Papers › CNN Based Autoencoder Application in Breast Cancer Image Retrieval

CNN Based Autoencoder Application in Breast Cancer Image Retrieval

4 Aug 2021International Seminar on Intelligent Technology and Its Applications (ISITIA) 2021 8archive 2025-07-28

Agus Eko Minarno, Kharisma Muzaki Ghufron, Trfebi Shina Sabrila, Lailatul Husniah, Fauzi Dwi Setiawan Sumadi

Content Based Medical Image Retrieval (CBMIR) is considered as a common technique to retrieve relevant images by comparing the features contained in the query image with the features contained in the image located in the database. Currently, the study related to CBMIR on breast cancer image however remains challenging due to inadequate research in such area. Previous study has a low performance and misinformation emphasizing the feature extraction process. Therefore, this study aims to utilize the CNN based Autoencoder method to minimize misinformation in the feature extraction process and to improve the performance result. The dataset used in this study is the BreakHis dataset. Overall, the results of image retrieval in breast cancer applying the CNN based Autoencoder method achieved higher performance compared to the method used in the previous study with an average precision of 0.9237 in the mainclass dataset category and 0.6825 in the subclass dataset category.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image RetrievalMedical Image RetrievalMisinformationRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Medical Image Retrieval BreakHis CNN AutoEncoder Average Precision 0.9237 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

3D ConvolutionAdam

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections