The Liver Tumor Segmentation Benchmark (LiTS).

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://medicaldecathlon.com/. In addition, both data and online evaluation are accessible via https://competitions.codalab.org/competitions/17094.

Patient-specific and global convolutional neural networks for robust automatic liver tumor delineation in follow-up CT studies.

Radiological longitudinal follow-up of tumors in CT scans is essential for disease assessment and liver tumor therapy. Currently, most tumor size measurements follow the RECIST guidelines, which can be off by as much as 50%. True volumetric measurements are more accurate but require manual delineation, which is time-consuming and user-dependent. We present a convolutional neural networks (CNN) based method for robust automatic liver tumor delineation in longitudinal CT studies that uses both global and patient specific CNNs trained on a small database of delineated images. The inputs are the baseline scan and the tumor delineation, a follow-up scan, and a liver tumor global CNN voxel classifier built from radiologist-validated liver tumor delineations. The outputs are the tumor delineations in the follow-up CT scan. The baseline scan tumor delineation serves as a high-quality prior for the tumor characterization in the follow-up scans. It is used to evaluate the global CNN performance on the new case and to reliably predict failures of the global CNN on the follow-up scan. High-scoring cases are segmented with a global CNN; low-scoring cases, which are predicted to be failures of the global CNN, are segmented with a patient-specific CNN built from the baseline scan. Our experimental results on 222 tumors from 31 patients yield an average overlap error of 17% (std = 11.2) and surface distance of 2.1 mm (std = 1.8), far better than stand-alone segmentation. Importantly, the robustness of our method improved from 67% for stand-alone global CNN segmentation to 100%. Unlike other medical imaging deep learning approaches, which require large annotated training datasets, our method exploits the follow-up framework to yield accurate tumor tracking and failure detection and correction with a small training dataset. Graphical abstract Flow diagram of the proposed method. In the offline mode (orange), a global CNN is trained as a voxel classifier to segment liver tumor as in [31]. The online mode (blue) is used for each new case. The input is baseline scan with delineation and the follow-up CT scan to be segmented. The main novelty is the ability to predict failures by trying the system on the baseline scan and the ability to correct them using the patient-specific CNN.

Validation of a stereo camera system to quantify brain deformation due to breathing and pulsatility.

PURPOSE: A new stereo vision system is presented to quantify brain shift and pulsatility in open-skull neurosurgeries. METHODS: The system is endowed with hardware and software synchronous image acquisition with timestamp embedding in the captured images, a brain surface oriented feature detection, and a tracking subroutine robust to occlusions and outliers. A validation experiment for the stereo vision system was conducted against a gold-standard optical tracking system, Optotrak CERTUS. A static and dynamic analysis of the stereo camera tracking error was performed tracking a customized object in different positions, orientations, linear, and angular speeds. RESULTS: The system is able to detect an immobile object position and orientation with a maximum error of 0.5 mm and 1.6° in all depth of field, and tracking a moving object until 3 mm/s with a median error of 0.5 mm. Three stereo video acquisitions were recorded from a patient, immediately after the craniotomy. The cortical pulsatile motion was captured and is represented in the time and frequency domain. The amplitude of motion of the cloud of features' center of mass was inferior to 0.8 mm. Three distinct peaks are identified in the fast Fourier transform analysis related to the sympathovagal balance, breathing, and blood pressure with 0.03-0.05, 0.2, and 1 Hz, respectively. CONCLUSIONS: The stereo vision system presented is a precise and robust system to measure brain shift and pulsatility with an accuracy superior to other reported systems.