{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:14:10Z","timestamp":1773803650840,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"30","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Robust medical image classification under input corruption\nand bag-level annotation remains a critical challenge in clinical\nAI applications. We propose QAPNet, a Quantum-\nAttentive Patchwise Network that integrates quantum neural\nencoding, additive attention-based instance reweighting, and\nprototype-contrastive regularization for reliable diagnosis\nfrom degraded inputs. Our framework uses a sliding-window\nstrategy to divide each MRI medical Image into overlapping\npatches, where each is encoded via an 8-qubit quantum circuit\nusing RY -based noise-sensitive layers for yielding expressive\nlow-dimensional representations without relying on\nclassical CNNs. A lightweight additive attention mechanism\ncomputes instance-wise importance weights that enable interpretable\nand noise-aware bag-level aggregation. To enhance\nrobustness, we apply a contrastive loss that aligns clean and\nnoisy embeddings and enforce prototype-guided clustering\nvia class-wise centroids. We evaluate QAPNet across seven\nbenchmark medical imaging datasets under three levels of\nadditive Gaussian noise (\u03c3 \u2208 {5%, 10%, 30%}). QAPNet\nconsistently outperforms eight strong baselines and achieves\nup to +20.8% higher accuracy in OASIS (with 30% noise),\n+17.7% in PathMNIST, and maintains stable performance\n(&lt; 4% degradation) in all settings. Ablation studies confirm\nthe critical role of quantum encoding, attention-based aggregation,\nand prototype contrastive learning. These results suggest\nthat QAPNet offers a scalable and interpretable architecture\nfor noisy medical imaging tasks in the real world to\nbridge the quantum representation learning with robust clinical\nprediction.<\/jats:p>","DOI":"10.1609\/aaai.v40i30.39695","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:02:30Z","timestamp":1773799350000},"page":"25065-25072","source":"Crossref","is-referenced-by-count":0,"title":["QAPNet: A Quantum-Attentive Patchwise Network for Robust Medical Image Classification Under Noisy Inputs"],"prefix":"10.1609","volume":"40","author":[{"given":"Maqsudur","family":"Rahman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39695\/43656","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39695\/43656","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:02:30Z","timestamp":1773799350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/39695"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"30","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i30.39695","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}