The Effectiveness of Machine Learning in Predicting Lateral Lymph Node Metastasis From Lower Rectal Cancer: A Single Center Development and Validation Study

Risk factors and development of machine learning diagnostic models for lateral lymph node metastasis in rectal cancer: multicentre study

BACKGROUND

The diagnostic criteria for lateral lymph node metastasis in rectal cancer have not been established. This research aimed to investigate the risk factors for lateral lymph node metastasis and develop machine learning models combining these risk factors to improve the diagnostic performance of standard imaging.

METHOD

This multicentre prospective study included patients who underwent lateral lymph node dissection without preoperative treatment for rectal cancer between 2017 and 2019 in 15 Japanese institutions. First, preoperative clinicopathological factors and magnetic resonance imaging findings were evaluated using multivariable analyses for their correlation with lateral lymph node metastasis. Next, machine learning diagnostic models for lateral lymph node metastasis were developed combining these risk factors. The models were tested in a training set and in an internal validation cohort and their diagnostic performance was tested using receiver operating characteristic curve analyses.

RESULTS

Of 212 rectal cancers, 122 patients were selected, including 232 lateral pelvic sides, 30 sides of which had pathological lateral lymph node metastasis. Multivariable analysis revealed that poorly differentiated/mucinous adenocarcinoma, extramural vascular invasion, tumour deposit and a short-axis diameter of lateral lymph node ≥ 6.0 mm were independent risk factors for lateral lymph node metastasis. Patients were randomly divided into a training cohort (139 sides) and a test cohort (93 sides) and machine learning models were computed on the basis of a combination of significant features (including: histological type, extramural vascular invasion, tumour deposit, short- and long-axis diameter of lateral lymph node, body mass index, serum carcinoembryonic antigen level, cT, cN, cM, irregular border and mixed signal intensity). The top three models with the highest sensitivity in the training cohort were as follows: support vector machine (sensitivity, 1.000; specificity, 0.773), light gradient boosting machine (sensitivity, 0.950; specificity, 0.918) and ensemble learning (sensitivity, 0.950; specificity, 0.917). The diagnostic performances of these models in the test cohort were as follows: support vector machine (sensitivity, 0.750; specificity, 0.667), light gradient boosting machine (sensitivity, 0.500; specificity, 0.852) and ensemble learning (sensitivity, 0.667; specificity, 0.864).

CONCLUSION

Machine learning models combining multiple risk factors can contribute to improving diagnostic performance of lateral lymph node metastasis.

Preoperative factors associated with lateral lymph node metastasis in lower rectal cancer and the evaluation of the middle rectal artery

PURPOSE

This study aimed to identify cases in which lateral lymph node (LLN) dissection (LLND) can be excluded by clarifying preoperative factors, including an evaluation of the middle rectal artery (MRA), associated with LLN metastasis.

METHODS

Fifty-five consecutive patients who underwent preoperative positron emission tomography-computed tomography (PET/CT) and total mesorectal excision with LLND for rectal cancer were included. We retrospectively investigated the preoperative clinical factors associated with pathological LLN (pLLN) metastasis. We analyzed the regions of pLLN metastasis using MRA.

RESULTS

pLLN metastasis occurred in 13 (23.6%) patients. According to a multivariate analysis, clinical LLN (cLLN) metastasis based on short-axis size and LLN status based on PET/CT were independent preoperative factors of pLLN metastasis. The negative predictive value (NPV) was high (97.1%) in patients evaluated as negative based on PET/CT and cLLN short-axis size. MRA was detected in 24 patients (43.6%) using contrast-enhanced CT, and there was a significant relationship between pLLN metastasis and the presence of MRA. pLLN metastasis in the internal iliac region but not in the obturator region was significantly correlated with the presence of MRA.

CONCLUSION

Combined cLLN metastasis based on short-axis size and PET/CT showed a higher NPV, suggesting this to be a useful method for identifying cases in which LLND can be excluded.

Risk factors for lateral lymph node metastasis based on the molecular profiling of rectal cancer

AIM

The association between molecular profiles and lateral lymph node metastasis (LLNM) in patients with rectal cancer remains unclear. Therefore, this study aimed to identify the molecular profiles of rectal cancer associated with LLNM.

METHOD

We retrospectively examined patients who underwent rectal cancer surgery with lateral lymph node dissection without preoperative treatment and whose surgically resected specimens were evaluated using multiomics-based analyses from 2014 to 2019. We compared the clinical characteristics and molecular profiles of patients with pathological LLNM (pLLNM+) with those of patients without (pLLNM-) and identified risk factors for LLNM.

RESULTS

We evaluated a total of 123 patients: 18 with and 105 without pLLNM. The accumulation of mutations in genes key for the development of colorectal cancer were similar between the groups, as was the tumour mutation burden. The distribution of consensus molecular subtypes (CMS) was significantly different between the groups (p = 0.0497). The pLLNM+ patients had a higher prevalance of CMS4 than the pLLNM- patients (77.8% vs. 51.4%). According to the multivariate analysis, the independent risk factors for LLNM were a short-axis diameter of the lateral lymph node of ≥6.0 mm and CMS4; furthermore, the presence of either or both had a sensitivity of 100% for the diagnosis of LLNM.

CONCLUSION

Lateral lymph node size and CMS4 are useful predictors of LLNM. The combination of CMS classification and size criteria was remarkably sensitive for the diagnosis of LLNM.

A Deep Learning Framework with Explainability for the Prediction of Lateral Locoregional Recurrences in Rectal Cancer Patients with Suspicious Lateral Lymph Nodes

Malignant lateral lymph nodes (LLNs) in low, locally advanced rectal cancer can cause (ipsi-lateral) local recurrences ((L)LR). Accurate identification is, therefore, essential. This study explored LLN features to create an artificial intelligence prediction model, estimating the risk of (L)LR. This retrospective multicentre cohort study examined 196 patients diagnosed with rectal cancer between 2008 and 2020 from three tertiary centres in the Netherlands. Primary and restaging T2W magnetic resonance imaging and clinical features were used. Visible LLNs were segmented and used for a multi-channel convolutional neural network. A deep learning model was developed and trained for the prediction of (L)LR according to malignant LLNs. Combined imaging and clinical features resulted in AUCs of 0.78 and 0.80 for LR and LLR, respectively. The sensitivity and specificity were 85.7% and 67.6%, respectively. Class activation map explainability methods were applied and consistently identified the same high-risk regions with structural similarity indices ranging from 0.772-0.930. This model resulted in good predictive value for (L)LR rates and can form the basis of future auto-segmentation programs to assist in the identification of high-risk patients and the development of risk stratification models.

MRI-Based Artificial Intelligence in Rectal Cancer

Rectal cancer (RC) accounts for approximately one-third of colorectal cancer (CRC), with death rates increasing in patients younger than 50 years old. Magnetic resonance imaging (MRI) is routinely performed for tumor evaluation. However, the semantic features from images alone remain insufficient to guide treatment decisions. Functional MRIs are useful for revealing microstructural and functional abnormalities and nevertheless have low or modest repeatability and reproducibility. Therefore, during the preoperative evaluation and follow-up treatment of patients with RC, novel noninvasive imaging markers are needed to describe tumor characteristics to guide treatment strategies and achieve individualized diagnosis and treatment. In recent years, the development of artificial intelligence (AI) has created new tools for RC evaluation based on MRI. In this review, we summarize the research progress of AI in the evaluation of staging, prediction of high-risk factors, genotyping, response to therapy, recurrence, metastasis, prognosis, and segmentation with RC. We further discuss the challenges of clinical application, including improvement in imaging, model performance, and the biological meaning of features, which may also be major development directions in the future. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: Stage 2.