Radiomic features derived from pretherapeutic MRI predict chemoradiation response in locally advanced rectal cancer.

BACKGROUND: The standard treatment for locally advanced rectal cancer (LARC) is neoadjuvant concurrent chemoradiotherapy (CRT) followed by surgical excision. Current evidence suggests a favorable prognosis for those with pathological complete response (pCR), and surgery may be spared for them. We trained and validated regression models for CRT response prediction with selected radiomic features extracted from pretreatment magnetic resonance (MR) images to recruit potential candidates for this watch-and-wait strategy. METHODS: We retrospectively enrolled patients with LARC who underwent pre-CRT MR imaging between 2010 and 2019. Pathological complete response in surgical specimens after CRT was defined as the ground truth. Quantitative features derived from both unfiltered and filtered images were extracted from manually segmented region of interests on T2-weighted images and selected using variance threshold, univariate statistical tests, and cross-validation least absolute shrinkage and selection operator (Lasso) regression. Finally, a regression model using selected features with high coefficients was optimized and evaluated. Model performance was measured by classification accuracies and area under the receiver operating characteristic (AUROC). RESULTS: We extracted 1223 radiomic features from each MRI study of 133 enrolled patients. After tumor excision, 34 (26 %) of 133 patients had pCR in resected specimens. When 25 image-derived features were selected from univariate analysis, classification AUROC was 0.86 and 0.79 with the addition of six clinical features on the hold-out internal validation dataset. When 11 image-derived features were used, the optimized linear regression model had an AUROC value of 0.79 and 0.65 with the addition of six clinical features on the hold-out dataset. Among the radiomic features, texture features including gray level variance, strength, and cluster prominence had the highest coefficient by Lasso regression. CONCLUSION: Radiomic features derived from pretreatment MR images demonstrated promising efficacy in predicting pCR after CRT. However, radiomic features combined with clinical features did not result in remarkable improvement in model performance.

Predictors of 30-day mortality after endovascular thrombectomy for large vessel occlusion in the elderly.

OBJECTIVES: Elderly acute ischemic stroke (AIS) patients (≥80 years) would have dismal clinical outcomes even after successful endovascular revascularization for large vessel occlusion (LVO) in the anterior circulation. We aimed to identify predictors of 30-day mortality after endovascular thrombectomy (EVT) in the elderly. MATERIALS AND METHODS: We included older patients who underwent EVT for AIS due to LVO within 6 h after stroke onset in the anterior circulation between 2017 and 2019. Patients due to posterior circulation stroke, with intracerebral hemorrhage (ICH) or pre-stroke modified Rankin Scale (mRS) score of 4 and 5 were excluded. The primary outcome was mortality within 30 days of EVT. The association between clinical, imaging, procedural, follow-up imaging and mortality were analyzed. Successful reperfusion was defined as modified Thrombolysis in Cerebral Infarction (mTICI) score of 2b or 3. Possible predictors of 30-day mortality were assessed by univariate and multivariable logistic regression. RESULTS: Total 238 AIS patients eligible for EVT were identified with 58 patients aged 80 years or more. 48 patients met inclusion criteria. Median age was 86 years (age range, 82-102 years). Successful reperfusion was achieved in 38 (79.2%) patients. The 30-day and 90-day mortality rate were 25% and 33.3%, respectively. The independent predictors of 30-day mortality were collateral scores <3 on mCTA (adjusted OR, 16.571; 95% CI, 1.041-263.868; p = 0.047) and number of passes (adjusted OR, 2.475; 95% CI, 1.047-5.847; p = 0.039). CONCLUSIONS: Lower collateral scores on mCTA and higher number of passes in thrombectomy were independently predictive of 30-day mortality in the elderly.

Impact of smoking on one year functional outcomes after thrombectomy for young stroke patients.

BACKGROUND: The incidence of stroke in young patients (20-50 years old) has increased in recent decades. Unlike the use of good functional outcomes to evaluate prognosis, excellent functional outcomes are a better indicator of return to work among younger patients. The rate of return to work increases with time after stroke. This study investigated the short term (3 months) and long term (1 year) predictors of excellent functional outcomes in young patients after endovascular thrombectomy (EVT). METHODS: We included young patients who underwent EVT for acute ischemic stroke (AIS) due to large vessel occlusion within 6 hours after stroke onset between 2015 and 2021. Patients with intracerebral hemorrhage on pretreatment CT were excluded. The associations between clinical, imaging, and procedure variables, and excellent functional outcomes were analyzed using univariate and multivariable logistic regression analyses. An excellent functional outcome was defined as a modified Rankin Scale score of ≤1. RESULTS: Of the 361 patients with AIS eligible for EVT, 55 young patients (aged 24-50 years) were included. Of these, 36.4% and 41.8% achieved excellent functional outcomes at 3 and 12 months, respectively. Multivariate analysis revealed that smoking was the independent negative predictor of both 3 month (adjusted OR (aOR) 0.232, 95% CI 0.058 to 0.928; p=0.039) and 12 month (aOR 0.180, 95% CI 0.044 to 0.741; p=0.018) excellent functional outcomes. CONCLUSIONS: Current or former smoking habit was an independent negative predictor of both short term and long term excellent functional outcomes in young adults with AIS.