In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients—manually annotated by up to four raters—and to 65 comparable scans generated using tumor image simulation software Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%–85%), illustrating the difficulty of this task We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource

/pdf/the-multimodal-brain-tumor-image-segmentation-benchmark-2gfraj98dk.pdf

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

Brain tumor segmentation with Deep Neural Networks

A morphable model for the synthesis of 3D faces

Among brain tumors, gliomas are the most common and aggressive, leading to a very short life expectancy in their highest grade. Thus, treatment planning is a key stage to improve the quality of life of oncological patients. Magnetic resonance imaging (MRI) is a widely used imaging technique to assess these tumors, but the large amount of data produced by MRI prevents manual segmentation in a reasonable time, limiting the use of precise quantitative measurements in the clinical practice. So, automatic and reliable segmentation methods are required; however, the large spatial and structural variability among brain tumors make automatic segmentation a challenging problem. In this paper, we propose an automatic segmentation method based on Convolutional Neural Networks (CNN), exploring small 3 $\times$ 3 kernels. The use of small kernels allows designing a deeper architecture, besides having a positive effect against overfitting, given the fewer number of weights in the network. We also investigated the use of intensity normalization as a pre-processing step, which though not common in CNN-based segmentation methods, proved together with data augmentation to be very effective for brain tumor segmentation in MRI images. Our proposal was validated in the Brain Tumor Segmentation Challenge 2013 database (BRATS 2013), obtaining simultaneously the first position for the complete, core, and enhancing regions in Dice Similarity Coefficient metric (0.88, 0.83, 0.77) for the Challenge data set. Also, it obtained the overall first position by the online evaluation platform. We also participated in the on-site BRATS 2015 Challenge using the same model, obtaining the second place, with Dice Similarity Coefficient metric of 0.78, 0.65, and 0.75 for the complete, core, and enhancing regions, respectively.

Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images

Deformable image registration is a fundamental task in medical image processing. Among its most important applications, one may cite: 1) multi-modality fusion, where information acquired by different imaging devices or protocols is fused to facilitate diagnosis and treatment planning; 2) longitudinal studies, where temporal structural or anatomical changes are investigated; and 3) population modeling and statistical atlases used to study normal anatomical variability. In this paper, we attempt to give an overview of deformable registration methods, putting emphasis on the most recent advances in the domain. Additional emphasis has been given to techniques applied to medical images. In order to study image registration methods in depth, their main components are identified and studied independently. The most recent techniques are presented in a systematic fashion. The contribution of this paper is to provide an extensive account of registration techniques in a systematic manner.

/pdf/deformable-medical-image-registration-a-survey-2uee59wp1z.pdf

Deformable Medical Image Registration: A Survey

MRI-based medical image analysis for brain tumor studies is gaining attention in recent times due to an increased need for efficient and objective evaluation of large amounts of data. While the pioneering approaches applying automated methods for the analysis of brain tumor images date back almost two decades, the current methods are becoming more mature and coming closer to routine clinical application. This review aims to provide a comprehensive overview by giving a brief introduction to brain tumors and imaging of brain tumors first. Then, we review the state of the art in segmentation, registration and modeling related to tumor-bearing brain images with a focus on gliomas. The objective in the segmentation is outlining the tumor including its sub-compartments and surrounding tissues, while the main challenge in registration and modeling is the handling of morphological changes caused by the tumor. The qualities of different approaches are discussed with a focus on methods that can be applied on standard clinical imaging protocols. Finally, a critical assessment of the current state is performed and future developments and trends are addressed, giving special attention to recent developments in radiological tumor assessment guidelines.

/pdf/a-survey-of-mri-based-medical-image-analysis-for-brain-tumor-4mtl4fktmo.pdf

A survey of MRI-based medical image analysis for brain tumor studies

Vertebroplasty, which is the percutaneous injection of bone cement into vertebral bodies has recently been used to treat painful osteoporotic compression fractures. Early clinical results have been encouraging, but very little is known about the consequences of augmentation with cement for the adjacent, non-augmented level. We therefore measured the overall failure, strength and structural stiffness of paired osteoporotic two-vertebra functional spine units (FSUs). One FSU of each pair was augmented with polymethylmethacrylate bone cement in the caudal vertebra, while the other served as an untreated control. Compared with the controls, the ultimate failure load for FSUs treated by injection of cement was lower. The geometric mean treated/untreated ratio of failure load was 0.81, with 95% confidence limits from 0.70 to 0.92, (p < 0.01). There was no significant difference in overall FSU stiffness. For treated FSUs, there was a trend towards lower failure loads with increased filling with cement (r2 = 0.262, p = 0.13). The current practice of maximum filling with cement to restore the stiffness and strength of a vertebral body may provoke fractures in adjacent, non-augmented vertebrae. Further investigation is required to determine an optimal protocol for augmentation.

Adjacent vertebral failure after vertebroplasty: A BIOMECHANICAL INVESTIGATION

Objective: Intraoperative fluoroscopy is a valuable tool for visualizing underlying bone and surgical tool positions in orthopedic procedures. Disadvantages of this technology include the need for continued radiation exposure for visual control, and cumbersome means of alignment. The purpose of this article was to highlight a new concept for a computer-assisted freehand navigation system that uses single intraoperatively acquired fluoroscopic images as a basis for real-time navigation of surgical toolsMaterials and Methods: Optoelectronic markers are placed on surgical tools, a patient reference, and the fluoroscope to track their position in space. Projection properties of the fluoro-scope are acquired through an initial precalibration procedure using a tracked radiopaque phantom grid. Corrections are applied to compensate for both the fluoroscope's image intensifier distortions and the mechanical bending of the C-arm frame. This enables real-time simulation of surgical tool positions simultaneously in s...

Fluoroscopy as an Imaging Means for Computer-Assisted Surgical Navigation

One goal of interbody fusion is to increase the height of the degenerated disc space. Interbody cages in particular have been promoted with the claim that they can maintain the disc space better than other methods. There are many factors that can affect the disc height maintenance, including graft or cage design, the quality of the surrounding bone and the presence of supplementary posterior fixation. The present study is an in vitro biomechanical investigation of the compressive behaviour of three different interbody cage designs in a human cadaveric model. The effect of bone density and posterior instrumentation were assessed. Thirty-six lumbar functional spinal units were instrumented with one of three interbody cages: (1) a porous titanium implant with endplate fit (Stratec), (2) a porous, rectangular carbon-fibre implant (Brantigan) and (3) a porous, cylindrical threaded implant (Ray). Posterior instrumentation (USS) was applied to half of the specimens. All specimens were subjected to axial compression displacement until failure. Correlations between both the failure load and the load at 3 mm displacement with the bone density measurements were observed. Neither the cage design nor the presence of posterior instrumentation had a significant effect on the failure load. The loads at 3 mm were slightly less for the Stratec cage, implying lower axial stiffness, but were not different with posterior instrumentation. The large range of observed failure loads overlaps the potential in vivo compressive loads, implying that failure of the bone-implant interface may occur clinically. Preoperative measurements of bone density may be an effective tool to predict settling around interbody cages.

/pdf/compressive-strength-of-interbody-cages-in-the-lumbar-spine-4ceqvfscpy.pdf

Compressive strength of interbody cages in the lumbar spine: the effect of cage shape, posterior instrumentation and bone density

Structural tensile properties analyses of 10-mm-wide central sections of quadriceps tendon-bone (QT-B) and bone-patellar ligament (B-PL) complexes from young male donors (mean age 24.9 years, range 19-32 years) were complemented by a cryosectional analysis: each QT-B complex was composed of the segment of the quadriceps tendon with the proximal half of the patella attached, each B-PL complex was composed of the distal half of the patella with the patellar ligament attached. A servohydraulic materials testing machine was used to assess ultimate failure load of 16 unconditioned and 16 preconditioned QT-B and B-PL complexes at an extension rate of 1 mm/s. Ligaments/tendons were preconditioned during 200 cycles from 50 to 800 N at 0.5 Hz. On cryosections the quadriceps tendons were significantly longer and thicker and exhibited a significantly larger bony attachment area than the patellar ligaments. Cross-sectional areas of 10-mm-wide, full-thickness, central parts of unconditioned quadriceps tendons were significantly greater and measured 64.6 +/- 8.4 mm2 with respect to the cross-sectional area of patellar ligaments, measuring 36.8 +/- 5.7 mm2 (P < 0.0025). Ultimate failure loads for unconditioned complexes resulted at 2173 +/- 618 N for QT-B complexes and at 1953 +/- 325 N for B-PL complexes (P = 0.43). Ultimate failure load values measured 2353 +/- 495 N for preconditioned QT-B complexes and 2376 +/- 152 N for preconditioned B-PL complexes, respectively (P = 0.77). Despite the fact that initial testing length, thickness, cross-sectional shape and area of unconditioned QT-B and B-PL complexes were significantly different, displacement at ultimate load, energy to failure and total energy were not. In terms of ultimate tensile strength, the 10-mm-wide central part of the QT-B complex compared favourably to the tensile properties of the human femur-anterior cruciate ligament-tibia complex from a comparable young age group. The evidence from anatomic, cryosectional and structural properties analyses suggests that the QT-B complex may be a valuable and versatile adjunct to the surgeon's armamentarium in reconstructive cruciate ligament surgery.

Lutz-Peter Nolte

Papers

A survey of MRI-based medical image analysis for brain tumor studies

Adjacent vertebral failure after vertebroplasty: A BIOMECHANICAL INVESTIGATION

Fluoroscopy as an Imaging Means for Computer-Assisted Surgical Navigation

Compressive strength of interbody cages in the lumbar spine: the effect of cage shape, posterior instrumentation and bone density

Quadriceps tendon and patellar ligament: cryosectional anatomy and structural properties in young adults.