{"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/llm-driven-multimodal-target-volume","title":"LLM-driven Multimodal Target Volume Contouring in Radiation Oncology","arxiv_id":"2311.01908","date":"2023-11-03","proceeding":null,"authors":["Yujin Oh","Sangjoon Park","Hwa Kyung Byun","Yeona Cho","Ik Jae Lee","Jin Sung Kim","Jong Chul Ye"],"abstract":"Target volume contouring for radiation therapy is considered significantly more challenging than the normal organ segmentation tasks as it necessitates the utilization of both image and text-based clinical information. Inspired by the recent advancement of large language models (LLMs) that can facilitate the integration of the textural information and images, here we present a novel LLM-driven multimodal AI, namely LLMSeg, that utilizes the clinical text information and is applicable to the challenging task of target volume contouring for radiation therapy, and validate it within the context of breast cancer radiation therapy target volume contouring. Using external validation and data-insufficient environments, which attributes highly conducive to real-world applications, we demonstrate that the proposed model exhibits markedly improved performance compared to conventional unimodal AI models, particularly exhibiting robust generalization performance and data efficiency. To our best knowledge, this is the first LLM-driven multimodal AI model that integrates the clinical text information into target volume delineation for radiation oncology.","url_abs":"https://arxiv.org/abs/2311.01908v4","url_pdf":"https://arxiv.org/pdf/2311.01908v4.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":"llm-driven-multimodal-target-volume","repo_url":"https://github.com/tvseg/mm-llm-ro","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"organ-segmentation","task_name":"Organ Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.01908","atlas_url":"https://app.syntology.ai/?focus=2311.01908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01908"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/tvseg/mm-llm-ro","reach":{"status":"ok"}}],"summary":{"ran_fixture":2,"ran_draft_wrong":4,"ran":5},"by_repo_kind":{"official":{"samples":11,"ran":11,"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":11,"samples":[{"code_sha256_prefix":"30d7eec482ebf6b1","entry":"repeat_kv","repo":"tvseg/mm-llm-ro","repo_kind":"official","path":"model/llama2/llama_custom.py","file_url":"https://github.com/tvseg/mm-llm-ro/blob/HEAD/model/llama2/llama_custom.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"30d7eec482ebf6b1"}},{"code_sha256_prefix":"f725bc2d76076485","entry":"apply_rotary_pos_emb","repo":"tvseg/mm-llm-ro","repo_kind":"official","path":"model/llama2/llama_custom.py","file_url":"https://github.com/tvseg/mm-llm-ro/blob/HEAD/model/llama2/llama_custom.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f725bc2d76076485"}},{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"tvseg/mm-llm-ro","repo_kind":"official","path":"model/text_encoder.py","file_url":"https://github.com/tvseg/mm-llm-ro/blob/HEAD/model/text_encoder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"9bd73c5e00265752","entry":"build_prompt","repo":"tvseg/mm-llm-ro","repo_kind":"official","path":"utils/data_utils.py","file_url":"https://github.com/tvseg/mm-llm-ro/blob/HEAD/utils/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9bd73c5e00265752"}},{"code_sha256_prefix":"92e339090ef65eaa","entry":"datafold_read_","repo":"tvseg/mm-llm-ro","repo_kind":"official","path":"utils/data_utils.py","file_url":"https://github.com/tvseg/mm-llm-ro/blob/HEAD/utils/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"92e339090ef65eaa"}},{"code_sha256_prefix":"7b0ecad70df7f175","entry":"dice","repo":"tvseg/mm-llm-ro","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/tvseg/mm-llm-ro/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7b0ecad70df7f175"}},{"code_sha256_prefix":"8b18111ad2f880f7","entry":"distributed_all_gather","repo":"tvseg/mm-llm-ro","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/tvseg/mm-llm-ro/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8b18111ad2f880f7"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"tvseg/mm-llm-ro","repo_kind":"official","path":"model/text_encoder.py","file_url":"https://github.com/tvseg/mm-llm-ro/blob/HEAD/model/text_encoder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"4ac07e45c0176d2d","entry":"resample_3d","repo":"tvseg/mm-llm-ro","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/tvseg/mm-llm-ro/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4ac07e45c0176d2d"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"tvseg/mm-llm-ro","repo_kind":"official","path":"model/llama2/llama_custom.py","file_url":"https://github.com/tvseg/mm-llm-ro/blob/HEAD/model/llama2/llama_custom.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"tvseg/mm-llm-ro","repo_kind":"official","path":"model/text_encoder.py","file_url":"https://github.com/tvseg/mm-llm-ro/blob/HEAD/model/text_encoder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9542161e9640b858"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}