{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T10:58:37Z","timestamp":1771844317998,"version":"3.50.1"},"reference-count":0,"publisher":"Slovenian Association Informatika","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJCAI"],"abstract":"<jats:p>Microarray imaging is a critical tool for large-scale gene expression analysis, yet its accuracy is oftencompromised by noise introduced during sample preparation, hybridization, and image acquisition. Traditionaldenoising approaches, including median, Wiener, and wavelet-based filtering, either rely on fixedparameters or degrade under mixed-noise conditions, while CNN-based methods treat all noise uniformly,limiting adaptability. To address these limitations, we propose MS-NADNet (Multi-Stream Noise-AwareDenoising Network), a deep-learning framework that integrates a Noise Characterization Module (NCM)to identify noise type, a set of Noise-Specific Denoising Modules (NSDMs) specialized for distinct noisedistributions, and a Global Refinement Block for residual suppression. A large-scale augmented datasetwas constructed from the Malignant Lymphoma Classification dataset, incorporating 17 noise variants, includingGaussian, Poisson, salt-and-pepper, speckle, and mixed combinations, to simulate realistic imagingconditions. Experimental evaluation demonstrates that MS-NADNet achieves an MSE of 0.00012, PSNR of42.73 dB, and SSIM of 0.9861, outperforming classical filters and state-of-the-art CNN denoisers. Theseresults confirm the robustness of MS-NADNet in handling diverse single and multi-noise environments,ensuring biologically reliable microarray image analysis and improved downstream gene expression profiling.<\/jats:p>","DOI":"10.31449\/inf.v50i8.11954","type":"journal-article","created":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T11:57:03Z","timestamp":1771761423000},"source":"Crossref","is-referenced-by-count":0,"title":["MS-NADNet: A Multi-Stream Noise-Aware Deep Learning Framework for Microarray Image Denoising"],"prefix":"10.31449","volume":"50","author":[{"given":"Shreenidhi","family":"BS","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R Saravana","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"16141","published-online":{"date-parts":[[2026,2,21]]},"container-title":["Informatica"],"original-title":[],"link":[{"URL":"https:\/\/www.informatica.si\/index.php\/informatica\/article\/download\/11954\/6515","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.informatica.si\/index.php\/informatica\/article\/download\/11954\/6515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T10:01:26Z","timestamp":1771840886000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.informatica.si\/index.php\/informatica\/article\/view\/11954"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":0,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,2,21]]}},"URL":"https:\/\/doi.org\/10.31449\/inf.v50i8.11954","relation":{},"ISSN":["1854-3871","0350-5596"],"issn-type":[{"value":"1854-3871","type":"electronic"},{"value":"0350-5596","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2,21]]}}}