RESUMEN
The fusion of probability maps is required when trying to analyse a collection of image labels or probability maps produced by several segmentation algorithms or human raters. The challenge is to weight the combination of maps correctly, in order to reflect the agreement among raters, the presence of outliers and the spatial uncertainty in the consensus. In this paper, we address several shortcomings of prior work in continuous label fusion. We introduce a novel approach to jointly estimate a reliable consensus map and to assess the presence of outliers and the confidence in each rater. Our robust approach is based on heavy-tailed distributions allowing local estimates of raters performances. In particular, we investigate the Laplace, the Student's t and the generalized double Pareto distributions, and compare them with respect to the classical Gaussian likelihood used in prior works. We unify these distributions into a common tractable inference scheme based on variational calculus and scale mixture representations. Moreover, the introduction of bias and spatial priors leads to proper rater bias estimates and control over the smoothness of the consensus map. Finally, we propose an approach that clusters raters based on variational boosting, and thus may produce several alternative consensus maps. Our approach was successfully tested on MR prostate delineations and on lung nodule segmentations from the LIDC-IDRI dataset.
Asunto(s)
Algoritmos , Imagen por Resonancia Magnética , Teorema de Bayes , Humanos , Imagen por Resonancia Magnética/métodos , Masculino , ProbabilidadRESUMEN
Monitoring the quality of image segmentation is key to many clinical applications. This quality assessment can be carried out by a human expert when the number of cases is limited. However, it becomes onerous when dealing with large image databases, so partial automation of this process is preferable. Previous works have proposed both supervised and unsupervised methods for the automated control of image segmentations. The former assume the availability of a subset of trusted segmented images on which supervised learning is performed, while the latter does not. In this paper, we introduce a novel unsupervised approach for quality assessment of segmented images based on a generic probabilistic model. Quality estimates are produced by comparing each segmentation with the output of a probabilistic segmentation model that relies on intensity and smoothness assumptions. Ranking cases with respect to these two assumptions allows the most challenging cases in a dataset to be detected. Furthermore, unlike prior work, our approach enables possible segmentation errors to be localized within an image. The proposed generic probabilistic segmentation method combines intensity mixture distributions with spatial regularization prior models whose parameters are estimated with variational Bayesian techniques. We introduce a novel smoothness prior based on the penalization of the derivatives of label maps which allows an automatic estimation of its hyperparameter in a fully data-driven way. Extensive evaluation of quality control on medical and COCO datasets is conducted, showing the ability to isolate atypical segmentations automatically and to predict, in some cases, the performance of segmentation algorithms.
Asunto(s)
Imagen por Resonancia Magnética , Modelos Estadísticos , Algoritmos , Teorema de Bayes , Humanos , Procesamiento de Imagen Asistido por Computador , Control de CalidadRESUMEN
Tumor mutational burden (TMB) has emerged as an important potential biomarker for prediction of response to immune-checkpoint inhibitors (ICIs), notably in non-small cell lung cancer (NSCLC). However, its in-house assessment in routine clinical practice is currently challenging and validation is urgently needed. We have analyzed sixty NSCLC and thirty-six melanoma patients with ICI treatment, using the FoundationOne test (FO) in addition to in-house testing using the Oncomine TML (OTML) panel and evaluated the durable clinical benefit (DCB), defined by >6 months without progressive disease. Comparison of TMB values obtained by both tests demonstrated a high correlation in NSCLC (R2 = 0.73) and melanoma (R2 = 0.94). The association of TMB with DCB was comparable between OTML (area-under the curve (AUC) = 0.67) and FO (AUC = 0.71) in NSCLC. Median TMB was higher in the DCB cohort and progression-free survival (PFS) was prolonged in patients with high TMB (OTML HR = 0.35; FO HR = 0.45). In contrast, we detected no differences in PFS and median TMB in our melanoma cohort. Combining TMB with PD-L1 and CD8-expression by immunohistochemistry improved the predictive value. We conclude that in our cohort both approaches are equally able to assess TMB and to predict DCB in NSCLC.