{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T00:15:19Z","timestamp":1777853719642,"version":"3.51.4"},"reference-count":0,"publisher":"SAGE Publications","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JID"],"published-print":{"date-parts":[[2021,1,13]]},"abstract":"<jats:p>This paper presents a fully-automated method to detect retinal abnormalities in both a global and local context by generating: (1) a disease label with a probability score and (2) a 4-channel pixel-level segmentation map of retinal lesions. The characteristics of retinal abnormalities, which occur as various shapes, sizes, and distribution at different regions, are a challenge in accomplishing these tasks. In addition, the small amount of image-level labelled images in public databases and the unavailability of lesion-level annotations for most of these publicly available images also pose as challenges. These shortcomings motivate our exploration of various CNN architectures to extract multi-scale contextual information, such that we investigate the impact of different arrangements of multi-sized convolutional kernels appended to a modified pre-trained encoder. Additionally, to prevent the loss of detailed information for small lesions, we exploit the advantages of feature map concatenation from the output of these multi-scale convolutions to its corresponding decoder layer. A new two-phase training strategy is also implemented to tackle the problem of dataset imbalance between image-level label and lesion-level label classes. The direct comparison between our proposed methods and currently published state-of-the-art methods with the same databases confirms that our best model outperforms existing published methods.<\/jats:p>","DOI":"10.3233\/jid190017","type":"journal-article","created":{"date-parts":[[2020,5,8]],"date-time":"2020-05-08T14:49:55Z","timestamp":1588949395000},"page":"5-41","source":"Crossref","is-referenced-by-count":1,"title":["Deep Learning for The Automatic Diagnosis and Detection of Multiple Retinal Abnormalities"],"prefix":"10.1177","volume":"23","author":[{"given":"Michelle K.S.","family":"Gian","sequence":"first","affiliation":[{"name":"Faculty of Engineering, Computing and Science, Swinburne University of Technology Sarawak, Kuching, Malaysia"}]},{"given":"Valliappan","family":"Raman","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Computing and Science, Swinburne University of Technology Sarawak, Kuching, Malaysia"}]},{"given":"Patrick H.H.","family":"Then","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Computing and Science, Swinburne University of Technology Sarawak, Kuching, Malaysia"}]}],"member":"179","container-title":["Journal of Integrated Design and Process Science"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JID190017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:56:22Z","timestamp":1777503382000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JID190017"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,13]]},"references-count":0,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.3233\/jid190017","relation":{},"ISSN":["1092-0617","1875-8959"],"issn-type":[{"value":"1092-0617","type":"print"},{"value":"1875-8959","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,13]]}}}