Search

Introduction: Reconstructive plastic surgeons have made great strides in the field of breast reconstruction to achieve the best results for patients undergoing treatment for breast cancer. As microsurgical techniques have evolved, these patients can benefit from additional treatment modalities to optimize the results of the reconstruction. Free tissue transfer from alternative donor sites for breast reconstruction is routinely performed, which was not possible in the past. Neurotization is now possible to address the numbness and lack of sensation to the reconstructed breast. For those patients who develop lymphedema of the upper extremity as a result of their breast cancer care, supermicrosurgical options are now available to treat and even to prevent the development of lymphedema. This study presents a narrative review regarding the latest microsurgical advancements in autologous free flap breast reconstruction. Methods: A literature review was performed on PubMed with the key words "autologous free flap breast reconstruction", "deep inferior epigastric perforator flap", "transverse upper gracilis flap", "profunda artery perforator flap", "superior gluteal artery perforator flap", "inferior gluteal artery perforator flap", "lumbar artery perforator flap", "breast neurotization", "lymphovenous bypass and anastomosis", and "vascularized lymph node transfer". Articles that specifically focused on free flap breast reconstruction, breast neurotization, and lymphedema surgery in the setting of breast cancer were evaluated and included in this literature review. Results: The literature search yielded a total of 4948 articles which were screened. After the initial screening, 413 articles were reviewed to assess the relevance and applicability to the current study. Conclusions: Breast reconstruction has evolved tremendously in recent years to provide the most natural and cosmetically pleasing results for those patients undergoing treatment for breast cancer. As technology and surgical techniques have progressed, breast cancer patients now have many more options, particularly if they are interested in autologous reconstruction. These advancements also provide the possibility of restoring sensibility to the reconstructed breast as well as treating the sequela of lymphedema due to their cancer treatment. [ABSTRACT FROM AUTHOR]

MRI brain structure segmentation plays an important role in neuroimaging studies. Existing methods either spend much CPU time, require considerable annotated data, or fail in segmenting volumes with large deformation. In this paper, we develop a novel multi-atlas-based algorithm for 3D MRI brain structure segmentation. It consists of three modules: registration, atlas selection and label fusion. Both registration and label fusion leverage an integrated flow based on grayscale and SIFT features. We introduce an effective and efficient strategy for atlas selection by employing the accompanying energy generated in the registration step. A 3D sequential belief propagation method and a 3D coarse-to-fine flow matching approach are developed in both registration and label fusion modules. The proposed method is evaluated on five public datasets. The results show that it has the best performance in almost all the settings compared to competitive methods such as ANTs, Elastix, Learning to Rank and Joint Label Fusion. Moreover, our registration method is more than 7 times as efficient as that of ANTs SyN, while our label transfer method is 18 times faster than Joint Label Fusion in CPU time. The results on the ADNI dataset demonstrate that our method is applicable to image pairs that require a significant transformation in registration. The performance on a composite dataset suggests that our method succeeds in a cross-modality manner. The results of this study show that the integrated 3D flow-based method is effective and efficient for brain structure segmentation. It also demonstrates the power of SIFT features, multi-atlas segmentation and classical machine learning algorithms for a medical image analysis task. The experimental results on public datasets show the proposed method's potential for general applicability in various brain structures and settings. [ABSTRACT FROM AUTHOR]

Potential radioactive hazards in full-dose positron emission tomography (PET) imaging remain a concern, whereas the quality of low-dose images is never desirable for clinical use. So it is of great interest to translate low-dose PET images into full-dose. Previous studies based on deep learning methods usually directly extract hierarchical features for reconstruction. We notice that the importance of each feature is different and they should be weighted dissimilarly so that tiny information can be captured by the neural network. Furthermore, the synthesis on some regions of interest is important in some applications. Here we propose a novel segmentation guided style-based generative adversarial network (SGSGAN) for PET synthesis. (1) We put forward a style-based generator employing style modulation, which specifically controls the hierarchical features in the translation process, to generate images with more realistic textures. (2) We adopt a task-driven strategy that couples a segmentation task with a generative adversarial network (GAN) framework to improve the translation performance. Extensive experiments show the superiority of our overall framework in PET synthesis, especially on those regions of interest. [ABSTRACT FROM AUTHOR]

A hybrid hidden Markov model/neural network wordspotter trained through the Figure of Merit (FOM) method delivered excellent performance with fewer parameters than those required by continuous-speech wordspotters. FOM training shapes parameters to improve performance metrics. Voice transformations also provided additional training examples. This wordspotter can easily be embedded in very compact devices because of its reduced complexity.

Automatic Non-rigid Histological Image Registration (ANHIR) challenge was organized to compare the performance of image registration algorithms on several kinds of microscopy histology images in a fair and independent manner. We have assembled 8 datasets, containing 355 images with 18 different stains, resulting in 481 image pairs to be registered. Registration accuracy was evaluated using manually placed landmarks. In total, 256 teams registered for the challenge, 10 submitted the results, and 6 participated in the workshop. Here, we present the results of 7 well-performing methods from the challenge together with 6 well-known existing methods. The best methods used coarse but robust initial alignment, followed by non-rigid registration, used multiresolution, and were carefully tuned for the data at hand. They outperformed off-the-shelf methods, mostly by being more robust. The best methods could successfully register over 98% of all landmarks and their mean landmark registration accuracy (TRE) was 0.44% of the image diagonal. The challenge remains open to submissions and all images are available for download. [ABSTRACT FROM AUTHOR]

3D medical image registration is of great clinical importance. However, supervised learning methods require a large amount of accurately annotated corresponding control points (or morphing), which are very difficult to obtain. Unsupervised learning methods ease the burden of manual annotation by exploiting unlabeled data without supervision. In this article, we propose a new unsupervised learning method using convolutional neural networks under an end-to-end framework, Volume Tweening Network (VTN), for 3D medical image registration. We propose three innovative technical components: (1) An end-to-end cascading scheme that resolves large displacement; (2) An efficient integration of affine registration network; and (3) An additional invertibility loss that encourages backward consistency. Experiments demonstrate that our algorithm is 880x faster (or 3.3x faster without GPU acceleration) than traditional optimization-based methods and achieves state-of-the-art performance in medical image registration. [ABSTRACT FROM AUTHOR]

Objective: A new image instance segmentation method is proposed to segment individual glands (instances) in colon histology images. This process is challenging since the glands not only need to be segmented from a complex background, they must also be individually identified. Methods: We leverage the idea of image-to-image prediction in recent deep learning by designing an algorithm that automatically exploits and fuses complex multichannel information—regional, location, and boundary cues—in gland histology images. Our proposed algorithm, a deep multichannel framework, alleviates heavy feature design due to the use of convolutional neural networks and is able to meet multifarious requirements by altering channels. Results: Compared with methods reported in the 2015 MICCAI Gland Segmentation Challenge and other currently prevalent instance segmentation methods, we observe state-of-the-art results based on the evaluation metrics. Conclusion: The proposed deep multichannel algorithm is an effective method for gland instance segmentation. Significance: The generalization ability of our model not only enable the algorithm to solve gland instance segmentation problems, but the channel is also alternative that can be replaced for a specific task. [ABSTRACT FROM PUBLISHER]

In this paper, we develop a new weakly supervised learning algorithm to learn to segment cancerous regions in histopathology images. This paper is under a multiple instance learning (MIL) framework with a new formulation, deep weak supervision (DWS); we also propose an effective way to introduce constraints to our neural networks to assist the learning process. The contributions of our algorithm are threefold: 1) we build an end-to-end learning system that segments cancerous regions with fully convolutional networks (FCNs) in which image-to-image weakly-supervised learning is performed; 2) we develop a DWS formulation to exploit multi-scale learning under weak supervision within FCNs; and 3) constraints about positive instances are introduced in our approach to effectively explore additional weakly supervised information that is easy to obtain and enjoy a significant boost to the learning process. The proposed algorithm, abbreviated as DWS-MIL, is easy to implement and can be trained efficiently. Our system demonstrates the state-of-the-art results on large-scale histopathology image data sets and can be applied to various applications in medical imaging beyond histopathology images, such as MRI, CT, and ultrasound images. [ABSTRACT FROM AUTHOR]

Background The principle reconstructive modality for segmental mandibulectomy defects is the osteocutaneous free fibula flap. Preoperative CT angiography has been recommended to assess the quality of arterial inflow to the flap and donor limb. However, the impact of the venous system on flap viability has not been explored. Methods A retrospective review of all patients undergoing free fibula flap mandible reconstruction was performed at a single tertiary cancer center from 2002 to 2015. Overall complications, including operative reexploration and total flap losses, were evaluated. Results One hundred seven patients underwent free fibula flap reconstruction of the mandible. Nine patients underwent multiple free flaps and were excluded from this study. Of the remaining 98 patients, 8 patients required operative exploration for microvascular compromise. All patients were found to have venous thrombosis. There were 3 total flaps losses with a salvage rate of 62.5% and overall flap survival of 96.9%. The size of the vena comitantes in the compromised flaps were significantly larger than those of the remaining patients (4.4 mm vs 3.1 mm; P < .0001). Although the total operative times were similar between the 2 groups (585.2 minutes vs 563.3 minutes), the ischemia time was significantly shorter in those cases that required operative takeback (76.5 minutes vs 104.0 minutes; P < .04). Conclusion Venous thrombosis of free fibula flaps is more common than arterial thrombosis. Venous stasis in larger vena comitantes may be a contributing factor to microvascular compromise. Anticoagulation and/or handsewn anastomosis may be beneficial if the veins are larger than 4.0 mm in size. [ABSTRACT FROM AUTHOR]

Purpose: In this paper, the authors proposed a new 3D registration algorithm, 3D-scale invariant feature transform (SIFT)-Flow, for multiatlas-based liver segmentation in computed tomography (CT) images. Methods: In the registration work, the authors developed a new registration method that takes advantage of dense correspondence using the informative and robust SIFT feature. The authors computed the dense SIFT features for the source image and the target image and designed an objective function to obtain the correspondence between these two images. Labeling of the source image was then mapped to the target image according to the former correspondence, resulting in accurate segmentation. In the fusion work, the 2D-based nonparametric label transfer method was extended to 3D for fusing the registered 3D atlases. Results: Compared with existing registration algorithms, 3D-SIFT-Flow has its particular advantage in matching anatomical structures (such as the liver) that observe large variation/deformation. The authors observed consistent improvement over widely adopted state-of-the-art registration methods such as ELASTIX, ANTS, and multiatlas fusion methods such as joint label fusion. Experimental results of liver segmentation on the MICCAI 2007 Grand Challenge are encouraging, e.g., Dice overlap ratio 96.27%±0.96% by our method compared with the previous state-of-the-art result of 94.90%±2.86%. Conclusions: Experimental results show that 3D-SIFT-Flow is robust for segmenting the liver from CT images, which has large tissue deformation and blurry boundary, and 3D label transfer is effective and efficient for improving the registration accuracy. [ABSTRACT FROM AUTHOR]

References to anatomical entities in medical records consist not only of explicit references to anatomical locations, but also other diverse types of expressions, such as specific diseases, clinical tests, clinical treatments, which constitute implicit references to anatomical entities. In order to identify these implicit anatomical entities, we propose a hierarchical framework, in which two layers of named entity recognizers (NERs) work in a cooperative manner. Each of the NERs is implemented using the Conditional Random Fields (CRF) model, which use a range of external resources to generate features. We constructed a dictionary of anatomical entity expressions by exploiting four existing resources, i.e., UMLS, MeSH, RadLex and BodyPart3D, and supplemented information from two external knowledge bases, i.e., Wikipedia and WordNet, to improve inference of anatomical entities from implicit expressions. conducted on 300 discharge summaries showed a micro-averaged performance of 0.8509 Precision, 0.7796 Recall and 0.8137 F1 for explicit anatomical entity recognition, and 0.8695 Precision, 0.6893 Recall and 0.7690 F1 for implicit anatomical entity recognition. The use of the hierarchical framework, which combines the recognition of named entities of various types (diseases, clinical tests, treatments) with information embedded in external knowledge bases, resulted in a 5.08% increment in F1. The resources constructed for this research will be made publicly available. [ABSTRACT FROM AUTHOR]