The analysis of Magnetic Resonance Imaging (MRI) sequences enables clinical professionals to monitor the progression of a brain tumor. As the interest for automatizing brain volume MRI analysis ...increases, it becomes convenient to have each sequence well identified. However, the unstandardized naming of MRI sequences makes their identification difficult for automated systems, as well as makes it difficult for researches to generate or use datasets for machine learning research. In the face of that, we propose a system for identifying types of brain MRI sequences based on deep learning. By training a Convolutional Neural Network (CNN) based on 18-layer ResNet architecture, our system can classify a volumetric brain MRI as a FLAIR, T1, T1c or T2 sequence, or whether it does not belong to any of these classes. The network was evaluated on publicly available datasets comprising both, pre-processed (BraTS dataset) and non-pre-processed (TCGA-GBM dataset), image types with diverse acquisition protocols, requiring only a few slices of the volume for training. Our system can classify among sequence types with an accuracy of 96.81%.
One of the main factors that contributed to the large advances in autonomous driving is the advent of deep learning. For safer self-driving vehicles, one of the problems that has yet to be solved ...completely is lane detection. Since methods for this task have to work in real-time (+30 FPS), they not only have to be effective (i.e., have high accuracy) but they also have to be efficient (i.e., fast). In this work, we present a novel method for lane detection that uses as input an image from a forward-looking camera mounted in the vehicle and outputs polynomials representing each lane marking in the image, via deep polynomial regression. The proposed method is shown to be competitive with existing state-of-the-art methods in the TuSimple dataset while maintaining its efficiency (115 FPS). Additionally, extensive qualitative results on two additional public datasets are presented, alongside with limitations in the evaluation metrics used by recent works for lane detection. Finally, we provide source code and trained models that allow others to replicate all the results shown in this paper, which is surprisingly rare in state-of-the-art lane detection methods. The full source code and pretrained models are available at https://github.com/lucastabelini/PolyLaneNet.
Miniaturized paper‐based electrochemical sensors were fabricated using kraft paper and CO2 laser, dispensing the need for chemical reagents and controlled atmospheric conditions. This study initially ...evaluated the paper type and laser processing parameters, enhancing the electrodes′ robustness, electrochemical response, and electrical resistance. The sensors were also treated by applying −1 V for 60 s in 1.0 mol L−1 KCl, which is a simple and rapid procedure. The electrochemical treatment increased the electroactive area and roughness, confirmed by scanning electron microscopy. These aspects helped modulate the sensors′ electrochemical response for nitrite determination, improving selectivity and sensitivity for this compound. The sensors also showed repeatability and batch‐to‐batch reproducibility, with 2.2 and 10 % RSD, respectively. Therefore, this work brings a protocol to fabricating competitive electrochemical sensors through a sustainable strategy, opening possibilities for designing new analytical systems.
Eco‐Friendly Laser‐Pyrolyzed Paper Sensors: A reagent less alternative is reported to produce low‐cost and miniaturized paper‐based electrochemical sensors using a CO2 laser source. The proposed devices were submitted to a simple and rapid electrochemical treatment, which enhanced the analytical performance of the sensors to determine nitrite in environmental and biological samples.
Display omitted
•Low-cost fused deposition modeling 3D-printed device for sampling and detection of TNT.•Graphene-doped polylacic acid (G-PLA) filament to fabricate the 3D-printed device.•Nanograms ...of TNT sampled from metallic, granite and glove surfaces were quantified.•Mechanical polishing of the 3D-printed surface improved the electrochemical properties.•Metal determination on the device was also shown; promising for gunshot residue analysis.
Fused deposition modelling 3D printing of a flexible, conductive, disposable and biodegradable platform using graphene-doped polylactic acid (G-PLA) was demonstrated as an integrated device for sampling and detection of explosives. As a proof-of-concept, traces of 2,4,6-Trinitrotoluene (TNT) impregnated on different surfaces were abrasively sampled using the 3D-printed device and readily assembled in a portable electrochemical cell for rapid square-wave voltammetry scans in the presence of 0.1 mol L–1 HCl electrolyte. Nanogram amounts of TNT sampled from metallic, granite and glove surfaces were detected and quantified using the Faraday equation applied to the voltammetric response of TNT immobilised on the electrode surface. Identification of TNT was possible due to the unique voltammetric behaviour obtained on the G-PLA sensor and efficient sampling due to the rough surface and flexibility of the device. Lead and copper determination by stripping voltammetry was also demonstrated on the same device, highlighting the possibility of detecting gunshot residues. Moreover, we demonstrated that simple mechanical polishing of the 3D-printed surface improved the electrochemical sensing properties of the sensor by exposing graphene nanoribbons within the PLA matrix. Hence, this 3D-printed integrated platform holds promise as a rapid and low-cost approach for on-site crime scene investigations.
The reconstruction of shredded documents consists of coherently arranging fragments of paper (shreds) to recover the original document(s). A great challenge in computational reconstruction is to ...properly evaluate the compatibility between the shreds. While traditional pixel-based approaches are not robust to real shredding, more sophisticated solutions compromise significantly time performance. The solution presented in this work extends our previous deep learning method for single-page reconstruction to a more realistic/complex scenario: the reconstruction of several mixed shredded documents at once. In our approach, the compatibility evaluation is modeled as a two-class (valid or invalid) pattern recognition problem. The model is trained in a self-supervised manner on samples extracted from simulated-shredded documents, which obviates manual annotation. Experimental results on three datasets -- including a new collection of 100 strip-shredded documents produced for this work -- have shown that the proposed method outperforms the competing ones on complex scenarios, achieving accuracy superior to 90%.
Deep learning has been successfully applied to several problems related to autonomous driving. Often, these solutions rely on large networks that require databases of real image samples of the ...problem (i.e., real world) for proper training. The acquisition of such real-world data sets is not always possible in the autonomous driving context, and sometimes their annotation is not feasible (e.g., takes too long or is too expensive). Moreover, in many tasks, there is an intrinsic data imbalance that most learning-based methods struggle to cope with. It turns out that traffic sign detection is a problem in which these three issues are seen altogether. In this work, we propose a novel database generation method that requires only (i) arbitrary natural images, i.e., requires no real image from the domain of interest, and (ii) templates of the traffic signs, i.e., templates synthetically created to illustrate the appearance of the category of a traffic sign. The effortlessly generated training database is shown to be effective for the training of a deep detector (such as Faster R-CNN) on German traffic signs, achieving 95.66% of mAP on average. In addition, the proposed method is able to detect traffic signs with an average precision, recall and F1-score of about 94%, 91% and 93%, respectively. The experiments surprisingly show that detectors can be trained with simple data generation methods and without problem domain data for the background, which is in the opposite direction of the common sense for deep learning.
Deep learning techniques have enabled the emergence of state-of-the-art models to address object detection tasks. However, these techniques are data-driven, delegating the accuracy to the training ...dataset which must resemble the images in the target task. The acquisition of a dataset involves annotating images, an arduous and expensive process, generally requiring time and manual effort. Thus, a challenging scenario arises when the target domain of application has no annotated dataset available, making tasks in such situation to lean on a training dataset of a different domain. Sharing this issue, object detection is a vital task for autonomous vehicles where the large amount of driving scenarios yields several domains of application requiring annotated data for the training process. In this work, a method for training a car detection system with annotated data from a source domain (day images) without requiring the image annotations of the target domain (night images) is presented. For that, a model based on Generative Adversarial Networks (GANs) is explored to enable the generation of an artificial dataset with its respective annotations. The artificial dataset (fake dataset) is created translating images from day-time domain to night-time domain. The fake dataset, which comprises annotated images of only the target domain (night images), is then used to train the car detector model. Experimental results showed that the proposed method achieved significant and consistent improvements, including the increasing by more than 10% of the detection performance when compared to the training with only the available annotated data (i.e., day images).
This study describes the development of a new analytical method for the separation and detection of cocaine (COC) and its adulterants, or cutting agents, using microchip electrophoresis (ME) devices ...coupled with capacitively coupled contactless conductivity detection (C4D). All the experiments were carried out using a glass commercial ME device containing two pairs of integrated sensing electrodes. The running buffer composed of 20 mmol/L amino‐2‐(hydroxymethyl) propane‐1,3‐diol and 10 mmol/L 3,4‐dimethoxycinnamic acid provided the best separation conditions for COC and its adulterants with baseline resolution (R > 1.6), separation efficiencies ranging from (2.9 ± 0.1) to (3.2 ± 0.2) × 105 plates/m, and estimated LOD values between 40 and 150 μmol/L. The quantification of COC was successfully performed in four samples seized by the Brazilian Federal Police Department and all predicted values agree with values estimated by the reference method. Some other interfering species were detected in the seized samples during the screening procedure on ME–C4D devices. While lidocaine was detected in sample 3, the presence of levamisole was observed in samples 2 and 4. However, their concentrations were estimated to be below the LOQ. ME–C4D devices have proved to be quite efficient for the identification and quantification of COC with errors lower than 10% when compared to the data obtained by a reference method. The approach herein reported offers great potential to be used for on‐site COC screening in seized samples.
The reconstruction of shredded documents consists in arranging the pieces of paper (shreds) in order to reassemble the original aspect of such documents. This task is particularly relevant for ...supporting forensic investigation as documents may contain criminal evidence. As an alternative to the laborious and time-consuming manual process, several researchers have been investigating ways to perform automatic digital reconstruction. A central problem in automatic reconstruction of shredded documents is the pairwise compatibility evaluation of the shreds, notably for binary text documents. In this context, deep learning has enabled great progress for accurate reconstructions in the domain of mechanically-shredded documents. A sensitive issue, however, is that current deep model solutions require an inference whenever a pair of shreds has to be evaluated. This work proposes a scalable deep learning approach for measuring pairwise compatibility in which the number of inferences scales linearly (rather than quadratically) with the number of shreds. Instead of predicting compatibility directly, deep models are leveraged to asymmetrically project the raw shred content onto a common metric space in which distance is proportional to the compatibility. Experimental results show that our method has accuracy comparable to the state-of-the-art with a speed-up of about 22 times for a test instance with 505 shreds (20 mixed shredded-pages from different documents).