MR radiomics predicts pathological complete response of esophageal squamous cell carcinoma after neoadjuvant chemoradiotherapy: a multicenter study

BACKGROUND

More than 40% of patients with resectable esophageal squamous cell cancer (ESCC) achieve pathological complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT), who have favorable prognosis and may benefit from an organ-preservation strategy. Our study aims to develop and validate a machine learning model based on MR radiomics to accurately predict the pCR of ESCC patients after nCRT.

METHODS

In this retrospective multicenter study, eligible patients with ESCC who underwent baseline MR (T2-weighted imaging) and nCRT plus surgery were enrolled between September 2014 and September 2022 at institution 1 (training set) and between December 2017 and August 2021 at institution 2 (testing set). Models were constructed using machine learning algorithms based on clinical factors and MR radiomics to predict pCR after nCRT. The area under the curve (AUC) and cutoff analysis were used to evaluate model performance.

RESULTS

A total of 155 patients were enrolled in this study, 82 in the training set and 73 in the testing set. The radiomics model was constructed based on two radiomics features, achieving AUCs of 0.968 (95%CI 0.933-0.992) in the training set and 0.885 (95%CI 0.800-0.958) in the testing set. The cutoff analysis resulted in an accuracy of 82.2% (95%CI 72.6-90.4%), a sensitivity of 75.0% (95%CI 58.3-91.7%), and a specificity of 85.7% (95%CI 75.5-96.0%) in the testing set.

CONCLUSION

A machine learning model based on MR radiomics was developed and validated to accurately predict pCR after nCRT in patients with ESCC.

Strategy to avoid local recurrence in patients with locally advanced rectal cancer

Background

To clarify the short- and long-term outcomes of radical surgery after neoadjuvant chemoradiotherapy (NCRT) with TS-1 and irinotecan, which enhances radiosensitivity, in patients with locally advanced rectal cancer.

Methods

The study group comprised 105 patients with locally advanced rectal cancer who received NCRT followed by radical surgery. NCRT consisted of pelvic radiotherapy (45 Gy in 25 fractions over a period of 5 weeks), S-1 (80 mg/m²) given concurrently for 25 days, and irinotecan (60 mg/m²), given once a week as a continuous intravenous infusion. Radical surgery was performed 8 weeks after treatment.

Results

A pathological complete response was confirmed in 23.8%. The 5-year recurrence-free survival rate was 79.3%, and the 5-year overall survival rate was 87.1%. Multivariate analysis showed that the following 4 variables were independent predictors of recurrence-free survival: Sex (male: p = 0.0172), Pre-treatment tumor diameter (< 40 mm: p = 0.0223), Histopathological treatment response (grade 0,1: p = 0.0169), and ypN (ypN1: p = 0.1995; ypN2: p = 0.0007). Only ypN was an independent predictor of overall survival (ypN1: p = 0.0009; ypN2: p = 0.0012).

Conclusions

Our treatment strategy combining TS-1 with irinotecan to increase radiosensitivity had a high response rate.

Can Haematology Blood Tests at Time of Diagnosis Predict Response to Neoadjuvant Treatment in Locally Advanced Rectal Cancer?

BACKGROUND

Outcomes in locally advanced rectal cancer are improved by neoadjuvant therapy followed by surgical resection. Some patients respond completely to preoperative treatment. Therefore, predicting the pathological response to preoperative therapy is of clinical importance. Accurate prediction would allow for tailored approaches to neoadjuvant therapy.

METHODS

All patients undergoing resection of rectal adenocarcinoma after neoadjuvant therapy between 2006 and 2015 were included in this cohort study. Patients were identified from a prospectively collected database and data were supplemented retrospectively with full blood count at diagnosis. Specimens resected following neoadjuvant therapy were graded according to pathological response. Follow-up data was obtained from the national registry. The primary outcome was complete pathological response.

RESULTS

Of 330 patients, 71 (21.5%) responded completely to preoperative therapy. Median age was 66 and 65% were male (n = 215). White cell count (WCC) was the most predictive marker, for predicting pCR; area under the curve (AUC) 0.666. This was higher than neutrophil/platelet ratio (AUC 0.652) or neutrophil/lymphocyte ratios (AUC = 0.437). Kaplan-Meier survival analysis showed those patients with WCC > 8 had poorer survival than those with WCC < 8 (p = 0.009).

CONCLUSION

Routinely collected haematology samples at the point of diagnosis can assist in predicting for complete response to neoadjuvant therapy. Although novel biomarkers will have a greater predictive value, this clinically available value test could help to assist in risk stratification of patients using routinely collected laboratory tests.