Is the aspect ratio of cells important in deep learning? A robust comparison of deep learning methods for multi-scale cytopathology cell image classification: from convolutional neural networks to visual transformers
This addresses a practical issue in medical imaging for cervical cancer screening, showing that direct resizing may not harm performance, which is incremental but useful for simplifying preprocessing.
The study investigated whether preserving the aspect ratio of cells in cytopathology images is necessary for deep learning classification, finding that models are robust to aspect ratio changes with classification accuracies above 95% on the SIPaKMeD dataset.
Cervical cancer is a very common and fatal type of cancer in women. Cytopathology images are often used to screen for this cancer. Given that there is a possibility that many errors can occur during manual screening, a computer-aided diagnosis system based on deep learning has been developed. Deep learning methods require a fixed dimension of input images, but the dimensions of clinical medical images are inconsistent. The aspect ratios of the images suffer while resizing them directly. Clinically, the aspect ratios of cells inside cytopathological images provide important information for doctors to diagnose cancer. Therefore, it is difficult to resize directly. However, many existing studies have resized the images directly and have obtained highly robust classification results. To determine a reasonable interpretation, we have conducted a series of comparative experiments. First, the raw data of the SIPaKMeD dataset are pre-processed to obtain standard and scaled datasets. Then, the datasets are resized to 224 x 224 pixels. Finally, 22 deep learning models are used to classify the standard and scaled datasets. The results of the study indicate that deep learning models are robust to changes in the aspect ratio of cells in cervical cytopathological images. This conclusion is also validated via the Herlev dataset.