DeFungi: Direct Mycological Examination of Microscopic Fungi Images

TL;DR

This research develops and benchmarks deep learning models for early-stage microscopic fungi classification, providing a dataset and initial performance metrics to advance computer-aided mycological diagnosis.

Contribution

Introduces a curated fungi image dataset and evaluates deep learning models for early mycological diagnosis, filling a gap in existing research.

Findings

Inception V3 trained from scratch achieved 73.2% accuracy.

VGG16 with transfer learning achieved 85.04% accuracy.

The dataset is publicly available to support future research.

Abstract

Traditionally, diagnosis and treatment of fungal infections in humans depend heavily on face-to-face consultations or examinations made by specialized laboratory scientists known as mycologists. In many cases, such as the recent mucormycosis spread in the COVID-19 pandemic, an initial treatment can be safely suggested to the patient during the earliest stage of the mycological diagnostic process by performing a direct examination of biopsies or samples through a microscope. Computer-aided diagnosis systems using deep learning models have been trained and used for the late mycological diagnostic stages. However, there are no reference literature works made for the early stages. A mycological laboratory in Colombia donated the images used for the development of this research work. They were manually labelled into five classes and curated with a subject matter expert assistance. The images were later cropped and patched with automated code routines to produce the final dataset. This paper presents experimental results classifying five fungi types using two different deep learning approaches and three different convolutional neural network models, VGG16, Inception V3, and ResNet50. The first approach benchmarks the classification performance for the models trained from scratch, while the second approach benchmarks the classification performance using pre-trained models based on the ImageNet dataset. Using k-fold cross-validation testing on the 5-class dataset, the best performing model trained from scratch was Inception V3, reporting 73.2% accuracy. Also, the best performing model using transfer learning was VGG16 reporting 85.04%. The statistics provided by the two approaches create an initial point of reference to encourage future research works to improve classification performance. Furthermore, the dataset built is published in Kaggle and GitHub to foster future research.