Ajna Fetić
Research Subjects
Research Interests
Ajna Fetić has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- Nevzudin Buzađija
Polytechnic Faculty, University of Zenica, 72000 Zenica, Bosnia and Herzegovina
1 shared publication
Latest Publications
- Open Access
- 18 March 2025
- Published by IntechOpen
Evaluation of U-Net Algorithm Precision for Segmentation and Classification of Breast and Lung Images on CBIS-DDSM and LIDC-IDRI Datasets
Cancer is the leading disease in the world in terms of increasing numbers of new patients and deaths annually, making it one of the most formidable diseases today. Lung cancer and breast cancer are widely acknowledged as two of the most prevalent forms of cancer, both falling under the carcinoma subtype. Early detection of these cancers is particularly crucial for patient outcomes. With cancer being a longstanding health challenge, comprehensive datasets containing essential information for cancer prediction and diagnosis are now available. Radiologists primarily rely on Computed Tomography (CT) scans for cancer diagnosis. However, the escalating demand for CT scans and their interpretation has led to radiologists prioritizing throughput over the quality of readings. To address this challenge, Computer-Aided Diagnosis (CAD) systems have been introduced into medical practice. This research paper delves into evaluating the accuracy of the implemented U-Net algorithm for segmentation and classification on two prominent medical datasets: Curated Breast Imaging Subset of DDSM (CBIS-DDSM) and Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). The primary objective of the study is to assess the algorithm’s performance in accurately identifying and classifying Regions of Interest (ROIs) in breast and lung medical images.
- 18 March 2025
- Published by IntechOpen
Open AccessEvaluation of U-Net Algorithm Precision for Segmentation and Classification of Breast and Lung Images on CBIS-DDSM and LIDC-IDRI Datasets
Cancer is the leading disease in the world in terms of increasing numbers of new patients and deaths annually, making it one of the most formidable diseases today. Lung cancer and breast cancer are widely acknowledged as two of the most prevalent forms of cancer, both falling under the carcinoma subtype. Early detection of these cancers is particularly crucial for patient outcomes. With cancer being a longstanding health challenge, comprehensive datasets containing essential information for cancer prediction and diagnosis are now available. Radiologists primarily rely on Computed Tomography (CT) scans for cancer diagnosis. However, the escalating demand for CT scans and their interpretation has led to radiologists prioritizing throughput over the quality of readings. To address this challenge, Computer-Aided Diagnosis (CAD) systems have been introduced into medical practice. This research paper delves into evaluating the accuracy of the implemented U-Net algorithm for segmentation and classification on two prominent medical datasets: Curated Breast Imaging Subset of DDSM (CBIS-DDSM) and Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). The primary objective of the study is to assess the algorithm’s performance in accurately identifying and classifying Regions of Interest (ROIs) in breast and lung medical images.