Florian Jung

Evaluation of prostate segmentation algorithms for MRI: the PROMISE12 challenge

Prostate MRI image segmentation has been an area of intense research due to the increased use of MRI as a modality for the clinical workup of prostate cancer. Segmentation is useful for various tasks, e.g. to accurately localize prostate boundaries for radiotherapy or to initialize multi-modal registration algorithms. In the past, it has been difficult for research groups to evaluate prostate segmentation algorithms on multi-center, multi-vendor and multi-protocol data. Especially because we are dealing with MR images, image appearance, resolution and the presence of artifacts are affected by differences in scanners and/or protocols, which in turn can have a large influence on algorithm accuracy. The Prostate MR Image Segmentation (PROMISE12) challenge was setup to allow a fair and meaningful comparison of segmentation methods on the basis of performance and robustness. In this work we will discuss the initial results of the online PROMISE12 challenge, and the results obtained in the live challenge workshop hosted by the MICCAI2012 conference. In the challenge, 100 prostate MR cases from 4 different centers were included, with differences in scanner manufacturer, field strength and protocol. A total of 11 teams from academic research groups and industry participated. Algorithms showed a wide variety in methods and implementation, including active appearance models, atlas registration and level sets. Evaluation was performed using boundary and volume based metrics which were combined into a single score relating the metrics to human expert performance. The winners of the challenge where the algorithms by teams Imorphics and ScrAutoProstate, with scores of 85.72 and 84.29 overall. Both algorithms where significantly better than all other algorithms in the challenge (p<0.05) and had an efficient implementation with a run time of 8min and 3s per case respectively. Overall, active appearance model based approaches seemed to outperform other approaches like multi-atlas registration, both on accuracy and computation time. Although average algorithm performance was good to excellent and the Imorphics algorithm outperformed the second observer on average, we showed that algorithm combination might lead to further improvement, indicating that optimal performance for prostate segmentation is not yet obtained. All results are available online at http://promise12.grand-challenge.org/.

Evaluation of segmentation methods on head and neck CT: Auto‐segmentation challenge 2015

Purpose Automated delineation of structures and organs is a key step in medical imaging. However, due to the large number and diversity of structures and the large variety of segmentation algorithms, a consensus is lacking as to which automated segmentation method works best for certain applications. Segmentation challenges are a good approach for unbiased evaluation and comparison of segmentation algorithms. Methods In this work, we describe and present the results of the Head and Neck Auto‐Segmentation Challenge 2015, a satellite event at the Medical Image Computing and Computer Assisted Interventions (MICCAI) 2015 conference. Six teams participated in a challenge to segment nine structures in the head and neck region of CT images: brainstem, mandible, chiasm, bilateral optic nerves, bilateral parotid glands, and bilateral submandibular glands. Results This paper presents the quantitative results of this challenge using multiple established error metrics and a well‐defined ranking system. The strengths and weaknesses of the different auto‐segmentation approaches are analyzed and discussed. Conclusions The Head and Neck Auto‐Segmentation Challenge 2015 was a good opportunity to assess the current state‐of‐the‐art in segmentation of organs at risk for radiotherapy treatment. Participating teams had the possibility to compare their approaches to other methods under unbiased and standardized circumstances. The results demonstrate a clear tendency toward more general purpose and fewer structure‐specific segmentation algorithms.

Personalized articulated atlas with a dynamic adaptation strategy for bone segmentation in CT or CT/MR head and neck images

This paper presents a novel segmentation method for the joint segmentation of individual bones in CT- or CT/MR- head and neck images. It is based on an articulated atlas for CT images that learned the shape and appearance of the individual bones along with the articulation between them from annotated training instances. First, a novel dynamic adaptation strategy for the atlas is presented in order to increase the rate of successful adaptations. Then, if a corresponding CT image is available the atlas can be enriched with personalized information about shape, appearance and size of the individual bones from that image. Using mutual information, this personalized atlas is adapted to an MR image in order to propagate segmentations. For evaluation, a head and neck bone atlas created from 15 manually annotated training images was adapted to 58 clinically acquired head andneck CT datasets. Visual inspection showed that the automatic dynamic adaptation strategy was successful for all bones in 86% of the cases. This is a 22% improvement compared to the traditional gradient descent based approach. In leave-one-out cross validation manner the average surface distance of the correctly adapted items was found to be 0.6 8mm. In 20 cases corresponding CT/MR image pairs were available and the atlas could be personalized and adapted to the MR image. This was successful in 19 cases.

COSMO - Coupled Shape Model for Radiation Therapy Planning of Head and Neck Cancer

Radiation therapy plays a major role in head and neck cancer treatment. Segmentation of organs at risk prior to the radiation therapy helps to prevent the radiation beam from damaging healthy tissue, whereas a concentrated ray can target the cancerous regions. Unfortunately, the manual annotation of all relevant structures in the head and neck area is very time-consuming and existing atlas-based solutions don’t provide sufficient segmentation accuracy. Therefore, we propose an coupled shape model (CoSMo) for the segmentation of key structures within the head and neck area. The model’s adaptation to a test image is done with respect to the appearance of its items and the trained articulation space. 40 data sets labeled by clinicians containing 22 structures were used to build the CoSMo. Even on very challenging data sets with unnatural postures, which occur far more often than expected, the model adaptation algorithm succeeds. A first evaluation showed an average directed Hausdorff distance of 13.22 mm and an average DICE overlap of 0.62. Furthermore, we review some of the challenges we encountered during the course of building our model from image data, taken from actual radiation therapy planing cases.

A Generic Approach to Organ Detection Using 3D Haar-Like Features

Automatic segmentation of medical images requires accurate detection of the desired organ as a first step. In contrast to application specific approaches, learning-based object detection algorithms are easily adaptable to new applications. We present a learning-based object detection approach based on the Viola-Jones algorithm. We propose several extensions to the original approach, including a new 3D feature type and a multi-organ detection scheme. The algorithm is used to detect six different organs in CT scans as well as the prostate in MRI data. Our evaluation shows that the algorithm provides fast and reliable detection results in all cases.

Automatic Sentinel Lymph Node Localization in Head and Neck Cancer Using a Coupled Shape Model Algorithm

The localization and analysis of the sentinel lymph node for patients diagnosed with cancer, has significant influence on the prognosis, outcome and treatment of the disease. We present a fully automatic approach to localize the sentinel lymph node and additional active nodes and determine their lymph node level on SPECT-CT data. This is a crucial prerequisite for the planning of radiation therapy or a surgical neck dissection. Our approach was evaluated on 17 lymph nodes. The detection rate of the lymph nodes was 94%; and 88% of the lymph nodes were correctly assigned to their corresponding lymph node level. The proposed algorithm targets a very important topic in clinical practice. The first results are already very promising. The next step has to be the evaluation on a larger data set.

Segmentierung von zervikalen Lymphknoten in T1-gewichteten MRT-Aufnahmen

Die Untersuchung von Grose und Aussehen eines Lymphknotens kann ein entscheidender Indikator fur die Existenz eines Tumors sein und ist auserdem ein probates Mittel, um Verlaufsanalysen bei einem Patienten durchzufuhren, welche wiederum masgeblichen Einfluss auf die Behandlung haben konnen. Um die Grose und andere Parameter des Lymphknotens bestimmen zu konnen, ist zuerst eine Segmentierung vonnoten.Wir prasentieren ein neues Verfahren fur die halbautomatische Segmentierung von Lymphknoten auf MR-Datensatzen. Unser Ansatz verwendet eine Wasserscheidentransformation als Grundlage und kombiniert diese mit einem Radialstrahlbasierten Verfahren, um eine moglichst akurate Segmentierung des Lymphknotens zu erhalten. Fur die Evaluation wurden 95 Lymphknoten-Segmentierungen aus 17 verschiedenen, kontrastverstarkten T1-gewichteten Patientendatensatzen verwendet. Das durchschnittliche Dice ¨ Ahnlichkeitsmas lag bei 0.69±0.15 und die mittlere Oberflachendistanz bei 0.65±0.54mm.