Fast Pre-Diagnosis of Neoplastic Changes in Cytology Images Using Machine Learning

Jakub Caputa,Daria Łukasik,Rafał Frączek,Michał Karwatowski,Maciej Wielgosz,Paweł Russek,Kazimierz Wiatr

doi:10.3390/app11167181

Abstract

We present the experiment results to use the YOLOv3 neural network architecture to automatically detect tumor cells in cytological samples taken from the skin in canines. A rich dataset of 1219 smeared sample images with 28,149 objects was gathered and annotated by the vet doctor to perform the experiments. It covers three types of common round cell neoplasms: mastocytoma, histiocytoma, and lymphoma. The dataset has been thoroughly described in the paper and is publicly available. The YOLOv3 neural network architecture was trained using various schemes involving original dataset modification and the different model parameters. The experiments showed that the prototype model achieved 0.7416 mAP, which outperforms the state-of-the-art machine learning and human estimated results. We also provided a series of analyses that may facilitate ML-based solutions by casting more light on some aspects of its performance. We also presented the main discrepancies between ML-based and human-based diagnoses. This outline may help depict the scenarios and how the automated tools may support the diagnosis process.

Highlights

Contrary to the cited works that use the classification after detection approach, we propose a single-step method thanks to the you only look once version 3 (YOLOv3) neural network [8]
Using multiple metrics and various tests enabled a comprehensive presentation of the model and the introduced methodology
As the validation set came from the same dataset as a training set, the model achieved the best performance of 0.7416 mean average precision (mAP) with this approach

Summary

Introduction

Academic Editor: Keun Ho Ryu. Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Veterinary oncology is a medical science field in which a precise diagnosis of the examined physical condition before introducing treatment is crucial for its effects and allows a doctor for a reasonable decision to be taken regarding the treatment of an oncological patient. Many diagnostic methods (including clinical examination, imaging tests, or endoscopic examination) allow examiners for excellent visualization of the lesions, as well as to recognize their structure, size, number, and features of clinical malignancy (rapid growth, large volume of lesion, binding to oral tissues), invasive, infiltrative nature of growth, and destruction of adjacent structures [1]. A microscopic examination of tissue samples allows us to determine actual tumor nature [1]

Objectives

Methods

Results

Discussion

Conclusion