eprintid: 10193306 rev_number: 8 eprint_status: archive userid: 699 dir: disk0/10/19/33/06 datestamp: 2024-06-12 10:14:19 lastmod: 2024-12-11 09:29:28 status_changed: 2024-06-12 10:14:19 type: article metadata_visibility: show sword_depositor: 699 creators_name: Yung, Ka-Wai creators_name: Sivaraj, Jayaram creators_name: De Coppi, Paolo creators_name: Stoyanov, Danail creators_name: Loukogeorgakis, Stavros creators_name: Mazomenos, Evangelos B title: Diagnosing Necrotising Enterocolitis Via Fine-Grained Visual Classification ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 divisions: F42 keywords: Necrotizing Enterocolitis, Fine Grained Visual Classification, Abdominal X-ray note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. abstract: Necrotizing Enterocolitis (NEC) is a devastating condition affecting prematurely born neonates. Reviewing Abdominal X-rays (AXRs) is a key step in NEC diagnosis, staging and treatment decision-making, but poses significant challenges due to the subtle, difficult-to-identify radiological signs of the disease. In this paper, we propose AIDNEC - AI D iagnosis of NEC rotizing enterocolitis, a deep learning method to automatically detect and stratify the severity (surgical or medical) of NEC from no pathology in AXRs. The model is trainable end-to-end and integrates a Detection Transformer and Graph Convolution modules for localizing discriminative areas in AXRs, used to formulate subtle local embeddings. These are then combined with global image features to perform Fine-Grained Visual Classification (FGVC). We evaluate AIDNEC on our GOSH NEC dataset of 1153 images from 334 patients, achieving 79.7% accuracy in classifying NEC against No Pathology. AIDNEC outperforms the backbone by 2.6%, FGVC models by 2.5% and CheXNet by 4.2%, with statistically significant (two-tailed p < 0.05) improvements, while providing meaningful discriminative regions to support the classification decision. Additional validation in the publicly available Chest X-ray14 dataset yields comparable performance to state-of-the-art methods, illustrating AIDNEC's robustness in a different X-ray classification task. Dataset and source code will be released in our institutional database. date: 2024-11 date_type: published publisher: Institute of Electrical and Electronics Engineers (IEEE) official_url: http://dx.doi.org/10.1109/tbme.2024.3409642 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2283978 doi: 10.1109/tbme.2024.3409642 lyricists_name: Mazomenos, Evangelos lyricists_name: Stoyanov, Danail lyricists_id: EMAZO45 lyricists_id: DSTOY26 actors_name: Flynn, Bernadette actors_id: BFFLY94 actors_role: owner full_text_status: public publication: IEEE Transactions on Biomedical Engineering volume: 71 number: 11 pagerange: 3160 -3169 issn: 0018-9294 citation: Yung, Ka-Wai; Sivaraj, Jayaram; De Coppi, Paolo; Stoyanov, Danail; Loukogeorgakis, Stavros; Mazomenos, Evangelos B; (2024) Diagnosing Necrotising Enterocolitis Via Fine-Grained Visual Classification. IEEE Transactions on Biomedical Engineering , 71 (11) 3160 -3169. 10.1109/tbme.2024.3409642 <https://doi.org/10.1109/tbme.2024.3409642>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10193306/1/Diagnosing_Necrotising_Enterocolitis_Via_Fine-Grained_Visual_Classification.pdf