Immune checkpoint antibodies that augment the programmed cell death protein 1 (PD-1)/PD-L1 pathway have demonstrated antitumor activity across multiple malignancies, and gained recent regulatory ...approval as single-agent therapy for the treatment of metastatic malignant melanoma and nonsmall-cell lung cancer. Knowledge of toxicities associated with PD-1/PD-L1 blockade, as well as effective management algorithms for these toxicities, is pivotal in order to optimize clinical efficacy and safety. In this article, we review selected published and presented clinical studies investigating single-agent anti-PD-1/PD-L1 therapy and trials of combination approaches with other standard anticancer therapies, in multiple tumor types. We summarize the key adverse events reported in these studies and their management algorithms.
This paper presents a new 3D point cloud classification benchmark data set with over four billion manually labelled points, meant as input for data-hungry (deep) learning methods. We also discuss ...first submissions to the benchmark that use deep convolutional neural networks (CNNs) as a work horse, which already show remarkable performance improvements over state-of-the-art. CNNs have become the de-facto standard for many tasks in computer vision and machine learning like semantic segmentation or object detection in images, but have no yet led to a true breakthrough for 3D point cloud labelling tasks due to lack of training data. With the massive data set presented in this paper, we aim at closing this data gap to help unleash the full potential of deep learning methods for 3D labelling tasks. Our semantic3D.net data set consists of dense point clouds acquired with static terrestrial laser scanners. It contains 8 semantic classes and covers a wide range of urban outdoor scenes: churches, streets, railroad tracks, squares, villages, soccer fields and castles. We describe our labelling interface and show that our data set provides more dense and complete point clouds with much higher overall number of labelled points compared to those already available to the research community. We further provide baseline method descriptions and comparison between methods submitted to our online system. We hope semantic3D.net will pave the way for deep learning methods in 3D point cloud labelling to learn richer, more general 3D representations, and first submissions after only a few months indicate that this might indeed be the case.
This paper describes a deep learning approach to semantic segmentation of very high resolution (aerial) images. Deep neural architectures hold the promise of end-to-end learning from raw images, ...making heuristic feature design obsolete. Over the last decade this idea has seen a revival, and in recent years deep convolutional neural networks (CNNs) have emerged as the method of choice for a range of image interpretation tasks like visual recognition and object detection. Still, standard CNNs do not lend themselves to per-pixel semantic segmentation, mainly because one of their fundamental principles is to gradually aggregate information over larger and larger image regions, making it hard to disentangle contributions from different pixels. Very recently two extensions of the CNN framework have made it possible to trace the semantic information back to a precise pixel position: deconvolutional network layers undo the spatial downsampling, and Fully Convolution Networks (FCNs) modify the fully connected classification layers of the network in such a way that the location of individual activations remains explicit. We design a FCN which takes as input intensity and range data and, with the help of aggressive deconvolution and recycling of early network layers, converts them into a pixelwise classification at full resolution. We discuss design choices and intricacies of such a network, and demonstrate that an ensemble of several networks achieves excellent results on challenging data such as the ISPRS semantic labeling benchmark, using only the raw data as input.
We present a novel approach for multi-object tracking which considers object detection and spacetime trajectory estimation as a coupled optimization problem. Our approach is formulated in a minimum ...description length hypothesis selection framework, which allows our system to recover from mismatches and temporarily lost tracks. Building upon a state-of-the-art object detector, it performs multiview/multicategory object recognition to detect cars and pedestrians in the input images. The 2D object detections are checked for their consistency with (automatically estimated) scene geometry and are converted to 3D observations which are accumulated in a world coordinate frame. A subsequent trajectory estimation module analyzes the resulting 3D observations to find physically plausible spacetime trajectories. Tracking is achieved by performing model selection after every frame. At each time instant, our approach searches for the globally optimal set of spacetime trajectories which provides the best explanation for the current image and for all evidence collected so far while satisfying the constraints that no two objects may occupy the same physical space nor explain the same image pixels at any point in time. Successful trajectory hypotheses are then fed back to guide object detection in future frames. The optimization procedure is kept efficient through incremental computation and conservative hypothesis pruning. We evaluate our approach on several challenging video sequences and demonstrate its performance on both a surveillance-type scenario and a scenario where the input videos are taken from inside a moving vehicle passing through crowded city areas.
Surgery is a valuable option for pharmacologically intractable epilepsy. However, significant post-operative improvements are not always attained. This is due in part to our incomplete understanding ...of the seizure generating (ictogenic) capabilities of brain networks. Here we introduce an in silico, model-based framework to study the effects of surgery within ictogenic brain networks. We find that factors conventionally determining the region of tissue to resect, such as the location of focal brain lesions or the presence of epileptiform rhythms, do not necessarily predict the best resection strategy. We validate our framework by analysing electrocorticogram (ECoG) recordings from patients who have undergone epilepsy surgery. We find that when post-operative outcome is good, model predictions for optimal strategies align better with the actual surgery undertaken than when post-operative outcome is poor. Crucially, this allows the prediction of optimal surgical strategies and the provision of quantitative prognoses for patients undergoing epilepsy surgery.
Robust Multiperson Tracking from a Mobile Platform Ess, A.; Leibe, B.; Schindler, K. ...
IEEE transactions on pattern analysis and machine intelligence,
10/2009, Letnik:
31, Številka:
10
Journal Article
Recenzirano
Odprti dostop
In this paper, we address the problem of multiperson tracking in busy pedestrian zones using a stereo rig mounted on a mobile platform. The complexity of the problem calls for an integrated solution ...that extracts as much visual information as possible and combines it through cognitive feedback cycles. We propose such an approach, which jointly estimates camera position, stereo depth, object detection, and tracking. The interplay between those components is represented by a graphical model. Since the model has to incorporate object-object interactions and temporal links to past frames, direct inference is intractable. We, therefore, propose a two-stage procedure: for each frame, we first solve a simplified version of the model (disregarding interactions and temporal continuity) to estimate the scene geometry and an overcomplete set of object detections. Conditioned on these results, we then address object interactions, tracking, and prediction in a second step. The approach is experimentally evaluated on several long and difficult video sequences from busy inner-city locations. Our results show that the proposed integration makes it possible to deliver robust tracking performance in scenes of realistic complexity.
Forest fires have devastating effects on biodiversity, climate, and humans. Producing detailed and reliable forest fire susceptibility maps is crucial for disaster management. Data-driven machine ...learning methods can be applied for forest fire susceptibility mapping, and learning data required for this purpose can be obtained from high-resolution satellite imagery along with a fire inventory. In this study, we assessed the performances of Random Forest (RF) and artificial neural network (ANN) classifiers for producing forest fire susceptibility maps of a region in north-east Türkiye covering Trabzon, Gümüşhane, Rize, and Bayburt provinces using freely available Earth observation data and forest inventory provided by the regional directorate. Forest type, EU-DEM v1.1 (25 m), and tree cover density were retrieved from Copernicus Land Monitoring Service. Sentinel-2 images were utilized for calculating spectral indices such as normalized difference vegetation index and modified normalized difference water index to assess surface water and vegetation characteristics. Thus, a total of twelve variables including topographic, anthropogenic, hydrologic, vegetation and land use data were used as input. The RF and ANN illustrated similar prediction performances based on receiver operating characteristics (ROC) area under the curve (AUC) values, which were 0.89 and 0.88, respectively. The RF performed better in terms of overall accuracy and F-1 score. The susceptibility maps with 25 m resolution were also investigated visually. The ANN results predicted higher susceptibility levels and larger areas were found prone to wildfire. Leave-one-out analysis results indicated that elevation was the most influential factor based on the achieved OA.
The problem of multi-target tracking is comprised of two distinct, but tightly coupled challenges: (i) the naturally discrete problem of data association, i.e. assigning image observations to the ...appropriate target; (ii) the naturally continuous problem of trajectory estimation, i.e. recovering the trajectories of all targets. To go beyond simple greedy solutions for data association, recent approaches often perform multi-target tracking using discrete optimization. This has the disadvantage that trajectories need to be pre-computed or represented discretely, thus limiting accuracy. In this paper we instead formulate multi-target tracking as a discrete-continuous optimization problem that handles each aspect in its natural domain and allows leveraging powerful methods for multi-model fitting. Data association is performed using discrete optimization with label costs, yielding near optimality. Trajectory estimation is posed as a continuous fitting problem with a simple closed-form solution, which is used in turn to update the label costs. We demonstrate the accuracy and robustness of our approach with state-of-the-art performance on several standard datasets.
Glacial retreat is changing biogeochemical cycling in the Arctic, where glacial runoff contributes iron for oceanic shelf primary production. We hypothesize that in Svalbard fjords, microbes catalyze ...intense iron and sulfur cycling in low-organic-matter sediments. This is because low organic matter limits sulfide generation, allowing iron mobility to the water column instead of precipitation as iron monosulfides. In this study, we tested this with high-depth-resolution 16S rRNA gene libraries in the upper 20 cm at two sites in Van Keulenfjorden, Svalbard. At the site closer to the glaciers, iron-reducing
, iron-oxidizing
and
, and sulfur-oxidizing
and
were abundant above a 12-cm depth. Below this depth, the relative abundances of sequences for sulfate-reducing
and
increased. At the outer station, the switch from iron-cycling clades to sulfate reducers occurred at shallower depths (∼5 cm), corresponding to higher sulfate reduction rates. Relatively labile organic matter (shown by δ
C and C/N ratios) was more abundant at this outer site, and ordination analysis suggested that this affected microbial community structure in surface sediments. Network analysis revealed more correlations between predicted iron- and sulfur-cycling taxa and with uncultured clades proximal to the glacier. Together, these results suggest that complex microbial communities catalyze redox cycling of iron and sulfur, especially closer to the glacier, where sulfate reduction is limited due to low availability of organic matter. Diminished sulfate reduction in upper sediments enables iron to flux into the overlying water, where it may be transported to the shelf.
Glacial runoff is a key source of iron for primary production in the Arctic. In the fjords of the Svalbard archipelago, glacial retreat is predicted to stimulate phytoplankton blooms that were previously restricted to outer margins. Decreased sediment delivery and enhanced primary production have been hypothesized to alter sediment biogeochemistry, wherein any free reduced iron that could potentially be delivered to the shelf will instead become buried with sulfide generated through microbial sulfate reduction. We support this hypothesis with sequencing data that showed increases in the relative abundance of sulfate reducing taxa and sulfate reduction rates with increasing distance from the glaciers in Van Keulenfjorden, Svalbard. Community structure was driven by organic geochemistry, suggesting that enhanced input of organic material will stimulate sulfate reduction in interior fjord sediments as glaciers continue to recede.