level of bottles and tiny machine learning algorithms. Tiny machine learning is represented by any Artificial Intelligence algorithm (spanning from conventional decision tree classifiers to artificial neural networks) that can be deployed into a resource constrained micro controller unit (MCU). The data presented has been originally collected for a joint research project by STMicroelectronics and Sesovera.ai. This article describes the recorded image data of bottles with 4 levels of filling. The bottles contain sodium chloride sterile liquid for intravenous administration. One subject of investigation using this dataset could be the classification of the liquid fill level, for example, to ease continuous human visual monitoring which may represent an onerous time-consuming task. Automating the task can help to increase the human work productivity thus saving time. Under normal circumstances, human visual monitoring of the saline level in the bottle is required from time to time. When the saline liquid in the bottle is fully consumed, and the bottle is not replaced or the infusion process stopped immediately, the difference between the patient's blood pressure and the empty saline bottle could cause an outward rush of blood into the saline.

Keywords: Fill level of bottles; Saline solution; Sodium chloride liquid; Visual monitoring.

Fig. 1

Exemple of images data capture for each class ID and fill level.

Fig. 2

Contents of saline_bottle_original_size.zip.

Fig. 3

Exemplary view of the saline bottle.

Fig. 4

Image examples of standard bottles with white wall as backgrounds at random distances and angles.

Fig. 5

Image examples of standard bottles with different type of backgrounds at random distances and angles.

Fig. 6

Directories tree generated with .ipynb provided with the dataset.

Fig. 7

Example of negative transformation applied on images of bottle saline dataset shown in Fig. 4.

Fig. 8

Data preprocessing pipeline before network training.

Fig. 9

Examples of augmentation on a starting image with fill level 50%; augmented a,b,c,d,e,f,g,h,i are the augmented images; augmented negative a,b,c,d,e,f,g,h,i are the augmented images with negative pre-processing and no image resize.

Fig. 10

Exemplary baseline network model summary.