A deep semantic segmentation correction network for multi-model tiny lesion areas detection

Background Semantic segmentation of white matter hyperintensities related to focal cerebral ischemia (FCI) and lacunar infarction (LACI) is of significant importance for the automatic screening of tiny cerebral lesions and early prevention of LACI. However, existing studies on brain magnetic resonance imaging lesion segmentation focus on large lesions with obvious features, such as glioma and acute cerebral infarction. Owing to the multi-model tiny lesion areas of FCI and LACI, reliable and precise segmentation and/or detection of these lesion areas is still a significant challenge task. Methods We propose a novel segmentation correction algorithm for estimating the lesion areas via segmentation and correction processes, in which we design two sub-models simultaneously: a segmentation network and a correction network. The segmentation network was first used to extract and segment diseased areas on T2 fluid-attenuated inversion recovery (FLAIR) images. Consequently, the correction network was used to classify these areas at the corresponding locations on T1 FLAIR images to distinguish between FCI and LACI. Finally, the results of the correction network were used to correct the segmentation results and achieve segmentation and recognition of the lesion areas. Results In our experiment on magnetic resonance images of 113 clinical patients, our method achieved a precision of 91.76% for detection and 92.89% for classification, indicating a powerful method to distinguish between small lesions, such as FCI and LACI. Conclusions Overall, we developed a complete method for segmentation and detection of WMHs related to FCI and LACI. The experimental results show that it has potential clinical application potential. In the future, we will collect more clinical data and test more types of tiny lesions at the same time.

Prinsip, Teknik, dan Algoritma untuk Karakterisasi Pencitraan Lesi-Lesi Adrenal Incidentaloma

Adrenal Incidentaloma lesions are commonly detected by Computed Tomography and Magnetic Resonance Imaging. Lesion characterization is essential to predict the prognosis of the primary disease, to assess staging, and direct therapy. Imaging plays a critical role in the characterization of adrenal incidentaloma lesions. Imaging modalities have been developed forr accurately differentiating lesions by using anatomic and physiologic imaging principles and major adrenal imaging techniques currently available which include newly developed promising techniques. An imaging algorithm is provided to guide radiologists in recognizing, reporting, and managing adrenal lesions, so it leads to the appropriate test to make correct diagnosis. The purpose of this article is to discuss the principles, techniques and imaging algorithms in characterizing adrenal lesions.

ANALYSIS OF THE TOPIC STUDY USING 2010 MCDONALD CRITERIA

IntroductionTOPIC (NCT00622700) was designed to evaluate teriflunomide in patients with a first clinical episode suggestive of multiple sclerosis (MS). Teriflunomide 14 mg reduced risk of relapse determining conversion to clinically definite MS by 42.6%, and of new relapse or magnetic resonance imaging lesion by 34.9% vs placebo. After study initiation, the 2005 McDonald criteria were revised, potentially allowing earlier MS diagnosis.MethodsThe 2010 McDonald criteria were applied retrospectively. Patients who received teriflunomide 14 mg or placebo for ≤108 weeks were grouped according to fulfilment of 2010 criteria at baseline. Time to MS was analysed for those not fulfilling the 2010 criteria at baseline. Additional post hoc analyses will evaluate differences in outcomes based on baseline radiological characteristics of reclassified patients.ResultsPatients receiving teriflunomide 14mg (n=214) or placebo (n=197) were analysed. For those not meeting the 2010 criteria (n=163), probability of conversion to MS was 54.1% (14 mg) and 74.4% (placebo). Teriflunomide 14mg reduced the probability of conversion to MS by 39.1% vs placebo. Data regarding time to MS based upon baseline radiological characteristics will be presented.ConclusionsTeriflunomide demonstrates a consistent treatment effect in patients with MS diagnosed according to differing diagnostic criteria. (Study supported by Genzyme, a Sanofi company).

Further investigation of safety monitoring guidelines based on magnetic resonance imaging lesion activity in multiple sclerosis clinical trials

We assess two modified guidelines for monitoring patient safety in multiple sclerosis (MS) trials. These guidelines flag patients with an increase in contrast enhancing lesion (CEL) count above a threshold over the CEL level 1–2 months earlier. We compare the new guidelines to the original guideline where the threshold is set according to the baseline by applying the guidelines to two previous studies. The odds ratios of a subsequent clinical relapse associated with meeting the CEL threshold based on the modified guidelines are similar to those based on the original guideline. There is a need for patient and cohort specific monitoring procedures.