Quantification of the Thoracic Aorta and Detection of Aneurysm at CT: Development and Validation of a Fully Automatic Methodology.

Purpose: To develop and validate a deep learning-based system that predicts the largest ascending and descending aortic diameters at chest CT through automatic thoracic aortic segmentation and identifies aneurysms in each segment. Materials and Methods: In this retrospective study conducted from July 2019 to February 2021, a U-Net and a postprocessing algorithm for thoracic aortic segmentation and measurement were developed by using a dataset (dataset A) that included 315 CT studies split into training, hyperparameter-tuning, and testing sets. The U-Net and postprocessing algorithm were associated with a Digital Imaging and Communications in Medicine series filter and visualization interface and were further validated by using a dataset (dataset B) that included 1400 routine CT studies. In dataset B, system-predicted measurements were compared with annotations made by two independent readers as well as radiology reports to evaluate system performance. Results: In dataset B, the mean absolute error between the automatic and reader-measured diameters was equal to or less than 0.27 cm for both the ascending aorta and the descending aorta. The intraclass correlation coefficients (ICCs) were greater than 0.80 for the ascending aorta and equal to or greater than 0.70 for the descending aorta, and the ICCs between readers were 0.91 (95% CI: 0.90, 0.92) and 0.82 (95% CI: 0.80, 0.84), respectively. Aneurysm detection accuracy was 88% (95% CI: 86, 90) and 81% (95% CI: 79, 83) compared with reader 1 and 90% (95% CI: 88, 91) and 82% (95% CI: 80, 84) compared with reader 2 for the ascending aorta and descending aorta, respectively. Conclusion: Thoracic aortic aneurysms were accurately predicted at CT by using deep learning.Keywords: Aorta, Convolutional Neural Network, Machine Learning, CT, Thorax, AneurysmsSupplemental material is available for this article.© RSNA, 2022.

Receptive Field Size as a Key Design Parameter for Ultrasound Image Segmentation with U-Net.

Automatic and accurate segmentation of medical images is an important task due to the direct impact of this procedure on both disease diagnosis and treatment. Segmentation of ultrasound (US) imaging is particularly challenging due to the presence of speckle noise. Recent deep learning approaches have demonstrated remarkable findings in image segmentation tasks, including segmentation of US images. However, many of the newly proposed structures are either task specific and suffer from poor generalization, or are computationally expensive. In this paper, we show that the receptive field plays a more significant role in the network's performance compared to the network's depth or the number of parameters. We further show that by controlling the size of the receptive field, a deep network can instead be replaced by a shallow network.

Fine-Tuning U-Net for Ultrasound Image Segmentation: Different Layers, Different Outcomes.

One way of resolving the problem of scarce and expensive data in deep learning for medical applications is using transfer learning and fine-tuning a network which has been trained on a large data set. The common practice in transfer learning is to keep the shallow layers unchanged and to modify deeper layers according to the new data set. This approach may not work when using a U-Net and when moving from a different domain to ultrasound (US) images due to their drastically different appearance. In this study, we investigated the effect of fine-tuning different sets of layers of a pretrained U-Net for US image segmentation. Two different schemes were analyzed, based on two different definitions of shallow and deep layers. We studied simulated US images, as well as two human US data sets. We also included a chest X-ray data set. The results showed that choosing which layers to fine-tune is a critical task. In particular, they demonstrated that fine-tuning the last layers of the network, which is the common practice for classification networks, is often the worst strategy. It may therefore be more appropriate to fine-tune the shallow layers rather than deep layers in US image segmentation when using a U-Net. Shallow layers learn lower level features which are critical in automatic segmentation of medical images. Even when a large US data set is available, we observed that fine-tuning shallow layers is a faster approach compared to fine-tuning the whole network.

Two-stage ultrasound image segmentation using U-Net and test time augmentation.

PURPOSE: Detecting breast lesions using ultrasound imaging is an important application of computer-aided diagnosis systems. Several automatic methods have been proposed for breast lesion detection and segmentation; however, due to the ultrasound artefacts, and to the complexity of lesion shapes and locations, lesion or tumor segmentation from ultrasound breast images is still an open problem. In this paper, we propose using a lesion detection stage prior to the segmentation stage in order to improve the accuracy of the segmentation. METHODS: We used a breast ultrasound imaging dataset which contained 163 images of the breast with either benign lesions or malignant tumors. First, we used a U-Net to detect the lesions and then used another U-Net to segment the detected region. We could show when the lesion is precisely detected, the segmentation performance substantially improves; however, if the detection stage is not precise enough, the segmentation stage also fails. Therefore, we developed a test-time augmentation technique to assess the detection stage performance. RESULTS: By using the proposed two-stage approach, we could improve the average Dice score by 1.8% overall. The improvement was substantially more for images wherein the original Dice score was less than 70%, where average Dice score was improved by 14.5%. CONCLUSIONS: The proposed two-stage technique shows promising results for segmentation of breast US images and has a much smaller chance of failure.

Assessment of Rigid Registration Quality Measures in Ultrasound-Guided Radiotherapy.

Image guidance has become the standard of care for patient positioning in radiotherapy, where image registration is often a critical step to help manage patient motion. However, in practice, verification of registration quality is often adversely affected by difficulty in manual inspection of 3-D images and time constraint, thus affecting the therapeutic outcome. Therefore, we proposed to employ both bootstrapping and the supervised learning methods of linear discriminant analysis and random forest to help robustly assess registration quality in ultrasound-guided radiotherapy. We validated both approaches using phantom and real clinical ultrasound images, and showed that both performed well for the task. While learning-based techniques offer better accuracy and shorter evaluation time, bootstrapping requires no prior training and has a higher sensitivity.

Virtual reality simulator: demonstrated use in neurosurgical oncology.

BACKGROUND: The overriding importance of patient safety, the complexity of surgical techniques, and the challenges associated with teaching surgical trainees in the operating room are all factors driving the need for innovative surgical simulation technologies. TECHNICAL DEVELOPMENT: Despite these issues, widespread use of virtual reality simulation technology in surgery has not been fully implemented, largely because of the technical complexities in developing clinically relevant and useful models. This article describes the successful use of the NeuroTouch neurosurgical simulator in the resection of a left frontal meningioma. CONCLUSION: The widespread application of surgical simulation technology has the potential to decrease surgical risk, improve operating room efficiency, and fundamentally change surgical training.

A computer model of soft tissue interaction with a surgical aspirator.

Surgical aspirators are one of the most frequently used neurosurgical tools. Effective training on a neurosurgery simulator requires a visually and haptically realistic rendering of surgical aspiration. However, there is little published data on mechanical interaction between soft biological tissues and surgical aspirators. In this study an experimental setup for measuring tissue response is described and results on calf brain and a range of phantom materials are presented. Local graphical and haptic models are proposed. They are simple enough for real-time application, and closely match the observed tissue response. Tissue resection (cutting) with suction is simulated using a volume sculpting approach. A simulation of suction is presented as a demonstration of the effectiveness of the approach.

Deformable ultrasound registration without reconstruction.

Ultrasound (US) imaging is often proposed as an interoperative imaging modality. This use nearly always requires that the collected data be registered to preoperative data of another modality. Existing intensity-based registration approaches all begin by reconstructing a 3D US volume from the collected 2D slices. We propose to directly register the set of 2D slices to the preoperative images. We argue this has a number of advantages, including the omission of the potentially complex reconstruction step, greater adaptability of the similarity measures, and easier parallelization. We describe a system for performing this task and present results on phantom data that show that our slice based method consistently outperforms a reconstruction based method in both speed and accuracy.