Search

Discordance and conversion of receptor expressions in metastatic lesions and primary tumors is often observed in patients with brain metastases from breast cancer. Therefore, personalized therapy requires continuous monitoring of receptor expressions and dynamic adaptation of applied targeted treatment options. Radiological in vivo techniques may allow receptor status tracking at high frequencies at low risk and cost. The present study aims to investigate the potential of receptor status prediction through machine-learning-based analysis of radiomic MR image features. The analysis is based on 412 brain metastases samples from 106 patients acquired between 09/2007 and 09/2021. Inclusion criteria were as follows: diagnosed cerebral metastases from breast cancer; histopathology reports on progesterone (PR), estrogen (ER), and human epidermal growth factor 2 (HER2) receptor status; and availability of MR imaging data. In total, 3367 quantitative features of T1 contrast-enhanced, T1 non-enhanced, and FLAIR images and corresponding patient age were evaluated utilizing random forest algorithms. Feature importance was assessed using Gini impurity measures. Predictive performance was tested using 10 permuted 5-fold cross-validation sets employing the 30 most important features of each training set. Receiver operating characteristic areas under the curves of the validation sets were 0.82 (95% confidence interval [0.78; 0.85]) for ER+, 0.73 [0.69; 0.77] for PR+, and 0.74 [0.70; 0.78] for HER2+. Observations indicate that MR image features employed in a machine learning classifier could provide high discriminatory accuracy in predicting the receptor status of brain metastases from breast cancer.

The hypoperfusion intensity ratio (HIR) is associated with collateral status and reflects the impaired microperfusion of brain tissue in patients with acute ischemic stroke and large vessel occlusion (AIS-LVO). As a deterioration in cerebral blood flow is associated with brain edema, we aimed to investigate whether HIR is correlated with the early edema progression rate (EPR) determined by the ischemic net water uptake (NWU) in a multicenter retrospective analysis of AIS-LVO patients anticipated for thrombectomy treatment. HIR was automatically calculated as the ratio of time-to-maximum (TMax) > 10 s/(TMax) > 6 s. HIRs < 0.4 were regarded as favorable (HIR+) and ≥0.4 as unfavorable (HIR−). Quantitative ischemic lesion NWU was delineated on baseline NCCT images and EPR was calculated as the ratio of NWU/time from symptom onset to imaging. Multivariable regression analysis was used to assess the association of HIR with EPR. This study included 731 patients. HIR+ patients exhibited a reduced median NWU upon admission CT (4% (IQR: 2.1–7.6) versus 8.2% (6–10.4); p < 0.001) and less median EPR (0.016%/h (IQR: 0.007–0.04) versus 0.044%/h (IQR: 0.021–0.089; p < 0.001) compared to HIR− patients. Multivariable regression showed that HIR+ (β: 0.53, SE: 0.02; p = 0.003) and presentation of the National Institutes of Health Stroke Scale (β: 0.2, SE: 0.0006; p = 0.001) were independently associated with EPR. In conclusion, favorable HIR was associated with lower early edema progression and decreased ischemic edema formation on baseline NCCT.

Background: The importance of an A1 aplasia remains unclear in stroke patients. In this work, we analyze the impact of an A1 aplasia contralateral to an acute occlusion of the distal internal carotid artery (ICA) on clinical outcomes. Methods: We conducted a retrospective study of consecutive stroke patients treated with mechanical thrombectomy at 12 tertiary care centers between January 2015 and February 2021 due to an occlusion of the distal ICA. Functional A1 aplasia was defined as the absence of A1 or hypoplastic A1 (>50% reduction to the contralateral site). Functional independence was measured by the modified Rankin Scale (mRS ≤ 2). Results: In total, 81 out of 1068 (8%) patients had functional A1 aplasia contralateral to distal ICA occlusion. Patients with functional contralateral A1 aplasia were more severely affected on admission (median NIHSS 18, IQR 15–23 vs. 17, IQR 13–21; aOR: 0.672, 95% CI: 0.448–1.007, p = 0.054) and post-interventional ischemic damage was larger (median ASPECTS 5, IQR 1–7, vs. 6, IQR 3–8; aOR: 1.817, 95% CI: 1.184–2.789, p = 0.006). Infarction occurred more often within the ipsilateral ACA territory (20/76, 26% vs. 110/961, 11%; aOR: 2.482, 95% CI: 1.389–4.437, p = 0.002) and both ACA territories (8/76, 11% vs. 5/961, 1%; aOR: 17.968, 95% CI: 4.979–64.847, p ≤ 0.001). Functional contralateral A1 aplasia was associated with a lower rate of functional independence at discharge (6/81, 8% vs. 194/965, 20%; aOR: 2.579, 95% CI: 1.086–6.122, p = 0.032) and after 90 days (5/55, 9% vs. 170/723, 24%; aOR: 2.664, 95% CI: 1.031–6.883, p = 0.043). Conclusions: A functional A1 aplasia contralateral to a distal ICA occlusion is associated with a poorer clinical outcome.