甲状腺がんの術前評価における AI 支援超音波技術の臨床応用

実験的：AI-Assisted Preoperative Review

Participants undergo standard preoperative thyroid ultrasonography followed by a standardized AI-assisted repeat examination and surgeon-led review incorporating the locked AI system's thyroid-nodule output. The AI system does not assess cervical lymph nodes. All supplementary examinations and final diagnostic and surgical decisions are made by clinicians.

診断テスト：Locked AI-Assisted Thyroid Ultrasound Repeat Examination and Review

After standard preoperative ultrasonography, the same participant underwent a standardized AI-assisted repeat examination. The locked system identified and classified thyroid nodules and provided malignancy-score information for surgeon-led review. It did not assess cervical lymph nodes and was not retrained or recalibrated during the study. Additional fine-needle aspiration, intraoperative pathologic examination, and surgical management were determined by clinicians using the complete clinical assessment.

Proportion of Participants Undergoing Supplementary Cytologic or Pathologic Examination

Number and proportion of enrolled participants who underwent at least one additional cytologic or pathologic examination, such as fine-needle aspiration or intraoperative frozen-section examination, after completion of conventional ultrasonography and AI-assisted review and before completion of surgery. Each participant is counted once regardless of the number of examinations. The decision remained clinician led; cervical lymph-node examinations were outside the AI system's task.

Proportion of Participants With a Change in Planned Surgical Management

Number and proportion of enrolled participants with at least one documented change in the surgeon-led planned surgical approach or extent after conventional ultrasonography, AI-assisted review, and any supplementary pathological examination, when performed. Changes may involve thyroid resection or cervical lymph-node management. Each participant is counted once regardless of the number of changes. The AI system provided thyroid-nodule information only and did not assess cervical lymph nodes.

Distribution of C-TIRADS Categories Among Evaluated Thyroid Nodules

Number and percentage of evaluated thyroid nodules in each clinician-assigned C-TIRADS category during conventional ultrasonography. Nodule size, composition, echogenicity, margins, calcifications, and clinician-assessed cervical lymph-node findings were recorded as descriptive covariates and were not treated as separate outcome measures.

Proportion of Evaluated Thyroid Nodules Classified as AI-Positive

Number and percentage of evaluated thyroid nodules with a locked AI malignancy score >0.5. The AI system evaluated thyroid nodules only and did not assess cervical lymph nodes.

Results of Supplementary Cytologic or Pathologic Examinations

Among participants who underwent at least one additional cytologic or pathologic examination, record the cytologic or histopathologic result for each sampled thyroid nodule or cervical lymph node. Results are summarized at the examination level as nonmalignant, indeterminate, malignant, or metastatic, as applicable.

Final Histopathological Diagnosis of Resected Thyroid Nodules

For each resected thyroid nodule linked unambiguously to the evaluated lesion, record the final diagnosis as benign, malignant, follicular tumor of uncertain malignant potential (FT-UMP), well-differentiated tumor of uncertain malignant potential (WDT-UMP), non-invasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP), or another borderline diagnosis.

Nodule-Level Sensitivity of AI and C-TIRADS

Using definitive postoperative histopathology as the reference standard, sensitivity is TP/(TP + FN), expressed as a percentage, for the locked AI classification (positive if score >0.5) and conventional C-TIRADS (positive if category 4a or higher). Include only pathology-matched nodules with an unambiguous lesion-level link and a definitive benign or malignant diagnosis. Exclude FT-UMP, WDT-UMP, NIFTP, other borderline diagnoses, and nodules without unambiguous lesion-level linkage. These lesion-level exclusions do not alter the 515-participant workflow cohort.

Nodule-Level False-Negative Rate of AI and C-TIRADS

For each method, the false-negative rate is FN/(TP + FN), expressed as a percentage, among definitively malignant thyroid nodules. AI positivity is defined as score >0.5; conventional ultrasound positivity is C-TIRADS category 4a or higher. Include only pathology-matched nodules with an unambiguous lesion-level link and a definitive benign or malignant diagnosis. Exclude FT-UMP, WDT-UMP, NIFTP, other borderline diagnoses, and nodules without unambiguous lesion-level linkage.

Nodule-Level Positive Predictive Value of AI and C-TIRADS

For each method, positive predictive value is TP/(TP + FP), expressed as a percentage, among thyroid nodules classified as positive. AI positivity is defined as score >0.5; conventional ultrasound positivity is C-TIRADS category 4a or higher. Include only pathology-matched nodules with an unambiguous lesion-level link and a definitive benign or malignant diagnosis. Exclude FT-UMP, WDT-UMP, NIFTP, other borderline diagnoses, and nodules without unambiguous lesion-level linkage.

Nodule-Level Youden Index of AI and C-TIRADS

For each method, the Youden index is sensitivity + specificity - 1 using fixed binary thresholds. AI positivity is defined as score >0.5; conventional ultrasound positivity is C-TIRADS category 4a or higher. Include only pathology-matched nodules with an unambiguous lesion-level link and a definitive benign or malignant diagnosis. Exclude FT-UMP, WDT-UMP, NIFTP, other borderline diagnoses, and nodules without unambiguous lesion-level linkage.

Distribution of Cervical Lymph-Node Metastasis Status Among Pathologically Examined Nodes

Among cervical lymph nodes actually removed or sampled and pathologically examined, record the number and percentage with and without metastasis. No pathologic reference diagnosis is assigned to unsampled lymph nodes.

Nodule-Level Specificity of AI and C-TIRADS

Using definitive postoperative histopathology as the reference standard, specificity is TN/(TN + FP), expressed as a percentage, for the locked AI classification (positive if score >0.5) and conventional C-TIRADS (positive if category 4a or higher). Include only pathology-matched nodules with an unambiguous lesion-level link and a definitive benign or malignant diagnosis. Exclude FT-UMP, WDT-UMP, NIFTP, other borderline diagnoses, and nodules without unambiguous lesion-level linkage.

Nodule-Level Negative Predictive Value of AI and C-TIRADS

Using definitive postoperative histopathology as the reference standard, negative predictive value is TN/(TN + FN), expressed as a percentage, for the locked AI classification (positive if score >0.5) and conventional C-TIRADS (positive if category 4a or higher). Include only pathology-matched nodules with an unambiguous lesion-level link and a definitive benign or malignant diagnosis. Exclude FT-UMP, WDT-UMP, NIFTP, other borderline diagnoses, and nodules without unambiguous lesion-level linkage.

Nodule-Level Accuracy of AI and C-TIRADS

Using definitive postoperative histopathology as the reference standard, accuracy is (TP + TN)/(TP + TN + FP + FN), expressed as a percentage, for the locked AI classification (positive if score >0.5) and conventional C-TIRADS (positive if category 4a or higher). Include only pathology-matched nodules with an unambiguous lesion-level link and a definitive benign or malignant diagnosis. Exclude FT-UMP, WDT-UMP, NIFTP, other borderline diagnoses, and nodules without unambiguous lesion-level linkage.

Area Under the ROC Curve for the Continuous AI Malignancy Score

Using definitive postoperative histopathology as the reference standard, calculate the area under the receiver operating characteristic curve for the continuous locked AI malignancy score. Include only pathology-matched nodules with an unambiguous lesion-level link and a definitive benign or malignant diagnosis. Exclude FT-UMP, WDT-UMP, NIFTP, other borderline diagnoses, and nodules without unambiguous lesion-level linkage. No AUC is calculated for the single-threshold C-TIRADS classification.