Deep learning in differentiating the colorectal cancer combined with hepatic enhancing nodules: liver metastases vs hemangiomas.
1/5 보강
PICO 자동 추출 (휴리스틱, conf 2/4)
유사 논문P · Population 대상 환자/모집단
환자: CRC is exceptionally challenging
I · Intervention 중재 / 시술
추출되지 않음
C · Comparison 대조 / 비교
추출되지 않음
O · Outcome 결과 / 결론
This DL model assists radiologists in distinguishing 10-30 mm CRLMs from HMs in CRC patients. Subcentimeter CRLMs and HMs can require further MRI scanning.
[OBJECTIVES] To assess a deep learning (DL) model using portal-venous phase CT for discriminating colorectal cancer liver metastasis (CRLMs) and hemangiomas (HMs).
- p-value p < 0.01
- p-value p = 0.015
- 95% CI 0.838-0.912
APA
Li S, Zhang S, et al. (2026). Deep learning in differentiating the colorectal cancer combined with hepatic enhancing nodules: liver metastases vs hemangiomas.. Insights into imaging, 17(1), 24. https://doi.org/10.1186/s13244-025-02192-2
MLA
Li S, et al.. "Deep learning in differentiating the colorectal cancer combined with hepatic enhancing nodules: liver metastases vs hemangiomas.." Insights into imaging, vol. 17, no. 1, 2026, pp. 24.
PMID
41586944 ↗
Abstract 한글 요약
[OBJECTIVES] To assess a deep learning (DL) model using portal-venous phase CT for discriminating colorectal cancer liver metastasis (CRLMs) and hemangiomas (HMs).
[MATERIALS AND METHODS] Colorectal cancer (CRC) patients diagnosed with CRLMs or HMs at two medical centers from January 2018 and April 2024 were retrospectively included. Lesions were automatically segmented using TotalSegmentator. DL models, DenseNet-201 and ResNet-152, were trained to classify CRLMs and HMs. Their performance, measured by AUC, was evaluated on validation and test sets. Subgroup analyses were conducted for lesions ≤ 10 mm (subcentimeter) and 10-30 mm. Radiologists' diagnostic performance with and without DL assistance was compared using a multi-reader multi-case analysis.
[RESULTS] 534 CRLMs (134 CRC-patients; median, 60 years) and 262 HMs (154 CRC-patients; median, 62 years) were divided into the training, validation and test set. The Dice coefficients of TotalSegmentor for automatically segmenting subcentimeter and 10-30 mm lesions were 0.692 ± 0.099 and 0.861 ± 0.033, respectively (p < 0.01). ResNet-152 model achieved AUCs of 0.875 (95% CI: 0.838-0.912), 0.858 (95% CI: 0.781-0.935), 0.776 (95% CI: 0.703-0.848) for classifying CRLMs and HMs on the training, validation, and test sets, respectively. The AUCs for distinguishing between 10-30 mm CRLMs and HMs improved from 0.851 (95% CI: 0.821-0.880) to 0.879 (95% CI: 0.853-0.906) with DL assistance compared to without (p = 0.015). For subcentimeter CRLMs and HMs, the AUCs for the radiologists and the DL-assisted diagnosis were 0.742 (95% CI: 0.669-0.814) and 0.763 (95% CI: 0.681-0.845), respectively (p = 0.558).
[CONCLUSION] DL can assist radiologists in distinguishing 10-30 mm CRLMs from HMs in CRC patients. The value of DL-assisted diagnosis is limited for subcentimetre CRLMs and HMs.
[CRITICAL RELEVANCE STATEMENT] Dynamic detection of hypoenhancing liver lesions in patients with CRC is exceptionally challenging. The DL tool we have developed can assist in evaluating CRLMs and HMs.
[KEY POINTS] TotalSegmentator can perform automatic segmentation of CRLMs and HMs, but demonstrates poorer segmentation consistency for subcentimeter lesions. This DL model assists radiologists in distinguishing 10-30 mm CRLMs from HMs in CRC patients. Subcentimeter CRLMs and HMs can require further MRI scanning.
[MATERIALS AND METHODS] Colorectal cancer (CRC) patients diagnosed with CRLMs or HMs at two medical centers from January 2018 and April 2024 were retrospectively included. Lesions were automatically segmented using TotalSegmentator. DL models, DenseNet-201 and ResNet-152, were trained to classify CRLMs and HMs. Their performance, measured by AUC, was evaluated on validation and test sets. Subgroup analyses were conducted for lesions ≤ 10 mm (subcentimeter) and 10-30 mm. Radiologists' diagnostic performance with and without DL assistance was compared using a multi-reader multi-case analysis.
[RESULTS] 534 CRLMs (134 CRC-patients; median, 60 years) and 262 HMs (154 CRC-patients; median, 62 years) were divided into the training, validation and test set. The Dice coefficients of TotalSegmentor for automatically segmenting subcentimeter and 10-30 mm lesions were 0.692 ± 0.099 and 0.861 ± 0.033, respectively (p < 0.01). ResNet-152 model achieved AUCs of 0.875 (95% CI: 0.838-0.912), 0.858 (95% CI: 0.781-0.935), 0.776 (95% CI: 0.703-0.848) for classifying CRLMs and HMs on the training, validation, and test sets, respectively. The AUCs for distinguishing between 10-30 mm CRLMs and HMs improved from 0.851 (95% CI: 0.821-0.880) to 0.879 (95% CI: 0.853-0.906) with DL assistance compared to without (p = 0.015). For subcentimeter CRLMs and HMs, the AUCs for the radiologists and the DL-assisted diagnosis were 0.742 (95% CI: 0.669-0.814) and 0.763 (95% CI: 0.681-0.845), respectively (p = 0.558).
[CONCLUSION] DL can assist radiologists in distinguishing 10-30 mm CRLMs from HMs in CRC patients. The value of DL-assisted diagnosis is limited for subcentimetre CRLMs and HMs.
[CRITICAL RELEVANCE STATEMENT] Dynamic detection of hypoenhancing liver lesions in patients with CRC is exceptionally challenging. The DL tool we have developed can assist in evaluating CRLMs and HMs.
[KEY POINTS] TotalSegmentator can perform automatic segmentation of CRLMs and HMs, but demonstrates poorer segmentation consistency for subcentimeter lesions. This DL model assists radiologists in distinguishing 10-30 mm CRLMs from HMs in CRC patients. Subcentimeter CRLMs and HMs can require further MRI scanning.
🏷️ 키워드 / MeSH 📖 같은 키워드 OA만
같은 제1저자의 인용 많은 논문 (5)
- Complications Following Subpectoral Versus Prepectoral Breast Augmentation: A Meta-analysis.
- Spasticity Treatment Beyond Botulinum Toxins.
- Association of patient health education with the postoperative health related quality of life in low- intermediate recurrence risk differentiated thyroid cancer patients.
- Heterogeneous associations between molecular subtypes of small cell lung cancer and survival prognosis: a systematic review highlighting knowledge gaps.
- ACTG1 facilitates proliferation and epithelial-mesenchymal transition-mediated metastasis via COL21A1 in gastric cancer.
🏷️ 같은 키워드 · 무료전문 — 이 논문 MeSH/keyword 기반
- LCMS-Net: Deep Learning for Raw High Resolution Mass Spectrometry Data Applied to Forensic Cause-of-Death Screening.
- PIBAdb: a public cohort of multimodal colonoscopy videos and images including polyps with histological information.
- Exploring the Role of Extracellular Vesicles in Pancreatic and Hepatobiliary Cancers: Advances Through Artificial Intelligence.
- Feasibility of Depth-in-Color En Face Optical Coherence Tomography for Colorectal Polyp Classification Using Ensemble Learning and Score-Level Fusion.
- Impact of CT Intensity and Contrast Variability on Deep-Learning-Based Lung-Nodule Detection: A Systematic Review of Preprocessing and Harmonization Strategies (2020-2025).
- A Transformer-Based Deep Learning Model for predicting Early Recurrence in Hepatocellular Carcinoma After Hepatectomy Using Intravoxel Incoherent Motion Images.