FUN-SIS: A Fully UNsupervised approach for Surgical Instrument Segmentation

Automatic surgical instrument segmentation of endoscopic images is a crucial building block of many computer-assistance applications for minimally invasive surgery. So far, state-of-the-art approaches completely rely on the availability of a ground-truth supervision signal, obtained via manual annotation, thus expensive to collect at large scale. In this paper, we present FUN-SIS, a Fully-UNsupervised approach for binary Surgical Instrument Segmentation. FUN-SIS trains a per-frame segmentation model on completely unlabelled endoscopic videos, by solely relying on implicit motion information and instrument shape-priors. We define shape-priors as realistic segmentation masks of the instruments, not necessarily coming from the same dataset/domain as the videos. The shape-priors can be collected in various and convenient ways, such as recycling existing annotations from other datasets. We leverage them as part of a novel generative-adversarial approach, allowing to perform unsupervised instrument segmentation of optical-flow images during training. We then use the obtained instrument masks as pseudo-labels in order to train a per-frame segmentation model; to this aim, we develop a learning-from-noisy-labels architecture, designed to extract a clean supervision signal from these pseudo-labels, leveraging their peculiar noise properties. We validate the proposed contributions on three surgical datasets, including the MICCAI 2017 EndoVis Robotic Instrument Segmentation Challenge dataset. The obtained fully-unsupervised results for surgical instrument segmentation are almost on par with the ones of fully-supervised state-of-the-art approaches. This suggests the tremendous potential of the proposed method to leverage the great amount of unlabelled data produced in the context of minimally invasive surgery.     

Beyond rankings: Learning (more) from algorithm validation

Challenges have become the state-of-the-art approach to benchmark image analysis algorithms in a comparative manner. While the validation on identical data sets was a great step forward, results analysis is often restricted to pure ranking tables, leaving relevant questions unanswered. Specifically, little effort has been put into the systematic investigation on what characterizes images in which state-of-the-art algorithms fail. To address this gap in the literature, we (1) present a statistical framework for learning from challenges and (2) instantiate it for the specific task of instrument instance segmentation in laparoscopic videos. Our framework relies on the semantic meta data annotation of images, which serves as foundation for a General Linear Mixed Models (GLMM) analysis. Based on 51,542 meta data annotations performed on 2,728 images, we applied our approach to the results of the Robust Medical Instrument Segmentation Challenge (ROBUST-MIS) challenge 2019 and revealed underexposure, motion and occlusion of instruments as well as the presence of smoke or other objects in the background as major sources of algorithm failure. Our subsequent method development, tailored to the specific remaining issues, yielded a deep learning model with state-of-the-art overall performance and specific strengths in the processing of images in which previous methods tended to fail. Due to the objectivity and generic applicability of our approach, it could become a valuable tool for validation in the field of medical image analysis and beyond.     

3D position estimation of flexible instruments: marker-less and marker-based methods

Purpose Endoscopic images can be used to allow accurate flexible endoscopic instrument control. This can be implemented using a pose estimation algorithm, which estimates the actual instrument pose from the endoscopic images. Methods In this paper, two pose estimation algorithms are compared: a marker-less and a marker-based method. The marker-based method uses the positions of three markers in the endoscopic image to update the state of a kinematic model of the endoscopic instrument. The marker-less method works similarly, but uses the positions of three feature points instead of the positions of markers. The algorithms are evaluated inside a colon model. The endoscopic instrument is manually operated, while an X-ray imager is used to obtain a ground-truth reference position. Results The marker-less method achieves an RMS error of 1.5, 1.6, and 1.8 mm in the horizontal, vertical, and away-from-camera directions, respectively. The marker-based method achieves an RMS error of 1.1, 1.7, and 1.5 mm in the horizontal, vertical, and away-from-camera directions, respectively. The differences between the two methods are not found to be statistically significant. Conclusions The proposed algorithms are suitable to realize accurate robotic control of flexible endoscopic instruments, enabling the physician to perform advanced procedures in an intuitive way.     

Histopathological bladder cancer gene mutation prediction with hierarchical deep multiple-instance learning

Gene mutation detection is usually carried out by molecular biological methods, which is expensive and has a long-time cycle. In contrast, pathological images are ubiquitous. If clinically significant gene mutations can be predicted only through pathological images, it will greatly promote the widespread use of gene mutation detection in clinical practice. However, current gene mutation prediction methods based on pathological images are ineffective because of the inability to identify mutated regions in gigapixel Whole Slide Image (WSI). To address this challenge, hereby we propose a carefully designed framework for WSI-based gene mutation prediction, which consists of three parts. (i) The first part of cancerous area segmentation, based on supervised learning, quickly filters out a large number of non-mutated regions; (ii) the second part of cancerous patch clustering, based on the representations derived from contrastive learning, ensures the comprehensiveness of patch selection; and (iii) the third part of mutation classification, based on the proposed hierarchical deep multi-instance learning method (HDMIL), ensures that sufficient patches are considered and inaccurate selections are ignored. In addition, benefiting from a two-stage attention mechanism in HDMIL, the patches that are highly correlated with gene mutations can be identified. This interpretability can help a pathologist to analyze the correlation between gene mutation and histopathological morphology. Experimental results demonstrate that the proposed gene mutation prediction framework significantly outperforms the state-of-the-art methods. In the TCGA bladder cancer dataset, five clinically relevant gene mutations are well predicted.     

ST-MTL: Spatio-Temporal multitask learning model to predict scanpath while tracking instruments in robotic surgery

Representation learning of the task-oriented attention while tracking instrument holds vast potential in image-guided robotic surgery. Incorporating cognitive ability to automate the camera control enables the surgeon to concentrate more on dealing with surgical instruments. The objective is to reduce the operation time and facilitate the surgery for both surgeons and patients. We propose an end-to-end trainable Spatio-Temporal Multi-Task Learning (ST-MTL) model with a shared encoder and spatio-temporal decoders for the real-time surgical instrument segmentation and task-oriented saliency detection. In the MTL model of shared-parameters, optimizing multiple loss functions into a convergence point is still an open challenge. We tackle the problem with a novel asynchronous spatio-temporal optimization (ASTO) technique by calculating independent gradients for each decoder. We also design a competitive squeeze and excitation unit by casting a skip connection that retains weak features, excites strong features, and performs dynamic spatial and channel-wise feature recalibration. To capture better long term spatio-temporal dependencies, we enhance the long-short term memory (LSTM) module by concatenating high-level encoder features of consecutive frames. We also introduce Sinkhorn regularized loss to enhance task-oriented saliency detection by preserving computational efficiency. We generate the task-aware saliency maps and scanpath of the instruments on the dataset of the MICCAI 2017 robotic instrument segmentation challenge. Compared to the state-of-the-art segmentation and saliency methods, our model outperforms most of the evaluation metrics and produces an outstanding performance in the challenge.     

A review of machine learning methods for retinal blood vessel segmentation and artery/vein classification

The eye affords a unique opportunity to inspect a rich part of the human microvasculature non-invasively via retinal imaging. Retinal blood vessel segmentation and classification are prime steps for the diagnosis and risk assessment of microvascular and systemic diseases. A high volume of techniques based on deep learning have been published in recent years. In this context, we review 158 papers published between 2012 and 2020, focussing on methods based on machine and deep learning (DL) for automatic vessel segmentation and classification for fundus camera images. We divide the methods into various classes by task (segmentation or artery-vein classification), technique (supervised or unsupervised, deep and non-deep learning, hand-crafted methods) and more specific algorithms (e.g. multiscale, morphology). We discuss advantages and limitations, and include tables summarising results at-a-glance. Finally, we attempt to assess the quantitative merit of DL methods in terms of accuracy improvement compared to other methods. The results allow us to offer our views on the outlook for vessel segmentation and classification for fundus camera images.     

A comparison of two algorithms for automated stone detection in clinical B-mode ultrasound images of the abdomen

Ultrasound (US) imaging is an indispensible technique for detection of abdominal stones which are a serious health hazard. Segmentation of stones from abdominal ultrasound images presents a unique challenge because these images contain strong speckle noise and attenuated artifacts. In clinical situations where a large number of stones must be identified, traditional methods such as manual identification become tedious and lack reproducibility too. The necessity of obtaining high reproducibility and the need to increase efficiency motivates the development of automated and fast procedures that segment out stones of all sizes and shapes in medical images by applying image segmentation techniques. In this paper we present and compare two fully automatic and unsupervised methods for robust stone detection in B-mode ultrasound images of the abdomen. Our approaches are based on the marker controlled watershed segmentation, along with some pre-processing and post-processing procedures that eliminate the inherent problems associated with medical ultrasound images. The first algorithm (Algorithm I) utilizes the advantage of the Speckle reducing anisotropic diffusion (SRAD) technique, along with unsharp filtering and histo- gram equalization for removal of speckle noise, and the second algorithm (Algorithm II) is based on the log decompression model which too serves as a tool for minimization of speckle. Experimental results obtained from processing a set of 50 ultrasound images ensure the robustness of both the proposed algorithms. Comparative results of both the algorithms based on efficiency and relative error in stone area have been provided.     

Iterative multi-atlas-based multi-image segmentation with tree-based registration

In this paper, we present a multi-atlas-based framework for accurate, consistent and simultaneous segmentation of a group of target images. Multi-atlas-based segmentation algorithms consider concurrently complementary information from multiple atlases to produce optimal segmentation outcomes. However, the accuracy of these algorithms relies heavily on the precise alignment of the atlases with the target image. In particular, the commonly used pairwise registration may result in inaccurate alignment especially between images with large shape differences. Additionally, when segmenting a group of target images, most current methods consider these images independently with disregard of their correlation, thus resulting in inconsistent segmentations of the same structures across different target images. We propose two novel strategies to address these limitations: 1) a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 2) an iterative groupwise segmentation method for simultaneous consideration of segmentation information propagated from all available images, including the atlases and other newly segmented target images. Evaluation based on various datasets indicates that the proposed multi-atlas-based multi-image segmentation (MABMIS) framework yields substantial improvements in terms of consistency and accuracy over methods that do not consider the group of target images holistically.     

Cardiac segmentation on late gadolinium enhancement MRI: A benchmark study from multi-sequence cardiac MR segmentation challenge

Accurate computing, analysis and modeling of the ventricles and myocardium from medical images are important, especially in the diagnosis and treatment management for patients suffering from myocardial infarction (MI). Late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) provides an important protocol to visualize MI. However, compared with the other sequences LGE CMR images with gold standard labels are particularly limited. This paper presents the selective results from the Multi-Sequence Cardiac MR (MS-CMR) Segmentation challenge, in conjunction with MICCAI 2019. The challenge offered a data set of paired MS-CMR images, including auxiliary CMR sequences as well as LGE CMR, from 45 patients who underwent cardiomyopathy. It was aimed to develop new algorithms, as well as benchmark existing ones for LGE CMR segmentation focusing on myocardial wall of the left ventricle and blood cavity of the two ventricles. In addition, the paired MS-CMR images could enable algorithms to combine the complementary information from the other sequences for the ventricle segmentation of LGE CMR. Nine representative works were selected for evaluation and comparisons, among which three methods are unsupervised domain adaptation (UDA) methods and the other six are supervised. The results showed that the average performance of the nine methods was comparable to the inter-observer variations. Particularly, the top-ranking algorithms from both the supervised and UDA methods could generate reliable and robust segmentation results. The success of these methods was mainly attributed to the inclusion of the auxiliary sequences from the MS-CMR images, which provide important label information for the training of deep neural networks. The challenge continues as an ongoing resource, and the gold standard segmentation as well as the MS-CMR images of both the training and test data are available upon registration via its homepage (www.sdspeople.fudan.edu.cn/zhuangxiahai/0/mscmrseg/).     

Statistical segmentation of surgical instruments in 3-D ultrasound images

The recent development of real-time 3-D ultrasound (US) enables intracardiac beating-heart procedures, but the distorted appearance of surgical instruments is a major challenge to surgeons. In addition, tissue and instruments have similar gray levels in US images and the interface between instruments and tissue is poorly defined. We present an algorithm that automatically estimates instrument location in intracardiac procedures. Expert-segmented images are used to initialize the statistical distributions of blood, tissue and instruments. Voxels are labeled through an iterative expectation-maximization algorithm using information from the neighboring voxels through a smoothing kernel. Once the three classes of voxels are separated, additional neighboring information is combined with the known shape characteristics of instruments to correct for misclassifications. We analyze the major axis of segmented data through their principal components and refine the results by a watershed transform, which corrects the results at the contact between instrument and tissue. We present results on 3-D in-vitro data from a tank trial and 3-D in-vivo data from cardiac interventions on porcine beating hearts, using instruments of four types of materials. The comparison of algorithm results to expert-annotated images shows the correct segmentation and position of the instrument shaft.     

A novel approach for improved tractography and quantitative analysis of probabilistic fibre tracking curves

This paper presents a novel approach for improved diffusion tensor fibre tractography, aiming to tackle a number of the limitations of current fibre tracking algorithms, and describes a quantitative analysis tool for probabilistic tracking algorithms. We consider the sampled random paths generated by a probabilistic tractography algorithm from a seed point as a set of curves, and develop a statistical framework for analysing the curve-set geometrically that finds the average curve and dispersion measures of the curve-set statistically. This study is motivated firstly by the goal of developing a robust fibre tracking algorithm, combining the power of both deterministic and probabilistic tracking methods using average curves. These typical curves produce strong connections to every anatomically distinct fibre tract from a seed point and also convey important information about the underlying probability distribution. These single well-defined trajectories overcome a number of the limitations of deterministic and probabilistic approaches. A new clustering algorithm for branching curves is employed to separate fibres into branches before applying the averaging methods. Secondly, a quantitative analysis tool for probabilistic tracking methods is introduced using statistical measures of curve-sets. Results on phantom and in vivo data confirm the efficiency and effectiveness of the proposed approach for the tracking algorithm and the quantitative analysis of the probabilistic methods.     

PAIP 2019: Liver cancer segmentation challenge

Pathology Artificial Intelligence Platform (PAIP) is a free research platform in support of pathological artificial intelligence (AI). The main goal of the platform is to construct a high-quality pathology learning data set that will allow greater accessibility. The PAIP Liver Cancer Segmentation Challenge, organized in conjunction with the Medical Image Computing and Computer Assisted Intervention Society (MICCAI 2019), is the first image analysis challenge to apply PAIP datasets. The goal of the challenge was to evaluate new and existing algorithms for automated detection of liver cancer in whole-slide images (WSIs). Additionally, the PAIP of this year attempted to address potential future problems of AI applicability in clinical settings. In the challenge, participants were asked to use analytical data and statistical metrics to evaluate the performance of automated algorithms in two different tasks. The participants were given the two different tasks: Task 1 involved investigating Liver Cancer Segmentation and Task 2 involved investigating Viable Tumor Burden Estimation. There was a strong correlation between high performance of teams on both tasks, in which teams that performed well on Task 1 also performed well on Task 2. After evaluation, we summarized the top 11 team’s algorithms. We then gave pathological implications on the easily predicted images for cancer segmentation and the challenging images for viable tumor burden estimation. Out of the 231 participants of the PAIP challenge datasets, a total of 64 were submitted from 28 team participants. The submitted algorithms predicted the automatic segmentation on the liver cancer with WSIs to an accuracy of a score estimation of 0.78. The PAIP challenge was created in an effort to combat the lack of research that has been done to address Liver cancer using digital pathology. It remains unclear of how the applicability of AI algorithms created during the challenge can affect clinical diagnoses. However, the results of this dataset and evaluation metric provided has the potential to aid the development and benchmarking of cancer diagnosis and segmentation.     

VerSe: A Vertebrae labelling and segmentation benchmark for multi-detector CT images

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision support systems for diagnosis, surgery planning, and population-based analysis of spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms tackling the labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the results of this evaluation and further investigate the performance variation at the vertebra level, scan level, and different fields of view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top-performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The VerSe content and code can be accessed at: https://github.com/anjany/verse.     

Development of a multi-scale object-based shadow detection method for high spatial resolution image

Effective treatment of shadows generated by the obstruction of trees and buildings is an inevitable task for extracting detailed spectral and spatial information from urban high-resolution images. Object-based shadow detection methods can take full advantages of spatial features in the urban very high resolution (VHR) images. However, the effect of different segmentation parameters for detecting shadows has not been well studied. In this study, we proposed an object-based method for shadow detection on urban high-resolution image and addressed quantitative assessment of segmentation. In proposed object-based method, a multi-scale segmentation method, known as fractal net evolution approach (FNEA), was employed to generate primitive objects; then, three spectral properties of shadows were fused based on Dempster–Shafer (D–S) evidence theory to identify shadows. In quantitative assessment, a method for ordering significance of parameters and deriving optimal parameters based on orthogonal experimental design was proposed to evaluate the impact of different segmentation variables on the accuracy of shadow detection. Experimental results indicate that the best overall accuracy (OA) for shadow detection of our method was 89.60% after segmentation parameters’ optimization and scale is the most influential parameter of FNEA segmentation parameters in determining the performance of shadow detection.     

Brain tumor detection and segmentation in a CRF (conditional random fields) framework with pixel-pairwise affinity and superpixel-level features

Purpose

Detection and segmentation of a brain tumor such as glioblastoma multiforme (GBM) in magnetic resonance (MR) images are often challenging due to its intrinsically heterogeneous signal characteristics. A robust segmentation method for brain tumor MRI scans was developed and tested.

Methods

Simple thresholds and statistical methods are unable to adequately segment the various elements of the GBM, such as local contrast enhancement, necrosis, and edema. Most voxel-based methods cannot achieve satisfactory results in larger data sets, and the methods based on generative or discriminative models have intrinsic limitations during application, such as small sample set learning and transfer. A new method was developed to overcome these challenges. Multimodal MR images are segmented into superpixels using algorithms to alleviate the sampling issue and to improve the sample representativeness. Next, features were extracted from the superpixels using multi-level Gabor wavelet filters. Based on the features, a support vector machine (SVM) model and an affinity metric model for tumors were trained to overcome the limitations of previous generative models. Based on the output of the SVM and spatial affinity models, conditional random fields theory was applied to segment the tumor in a maximum a posteriori fashion given the smoothness prior defined by our affinity model. Finally, labeling noise was removed using “structural knowledge” such as the symmetrical and continuous characteristics of the tumor in spatial domain.

Results

The system was evaluated with 20 GBM cases and the BraTS challenge data set. Dice coefficients were computed, and the results were highly consistent with those reported by Zikic et al. (MICCAI 2012, Lecture notes in computer science. vol 7512, pp 369–376, 2012).

Conclusion

A brain tumor segmentation method using model-aware affinity demonstrates comparable performance with other state-of-the art algorithms.     

Towards ultrasound cardiac image segmentation based on the radiofrequency signal

In echocardiography, the radio-frequency (RF) image is a rich source of information about the investigated tissues. Nevertheless, very few works are dedicated to boundary detection based on the RF image, as opposed to envelope image. In this paper, we investigate the feasibility and limitations of boundary detection in echocardiographic images based on the RF signal. We introduce two types of RF-derived parameters: spectral autoregressive parameters and velocity-based parameters, and we propose a discontinuity adaptive framework to perform the detection task. In classical echographic cardiac acquisitions, we show that it is possible to use the spectral contents for boundary detection, and that improvement can be expected with respect to traditional methods. Using the system approach, we study on simulations how the spectral contents can be used for boundary detection. We subsequently perform boundary detection in high frame rate simulated and in vivo cardiac sequences using the variance of velocity, obtaining very promising results. Our work opens the perspective of a RF-based framework for ultrasound cardiac image segmentation and tracking.     

Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: the VESSEL12 study

The VESSEL12 (VESsel SEgmentation in the Lung) challenge objectively compares the performance of different algorithms to identify vessels in thoracic computed tomography (CT) scans. Vessel segmentation is fundamental in computer aided processing of data generated by 3D imaging modalities. As manual vessel segmentation is prohibitively time consuming, any real world application requires some form of automation. Several approaches exist for automated vessel segmentation, but judging their relative merits is difficult due to a lack of standardized evaluation. We present an annotated reference dataset containing 20 CT scans and propose nine categories to perform a comprehensive evaluation of vessel segmentation algorithms from both academia and industry. Twenty algorithms participated in the VESSEL12 challenge, held at International Symposium on Biomedical Imaging (ISBI) 2012. All results have been published at the VESSEL12 website http://vessel12.grand-challenge.org. The challenge remains ongoing and open to new participants. Our three contributions are: (1) an annotated reference dataset available online for evaluation of new algorithms; (2) a quantitative scoring system for objective comparison of algorithms; and (3) performance analysis of the strengths and weaknesses of the various vessel segmentation methods in the presence of various lung diseases.     

Detection and analysis of cerebral aneurysms based on X-ray rotational angiography - the CADA 2020 challenge

The Cerebral Aneurysm Detection and Analysis (CADA) challenge was organized to support the development and benchmarking of algorithms for detecting, analyzing, and risk assessment of cerebral aneurysms in X-ray rotational angiography (3DRA) images. 109 anonymized 3DRA datasets were provided for training, and 22 additional datasets were used to test the algorithmic solutions. Cerebral aneurysm detection was assessed using the F2 score based on recall and precision, and the fit of the delivered bounding box was assessed using the distance to the aneurysm. The segmentation quality was measured using the Jaccard index and a combination of different surface distance measures. Systematic errors were analyzed using volume correlation and bias. Rupture risk assessment was evaluated using the F2 score. 158 participants from 22 countries registered for the CADA challenge. The U-Net-based detection solutions presented by the community show similar accuracy compared to experts (F2 score 0.92), with a small number of missed aneurysms with diameters smaller than 3.5 mm. In addition, the delineation of these structures, based on U-Net variations, is excellent, with a Jaccard score of 0.92. The rupture risk estimation methods achieved an F2 score of 0.71. The performance of the detection and segmentation solutions is equivalent to that of human experts. The best results are obtained in rupture risk estimation by combining different image-based, morphological, and computational fluid dynamic parameters using machine learning methods. Furthermore, we evaluated the best methods pipeline, from detecting and delineating the vessel dilations to estimating the risk of rupture. The chain of these methods achieves an F2-score of 0.70, which is comparable to applying the risk prediction to the ground-truth delineation (0.71).     

Fetal brain tissue annotation and segmentation challenge results

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, gray matter, white matter, ventricles, cerebellum, brainstem, deep gray matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero.