1
|
Dai Z, Wei R, Wang H, Hu W, Sun X, Zhu J, Li H, Ge Y, Song B. Multimodality MRI-based radiomics for aggressiveness prediction in papillary thyroid cancer. BMC Med Imaging 2022; 22:54. [PMID: 35331162 PMCID: PMC8952254 DOI: 10.1186/s12880-022-00779-5] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2021] [Accepted: 03/15/2022] [Indexed: 11/13/2022] Open
Abstract
Objective To investigate the ability of a multimodality MRI-based radiomics model in predicting the aggressiveness of papillary thyroid carcinoma (PTC). Methods This study included consecutive patients who underwent neck magnetic resonance (MR) scans and subsequent thyroidectomy during the study period. The pathological diagnosis of thyroidectomy specimens was the gold standard to determine the aggressiveness. Thyroid nodules were manually segmented on three modal MR images, and then radiomics features were extracted. A machine learning model was established to evaluate the prediction of PTC aggressiveness. Results The study cohort included 107 patients with PTC confirmed by pathology (cross-validation cohort: n = 71; test cohort: n = 36). A total of 1584 features were extracted from contrast-enhanced T1-weighted (CE-T1 WI), T2-weighted (T2 WI) and diffusion weighted (DWI) images of each patient. Sparse representation method is used for radiation feature selection and classification model establishment. The accuracy of the independent test set that using only one modality, like CE-T1WI, T2WI or DWI was not particularly satisfactory. In contrast, the result of these three modalities combined achieved 0.917. Conclusion Our study shows that multimodality MR image based on radiomics model can accurately distinguish aggressiveness in PTC from non-aggressiveness PTC before operation. This method may be helpful to inform the treatment strategy and prognosis of patients with aggressiveness PTC.
Collapse
Affiliation(s)
- Zedong Dai
- Department of Radiology, Minhang Hospital, Fudan University, 170 Xinsong Road, Shanghai, 201199, People's Republic of China
| | - Ran Wei
- Department of Radiology, Minhang Hospital, Fudan University, 170 Xinsong Road, Shanghai, 201199, People's Republic of China
| | - Hao Wang
- Department of Radiology, Minhang Hospital, Fudan University, 170 Xinsong Road, Shanghai, 201199, People's Republic of China
| | - Wenjuan Hu
- Department of Radiology, Minhang Hospital, Fudan University, 170 Xinsong Road, Shanghai, 201199, People's Republic of China
| | - Xilin Sun
- Department of Radiology, Minhang Hospital, Fudan University, 170 Xinsong Road, Shanghai, 201199, People's Republic of China
| | - Jie Zhu
- Department of Radiology, Minhang Hospital, Fudan University, 170 Xinsong Road, Shanghai, 201199, People's Republic of China
| | - Hong Li
- Department of Radiology, Minhang Hospital, Fudan University, 170 Xinsong Road, Shanghai, 201199, People's Republic of China
| | - Yaqiong Ge
- GE Healthcare, Shanghai, People's Republic of China
| | - Bin Song
- Department of Radiology, Minhang Hospital, Fudan University, 170 Xinsong Road, Shanghai, 201199, People's Republic of China.
| |
Collapse
|
2
|
Abstract
Background: The incidence of thyroid carcinoma is growing worldwide. More than 50% of new malignant tumors are classified as classical papillary carcinomas in low-risk category with a low rate of recurrence and high long-term survival. Active surveillance is a strategy to control low-risk tumor evolution with the intention to avoid unnecessary treatments and maintain thyroid function. The aim of this study was to report a cohort of patients with thyroid nodules classified as Bethesda V-VI and who are under active surveillance in Colombia. Methods: A prospective cohort was assembled since January 2015. All patients had been evaluated clinically, biochemically with ultrasonography and fine needle aspiration biopsy previous to the first evaluation. Active surveillance was proposed to patients with asymptomatic low-risk carcinoma (<1.5 cm, encapsulated, without evidence of lymph node metastasis), independent of sex or age. The strategy included a specific discussion about the surgical option and expected risk of complications, risk of long-term thyroxine support, and the active surveillance strategy. The data on age, sex, reason for an ultrasound examination, ultrasound risk by American Thyroid Association (ATA) classification, size and volume of the nodule, reason to consider active surveillance and follow-up ultrasounds, and surgical decision were recorded prospectively. A Kaplan-Meier curve was constructed for the rate of growth and increase in volume of the nodule, growth >3 mm and increase in volume >50%, and need of operation. Results: One hundred two patients were analyzed. Seventy-five percent of patients had a nodule smaller than 1 cm. Only 24/102 (23%) nodules were classified as ATA low risk. Thirty-four of 102 (33.3%) nodules were classified as Bethesda VI and the others were Bethesda V. The median follow-up was 13.9 months, and 32.3% of patients had more than 24 months of follow-up. Only 11/102 (10.8%) nodules grew more than 3 mm and 26/102 (25.5%) nodules grew more than 50% in volume. 12.7% patients were submitted to surgery. The overall stability rate without growth >3 mm, without volume increase >50%, and without surgery at 24 months were 89.8%, 77.0%, and 85.5%, respectively Conclusions: Active surveillance is possible in developing Western countries with similar results to those provided by Asian and American authors.
Collapse
Affiliation(s)
- Alvaro Sanabria
- Department of Surgery, School of Medicine, Universidad de Antioquia, Medellín, Colombia
- Centro de Excelencia en Enfermedades de Cabeza y Cuello (CEXCA), Medellín, Colombia
| |
Collapse
|