Quantitative comparison of automatic results for multi-organ segmentation by means of Dice scores often does not yield satisfactory results. It is especially challenging, when reference contours may be prone to errors. We developed a novel approach that analyzes regions of high mismatch between automatic and reference segmentations. We extract various metrics characterizing these mismatch clusters and compare them to other metrics derived from volume overlap and surface distance histograms by correlating them with qualitative ratings from clinical experts. We show that some novel features based on the mismatch sets or surface distance histograms performed better than the Dice score. We also show how the mismatch clusters can be used to gene...
The importance of medical image segmentation increases in fields like treatment planning or computer...
The importance of medical image segmentation increases in fields like treatment planning or computer...
Organs-at-risk contouring is time consuming and labour intensive. Automation by deep learning algori...
The quality of automatic 3D medical segmentation algorithms needs to be assessed on test datasets co...
All medical image segmentation algorithms need to be validated and compared, and yet no evaluation f...
All medical image segmentation algorithms need to be validated and compared, yet no evaluation frame...
3D medical image segmentation is needed for diagnosis and treatment. As manual segmentation is very ...
Abstract. 3D medical image segmentation is needed for diagnosis and treatment. As manual segmentatio...
Several diagnostic and treatment procedures require the segmentation of anatomical structures from m...
The quantification of similarity between image segmen-tations is a complex yet important task. The i...
Abstract The evaluation of 3D medical image segmenta-tion quality requires a reliable detailed compa...
Purpose: To characterize discrepancies between expert manually segmented brain images from Hammers A...
Purpose: When using convolutional neural networks (CNNs) for segmentation of organs and lesions in m...
Abstract. This paper is a joint effort between five institutions that introduces several novel simil...
In this paper we present an evaluation of four different 3D segmentation algorithms with respect to ...
The importance of medical image segmentation increases in fields like treatment planning or computer...
The importance of medical image segmentation increases in fields like treatment planning or computer...
Organs-at-risk contouring is time consuming and labour intensive. Automation by deep learning algori...
The quality of automatic 3D medical segmentation algorithms needs to be assessed on test datasets co...
All medical image segmentation algorithms need to be validated and compared, and yet no evaluation f...
All medical image segmentation algorithms need to be validated and compared, yet no evaluation frame...
3D medical image segmentation is needed for diagnosis and treatment. As manual segmentation is very ...
Abstract. 3D medical image segmentation is needed for diagnosis and treatment. As manual segmentatio...
Several diagnostic and treatment procedures require the segmentation of anatomical structures from m...
The quantification of similarity between image segmen-tations is a complex yet important task. The i...
Abstract The evaluation of 3D medical image segmenta-tion quality requires a reliable detailed compa...
Purpose: To characterize discrepancies between expert manually segmented brain images from Hammers A...
Purpose: When using convolutional neural networks (CNNs) for segmentation of organs and lesions in m...
Abstract. This paper is a joint effort between five institutions that introduces several novel simil...
In this paper we present an evaluation of four different 3D segmentation algorithms with respect to ...
The importance of medical image segmentation increases in fields like treatment planning or computer...
The importance of medical image segmentation increases in fields like treatment planning or computer...
Organs-at-risk contouring is time consuming and labour intensive. Automation by deep learning algori...