Deep learning in differentiating the colorectal cancer combined with hepatic enhancing nodules: liver metastases vs hemangiomas.
Authors
Affiliations (14)
Affiliations (14)
- Department of Radiology, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, China.
- Department of Evidence-Based Medicine and Social Medicine, School of Public Health, Chengdu Medical College, Chengdu, China.
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China.
- Second clinical school, Lanzhou University, Lanzhou, China.
- Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China.
- Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou, China.
- Department of Pharmaceuticals Diagnostics, GE HealthCare, Beijing, China.
- Department of Medical Imaging, Zhangye People's Hospital Affiliated to Hexi University, Zhangye, China.
- Department of Radiology, Gansu Province Hospital, Lanzhou, China.
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou, China. [email protected].
- Second clinical school, Lanzhou University, Lanzhou, China. [email protected].
- Key Laboratory of Medical Imaging of Gansu Province, Lanzhou, China. [email protected].
- Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou, China. [email protected].
- Department of Radiology, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, China. [email protected].
Abstract
To assess a deep learning (DL) model using portal-venous phase CT for discriminating colorectal cancer liver metastasis (CRLMs) and hemangiomas (HMs). 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. 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). 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. 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. 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.