{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multi-view-breast-cancer-classification-via","title":"Multi-View Hypercomplex Learning for Breast Cancer Screening","arxiv_id":"2204.05798","date":"2022-04-12","proceeding":null,"authors":["Eleonora Lopez","Eleonora Grassucci","Martina Valleriani","Danilo Comminiello"],"abstract":"Traditionally, deep learning methods for breast cancer classification perform a single-view analysis. However, radiologists simultaneously analyze all four views that compose a mammography exam, owing to the correlations contained in mammography views, which present crucial information for identifying tumors. In light of this, some studies have started to propose multi-view methods. Nevertheless, in such existing architectures, mammogram views are processed as independent images by separate convolutional branches, thus losing correlations among them. To overcome such limitations, in this paper, we propose a methodological approach for multi-view breast cancer classification based on parameterized hypercomplex neural networks. Thanks to hypercomplex algebra properties, our networks are able to model, and thus leverage, existing correlations between the different views that comprise a mammogram, thus mimicking the reading process performed by clinicians. This happens because hypercomplex networks capture both global properties, as standard neural models, as well as local relations, i.e., inter-view correlations, which real-valued networks fail at modeling. We define architectures designed to process two-view exams, namely PHResNets, and four-view exams, i.e., PHYSEnet and PHYBOnet. Through an extensive experimental evaluation conducted with publicly available datasets, we demonstrate that our proposed models clearly outperform real-valued counterparts and state-of-the-art methods, proving that breast cancer classification benefits from the proposed multi-view architectures. We also assess the method generalizability beyond mammogram analysis by considering different benchmarks, as well as a finer-scaled task such as segmentation. Full code and pretrained models for complete reproducibility of our experiments are freely available at https://github.com/ispamm/PHBreast.","url_abs":"https://arxiv.org/abs/2204.05798v3","url_pdf":"https://arxiv.org/pdf/2204.05798v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multi-view-breast-cancer-classification-via","repo_url":"https://github.com/ispamm/phbreast","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"breast-tumour-classification","task_name":"Breast Tumour Classification"},{"task_slug":"cancer-classification","task_name":"Cancer Classification"},{"task_slug":"cancer-no-cancer-per-breast-classification","task_name":"Cancer-no cancer per breast classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"multiview-learning","task_name":"Multiview Learning"},{"task_slug":"tumor-segmentation","task_name":"Tumor Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cancer-no-cancer-per-breast-classification-on","task":"Cancer-no cancer per breast classification","dataset":"CBIS-DDSM","model":"PHResNet50 (n=2)","rank_in_archive_order":3,"of":3,"metrics":{"AUC":"0.739"},"uses_additional_data":false},{"leaderboard":"/sota/cancer-no-cancer-per-breast-classification-on-1","task":"Cancer-no cancer per breast classification","dataset":"InBreast","model":"PHYSEnet (n=2)","rank_in_archive_order":1,"of":3,"metrics":{"AUC":"0.814"},"uses_additional_data":true},{"leaderboard":"/sota/cancer-no-cancer-per-breast-classification-on-1","task":"Cancer-no cancer per breast classification","dataset":"InBreast","model":"PHResNet18 (n=2)","rank_in_archive_order":2,"of":3,"metrics":{"AUC":"0.793"},"uses_additional_data":true},{"leaderboard":"/sota/cancer-no-cancer-per-breast-classification-on-1","task":"Cancer-no cancer per breast classification","dataset":"InBreast","model":"PHYBOnet (n=4)","rank_in_archive_order":3,"of":3,"metrics":{"AUC":"0.764"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2204.05798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.05798"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ispamm/phbreast","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"01423bbbb5930bbd","entry":"get_i","repo":"ispamm/phbreast","repo_kind":"official","path":"models/hypercomplex_ops.py","file_url":"https://github.com/ispamm/phbreast/blob/HEAD/models/hypercomplex_ops.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01423bbbb5930bbd"}},{"code_sha256_prefix":"250d2abbf60ffa77","entry":"get_r","repo":"ispamm/phbreast","repo_kind":"official","path":"models/hypercomplex_ops.py","file_url":"https://github.com/ispamm/phbreast/blob/HEAD/models/hypercomplex_ops.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"250d2abbf60ffa77"}},{"code_sha256_prefix":"917981cbd6f167d2","entry":"q_normalize","repo":"ispamm/phbreast","repo_kind":"official","path":"models/hypercomplex_ops.py","file_url":"https://github.com/ispamm/phbreast/blob/HEAD/models/hypercomplex_ops.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"917981cbd6f167d2"}},{"code_sha256_prefix":"806d8eb91cb8b733","entry":"MyDataLoader","repo":"ispamm/phbreast","repo_kind":"official","path":"utils/dataloaders.py","file_url":"https://github.com/ispamm/phbreast/blob/HEAD/utils/dataloaders.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"806d8eb91cb8b733"}},{"code_sha256_prefix":"b9525c5741564d65","entry":"ResNet18","repo":"ispamm/phbreast","repo_kind":"official","path":"models/real_models.py","file_url":"https://github.com/ispamm/phbreast/blob/HEAD/models/real_models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b9525c5741564d65"}},{"code_sha256_prefix":"0626a1882fcbfc15","entry":"ResNet50","repo":"ispamm/phbreast","repo_kind":"official","path":"models/real_models.py","file_url":"https://github.com/ispamm/phbreast/blob/HEAD/models/real_models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0626a1882fcbfc15"}},{"code_sha256_prefix":"519e9cfd9abb2442","entry":"readFile","repo":"ispamm/phbreast","repo_kind":"official","path":"utils/readFile.py","file_url":"https://github.com/ispamm/phbreast/blob/HEAD/utils/readFile.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"519e9cfd9abb2442"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}