Szczegóły publikacji
Opis bibliograficzny
Enhanced medical image segmentation using CNN based on histogram equalization / Shoffan SAIFULLAH, Rafał DREŻEWSKI // W: 2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC) [Dokument elektroniczny] : 4-6 May 2023, Salem, India / IEEE. — [USA] : IEEE, [2023]. — Dod. ISBN 978-1-6654-5629-6 (DVD ISBN), 978-1-6654-5631-9 (print on demand). — e-ISBN: 978-1-6654-5630-2. — S. 121-126. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 125-126, Abstr. — Publikacja dostępna online od: 2023-06-08
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 147595 |
|---|---|
| Data dodania do BaDAP | 2023-07-27 |
| Tekst źródłowy | URL |
| DOI | 10.1109/ICAAIC56838.2023.10141065 |
| Rok publikacji | 2023 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
Abstract
Medical image segmentation is an essential process in disease analysis and diagnosis, in which medical images are divided into specific areas of anatomic or pathological structures. However, this process has challenges, such as the quality, variability, and complexity of medical images. Thus, we propose a medical image segmentation method using the Convolutional Neural Network (CNN) and the Histogram Equalization (HE) image preprocessing. We evaluated medical image segmentation using 2 secondary datasets, namely Lung CT-Scan and Chest X-Rays, with 267 and 3616 images, respectively. The HE method uses an averaging of the optimal cumulative distribution function (CDF) values with a range of 0 to 39. The experimental results show that adding the HE method can increase the accuracy of CNN on the Lung CT-Scan and Chest X-rays data sets, respectively, by 0.73 percentage points from 91.28% to 92.08 % and 1.23 percentage points from 95.56% to 96.85% for the training process. The results of the testing process (validation) have an increase in accuracy of 2.82 percentage points from 89.77% to 92.59% and 0.91 percentage points from 96.06% to 96.97%. Implementing the HE method increases accuracy in CNN medical image segmentation based on the value of dice similarity coefficient (DSC) and structural similarity index measurement (SSIM) close to 0.95.
