{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:42:27Z","timestamp":1760060547780,"version":"build-2065373602"},"reference-count":51,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:00:00Z","timestamp":1756771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>The accurate segmentation of pigmented skin lesions is a critical prerequisite for reliable melanoma detection, yet approximately 30% of lesions exhibit fuzzy or poorly defined borders. This ambiguity makes the definition of a single contour unreliable and limits the effectiveness of computer-assisted diagnosis (CAD) systems. While clinical assessment based on the ABCDE criteria (asymmetry, border, color, diameter, and evolution), dermoscopic imaging, and scoring systems remains the standard, these methods are inherently subjective and vary with clinician experience. We address this challenge by reframing segmentation into three distinct regions: background, border, and lesion core. These regions are delineated using superpixels generated via the Simple Linear Iterative Clustering (SLIC) algorithm, which provides meaningful structural units for analysis. Our contributions are fourfold: (1) redefining lesion borders as regions, rather than sharp lines; (2) generating superpixel-level embeddings with a transformer-based autoencoder; (3) incorporating these embeddings as features for superpixel classification; and (4) integrating neighborhood information to construct enhanced feature vectors. Unlike pixel-level algorithms that often overlook boundary context, our pipeline fuses global class information with local spatial relationships, significantly improving precision and recall in challenging border regions. An evaluation on the HAM10000 melanoma dataset demonstrates that our superpixel\u2013RAG\u2013transformer (region adjacency graph) pipeline achieves exceptional performance (100% F1 score, accuracy, and precision) in classifying background, border, and lesion core superpixels. By transforming raw dermoscopic images into region-based structured representations, the proposed method generates more informative inputs for downstream deep learning models. This strategy not only advances melanoma analysis but also provides a generalizable framework for other medical image segmentation and classification tasks.<\/jats:p>","DOI":"10.3390\/a18090551","type":"journal-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T12:04:28Z","timestamp":1756814668000},"page":"551","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SPADE: Superpixel Adjacency Driven Embedding for Three-Class Melanoma Segmentation"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0069-5346","authenticated-orcid":false,"given":"Pablo","family":"Ord\u00f3\u00f1ez","sequence":"first","affiliation":[{"name":"College of Computer Science and Software Engineering, Kennesaw State University, Marietta, GA 30060, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8661-8877","authenticated-orcid":false,"given":"Ying","family":"Xie","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Kennesaw State University, Marietta, GA 30060, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4243-083X","authenticated-orcid":false,"given":"Xinyue","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Kennesaw State University, Marietta, GA 30060, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4436-3474","authenticated-orcid":false,"given":"Chloe Yixin","family":"Xie","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Kennesaw State University, Marietta, GA 30060, USA"}]},{"given":"Santiago","family":"Acosta","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Kennesaw State University, Marietta, GA 30060, USA"}]},{"given":"Issac","family":"Guitierrez","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Kennesaw State University, Marietta, GA 30060, USA"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,2]]},"reference":[{"key":"ref_1","unstructured":"SEER (2025, January 19). Melanoma of the Skin\u2013Cancer Stat Facts, Available online: https:\/\/seer.cancer.gov\/statfacts\/html\/melan.html."},{"key":"ref_2","unstructured":"ACS (American Cancer Society) (2025, January 19). Melanoma Skin Cancer Statistics. Available online: https:\/\/www.cancer.org\/cancer\/types\/melanoma-skin-cancer\/about\/key-statistics.html."},{"key":"ref_3","first-page":"7","article-title":"Cancer statistics, 2022","volume":"72","author":"Siegel","year":"2022","journal-title":"CA Cancer J. Clin."},{"key":"ref_4","unstructured":"Society, A.C. (2025, January 19). Cancer Facts and Figures 2022. Available online: https:\/\/www.cancer.org\/research\/cancer-facts-statistics\/all-cancer-facts-figures\/cancer-facts-figures-2022.html."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e466","DOI":"10.1016\/S2589-7500(22)00023-1","article-title":"Artificial intelligence and machine learning algorithms for early detection of skin cancer in community and primary care settings: A systematic review","volume":"4","author":"Jones","year":"2022","journal-title":"Lancet Digit. Health"},{"key":"ref_6","unstructured":"Kang, S., Amagai, M., Bruckner, A.L., Enk, A.H., Margolis, D.J., McMichael, A.J., and Orringer, J.S. (2019). Fitzpatrick\u2019s Dermatology, 9e, McGraw-Hill Education. Chapter 116."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1016\/S0190-9622(96)80059-4","article-title":"Skin cancer diagnosis in a primary care setting","volume":"34","author":"Boiko","year":"1996","journal-title":"J. Am. Acad. Dermatol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1016\/S0140-6736(87)92540-2","article-title":"Early diagnosis of malignant melanoma by surface microscopy","volume":"330","author":"Soyer","year":"1987","journal-title":"Lancet"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1109\/TC.1972.5008949","article-title":"Fourier descriptors for plane closed curves","volume":"C-21","author":"Zahn","year":"1972","journal-title":"IEEE Trans. Comput."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Toureau, V., Bibiloni, P., Talavera-Mart\u00ednez, L., and Gonz\u00e1lez-Hidalgo, M. (2020, January 15\u201319). Automatic Detection of Symmetry in Dermoscopic Images Based on Shape and Texture. Proceedings of the Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU 2020), Lisbon, Portugal.","DOI":"10.1007\/978-3-030-50146-4_46"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"297","DOI":"10.3389\/fmed.2020.00297","article-title":"A Novel Fuzzy Multilayer Perceptron (F-MLP) for the Detection of Border Irregularity in Skin Lesions","volume":"7","author":"Ali","year":"2020","journal-title":"Front. Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e0234352","DOI":"10.1371\/journal.pone.0234352","article-title":"Towards the automatic detection of skin lesion shape asymmetry, color variegation and diameter in dermoscopic images","volume":"15","author":"Ali","year":"2020","journal-title":"PLoS ONE"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Samuel, N.E., and Anitha, J. (2022, January 21\u201323). Melanoma Detection and Classification based on Dermoscopic Images using Deep Learning Architectures-A Study. Proceedings of the 2022 4th International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India.","DOI":"10.1109\/ICIRCA54612.2022.9985523"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Alsahafi, Y.S., Elshora, D.S., Mohamed, E.R., and Hosny, K.M. (2023). Multilevel threshold segmentation of skin lesions in color images using Coronavirus Optimization Algorithm. Diagnostics, 13.","DOI":"10.3390\/diagnostics13182958"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Codella, N.C.F., Gutman, D., Celebi, M.E., Helba, B., Marchetti, M.A., Dusza, S.W., Kalloo, A., Liopyris, K., Mishra, N., and Kittler, H. (2018). Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC). arXiv.","DOI":"10.1109\/ISBI.2018.8363547"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Patel, R.H., Foltz, E.A., Witkowski, A., and Ludzik, J. (2023). Analysis of Artificial Intelligence-Based Approaches Applied to Non-Invasive Imaging for Early Detection of Melanoma: A Systematic Review. Cancers, 15.","DOI":"10.3390\/cancers15194694"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Rosas-Lara, M., Mendoza-Tello, J.C., Flores, A., and Zumba-Acosta, G. (2022, January 8\u201310). A Convolutional Neural Network-Based Web Prototype to Support Melanoma Skin Cancer Detection. Proceedings of the 2022 Third International Conference on Information Systems and Software Technologies (ICI2ST), Quito, Ecuador.","DOI":"10.1109\/ICI2ST57350.2022.00008"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Subramanian, B., Muthusamy, S., Thangaraj, K., Panchal, H., Kasirajan, E., Marimuthu, A., and Ravi, A. A new method for detection and classification of melanoma skin cancer using deep learning based transfer learning architecture models. Res. Sq., 2022.","DOI":"10.21203\/rs.3.rs-1857063\/v1"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Sagar, A., and Jacob, D. (2020). Convolutional Neural Networks for Classifying Melanoma Images. bioRXiv.","DOI":"10.1101\/2020.05.22.110973"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Gangwani, D., Liang, Q., Wang, S., and Zhu, X. (2021, January 7\u20138). An Empirical Study of Deep Learning Frameworks for Melanoma Cancer Detection using Transfer Learning and Data Augmentation. Proceedings of the 2021 IEEE International Conference on Big Knowledge (ICBK), Auckland, New Zealand.","DOI":"10.1109\/ICKG52313.2021.00015"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Cirrincione, G., Cannata, S., Cicceri, G., Prinzi, F., Currieri, T., Lovino, M., Militello, C., Pasero, E., and Vitabile, S. (2023). Transformer-Based Approach to Melanoma Detection. Sensors, 23.","DOI":"10.3390\/s23125677"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e0295151","DOI":"10.1371\/journal.pone.0295151","article-title":"SkinViT: A transformer based method for Melanoma and Nonmelanoma classification","volume":"18","author":"Khan","year":"2023","journal-title":"PLoS ONE"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Xie, J., Wu, Z., Zhu, R., and Zhu, H. (2021, January 15\u201317). Melanoma Detection based on Swin Transformer and SimAM. Proceedings of the 2021 IEEE 5th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), Xi\u2019an, China.","DOI":"10.1109\/ITNEC52019.2021.9587071"},{"key":"ref_24","unstructured":"Tan, M., and Le, Q.V. (2020). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"85467","DOI":"10.1109\/ACCESS.2023.3303961","article-title":"Deep Learning and Optimization-Based Methods for Skin Lesions Segmentation: A Review","volume":"11","author":"Hosny","year":"2023","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zafar, M., Amin, J., Sharif, M., Anjum, M.A., Mallah, G.A., and Kadry, S. (2023). DeepLabv3+-Based Segmentation and Best Features Selection Using Slime Mould Algorithm for Multi-Class Skin Lesion Classification. Mathematics, 11.","DOI":"10.3390\/math11020364"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1109\/TETCI.2023.3309626","article-title":"TransAttUnet: Multi-Level Attention-Guided U-Net With Transformer for Medical Image Segmentation","volume":"8","author":"Chen","year":"2024","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Akyel, C., and Ar\u0131c\u0131, N. (2022). LinkNet-B7: Noise Removal and Lesion Segmentation in Images of Skin Cancer. Mathematics, 10.","DOI":"10.3390\/math10050736"},{"key":"ref_29","unstructured":"Shreshth, S., Divij, G., and Anil, K.T. (2020). Detector-SegMentor Network for Skin Lesion Localization and Segmentation. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, L. (2023, January 24\u201326). FITrans: Skin Lesion Segmentation Based on Feature Integration and Transformer. Proceedings of the 2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE), Guangzhou, China.","DOI":"10.1109\/NNICE58320.2023.10105777"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e0277578","DOI":"10.1371\/journal.pone.0277578","article-title":"TC-Net: Dual coding network of Transformer and CNN for skin lesion segmentation","volume":"17","author":"Dong","year":"2022","journal-title":"PLoS ONE"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"81953","DOI":"10.1109\/ACCESS.2023.3298826","article-title":"A VAN-Based Multi-Scale Cross-Attention Mechanism for Skin Lesion Segmentation Network","volume":"11","author":"Liu","year":"2023","journal-title":"IEEE Access"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/S1470-2045(02)00679-4","article-title":"Diagnostic accuracy of dermoscopy","volume":"3","author":"Kittler","year":"2002","journal-title":"Lancet Oncol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"622","DOI":"10.1109\/TITB.2011.2150758","article-title":"Generalizing Common Tasks in Automated Skin Lesion Diagnosis","volume":"15","author":"Wighton","year":"2011","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. arXiv.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Adegun, A.A., Viriri, S., and Yousaf, M.H. (2021). A Probabilistic-Based Deep Learning Model for Skin Lesion Segmentation. Appl. Sci., 11.","DOI":"10.3390\/app11073025"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"\u00dcnver, H.M., and Ayan, E. (2019). Skin Lesion Segmentation in Dermoscopic Images with Combination of YOLO and GrabCut Algorithm. Diagnostics, 9.","DOI":"10.3390\/diagnostics9030072"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Mirikharaji, Z., Abhishek, K., Izadi, S., and Hamarneh, G. (2021). D-LEMA: Deep Learning Ensembles from Multiple Annotations\u2014Application to Skin Lesion Segmentation. arXiv.","DOI":"10.1109\/CVPRW53098.2021.00203"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Li, X., Peng, B., Hu, J., Ma, C., Yang, D., and Xie, Z. (2024). USL-Net: Uncertainty Self-Learning Network for Unsupervised Skin Lesion Segmentation. arXiv.","DOI":"10.2139\/ssrn.4570902"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"107924","DOI":"10.1016\/j.patcog.2021.107924","article-title":"Boundarymix: Generating pseudo-training images for improving segmentation with scribble annotations","volume":"117","author":"Lu","year":"2021","journal-title":"Pattern Recognit."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Avelar, P.H.C., Tavares, A.R., da Silveira, T.L.T., Jung, C.R., and Lamb, L.C. (2020, January 7\u201310). Superpixel Image Classification with Graph Attention Networks. Proceedings of the 2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Ipojuca, Brazil.","DOI":"10.1109\/SIBGRAPI51738.2020.00035"},{"key":"ref_42","unstructured":"Nazir, U., Wang, H., and Taj, M. (2021). Survey of Image Based Graph Neural Networks. arXiv."},{"key":"ref_43","first-page":"102935","article-title":"Extended SLIC superpixels algorithm for applications to non-imagery geospatial rasters","volume":"112","author":"Nowosad","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"095017","DOI":"10.1088\/1361-6560\/aabd19","article-title":"Superpixel-based and boundary-sensitive convolutional neural network for automated liver segmentation","volume":"63","author":"Qin","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","article-title":"SLIC Superpixels Compared to State-of-the-Art Superpixel Methods","volume":"34","author":"Achanta","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"3199","DOI":"10.1109\/TIP.2019.2957937","article-title":"Superpixel Embedding Network","volume":"29","author":"Gaur","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_47","unstructured":"OpenCV Team (2025, January 19). OpenCV (Open Source Computer Vision Library). Version 4.9.0.2023. Available online: https:\/\/opencv.org\/."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Jaworek-Korjakowska, J., and Kleczek, P. (2018). Region Adjacency Graph Approach for Acral Melanocytic Lesion Segmentation. Appl. Sci., 8.","DOI":"10.3390\/app8091430"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"180161","DOI":"10.1038\/sdata.2018.161","article-title":"The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions","volume":"5","author":"Tschandl","year":"2018","journal-title":"Sci. Data"},{"key":"ref_50","unstructured":"Neo4j, Inc. (2025, January 19). Neo4j: Graph Data Platform. Available online: https:\/\/neo4j.com\/."},{"key":"ref_51","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/9\/551\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:37:48Z","timestamp":1760035068000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/9\/551"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,2]]},"references-count":51,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["a18090551"],"URL":"https:\/\/doi.org\/10.3390\/a18090551","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2025,9,2]]}}}