Identification of early-stage pulmonary adenocarcinomas before surgery, especially in cases of subcentimeter cancers, would be clinically important and could provide guidance to clinical decision making. In this study, we developed a deep learning system based on 3D convolutional neural networks and multitask learning, which automatically predicts tumor invasiveness, together with 3D nodule segmentation masks. The system processes a 3D nodule-centered patch of preprocessed CT and learns a deep representation of a given nodule without the need for any additional information. A dataset of 651 nodules with manually segmented voxel-wise masks and pathological labels of atypical adenomatous hyperplasia (AAH), adenocarcinomas in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive pulmonary adenocarcinoma (IA) was used in this study. We trained and validated our deep learning system on 523 nodules and tested its performance on 128 nodules. An observer study with 2 groups of radiologists, 2 senior and 2 junior, was also investigated. We merged AAH and AIS into one single category AAH-AIS, comprising a 3-category classification in our study. The proposed deep learning system achieved better classification performance than the radiologists; in terms of 3-class weighted average F1 score, the model achieved 63.3% while the radiologists achieved 55.6%, 56.6%, 54.3%, and 51.0%, respectively. These results suggest that deep learning methods improve the yield of discriminative results and hold promise in the CADx application domain, which could help doctors work efficiently and facilitate the application of precision medicine. Significance: Machine learning tools are beginning to be implemented for clinical applications. This study represents an important milestone for this emerging technology, which could improve therapy selection for patients with lung cancer.

The aim of the present study was to develop and validate a radiomics-based nomogram for differentiation of pre-invasive lesions from invasive lesions that appearing as ground-glass opacity nodules (GGNs) ≤10 mm (sub-centimeter) in diameter at CT. A total of 542 consecutive patients with 626 pathologically confirmed pulmonary subcentimeter GGNs were retrospectively studied from October 2011 to September 2017. All the GGNs were divided into a training set (n = 334) and a validation set (n = 292). Researchers extracted 475 radiomics features from the plain CT images; a radiomics signature was constructed with the least absolute shrinkage and selection operator (LASSO) based on multivariable regression in the training set. Based on the multivariable logistic regression model, a radiomics nomogram was developed in the training set. The performance of the nomogram was evaluated with respect to its calibration, discrimination, and clinical-utility and this was assessed in the validation set. The constructed radiomics signature, which consisted of 15 radiomics features, was significantly associated with the invasiveness of subcentimeter GGNs (P < 0.0001 for both training set and validation set). To build the nomogram model, radiomics signature and mean CT value were used. The nomogram model demonstrated good discrimination and calibration in both training set (C-index, 0.716 [95% CI, 0.632 to 0.801]) and validation set (C-index, 0.707 [95% CI, 0.625 to 0.788]). Decision curve analysis (DCA) indicated that radiomics-based nomogram was clinically useful. A radiomics-based nomogram that incorporates both radiomics signature and mean CT value is constructed in the study, which can be conveniently used to facilitate the preoperative individualized prediction of the invasiveness in patients with subcentimeter GGNs.

Tele-immersive 3D multi-camera room environments are starting to emerge and with them new challenging research questions. One important question is how to organize the large amount of visual data, being captured, processed, transmitted and displayed, and their corresponding resources, over current COTS computing and networking infrastructures so that "everybody" would be able to install and use tele-immersive environments for conferencing and other activities. In this paper, we propose a novel cross-layer control and streaming framework over general purpose delivery infrastructure, called TEEVE (tele-immersive environments for everybody). TEEVE aims for effective and adaptive coordination, synchronization, and soft QoS-enabled delivery of tele-immersive visual streams to remote room(s). The TEEVE experiments between two tele-immersive rooms residing in different institutions more than 2000 miles apart show that we can sustain communication of up to 12 3D video streams with 4/spl sim/5 3D frames per second for each stream, yielding 4/spl sim/5 tele-immersive video rate.

Automatic rib labeling and anatomical centerline extraction are common prerequisites for various clinical applications. Prior studies either use in-house datasets that are inaccessible to communities, or focus on rib segmentation that neglects the clinical significance of rib labeling. To address these issues, we extend our prior dataset ( RibSeg ) on the binary rib segmentation task to a comprehensive benchmark, named RibSeg v2 , with 660 CT scans (15,466 individual ribs in total) and annotations manually inspected by experts for rib labeling and anatomical centerline extraction. Based on the RibSeg v2 , we develop a pipeline including deep learning-based methods for rib labeling, and a skeletonization-based method for centerline extraction. To improve computational efficiency, we propose a sparse point cloud representation of CT scans and compare it with standard dense voxel grids. Moreover, we design and analyze evaluation metrics to address the key challenges of each task. Our dataset, code, and model are available online to facilitate open research at https://github.com/M3DV/RibSeg.

Rib fractures are a common and potentially severe injury that can be challenging and labor-intensive to detect in CT scans. While there have been efforts to address this field, the lack of large-scale annotated datasets and evaluation benchmarks has hindered the development and validation of deep learning algorithms. To address this issue, the RibFrac Challenge was introduced, providing a benchmark dataset of over 5,000 rib fractures from 660 CT scans, with voxel-level instance mask annotations and diagnosis labels for four clinical categories (buckle, nondisplaced, displaced, or segmental). The challenge includes two tracks: a detection (instance segmentation) track evaluated by an FROC-style metric and a classification track evaluated by an F1-style metric. During the MICCAI 2020 challenge period, 243 results were evaluated, and seven teams were invited to participate in the challenge summary. The analysis revealed that several top rib fracture detection solutions achieved performance comparable or even better than human experts. Nevertheless, the current rib fracture classification solutions are hardly clinically applicable, which can be an interesting area in the future. As an active benchmark and research resource, the data and online evaluation of the RibFrac Challenge are available at the challenge website (https://ribfrac. grand-challenge.org/). In addition, we further analyzed the impact of two post-challenge advancements—largescale pretraining and rib segmentation—based on our internal baseline for rib fracture detection. These findings lay a foundation for future research and development in AI-assisted rib fracture diagnosis.

The KCNK4 gene, predominantly distributed in neurons, plays an essential role in controlling the resting membrane potential and regulating cellular excitability. Previously, only two variants were identified to be associated with human disease, facial dysmorphism, hypertrichosis, epilepsy, intellectual/developmental delay, and gingival overgrowth (FHEIG) syndrome. In this study, we performed trio-based whole exon sequencing (WES) in a cohort of patients with epilepsy. Two de novo likely pathogenic variants were identified in two unrelated cases with heterogeneous phenotypes, including one with Rolandic epilepsy and one with the FHEIG syndrome. The two variants were predicted to be damaged by the majority of in silico algorithms. These variants showed no allele frequencies in controls and presented statistically higher frequencies in the case cohort than that in controls. The FHEIG syndrome-related variants were all located in the region with vital functions in stabilizing the conductive conformation, while the Rolandic epilepsy-related variant was distributed in the area with less impact on the conductive conformation. This study expanded the genetic and phenotypic spectrum of KCNK4. Phenotypic variations of KCNK4 are potentially associated with the molecular sub-regional effects. Carbamazepine/oxcarbazepine and valproate may be effective antiepileptic drugs for patients with KCNK4 variants.