A method for utilizing automated machine learning for histopathological classification of testis based on Johnsen scores

We examined whether a tool for determining Johnsen scores automatically using artificial intelligence (AI) could be used in place of traditional Johnsen scoring to support pathologists' evaluations. Average precision, precision, and recall were assessed by the Google Cloud AutoML Vision platform. We obtained testicular tissues for 275 patients and were able to use haematoxylin and eosin (H&E)-stained glass microscope slides from 264 patients. In addition, we cut out of parts of the histopathology images (5.0 x 5.0 cm) for expansion of Johnsen's characteristic areas with seminiferous tubules. We defined four labels: Johnsen score 1-3, 4-5, 6-7, and 8-10 to distinguish Johnsen scores in clinical practice. All images were uploaded to the Google Cloud AutoML Vision platform. We obtained a dataset of 7155 images at magnification 400x and a dataset of 9822 expansion images for the 5.0 x 5.0 cm cutouts. For the 400x magnification image dataset, the average precision (positive predictive value) of the algorithm was 82.6%, precision was 80.31%, and recall was 60.96%. For the expansion image dataset (5.0 x 5.0 cm), the average precision was 99.5%, precision was 96.29%, and recall was 96.23%. This is the first report of an AI-based algorithm for predicting Johnsen scores.

Automated summary

The study examined the possibility of using AI to automatically determine Johnsen scores, achieving high levels of precision and recall in evaluation. The Google Cloud AutoML Vision platform was used to assess the accuracy and recall rates for different datasets, showing promising results for potential clinical applications.