Fugu-MT 論文翻訳(概要): Hybrid Context Forests and Bilateral Viterbi Matching for 3D Rib Centerline Tracing in CT

論文の概要: Hybrid Context Forests and Bilateral Viterbi Matching for 3D Rib Centerline Tracing in CT

arxiv url: http://arxiv.org/abs/2610.16047v2
Date: Sun, 18 Oct 2026 01:28:06 GMT
ステータス: 情報取得中
システム内更新日: 2026-10-20 22:19:04.907313
Title: Hybrid Context Forests and Bilateral Viterbi Matching for 3D Rib Centerline Tracing in CT
Title（参考訳）: CTにおける3次元中心線追跡のためのハイブリッド環境森林とバイラテラルビタビマッチング
Abstract要約: Riblineはオープンソースの3段階のフレームワークで、肺・肺・脊椎・中葉の座標フレームと、各リブに沿って点を並べるキプロスを意識した方位角を組み合わせたものである。 The Siemens Corporate Research 2 mm thoracic CT benchmark, our pipeline achieves a labeled Chamfer distance of 2.05 mm, labeled clDice of 0.886 (3 mm) and 0.945 (4 mm), and 97.2% labeling accuracy (278/286 ribs)。
参考スコア（独自算出の注目度）: 10.666994450382576
License:
Abstract: Automatic extraction and anatomical numbering (R01-R12, L01-L12) of all 24 rib centerlines in thoracic CT is essential for unfolded rib visualization, fracture detection, and surgical navigation, but remains challenging due to adjacent-bone confluence, calcified costal cartilage bridges, kyphotic pose variation, and partial visibility of terminal ribs. We present ribline, an open-source three-stage framework combining: (1) an automatically detected lung-apex and vertebral-midline coordinate frame with a kyphosis-aware azimuthal angle for point ordering along each rib; (2) a hybrid voxel detector fusing an anatomically anchored Semantic Context Forest (SCF) with a lightweight 3D U-Net; and (3) a global stage that decomposes the probability skeleton into candidate curves, assigns rib indices via a bilateral Viterbi dynamic program coupled across both hemithoraces, and refines curves via template recovery and normal-plane centering (RibSnake). On the Siemens Corporate Research 2 mm thoracic CT benchmark (47 training and 12 evaluation scans), our pipeline achieves a labeled Chamfer distance of 2.05 mm, labeled clDice of 0.886 (3 mm) and 0.945 (4 mm), 97.2% labeling accuracy (278/286 ribs), and zero false-positive curves on the evaluation split, and 3.64 mm (median 2.39 mm) with 91.8% labeling accuracy across all 59 annotated scans (1,402 ribs) in 5-fold cross-validation. Code: https://github.com/wq2012/ribline Pretrained Models: https://huggingface.co/collections/wq2012/ribline
Abstract（参考訳）: 胸部CTにおける24リブ中心線の自動抽出および解剖学的番号付け(R01-R12,L01-L12)は, 開胸リブの可視化, 骨折検出, 手術ナビゲーションに必須であるが, 隣接骨合流, 石灰化軟骨ブリッジ, キフォティックポーズ変動, 終端リブの部分視認性などにより, 依然として困難である。著者らは,(1)肺動脈と脊椎動脈の座標フレームを自動的に検出し,各リブに沿って点秩序を考慮し,かつ,(2)解剖学的に固定されたセマンティック・コンテクスト・フォレスト(SCF)を軽量な3次元U-Netで融合させたハイブリッドボクセル検出器,(3)確率骨格を候補曲線に分解し,両側のビテルビダイナミック・プログラムを介してリブインデックスを割り当てるグローバルステージ,およびテンプレート・リカバリーと正常な平面中心化(RibSnake)により曲線を洗練させる,という3段階のオープンソースフレームワークを提案する。 Siemens Corporate Research 2 mm thoracic CT benchmark 2 mm thoracic CT benchmark (47 training and 12 evaluation scans)では,Chamfer distance 2.05 mm, labeled clDice 0.886 (3 mm) and 0.945 (4 mm), 97.2% labeling accuracy (278/286 ribs), zero false- positive curves on the evaluation split, and 3.64 mm (median 2.39 mm) with 91.8% labeling accuracy of 59 annotated scans (1,402 ribs) in 5-fold cross-validationを行った。コード: https://github.com/wq2012/ribline Pretrained Models: https://huggingface.co/collections/wq2012/ribline

論文の概要: Hybrid Context Forests and Bilateral Viterbi Matching for 3D Rib Centerline Tracing in CT

関連論文リスト