Prediction of lymph node metastases using pre-treatment PET radiomics of the primary tumour in esophageal adenocarcinoma: an external validation study

Abstract

Objectives: To improve clinical lymph node staging (cN-stage) in esophageal adenocarcinoma by developing and externally validating three prediction models; one with clinical variables only, one with positron emission tomography (PET) radiomics only, and a combined clinical and radiomics model. Methods: Consecutive patients with fluorodeoxyglucose (FDG) avid tumours treated with neo-adjuvant therapy between 2010 and 2016 in two international centres (n = 130 and n = 60, respectively) were included. Four clinical variables (age, gender, clinical T-stage and tumour regression grade) and PET radiomics from the primary tumour were used for model development. Diagnostic accuracy, area under curve (AUC), discrimination and calibration were calculated for each model. The prognostic significance was also assessed. Results: The incidence of lymph node metastases was 58% in both cohorts. The AUCs of the clinical, radiomics and combined models were 0.79, 0.69 and 0.82 in the developmental cohort, and 0.65, 0.63 and 0.69 in the external validation cohort, with good calibration demonstrated. The AUC of current cN-stage in development and validation cohorts was 0.60 and 0.66, respectively. For overall survival, the combined clinical and radiomics model achieved the best discrimination performance in the external validation cohort (X2 = 6.08, df = 1, p = 0.01). Conclusion: Accurate diagnosis of lymph node metastases is crucial for prognosis and guiding treatment decisions. Despite finding improved predictive performance in the development cohort, the models using PET radiomics derived from the primary tumour were not fully replicated in an external validation cohort. Advances in knowledge: This international study attempted to externally validate a new prediction model for lymph node metastases using PET radiomics. A model combining clinical variables and PET radiomics improved discrimination of lymph node metastases, but these results were not externally replicated.

Using Genomics Feature Selection Method in Radiomics Pipeline Improves Prognostication Performance in Locally Advanced Esophageal Squamous Cell Carcinoma—A Pilot Study

“…Our study established a radiomics-based clinical nomogram with a relatively larger sample size and validated on an external dataset. This was similar to previous findings that nomogram incorporating clinical factors and imaging features were of predictive value for EC patients [ 45 , 46 , 47 ]. Zhang et al [ 45 ] reported that a nomogram based on clinical variables and imaging radiomic features was predictive of lymph node metastases.…”

Methodological quality of machine learning-based quantitative imaging analysis studies in esophageal cancer: a systematic review of clinical outcome prediction after concurrent chemoradiotherapy

“…Applying the selection criteria led to 52 studies for full-text screening. At the end, a total of 37 articles were deemed eligible [ 28 – 64 ], including 30 articles within 5 years [ 28 – 38 , 41 – 43 , 45 , 47 – 50 , 52 – 54 , 57 – 64 ].

Fig.

…”

“… HF PyRadiomics (V2.0.1) Clinical and classical PET Xie: 2020 [ 58 ] ESCC 2008–2014 CT 120 kV, 180–280 mA, 3 mm CCRT 57 HF IBEX (V1.0β) Clinical factors Hu: 2020 [ 29 ] ESCC 2007–2018 CT 120 kV, 200–400 mA 2.5 mm (inst 1) 5 mm (inst 2) voxel sizes: 1 × 1 × 5 mm3 nCRT 161 (train) 70 (test) HF PyRadiomics (V3.0) No Luo: 2020 [ 41 ] ESCC 2013–2015 CT 120 kV, 120 mAs, 5 mm dCCRT 160 (train) 66 (val.) HF 3DSlicer (V4.10.2) Clinical factors Li: 2020 [ 54 ] ESCC 2012–2019 CT 120 kV/140 kV, 140–300 mA, 5 mm nCRT 121 HF IBEX Clinical factors Zhang: 2020 [ 47 ] EAD 2010–2016 PET/ CT 120 kVp, 20–200 mA surgery alone, neoadjuvant chemotherapy, and nCRT 190 HF Matlab Clinical factors Du: 2020 [ 42 ] …”

“…The majority of imaging modalities mentioned in the retrieved studies were PET (20/37) [ 28 , 30 , 34 – 40 , 44 – 47 , 49 , 50 , 52 , 55 , 56 , 59 , 61 ], CT (16/37) [ 29 , 31 – 33 , 41 , 43 , 48 , 51 , 53 , 54 , 57 , 58 , 60 , 62 – 64 ], and one cone beam CT (CBCT) [ 42 ]. Although the search criteria included MRI, we did not locate any eligible study in our search.…”

Development of High-Resolution Dedicated PET-Based Radiomics Machine Learning Model to Predict Axillary Lymph Node Status in Early-Stage Breast Cancer

“…Recently, the WB-PET-based radiomics model showed promising results in predicting occult lymph node metastasis in cN0 tumors, including lung cancer, cervical cancer, and esophageal adenocarcinoma [ 25 , 26 , 27 ]. Hasan et al analyzed the textural features of WB-PET/CT coming from 124 breast cancer patients and showed the gray-level zone length matrix (GLZLM) could be the predictive parameter of ALN, but the AUC was only 0.64 [ 28 ].…”