{"ID":2899765,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.00993","arxiv_id":"2507.00993","title":"Advancing Lung Disease Diagnosis in 3D CT Scans","abstract":"To enable more accurate diagnosis of lung disease in chest CT scans, we propose a straightforward yet effective model. Firstly, we analyze the characteristics of 3D CT scans and remove non-lung regions, which helps the model focus on lesion-related areas and reduces computational cost. We adopt ResNeSt50 as a strong feature extractor, and use a weighted cross-entropy loss to mitigate class imbalance, especially for the underrepresented squamous cell carcinoma category. Our model achieves a Macro F1 Score of 0.80 on the validation set of the Fair Disease Diagnosis Challenge, demonstrating its strong performance in distinguishing between different lung conditions.","short_abstract":"To enable more accurate diagnosis of lung disease in chest CT scans, we propose a straightforward yet effective model. Firstly, we analyze the characteristics of 3D CT scans and remove non-lung regions, which helps the model focus on lesion-related areas and reduces computational cost. We adopt ResNeSt50 as a strong fe...","url_abs":"https://arxiv.org/abs/2507.00993","url_pdf":"https://arxiv.org/pdf/2507.00993v1","authors":"[\"Qingqiu Li\",\"Runtian Yuan\",\"Junlin Hou\",\"Jilan Xu\",\"Yuejie Zhang\",\"Rui Feng\",\"Hao Chen\"]","published":"2025-07-01T17:44:53Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\"]","methods":"[]","has_code":false}