Mátyás Petró
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mátyás Petró has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Balazs Harangi
Department of Data Science and Visualization, Faculty of Informatics, University of Debrecen, H-4032 Debrecen, Hungary
2 shared publications - Gábor Tóth
Department of Laboratory Medicine, Faculty of Medicine, University of Debrecen, 4032 Debrecen, Hungary
2 shared publications - Tamás Katona
Doctoral School of Informatics, University of Debrecen, 4028 Debrecen, Hungary
2 shared publications András Székely
Department of Radiology, Kenézy Gyula Hospital and Clinic, University of Debrecen, Hungary
1 shared publicationAnnamária Silye
Department of Medical Imaging, Faculty of Medicine, University of Debrecen, Hungary
1 shared publicationChang C Yi-Che
Department of Pathology, Faculty of Medicine, University of Debrecen, Hungary
1 shared publication
Latest Publications
- Open Access
- 7 June 2024
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 6 (2) , 1281-1297
Advanced Multi-Label Image Classification Techniques Using Ensemble Methods
Chest X-rays are vital in healthcare for diagnosing various conditions due to their low Radiation exposure, widespread availability, and rapid interpretation. However, their interpretation requires specialized expertise, which can limit scalability and delay diagnoses. This study addresses the multi-label classification challenge of chest X-ray images using the Chest X-ray14 dataset. We propose a novel online ensemble technique that differs from previous penalty-based methods by focusing on combining individual model losses with the overall ensemble loss. This approach enhances interaction and feedback among models during training. Our method integrates multiple pre-trained CNNs using strategies like combining CNNs through an additional fully connected layer and employing a label-weighted average for outputs. This multi-layered approach leverages the strengths of each model component, improving classification accuracy and generalization. By focusing solely on image data, our ensemble model addresses the challenges posed by null vectors and diverse pathologies, advancing computer-aided radiology.
- 7 June 2024
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 6 (2) , 1281-1297
Open AccessAdvanced Multi-Label Image Classification Techniques Using Ensemble Methods
Chest X-rays are vital in healthcare for diagnosing various conditions due to their low Radiation exposure, widespread availability, and rapid interpretation. However, their interpretation requires specialized expertise, which can limit scalability and delay diagnoses. This study addresses the multi-label classification challenge of chest X-ray images using the Chest X-ray14 dataset. We propose a novel online ensemble technique that differs from previous penalty-based methods by focusing on combining individual model losses with the overall ensemble loss. This approach enhances interaction and feedback among models during training. Our method integrates multiple pre-trained CNNs using strategies like combining CNNs through an additional fully connected layer and employing a label-weighted average for outputs. This multi-layered approach leverages the strengths of each model component, improving classification accuracy and generalization. By focusing solely on image data, our ensemble model addresses the challenges posed by null vectors and diverse pathologies, advancing computer-aided radiology.
- Open Access
- 8 March 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (6) , 806
Developing New Fully Connected Layers for Convolutional Neural Networks with Hyperparameter Optimization for Improved Multi-Label Image Classification
Chest X-ray evaluation is challenging due to its high demand and the complexity of diagnoses. In this study, we propose an optimized deep learning model for the multi-label classification of chest X-ray images. We leverage pretrained convolutional neural networks (CNNs) such as VGG16, ResNet 50, and DenseNet 121, modifying their output layers and fine-tuning the models. We employ a novel optimization strategy using the Hyperband algorithm to efficiently search the hyperparameter space while adjusting the fully connected layers of the CNNs. The effectiveness of our approach is evaluated on the basis of the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) metric. Our proposed methodology could assist in automated chest radiograph interpretation, offering a valuable tool that can be used by clinicians in the future.
- 8 March 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (6) , 806
Open AccessDeveloping New Fully Connected Layers for Convolutional Neural Networks with Hyperparameter Optimization for Improved Multi-Label Image Classification
Chest X-ray evaluation is challenging due to its high demand and the complexity of diagnoses. In this study, we propose an optimized deep learning model for the multi-label classification of chest X-ray images. We leverage pretrained convolutional neural networks (CNNs) such as VGG16, ResNet 50, and DenseNet 121, modifying their output layers and fine-tuning the models. We employ a novel optimization strategy using the Hyperband algorithm to efficiently search the hyperparameter space while adjusting the fully connected layers of the CNNs. The effectiveness of our approach is evaluated on the basis of the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) metric. Our proposed methodology could assist in automated chest radiograph interpretation, offering a valuable tool that can be used by clinicians in the future.
- Open Access
- 22 February 2021
- Published by SAGE Publications in Acta Radiologica Open
- Vol. 10 (2)
An intra-abdominal desmoid tumor
Desmoid tumor is a very rare neoplasm which develops from fibroblasts. These tumors do not have the ability to metastasize, but they can cause significant morbidity and mortality by local invasion and they are prone to local recurrence. We present a case of an aggressive fibromatosis in a 28-year-old male patient with no previous medical history. The tumor was in the retroperitoneum and eventually caused perforation of the coecum. During the operation, no metastasis was found; however, local lymphadenopathy was seen. After the surgical resection, no adjuvant therapy (radio or chemotherapy) was given to the patient and on follow-up (after three years), no recurrence was observed.
- 22 February 2021
- Published by SAGE Publications in Acta Radiologica Open
- Vol. 10 (2)
Open AccessAn intra-abdominal desmoid tumor
Desmoid tumor is a very rare neoplasm which develops from fibroblasts. These tumors do not have the ability to metastasize, but they can cause significant morbidity and mortality by local invasion and they are prone to local recurrence. We present a case of an aggressive fibromatosis in a 28-year-old male patient with no previous medical history. The tumor was in the retroperitoneum and eventually caused perforation of the coecum. During the operation, no metastasis was found; however, local lymphadenopathy was seen. After the surgical resection, no adjuvant therapy (radio or chemotherapy) was given to the patient and on follow-up (after three years), no recurrence was observed.