Fast Pre-Diagnosis of Neoplastic Changes in Cytology Images Using Machine Learning
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 expe...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/16/7181 |
| _version_ | 1797524860184821760 |
|---|---|
| author | Jakub Caputa Daria Łukasik Maciej Wielgosz Michał Karwatowski Rafał Frączek Paweł Russek Kazimierz Wiatr |
| author_facet | Jakub Caputa Daria Łukasik Maciej Wielgosz Michał Karwatowski Rafał Frączek Paweł Russek Kazimierz Wiatr |
| author_sort | Jakub Caputa |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T09:02:40Z |
| format | Article |
| id | doaj.art-ab8e57b404a64fa58a2aea9ffc495465 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T09:02:40Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-ab8e57b404a64fa58a2aea9ffc4954652023-11-22T06:37:41ZengMDPI AGApplied Sciences2076-34172021-08-011116718110.3390/app11167181Fast Pre-Diagnosis of Neoplastic Changes in Cytology Images Using Machine LearningJakub Caputa0Daria Łukasik1Maciej Wielgosz2Michał Karwatowski3Rafał Frączek4Paweł Russek5Kazimierz Wiatr6Academic Computer Centre CYFRONET AGH, ul. Nawojki 11, 30-072 Kraków, PolandAcademic Computer Centre CYFRONET AGH, ul. Nawojki 11, 30-072 Kraków, PolandAcademic Computer Centre CYFRONET AGH, ul. Nawojki 11, 30-072 Kraków, PolandAcademic Computer Centre CYFRONET AGH, ul. Nawojki 11, 30-072 Kraków, PolandAcademic Computer Centre CYFRONET AGH, ul. Nawojki 11, 30-072 Kraków, PolandAcademic Computer Centre CYFRONET AGH, ul. Nawojki 11, 30-072 Kraków, PolandAcademic Computer Centre CYFRONET AGH, ul. Nawojki 11, 30-072 Kraków, PolandWe 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.https://www.mdpi.com/2076-3417/11/16/7181caninesneoplasmsdetectiondeep learningYOLOv3 |
| spellingShingle | Jakub Caputa Daria Łukasik Maciej Wielgosz Michał Karwatowski Rafał Frączek Paweł Russek Kazimierz Wiatr Fast Pre-Diagnosis of Neoplastic Changes in Cytology Images Using Machine Learning Applied Sciences canines neoplasms detection deep learning YOLOv3 |
| title | Fast Pre-Diagnosis of Neoplastic Changes in Cytology Images Using Machine Learning |
| title_full | Fast Pre-Diagnosis of Neoplastic Changes in Cytology Images Using Machine Learning |
| title_fullStr | Fast Pre-Diagnosis of Neoplastic Changes in Cytology Images Using Machine Learning |
| title_full_unstemmed | Fast Pre-Diagnosis of Neoplastic Changes in Cytology Images Using Machine Learning |
| title_short | Fast Pre-Diagnosis of Neoplastic Changes in Cytology Images Using Machine Learning |
| title_sort | fast pre diagnosis of neoplastic changes in cytology images using machine learning |
| topic | canines neoplasms detection deep learning YOLOv3 |
| url | https://www.mdpi.com/2076-3417/11/16/7181 |
| work_keys_str_mv | AT jakubcaputa fastprediagnosisofneoplasticchangesincytologyimagesusingmachinelearning AT dariałukasik fastprediagnosisofneoplasticchangesincytologyimagesusingmachinelearning AT maciejwielgosz fastprediagnosisofneoplasticchangesincytologyimagesusingmachinelearning AT michałkarwatowski fastprediagnosisofneoplasticchangesincytologyimagesusingmachinelearning AT rafałfraczek fastprediagnosisofneoplasticchangesincytologyimagesusingmachinelearning AT pawełrussek fastprediagnosisofneoplasticchangesincytologyimagesusingmachinelearning AT kazimierzwiatr fastprediagnosisofneoplasticchangesincytologyimagesusingmachinelearning |