Performance comparison of medical image classification systems using TensorFlow Keras, PyTorch, and JAX
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916851980697600 |
|---|---|
| author | Bećirović, Merjem Kurtović, Amina Smajlović, Nordin Kapo, Medina Akagić, Amila |
| author_facet | Bećirović, Merjem Kurtović, Amina Smajlović, Nordin Kapo, Medina Akagić, Amila |
| contents | Medical imaging plays a vital role in early disease diagnosis and monitoring. Specifically, blood microscopy offers valuable insights into blood cell morphology and the detection of hematological disorders. In recent years, deep learning-based automated classification systems have demonstrated high potential in enhancing the accuracy and efficiency of blood image analysis. However, a detailed performance analysis of specific deep learning frameworks appears to be lacking. This paper compares the performance of three popular deep learning frameworks, TensorFlow with Keras, PyTorch, and JAX, in classifying blood cell images from the publicly available BloodMNIST dataset. The study primarily focuses on inference time differences, but also classification performance for different image sizes. The results reveal variations in performance across frameworks, influenced by factors such as image resolution and framework-specific optimizations. Classification accuracy for JAX and PyTorch was comparable to current benchmarks, showcasing the efficiency of these frameworks for medical image classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14587 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Performance comparison of medical image classification systems using TensorFlow Keras, PyTorch, and JAX Bećirović, Merjem Kurtović, Amina Smajlović, Nordin Kapo, Medina Akagić, Amila Computer Vision and Pattern Recognition Artificial Intelligence Medical imaging plays a vital role in early disease diagnosis and monitoring. Specifically, blood microscopy offers valuable insights into blood cell morphology and the detection of hematological disorders. In recent years, deep learning-based automated classification systems have demonstrated high potential in enhancing the accuracy and efficiency of blood image analysis. However, a detailed performance analysis of specific deep learning frameworks appears to be lacking. This paper compares the performance of three popular deep learning frameworks, TensorFlow with Keras, PyTorch, and JAX, in classifying blood cell images from the publicly available BloodMNIST dataset. The study primarily focuses on inference time differences, but also classification performance for different image sizes. The results reveal variations in performance across frameworks, influenced by factors such as image resolution and framework-specific optimizations. Classification accuracy for JAX and PyTorch was comparable to current benchmarks, showcasing the efficiency of these frameworks for medical image classification. |
| title | Performance comparison of medical image classification systems using TensorFlow Keras, PyTorch, and JAX |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2507.14587 |