CarveMix: A simple data augmentation method for brain lesion segmentation.

Brain lesion segmentation provides a valuable tool for clinical diagnosis and research, and convolutional neural networks (CNNs) have achieved unprecedented success in the segmentation task. Data augmentation is a widely used strategy to improve the training of CNNs. In particular, data augmentation approaches that mix pairs of annotated training images have been developed. These methods are easy to implement and have achieved promising results in various image processing tasks. However, existing data augmentation approaches based on image mixing are not designed for brain lesions and may not perform well for brain lesion segmentation. Thus, the design of this type of simple data augmentation method for brain lesion segmentation is still an open problem. In this work, we propose a simple yet effective data augmentation approach, dubbed as CarveMix, for CNN-based brain lesion segmentation. Like other mixing-based methods, CarveMix stochastically combines two existing annotated images (annotated for brain lesions only) to obtain new labeled samples. To make our method more suitable for brain lesion segmentation, CarveMix is lesion-aware, where the image combination is performed with a focus on the lesions and preserves the lesion information. Specifically, from one annotated image we carve a region of interest (ROI) according to the lesion location and geometry with a variable ROI size. The carved ROI then replaces the corresponding voxels in a second annotated image to synthesize new labeled images for network training, and additional harmonization steps are applied for heterogeneous data where the two annotated images can originate from different sources. Besides, we further propose to model the mass effect that is unique to whole brain tumor segmentation during image mixing. To evaluate the proposed method, experiments were performed on multiple publicly available or private datasets, and the results show that our method improves the accuracy of brain lesion segmentation. The code of the proposed method is available at https://github.com/ZhangxinruBIT/CarveMix.git.

Deep learning-assisted classification of calcaneofibular ligament injuries in the ankle joint.

Background: The classification of calcaneofibular ligament (CFL) injuries on magnetic resonance imaging (MRI) is time-consuming and subject to substantial interreader variability. This study explores the feasibility of classifying CFL injuries using deep learning methods by comparing them with the classifications of musculoskeletal (MSK) radiologists and further examines image cropping screening and calibration methods. Methods: The imaging data of 1,074 patients who underwent ankle arthroscopy and MRI examinations in our hospital were retrospectively analyzed. According to the arthroscopic findings, patients were divided into normal (class 0, n=475); degeneration, strain, and partial tear (class 1, n=217); and complete tear (class 2, n=382) groups. All patients were divided into training, validation, and test sets at a ratio of 8:1:1. After preprocessing, the images were cropped using Mask region-based convolutional neural network (R-CNN), followed by the application of an attention algorithm for image screening and calibration and the implementation of LeNet-5 for CFL injury classification. The diagnostic effects of the axial, coronal, and combined models were compared, and the best method was selected for outgroup validation. The diagnostic results of the models in the intragroup and outgroup test sets were compared with those results of 4 MSK radiologists of different seniorities. Results: The mean average precision (mAP) of the Mask R-CNN using the attention algorithm for the left and right image cropping of axial and coronal sequences was 0.90-0.96. The accuracy of LeNet-5 for classifying classes 0-2 was 0.92, 0.93, and 0.92, respectively, for the axial sequences and 0.89, 0.92, and 0.90, respectively, for the coronal sequences. After sequence combination, the classification accuracy for classes 0-2 was 0.95, 0.97, and 0.96, respectively. The mean accuracies of the 4 MSK radiologists in classifying the intragroup test set as classes 0-2 were 0.94, 0.91, 0.86, and 0.85, all of which were significantly different from the model. The mean accuracies of the MSK radiologists in classifying the outgroup test set as classes 0-2 were 0.92, 0.91, 0.87, and 0.85, with the 2 senior MSK radiologists demonstrating similar diagnostic performance to the model and the junior MSK radiologists demonstrating worse accuracy. Conclusions: Deep learning can be used to classify CFL injuries at similar levels to those of MSK radiologists. Adding an attention algorithm after cropping is helpful for accurately cropping CFL images.

Knowledge transfer between brain lesion segmentation tasks with increased model capacity.

Convolutional neural networks (CNNs) have become an increasingly popular tool for brain lesion segmentation in recent years due to its accuracy and efficiency. However, CNN-based brain lesion segmentation generally requires a large amount of annotated training data, which can be costly for medical imaging. In many scenarios, only a few annotations of brain lesions are available. One common strategy to address the issue of limited annotated data is to transfer knowledge from a different yet relevant source task, where training data is abundant, to the target task of interest. Typically, a model can be pretrained for the source task, and then fine-tuned with the scarce training data associated with the target task. However, classic fine-tuning tends to make small modifications to the pretrained model, which could hinder its adaptation to the target task. Fine-tuning with increased model capacity has been shown to alleviate this negative impact in image classification problems. In this work, we extend the strategy of fine-tuning with increased model capacity to the problem of brain lesion segmentation, and then develop an advanced version that is better suitable for segmentation problems. First, we propose a vanilla strategy of increasing the capacity, where, like in the classification problem, the width of the network is augmented during fine-tuning. Second, because unlike image classification, in segmentation problems each voxel is associated with a labeling result, we further develop a spatially adaptive augmentation strategy during fine-tuning. Specifically, in addition to the vanilla width augmentation, we incorporate a module that computes a spatial map of the contribution of the information given by width augmentation in the final segmentation. For demonstration, the proposed method was applied to ischemic stroke lesion segmentation, where a model pretrained for brain tumor segmentation was fine-tuned, and the experimental results indicate the benefit of our method.

One-step articular cartilage repair: combination of in situ bone marrow stem cells with cell-free poly(L-lactic-co-glycolic acid) scaffold in a rabbit model.

Focal full-thickness articular cartilage defects are challenging to repair. The purpose of this study was to find a simple, effective 1-step articular cartilage repair method. Because stem cell niches produce a microenvironment for stem cell self-renewal, proliferation, and differentiation, we integrated in situ bone marrow stem cells with an implanted poly(L-lactic-co-glycolic acid) (PLLGA) scaffold. Marrow stem cells grew and proliferated on cell-free PLLGA scaffolds, which were evaluated by scanning electronic microscopy (SEM) and Cell Counting Kit-8 (Dojindo, Kumamoto, Japan). Twenty-seven rabbits (54 knees) with large cylinder femoral trochlear cartilage defects were created and repaired with microfracture and cell-free PLLGA scaffold implantation (group 1), microfracture (group 2), or cell-free PLLGA scaffold implantation (group 3).Outcomes were evaluated by magnetic resonance imaging, International Cartilage Repair Society scores, histology, and immunohistochemistry. The repair effects were better in group 1 than in groups 2 and 3. In group 1, hyaline-like cartilage formed at week 24. Magnetic resonance imaging showed homogeneous signals as the adjacent normal cartilage. Collagen type II and toluidine blue were stained positively as normal cartilage tissue, and the color and thickness of regenerated tissue were similar to surrounding normal tissue. The combination of microfracture and cell-free PLLGA scaffold implantation used endogenous marrow stem cells in situ and promoted hyaline-like cartilage regeneration rapidly and effectively.

Mixed epithelial and stromal tumor of the kidney: an analysis of multidetector computed tomography manifestations and clinicopathologic findings.

OBJECTIVES: To explore the features of mixed epithelial and stromal tumor of kidney (MESTK) on the images of multidetector computed tomography with clinical manifestations and pathological findings as a reference. METHODS: On the basis of a blind retrospective review, we analyzed the images of 6 cases of MESTK on multidetector computed tomography and compared them with pathological results postoperatively. Two reviewers were asked to classify the tumors according to the Bosniak classification. We also combined them with clinical data, pathological findings, and reviewed literatures. RESULTS: All tumors were single, unilateral, and well circumscribed with a clear delineation from renal parenchyma. Five were round or oval, whereas 1 was irregularly shaped. One tumor processed to renal pelvis, 1 protruded from the cortex, and 4 large masses processed to both the cortex and the pelvis. In 6 cases, all MESTKs consisted of an irregular mixture of solid and cystic areas. The cysts were multilocular with smooth walls and low-density cystic liquid. No mural nodules were observed. Five tumors were diagnosed as Bosniak III, and 1 as Bosniak IV. Solid parts presented a mild-to-moderate enhancement and delayed enhancement without any enhancement of the cystic ones. CONCLUSIONS: Radiologists should consider the possibility of MESTK when they find that the tumor is a single solid or a cystic solid mass, especially in a female patient, and that the solid components present a mild-to-moderate enhancement during the corticomedullary phase and delayed enhancement, but the definite diagnosis depends on pathology.