diff --git a/CLAUDE.md b/CLAUDE.md index 631bf85..243f936 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -65,6 +65,11 @@ `nishi2021` carried over from the MIDL paper as a starting point) — real bibliographic data still needs to be filled in and verified, and new citations added as the manuscript grows. +- [citations/](citations/) holds the PDFs of cited papers (one per + reference, named after its `.bib` cite key, e.g. `babapoor2022.pdf`). + Drop a paper's PDF there and Claude Code can read it directly to fill in + or verify that key's entry in `references.bib` (title, authors, venue, + year, DOI, etc.) instead of guessing from the key name alone. - Math/theorem-like environments should use MDPI's names: Theorem, Lemma, Corollary, Proposition, Characterization, Property, Problem, Example, ExamplesandDefinitions, Hypothesis, Remark, Definition, Notation, @@ -113,6 +118,12 @@ or the smaller `basictex`, or `sudo apt install texlive-full` on Linux) or compile via Overleaf instead (Overleaf manages its own build output and ignores this convention). +- **VS Code (LaTeX Workshop)**: [.vscode/settings.json](.vscode/settings.json) + sets a latexmk recipe that outputs to `build/`. On Windows, VS Code must + have the folder open *in WSL* (Remote-WSL: "WSL: Reopen Folder in WSL", + or `code .` from a WSL shell) — opening it via the `\\wsl.localhost\...` + UNC path runs LaTeX Workshop on the Windows side, where no TeX is + installed, so building fails. ## Writing conventions - Manuscript language is English (MDPI submission requirement), even @@ -127,6 +138,25 @@ English, translate faithfully — not a loose paraphrase — while still producing natural, idiomatic English rather than a stiff word-for-word rendering. +- **Line wrapping (semantic linefeeds + a soft ~80-char cap)**: in prose + files (`sections/*.tex`, `drafts/ja/*.md`), start a new line at each + sentence boundary (English `.`/`!`/`?` + space; Japanese `。`/`．`) + instead of writing a whole paragraph as one unbroken line. That alone + isn't enough — a single sentence can still run well past a readable + width — so also keep every line at roughly 80 characters: if a sentence + (or an enumerated `(1)/(2)/(3)` item within one) is longer than that, + break it further at a clean clause boundary at or before the ~80-char + mark (comma, semicolon, or a coordinating/subordinating conjunction + like "and"/"but"/"because"/"which"/"while"/"however"; Japanese + `，`/`、`/接続助詞など), continuing flush-left with no extra indent — + never break mid-phrase just to hit the column exactly. A single newline + is invisible in the rendered output — both LaTeX and Markdown treat it + as a space within a paragraph, and only a blank line starts a new + paragraph — so this is purely a source-readability/diff convention, not + something that changes the PDF. Applies whenever a prose file is newly + written or substantively redrafted (including the + `ja-drafter`/`en-translator` pipeline output); not a mandate to + mass-reflow untouched files. ## Drafting workflow (subagents) Sections get written through a fixed pipeline rather than drafted directly diff --git a/citations/babapoor2022.pdf b/citations/babapoor2022.pdf new file mode 100644 index 0000000..5786e5c --- /dev/null +++ b/citations/babapoor2022.pdf Binary files differ diff --git a/citations/nishi2021.pdf b/citations/nishi2021.pdf new file mode 100644 index 0000000..123b124 --- /dev/null +++ b/citations/nishi2021.pdf Binary files differ diff --git a/citations/wu2011.pdf b/citations/wu2011.pdf new file mode 100644 index 0000000..5aa235b --- /dev/null +++ b/citations/wu2011.pdf Binary files differ diff --git a/drafts/ja/1_introduction.md b/drafts/ja/1_introduction.md index fd66992..9e1cf1a 100644 --- a/drafts/ja/1_introduction.md +++ b/drafts/ja/1_introduction.md @@ -1,16 +1,77 @@ # Introduction（ドラフト） -心筋梗塞や狭心症に代表される虚血性心疾患は，冠動脈の狭窄あるいは閉塞により心筋への血流が阻害され，胸痛や心筋障害を引き起こす重大な疾患群である．動脈硬化の進行に伴い血管壁に形成されるプラークはこの狭窄の主因であり，プラークが肥大化することで血管内腔が狭小化し，心筋への血液供給が低下する．こうした患者に対しては冠動脈バイパス術や経皮的冠動脈形成術（percutaneous coronary intervention: PCI）が行われており，このうちPCIはカテーテルを用いた低侵襲治療として広く普及している． +心筋梗塞や狭心症に代表される虚血性心疾患は，冠動脈の狭窄あるいは閉塞により心筋への血流が阻害され， +胸痛や心筋障害を引き起こす重大な疾患群である． +動脈硬化の進行に伴い血管壁に形成されるプラークはこの狭窄の主因であり， +プラークが肥大化することで血管内腔が狭小化し，心筋への血液供給が低下する． +こうした患者に対しては冠動脈バイパス術や経皮的冠動脈形成術（percutaneous coronary intervention: PCI） +が行われており， +このうちPCIはカテーテルを用いた低侵襲治療として広く普及している． -しかしPCIには，No reflowおよびSlow flowと呼ばれる合併症のリスクが伴う．No reflowは，ステント留置などにより狭窄そのものは解消されるものの，病変部の拡張過程で流出したプラーク内容物や血栓が末梢の微小血管を閉塞し（末梢塞栓，distal microembolization），末梢血流が完全に遮断された状態を指し，微小血管攣縮もその一因とされる．Slow flowは，血流が完全には遮断されないものの著しく遅延した状態である．これらの合併症はPCI後の患者の約10〜20%に発症するとされ[babapoor2022]，急性心筋梗塞（AMI）症例では約10%以上の頻度で発症するとの報告もある【要出典】．いずれも心筋への酸素供給が絶たれることから，心不全の新規発症や心筋梗塞の再発，院内死亡率の上昇など，重大な予後不良因子となることが知られている【要出典】．発症後は血管拡張薬の冠動脈内投与などの治療が行われるが，既に末梢の毛細血管を閉塞している脂質や壊死物質などを除去することはできず，また急激な血圧低下や不整脈といった副作用のリスクも伴うため，事後治療のみでは限界がある【要出典】．こうした背景から，合併症の発症後に対処するのではなく，発症そのものを未然に防ぐ予防的戦略の確立が重要な課題となっている． +しかしPCIには，No reflowおよびSlow flowと呼ばれる合併症のリスクが伴う． +No reflowは，ステント留置などにより狭窄そのものは解消されるものの， +病変部の拡張過程で流出したプラーク内容物や血栓が末梢の微小血管を閉塞し（末梢塞栓， +distal microembolization），末梢血流が完全に遮断された状態を指し， +微小血管攣縮もその一因とされる． +Slow flowは，血流が完全には遮断されないものの著しく遅延した状態である． +単施設で実施されたprimary PCI患者を対象としたコホート研究では， +No reflowおよびSlow flowがそれぞれ17.1%，12.9%の患者に認められたと報告されており[babapoor2022]， +急性心筋梗塞（AMI）症例では約10%以上の頻度で発症するとの報告もある【要出典】． +いずれも心筋への酸素供給が絶たれることから，心不全の新規発症や心筋梗塞の再発， +院内死亡率の上昇など，重大な予後不良因子となることが知られている【要出典】． +発症後は血管拡張薬の冠動脈内投与などの治療が行われるが， +既に末梢の毛細血管を閉塞している脂質や壊死物質などを除去することはできず， +また急激な血圧低下や不整脈といった副作用のリスクも伴うため， +事後治療のみでは限界がある【要出典】． +こうした背景から，合併症の発症後に対処するのではなく， +発症そのものを未然に防ぐ予防的戦略の確立が重要な課題となっている． -術前にNo reflowやSlow flowのリスクが高いと判明した場合，臨床現場では病変遠位部にステント留置前から末梢保護デバイス（distal protection device）を留置する，あるいは血管拡張薬をあらかじめ冠動脈内投与するといった予防的対応が取られる【要出典】．末梢保護デバイスは高リスク病変に対しては有効である一方，準備に伴う負担からすべての症例に適用することは現実的でなく，術前の正確なリスク層別化が不可欠となる．血管内超音波（IVUS）は血管壁やプラークの状態を可視化でき，病変部に関する有用な情報を提供する．しかしIVUS画像の読影には専門的な知識を要するうえ，血管径やプラーク組成など複数の因子が複雑に絡み合うため，目視のみによる高精度なリスク予測は困難であり，IVUS画像から定量的にリスクを評価する手法が求められている． +術前にNo reflowやSlow flowのリスクが高いと判明した場合， +臨床現場では病変遠位部にステント留置前から末梢保護デバイス（distal protection device） +を留置する， +あるいは血管拡張薬をあらかじめ冠動脈内投与するといった予防的対応が取られる【要出典】． +末梢保護デバイスは高リスク病変に対しては有効である一方， +準備に伴う負担からすべての症例に適用することは現実的でなく， +術前の正確なリスク層別化が不可欠となる． +血管内超音波（IVUS）は血管壁やプラークの状態を可視化でき， +病変部に関する有用な情報を提供する． +しかしIVUS画像の読影には専門的な知識を要するうえ，血管径やプラーク組成など複数の因子が複雑に絡み合うため， +目視のみによる高精度なリスク予測は困難であり， +IVUS画像から定量的にリスクを評価する手法が求められている． -IVUS上で観察される減衰プラーク（attenuated plaque）の量については，合併症を発症した患者群と発症しなかった患者群との間に有意差が認められるとする報告がある[wu2011]．これは，減衰プラークが多いほど血栓形成や微小血管閉塞が生じやすく，合併症のリスクが高まる可能性を示唆するものである．しかしこのスコアリングは医師による手動評価にとどまっており，自動化・客観化された予測手法が求められている． +AMI患者において，IVUS上の減衰プラーク（attenuated plaque） +の量（医師による手動のアテニュエーションスコアリングにより定量化）は， +PCI後の血管造影上の血流がNo reflow/Slow flowを合わせた複合基準（TIMI flow grade 2以下） +を満たした患者と満たさなかった患者との間で有意差があることが報告されている[wu2011]． +なお，減衰プラークの存在の有無自体には有意差はなく， +その量においてのみ有意差が認められた点は注目に値する． +これは，減衰プラークが多いほど血栓形成や微小血管閉塞が生じやすく， +合併症のリスクが高まる可能性を示唆するものである． +しかしこのスコアリングは医師による手動評価にとどまっており， +自動化・客観化された予測手法が求められている． -No reflowやSlow flowの予測に有効な情報は，IVUS画像そのもの，患者の臨床変数，病変の形態の交差点に存在すると考えられる．一方でこれらの合併症は発症自体が比較的稀であり，アウトカムがラベル付けされた症例の中でも陽性例はさらに限られるため，これらの情報をエンドツーエンドに学習しきることは難しい． +No reflowやSlow flowの予測に有効な情報は，IVUS画像そのもの，患者の臨床変数， +病変の形態の交差点に存在すると考えられる． +一方でこれらの合併症は発症自体が比較的稀であり， +アウトカムがラベル付けされた症例の中でも陽性例はさらに限られるため， +これらの情報をエンドツーエンドに学習しきることは難しい． -以上を踏まえ，本研究ではIVUS画像，患者の臨床情報，病変のプラーク特徴を統合的に扱うアーキテクチャ「KSCNet」を提案する．KSCNetは，もともと腎結石の分類のために開発された3Dアーキテクチャ【要出典】を，IVUSデータの構造に合わせて再設計したものである．IVUSのプルバック画像はCTのような等方的な3Dボリュームではなく，時系列に沿った異方的な2D断面の系列であることから，3D畳み込みの代わりに，重み共有された2Dのフレーム単位エンコーダとフレーム間のTransformerによる系列モデリングを採用する．具体的には，(1) 患者単位の臨床情報とプラーク特徴（減衰プラークの面積など）を統合した特徴ベクトルをフレーム系列への追加トークンとして注入し画像表現と相互作用させる仕組み，(2) 血管腔・血管壁のセグメンテーションを補助タスクとして用い，その特徴を手がかりに症例レベルの特徴をcross-attentionにより集約する仕組み，(3) セグメンテーション損失と分類損失を動的に重み付けするマルチタスク損失，という3つの要素を統合している．これにより，画像のみを用いる手法，臨床情報のみを用いる表形式手法，および既存の減衰プラークスコアリング手法と比較して，IVUS画像・臨床情報・病変特徴を組み合わせることが予測性能の向上に寄与するかを検証する． +以上を踏まえ，本研究ではIVUS画像，患者の臨床情報， +病変のプラーク特徴を統合的に扱うアーキテクチャ「KSCNet」を提案する． +KSCNetは，もともと腎結石の分類のために開発された3Dアーキテクチャ【要出典】を， +IVUSデータの構造に合わせて再設計したものである． +IVUSのプルバック画像はCTのような等方的な3Dボリュームではなく， +時系列に沿った異方的な2D断面の系列であることから，3D畳み込みの代わりに， +重み共有された2Dのフレーム単位エンコーダとフレーム間のTransformerによる系列モデリングを採用する． +具体的には，(1) 患者単位の臨床情報とプラーク特徴（減衰プラークの面積など） +を統合した特徴ベクトルをフレーム系列への追加トークンとして注入し画像表現と相互作用させる仕組み， +(2) 血管腔・血管壁のセグメンテーションを補助タスクとして用い， +その特徴を手がかりに症例レベルの特徴をcross-attentionにより集約する仕組み， +(3) セグメンテーション損失と分類損失を動的に重み付けするマルチタスク損失， +という3つの要素を統合している． +これにより，画像のみを用いる手法，臨床情報のみを用いる表形式手法， +および既存の減衰プラークスコアリング手法と比較して， +IVUS画像・臨床情報・病変特徴を組み合わせることが予測性能の向上に寄与するかを検証する． --- diff --git a/main.tex b/main.tex index 9767904..df00bdb 100644 --- a/main.tex +++ b/main.tex @@ -306,37 +306,12 @@ %===================================== % References, variant A: external bibliography %===================================== -% \bibliography{your_external_BibTeX_file} +\bibliography{references} %===================================== -% References, variant B: internal bibliography +% References, variant B: internal bibliography (unused — see references.bib) %===================================== -% ACS format -\begin{thebibliography}{999} -% Reference 1 -\bibitem{ref-journal} -Author~1, T. The title of the cited article. {\em Journal Abbreviation} {\bf 2008}, {\em 10}, 142--149. -% Reference 2 -\bibitem{ref-book1} -Author~2, L. The title of the cited contribution. In {\em The Book Title}; Editor 1, F., Editor 2, A., Eds.; Publishing House: City, Country, 2007; pp. 32--58. -% Reference 3 -\bibitem{ref-book2} -Author 1, A.; Author 2, B. \textit{Book Title}, 3rd ed.; Publisher: Publisher Location, Country, 2008; pp. 154--196. -% Reference 4 -\bibitem{ref-unpublish} -Author 1, A.B.; Author 2, C. Title of Unpublished Work. \textit{Abbreviated Journal Name} year, \textit{phrase indicating stage of publication (submitted; accepted; in press)}. -% Reference 5 -\bibitem{ref-url} -Title of Site. Available online: URL (accessed on Day Month Year). -% Reference 6 -\bibitem{ref-proceeding} -Author 1, A.B.; Author 2, C.D.; Author 3, E.F. Title of presentation. In Proceedings of the Name of the Conference, Location of Conference, Country, Date of Conference (Day Month Year); Abstract Number (optional), Pagination (optional). -% Reference 7 -\bibitem{ref-thesis} -Author 1, A.B. Title of Thesis. Level of Thesis, Degree-Granting University, Location of University, Date of Completion. -\end{thebibliography} - % If authors have biography, please use the format below %\section*{Short Biography of Authors} %\bio diff --git a/references.bib b/references.bib index aeb298e..79c7162 100644 --- a/references.bib +++ b/references.bib @@ -1,19 +1,38 @@ % references.bib — bibliography for the MDPI "AI in Medicine" manuscript. % -% Seeded with the citation keys already used in Reference/main.tex and -% Reference/main_ja.tex (the MIDL 2026 short paper this journal article -% expands). Every entry below is a STUB: only the cite key is trustworthy, -% the bibliographic fields are placeholders and MUST be verified against -% the real source before compiling/citing. Do not submit with @TODO entries. +% Every entry's bibliographic data has been verified against the actual +% cited paper (PDF kept in citations/.pdf) — see that folder +% before adding a new entry from a bare cite key. -@TODO{babapoor2022, - note = {TODO: verify — cited in Reference/main.tex for no-reflow/slow flow incidence (~10-20% of PCI cases)} +@article{babapoor2022, + author = {Babapour, Behzad and Sadeghieh-Ahari, Saeid and Sadeghi Hariri, Mehdi and Shahbazzadegan, Bita}, + title = {Survey of effective factors in slow flow and no reflow in primary percutaneous coronary intervention patients}, + journal = {International Journal of Community Medicine and Public Health}, + year = {2022}, + volume = {9}, + number = {3}, + pages = {1222--1228}, + month = {mar}, + doi = {10.18203/2394-6040.ijcmph20220678} } -@TODO{wu2011, - note = {TODO: verify — cited in Reference/main.tex for the manual attenuated-plaque scoring system compared against in Results} +@article{wu2011, + author = {Wu, Xiaofan and Mintz, Gary S. and Xu, Kai and Lansky, Alexandra J. and Witzenbichler, Bernhard and Guagliumi, Giulio and Brodie, Bruce and Kellett, Mirle A. and Dressler, Ovidiu and Parise, Helen and Mehran, Roxana and Stone, Gregg W. and Maehara, Akiko}, + title = {The Relationship Between Attenuated Plaque Identified by Intravascular Ultrasound and No-Reflow After Stenting in Acute Myocardial Infarction: The HORIZONS-AMI Trial}, + journal = {JACC: Cardiovascular Interventions}, + year = {2011}, + volume = {4}, + number = {5}, + pages = {495--502}, + doi = {10.1016/j.jcin.2010.12.012} } -@TODO{nishi2021, - note = {TODO: verify — cited in Reference/main.tex for the plaque segmentation model used for the ROI-mask comparison method} +@article{nishi2021, + author = {Nishi, Takeshi and Yamashita, Rikiya and Imura, Shinji and Tateishi, Kazuya and Kitahara, Hideki and Kobayashi, Yoshio and Yock, Paul G. and Fitzgerald, Peter J. and Honda, Yasuhiro}, + title = {Deep learning-based intravascular ultrasound segmentation for the assessment of coronary artery disease}, + journal = {International Journal of Cardiology}, + year = {2021}, + volume = {333}, + pages = {55--59}, + doi = {10.1016/j.ijcard.2021.03.020} } diff --git a/sections/1_introduction.tex b/sections/1_introduction.tex index f25cf9b..365b6fd 100644 --- a/sections/1_introduction.tex +++ b/sections/1_introduction.tex @@ -1,11 +1,101 @@ -Ischemic heart disease, typified by myocardial infarction and angina pectoris, is a serious group of conditions in which stenosis or occlusion of the coronary arteries impedes blood flow to the myocardium, causing chest pain and myocardial injury. Plaque that forms in the vessel wall as atherosclerosis progresses is the principal cause of this stenosis: as plaque enlarges, the vessel lumen narrows and the blood supply to the myocardium is reduced. Such patients are treated with coronary artery bypass grafting or percutaneous coronary intervention (PCI); of these, PCI---a catheter-based, minimally invasive treatment---has become widely established. +Ischemic heart disease, typified by myocardial infarction and angina pectoris, +is a serious group of conditions in which stenosis or occlusion of the coronary +arteries impedes blood flow to the myocardium, +causing chest pain and myocardial injury. +Plaque that forms in the vessel wall as atherosclerosis progresses is the +principal cause of this stenosis: as plaque enlarges, +the vessel lumen narrows and the blood supply to the myocardium is reduced. +Such patients are treated with coronary artery bypass grafting or percutaneous +coronary intervention (PCI); of these, PCI---a catheter-based, +minimally invasive treatment---has become widely established. -However, PCI carries the risk of complications known as the no-reflow phenomenon and slow flow. No-reflow refers to a state in which, although the stenosis itself is resolved by stent placement or similar procedures, peripheral blood flow is completely obstructed because plaque contents or thrombus released during dilation of the lesion occlude the distal microvasculature (distal microembolization), with microvascular spasm also considered a contributing factor. Slow flow is a state in which blood flow is not completely obstructed but is markedly delayed. These complications are reported to occur in approximately 10--20\% of patients after PCI \citep{babapoor2022}, and some reports indicate an incidence of 10\% or more in cases of acute myocardial infarction (AMI) \textbf{[citation needed]}. Because both cut off the myocardial oxygen supply, they are known to be significant predictors of poor prognosis, including new-onset heart failure, recurrent myocardial infarction, and increased in-hospital mortality \textbf{[citation needed]}. After onset, treatment such as intracoronary administration of vasodilators is performed; however, this cannot remove the lipid and necrotic material that have already occluded the peripheral capillaries, and it also carries the risk of adverse effects such as acute hypotension and arrhythmia, so post-hoc treatment alone has its limits \textbf{[citation needed]}. Against this background, establishing a preventive strategy that forestalls the onset of these complications altogether---rather than addressing them after they occur---has become a critical challenge. +However, PCI carries the risk of complications known as the no-reflow phenomenon +and slow flow. +No-reflow refers to a state in which, although the stenosis itself is resolved +by stent placement or similar procedures, +peripheral blood flow is completely obstructed because plaque contents or +thrombus released during dilation of the lesion occlude the distal +microvasculature (distal microembolization), +with microvascular spasm also considered a contributing factor. +Slow flow is a state in which blood flow is not completely obstructed but is +markedly delayed. +In a single-center cohort of primary PCI patients, +no-reflow and slow-flow phenomena were reported in 17.1\% and 12.9\% of +patients, respectively \citep{babapoor2022}, +and some reports indicate an incidence of 10\% or more in cases of acute +myocardial infarction (AMI) \textbf{[citation needed]}. +Because both cut off the myocardial oxygen supply, +they are known to be significant predictors of poor prognosis, +including new-onset heart failure, recurrent myocardial infarction, +and increased in-hospital mortality \textbf{[citation needed]}. +After onset, treatment such as intracoronary administration of vasodilators is +performed; however, this cannot remove the lipid and necrotic material that have +already occluded the peripheral capillaries, +and it also carries the risk of adverse effects such as acute hypotension and +arrhythmia, so post-hoc treatment alone has its limits +\textbf{[citation needed]}. +Against this background, establishing a preventive strategy that forestalls the +onset of these complications altogether---rather than addressing them after they +occur---has become a critical challenge. -When the risk of no-reflow or slow flow is found to be high before the procedure, clinical practice takes preventive measures such as placing a distal protection device distal to the lesion before stent deployment, or administering vasodilators intracoronarily in advance \textbf{[citation needed]}. While distal protection devices are effective for high-risk lesions, applying them to every case is not realistic given the burden of preparation, making accurate pre-procedural risk stratification essential. Intravascular ultrasound (IVUS) can visualize the condition of the vessel wall and plaque, providing useful information about the lesion. However, interpreting IVUS images requires specialized expertise, and because multiple factors---such as vessel diameter and plaque composition---interact in complex ways, high-precision risk prediction by visual assessment alone is difficult, creating a need for methods that quantitatively assess risk from IVUS images. +When the risk of no-reflow or slow flow is found to be high before the +procedure, clinical practice takes preventive measures such as placing a distal +protection device distal to the lesion before stent deployment, +or administering vasodilators intracoronarily in advance +\textbf{[citation needed]}. +While distal protection devices are effective for high-risk lesions, +applying them to every case is not realistic given the burden of preparation, +making accurate pre-procedural risk stratification essential. +Intravascular ultrasound (IVUS) can visualize the condition of the vessel wall +and plaque, providing useful information about the lesion. +However, interpreting IVUS images requires specialized expertise, +and because multiple factors---such as vessel diameter and plaque +composition---interact in complex ways, high-precision risk prediction by visual +assessment alone is difficult, creating a need for methods that quantitatively +assess risk from IVUS images. -Regarding the amount of attenuated plaque observed on IVUS, a significant difference has been reported between patients who developed complications and those who did not \citep{wu2011}. This suggests that a greater amount of attenuated plaque may make thrombus formation and microvascular occlusion more likely, thereby increasing the risk of complications. However, this scoring remains a manual assessment performed by physicians, motivating the need for an automated and objective predictive approach. +In AMI patients, a significant difference in the amount of attenuated plaque +(quantified via a manual attenuation scoring system) has been reported between +patients whose post-PCI angiographic flow met a composite no-reflow/slow-flow +definition (TIMI flow grade $\leq$2) and those who did not \citep{wu2011}; +notably, the mere presence of attenuated plaque did not differ +significantly---only its extent did. +This suggests that a greater amount of attenuated plaque may make thrombus +formation and microvascular occlusion more likely, +thereby increasing the risk of complications. +However, this scoring remains a manual assessment performed by physicians, +motivating the need for an automated and objective predictive approach. -Information useful for predicting no-reflow and slow flow is thought to lie at the intersection of the IVUS images themselves, the patient's clinical variables, and the morphology of the lesion. At the same time, because these complications are relatively rare in themselves, and positive cases are even more limited among the cases whose outcomes are labeled, it is difficult to learn all of this information in an end-to-end manner. +Information useful for predicting no-reflow and slow flow is thought to lie at +the intersection of the IVUS images themselves, +the patient's clinical variables, and the morphology of the lesion. +At the same time, because these complications are relatively rare in themselves, +and positive cases are even more limited among the cases whose outcomes are +labeled, it is difficult to learn all of this information in an end-to-end +manner. -Building on the above, this study proposes KSCNet, an architecture that integrally handles IVUS images, patient clinical information, and lesion plaque features. KSCNet is a redesign, adapted to the structure of IVUS data, of a 3D architecture originally developed for kidney stone classification \textbf{[citation needed]}. Because an IVUS pullback is not an isotropic 3D volume like a CT scan but rather an anisotropic sequence of 2D cross-sections arranged along a time series, we adopt, in place of 3D convolution, a weight-shared, per-frame 2D encoder together with sequence modeling via a Transformer across frames. Specifically, it integrates three elements: (1) a mechanism that injects a feature vector---combining patient-level clinical information and plaque features (such as attenuated-plaque area)---as an additional token into the frame sequence, allowing it to interact with the image representation; (2) a mechanism that uses segmentation of the vessel lumen and vessel wall as an auxiliary task and aggregates case-level features via cross-attention, guided by those features; and (3) a multi-task loss that dynamically weights the segmentation loss and the classification loss. This allows us to verify whether combining IVUS images, clinical information, and lesion features contributes to improved predictive performance, compared with methods that use only images, tabular methods that use only clinical information, and existing attenuated-plaque scoring methods. +Building on the above, this study proposes KSCNet, +an architecture that integrally handles IVUS images, +patient clinical information, and lesion plaque features. +KSCNet is a redesign, adapted to the structure of IVUS data, +of a 3D architecture originally developed for kidney stone classification +\textbf{[citation needed]}. +Because an IVUS pullback is not an isotropic 3D volume like a CT scan but rather +an anisotropic sequence of 2D cross-sections arranged along a time series, +we adopt, in place of 3D convolution, a weight-shared, +per-frame 2D encoder together with sequence modeling via a Transformer across +frames. +Specifically, it integrates three elements: (1) a mechanism that injects a +feature vector---combining patient-level clinical information and plaque +features (such as attenuated-plaque area)---as an additional token into the +frame sequence, allowing it to interact with the image representation; +(2) a mechanism that uses segmentation of the vessel lumen and vessel wall as an +auxiliary task and aggregates case-level features via cross-attention, +guided by those features; and +(3) a multi-task loss that dynamically weights the segmentation loss and the +classification loss. +This allows us to verify whether combining IVUS images, clinical information, +and lesion features contributes to improved predictive performance, +compared with methods that use only images, +tabular methods that use only clinical information, +and existing attenuated-plaque scoring methods.