Can natural language processing help differentiate inflammatory intestinal diseases in China? Models applying random forest and convolutional neural network approaches

Background Differentiating between ulcerative colitis (UC), Crohn’s disease (CD) and intestinal tuberculosis (ITB) is challenging under endoscopy. We aimed to realise automatic differential diagnosis among these diseases through machine learning algorithms. Methods A total of 6399 consecutive patients (5128 UC, 875 CD and 396 ITB) who had taken colonoscopy examinations in Peking Union Medical College Hospital from January 2008 to November 2018 was enrolled. The input was the description of the endoscopic image in the form of free-text. Word segmentation and key word infiltration were conducted as data pre-processing. Random forest (RF) and convolutional neural network (CNN) were applied to different disease entities. Three two-class classifiers (UC and CD, UC and ITB, CD and ITB) and a three-class classifier (UC, CD and ITB) were built. Sensitivity/specificity and precision/recall were applied to evaluate the performance of two-class classifiers and the three-class classifier, respectively. Results The classifiers built in this research were well-performed and the CNN had a better performance in general. The RF sensitivities/specificities of UC-CD, UC-ITB and CD-ITB were 0.89/0.84, 0.83/0.82 and 0.72/0.77, while the CNN of CD-ITB was 0.90/0.77. The precision/recall of UC-CD-ITB was 0.97/0.97, 0.65/0.53 and 0.68/0.76 by RF, respectively, and 0.99/0.97,0.87/0.83 and 0.52/0.81 by CNN, respectively. Conclusion Classifiers built by RF and CNN had an excellent performance when classifying UC with CD or ITB. For the differentiation of CD and ITB, high specificity and sensitivity were reached as well. Artificial intelligence through machine learning is very promising in helping unexperienced endoscopists differentiate inflammatory intestinal diseases.

<p><strong>Potential of Sentinel-1 and Sentinel-2 data for Mapping Irrigated areas at plot scale</strong></p><p>Hassan Bazzi <sup>1</sup>, Nicolas Baghdadi <sup>1</sup>, Dino Ienco <sup>1</sup>, Mehrez Zribi <sup>2</sup>, Hatem Belhouchette <sup>3</sup></p><p>Irrigation plays a significant role in agricultural production in order to meet the global food requirement under changing climatic conditions. To fulfill the high demand for food with an ever-increasing global population, better planning of irrigation is required. Therefore, more focus is being set on the assessment of irrigation performance for improving water management in order to achieve higher water productivity and increase agricultural water sustainability.</p><p>In the context of mapping irrigated areas, we propose an innovative approach to map irrigated areas using Sentinel-1 (S1) SAR (Synthetic Aperture Radar) and Sentinel-2 (S2) optical time series. Our proposed approach is based on the use of S1 and/or S2 time series combined with statistical and mathematical functions such as principal component analysis (PCA) and wavelet transformation (WT). The proposed approach was tested over the Catalonia region, Spain with a dataset containing 126 000 irrigated and 67 000 non-irrigated plots. The novelty of our study resides in eliminating the ambiguity between irrigation and rainfall by comparing between the SAR backscattering signal of each plot and that of the corresponding grid (10 km × 10 km). The potential of S2 images to classify irrigated areas by means of NDVI time series was also investigated in this study. Random forest (RF) and convolutional neural network (CNN) approaches were used to build up classification models using the PCA or WT parameters in three different scenarios: The first using only S1 data, the second using only S2 data, and the third using both S1 and S2 data.</p><p>The RF classifiers built using the PCA or WT on the S1 time series perform well in mapping irrigated areas with an accuracy of 90.7% and 89.1% respectively. However, the CNN classification on the S1 temporal series produces a significant overall accuracy of 94.1%. The overall accuracy obtained using the NDVI time series in RF classifier reached 89.5% while that in the CNN reached 91.6%. Finally, the combined use of the SAR and optical data enhanced the accuracy of the RF classification but did not significantly change the overall accuracy of the CNN model.</p>

Object detection is one of the important techniques in the field of computer vision and image processing. In this study, a validation and evaluation analysis of the object detection model of ginger variants using the YOLOv5 algorithm with a Convolutional Neural Network (CNN) approach was carried out. The dataset used consists of various ginger variants taken from several sources. The dataset is divided into two parts, namely the training data and the testing data. Model training is carried out on the training data using the YOLOv5 algorithm with a CNN approach. Testing is carried out on the testing data to measure the model's performance in detecting ginger variants. The analysis results showed that the object detection model of ginger variants using the YOLOv5 algorithm with a CNN approach can provide quite accurate results with a detection accuracy rate of 93,9%, So, the detection of ginger variants can be a useful recommendation as a means of varieties authenticity verification utilizing diverse ginger variants. However, there were several challenges faced in processing the dataset, such as variations in lighting and different angles of image capture. Therefore, this study provides recommendations for improving the dataset and optimizing parameter settings to improve the performance of the object detection model of ginger variants using the YOLOv5 algorithm with a CNN approach.

Estimating ground-level PM2.5 using micro-satellite images by a convolutional neural network and random forest approach

Background: Genes expression is high dimensional data, so it is very difficult to classify high dimensional data through traditional machine learning approaches. In this work we have proposed a model based on combined approach of Convolutional Neural Network and Recurrent Neural Network, both belong to deep learning model. The prediction has shown improved result than other machine learning algorithms. Expressions are generated through histone modification. Methods: To improve the accuracy deep learning model is proposed i.e. based on Convolutional and Recurrent neural network. This proposed model uses filter, causal convolutional layers and Residual Block for predictions. Results: In this work we have implemented the machine learning algorithms and deep learning algorithms like Logistic Regression, SVM, CNN, Deep Chrome and the proposed Temporal Neural Network. The performance is measured on the basis of parameters like accuracy, precision and AUC on the training and testing set. Conclusion: The proposed Temporal Neural Network model has shown better performance than other machine learning and deep learning algorithms. Due to this proposed deep learning algorithm can be successfully applied on the genes expression dataset.

Introduction: Differentiating intestinal luminal tuberculosis from Crohn’s disease (CD) is an important clinical challenge of considerable therapeutic significance. Likewise differentiating ulcerative colitis from Crohn’s disease with colonic or ileocolonic involvement is difficult. The aim of this study was to investigate the clinical, endoscopic, radiologic and histological features that will help to differentiate Crohn’s disease from intestinal luminal tuberculosis as well as from ulcerative colitis. Methods: A total of 40 patients diagnosed with Crohn’s disease, Intestinal luminal TB and Ulcerative colitis who were admitted under the Gastroenterology Department TUTH from July 2017 to February 2018 were included in this retrospective study. Clinical, endoscopic, radiologic, histopathologic and microbiologic features as well as response to treatment of these patients were studied in detail. Results: Among 40 patients, Intestinal TB was diagnosed in 52.5% patients, ulcerative colitis in 32.5% patients and Crohn’s disease in 15% patients. There was a higher incidence of fever, night sweats, lung involvement and ascites in Intestinal TB whereas diarrhea, perianal disease, hematochezia and extraintestinal were predictive for Crohn’s disease. Similarly on colonoscopy involvement of IC valve, patulous IC valve and transverse ulcers favored a diagnosis of intestinal TB in contrast to Crohn’s disease where longitudinal ulcers, aphthous ulcers, cobblestone appearance and rectal involvement were seen. Similarly the diagnosis of Ulcerative colitis was favored by rectal involvement and contiguous involvement whereas patients with Crohn’s disease had significantly more deep ulcers, cobblestoning, skip areas and ileal involvement. Conclusions: Crohn’s disease must be differentiated from Intestinal luminal TB and Ulcerative colitis before treatment. According to our study, a combination of clinical, endoscopic, serologic, radiologic, histopathologic and microbiologic features can be utilized in order to reliably predict and distinguish Crohn’s disease from Intestinal luminal TB and from Ulcerative colitis. In complicated cases deep enteroscopy and surgery may be needed before a confident diagnosis is reached.

A convolutional neural network (CNN) approach to recognition of buried explosive hazards in forward-looking long-wave infrared (FL-LWIR) imagery is presented. The convolutional filters in the first layer of the network are learned in the frequency domain, making enforcement of zero-phase and zero-dc response characteristics much easier. The spatial domain representations of the filters are forced to have unit l2 norm, and penalty terms are added to the online gradient descent update to encourage orthonormality among the convolutional filters, as well smooth first and second order derivatives in the spatial domain. The impact of these modifications on the generalization performance of the CNN model is investigated. The CNN approach is compared to a second recognition algorithm utilizing shearlet and log-gabor decomposition of the image coupled with cell-structured feature extraction and support vector machine classification. Results are presented for multiple FL-LWIR data sets recently collected from US Army test sites. These data sets include vehicle position information allowing accurate transformation between image and world coordinates and realistic evaluation of detection and false alarm rates.

Delimiting species boundaries is a major goal in evolutionary biology. An increasing volume of literature has focused on the challenges of investigating cryptic diversity within complex evolutionary scenarios of speciation, including gene flow and demographic fluctuations. New methods based on model selection, such as approximate Bayesian computation, approximate likelihoods, and machine learning are promising tools arising in this field. Here, we introduce a framework for species delimitation using the multispecies coalescent model coupled with a deep learning algorithm based on convolutional neural networks (CNNs). We compared this strategy with a similar ABC approach. We applied both methods to test species boundary hypotheses based on current and previous taxonomic delimitations as well as genetic data (sequences from 41loci) in Pilosocereus aurisetus, a cactus species complex with a sky-island distribution and taxonomic uncertainty. To validate our method, we also applied the same strategy on data from widely accepted species from the genus Drosophila. The results show that our CNN approach has a high capacity to distinguish among the simulated species delimitation scenarios, with higher accuracy than ABC. For the cactus data set, a splitter hypothesis without gene flow showed the highest probability in both CNN and ABC approaches, a result agreeing with previous taxonomic classifications and in line with the sky-island distribution and low dispersal of P.aurisetus. Our results highlight the cryptic diversity within the P.aurisetus complex and show that CNNs are a promising approach for distinguishing complex evolutionary histories, even outperforming the accuracy of other model-based approaches such as ABC.

Studying the motion of some roundworms types such as Caenorhabditis elegans (CE) is important to identify the actions and reactions and their effects of worm’s life. In this study, the time series of CE motion represented by the angles of wave-motion between 1 to 177 degrees will be the case study. Each observation of this time series is a recorded frame (0.5 second) of 2.5 hours video of CE motion. A convolutional neural network (CNN) as one of deep learning techniques will be used to classify CE motion as dependent variable in binary cases based on the images of the angles of wave-motion as explanatory variable. The images of motion angles are imagined and designed by two dimensions image corresponding to every observation. These images combined into 4-d image (four dimensions matrix) to represent univariate explanatory variable. Support vector machine (SVM) will be also used to classify the angles of CE. In these types of data, the nonlinearity and uncertainty will be the most probably problems as reasons for in accurate classifications. CNN and SVM used with this type of dataset to improve the classification results. The results of comparisons explain that CNN approach outperforms SVM absolutely. In conclusion, CNN approach can be used to classify this type of time series with accurate results.

As an application of EEG, Motor Imagery based Brain-Computer Interface (MI BCI) plays a significant role in assisting patients with disability to communicate with their environment. MI BCI could now be realized through various methods such as machine learning. Many attempts using different machine learning approaches as MI BCI applications have been done with every one of them yielding various results. While some attempts managed to achieve agreeable results, some still failed. This failure may be caused by the separation of the feature extraction and classification steps, as this may lead to the loss of information which in turn causes lower classification accuracy. This problem can be solved by integrating feature extraction and classification by harnessing a classification algorithm that processed the input data as a whole until it produces the prediction, hence the use of convolutional neural network (CNN) approach which is known for its versatility in processing and classifying data all in one go. In this study, the CNN exploration involved a task to classify 5 different classes of fingers’ imaginary movement (thumb, index, middle, ring, and pinky) based on the processed raw signal provided. The CNN performance was observed for both non-augmented and augmented data with the data augmentation techniques used include sliding window, noise addition, and the combination of those two methods. From these experiments, the results show that the CNN model managed to achieve an averaged accuracy of 47%, meanwhile with the help of augmentation techniques of sliding window, noise addition, and the combined methods, the model achieved even higher averaged accuracy of 57,1%, 47,2%, and 57,5% respectively.

The KITSUNE satellite is a 6-unit CubeSat platform with the main mission of 5-m-class Earth observation in low Earth orbit (LEO), and the payload is developed with a 31.4 MP commercial off-the-shelf sensor, customized optics, and a camera controller board. Even though the payload is designed for Earth observation and to capture man-made patterns on the ground as the main mission, a secondary mission is planned for the classification of wildfire images by the convolution neural network (CNN) approach. Therefore, KITSUNE will be the first CubeSat to employ CNN to classify wildfire images in LEO. In this study, a deep-learning approach is utilized onboard the satellite in order to reduce the downlink data by pre-processing instead of the traditional method of performing the image processing at the ground station. The pre-trained CNN models generated in Colab are saved in RPi CM3+, in which, an uplink command will execute the image classification algorithm and append the results on the captured image data. The on-ground testing indicated that it could achieve an overall accuracy of 98% and an F1 score of a 97% success rate in classifying the wildfire events running on the satellite system using the MiniVGGNet network. Meanwhile, the LeNet and ShallowNet models were also compared and implemented on the CubeSat with 95% and 92% F1 scores, respectively. Overall, this study demonstrated the capability of small satellites to perform CNN onboard in orbit. Finally, the KITSUNE satellite is deployed from ISS on March 2022.

Mapping irrigated plots is essential for better water resource management. Today, the free and open access Sentinel-1 (S1) and Sentinel-2 (S2) data with high revisit time offers a powerful tool for irrigation mapping at plot scale. Up to date, few studies have used S1 and S2 data to provide approaches for mapping irrigated plots. This study proposes a method to map irrigated plots using S1 SAR (synthetic aperture radar) time series. First, a dense temporal series of S1 backscattering coefficients were obtained at plot scale in VV (Vertical-Vertical) and VH (Vertical-Horizontal) polarizations over a study site located in Catalonia, Spain. In order to remove the ambiguity between rainfall and irrigation events, the S1 signal obtained at plot scale was used conjointly to S1 signal obtained at a grid scale (10 km × 10 km). Later, two mathematical transformations, including the principal component analysis (PCA) and the wavelet transformation (WT), were applied to the several SAR temporal series obtained in both VV and VH polarization. Irrigated areas were then classified using the principal component (PC) dimensions and the WT coefficients in two different random forest (RF) classifiers. Another classification approach using one dimensional convolutional neural network (CNN) was also performed on the obtained S1 temporal series. The results derived from the RF classifiers with S1 data show high overall accuracy using the PC values (90.7%) and the WT coefficients (89.1%). By applying the CNN approach on SAR data, a significant overall accuracy of 94.1% was obtained. The potential of optical images to map irrigated areas by the mean of a normalized differential vegetation index (NDVI) temporal series was also tested in this study in both the RF and the CNN approaches. The overall accuracy obtained using the NDVI in RF classifier reached 89.5% while that in the CNN reached 91.6%. The combined use of optical and radar data slightly enhanced the classification in the RF classifier but did not significantly change the accuracy obtained in the CNN approach using S1 data.

For accurate weed disease classification, this paper presents a novel hybrid model that combines Random Forest (RF) and Convolutional Neural Network (CNN) approaches. The model, which cleverly combines the unique strengths of CNN and RF, is carefully tested and produces impressive results on a range of performance criteria. With spectacular accuracy percentages ranging from 86.20% to 94.29%, the CNN-RF hybrid model that is shown is very proficient in reducing false positives while maintaining elevated precision. Meanwhile, recall rates, which range from 84.31% to 94.06%, highlight the model’s strong capacity to correctly detect occurrences of the desired weed classifications, hence reducing the likelihood of false negatives. The balanced F1 scores, which range from 88.28% to 94.17%, support the model’s sophisticated performance and overall accuracy even further. Support values are real-world examples of each weed class, indicating a large dataset that is essential to the model’s thorough training and analysis. The algorithm demonstrates its ability to make accurate predictions over the whole range of cannabis classes, with an overall accuracy ranging from an astonishing 97% to 99%. The suggested CNN-RF hybrid model shows great promise for agricultural diagnostics as an extremely effective tool for classifying weed diseases.

Predicting lithology from seismic attribute data plays an important role in characterizing subsurface properties, including stratigraphy, sedimentary facies, and hydrocarbon potential, particularly in areas with limited well data. One of the main challenges in seismic interpretation arises from the limited resolution, which hinders the ability to detect thin and geologically complex layers. To overcome these limitations, machine learning (ML)-driven approaches offer a robust methodology for establishing correlations between seismic attributes and lithological variations, using well data as a reference. In this study, advanced ML algorithms are employed to identify complex trends in seismic data and their relationships with lithology distribution. The proposed approach was tested on 3D seismic data from the “TGF” Field in the North Kalimantan Basin. The methodologies applied include convolutional neural networks (CNN), random forest (RF), and K-nearest neighbors (KNN). Seismic datasets were transformed into multiple attributes such as RMS amplitude, chaos, envelope, gradient magnitude, sweetness, instantaneous frequency, dominant frequency, instantaneous bandwidth, and instantaneous quality which were subsequently utilized as inputs for gamma ray and lithology prediction. To enhance frequency information, the Continuous Wavelet Transform (CWT) was implemented to derive a time–frequency representation as CNN input. While RF and KNN estimate lithology by analysing statistical relationships between the attributes, CNN evaluates image-based trends across a range of seismic frequency data. The findings demonstrate that the CNN approach with CWT methods can be predicted lithology however with limitations data get overfitting result. Random forest has achieved the highest R2 score 0.84 with lowest MAE 3.15 lowest error rates based on established evaluation metrics. CNN reveals higher sensitivity detect pattern frequency CWT compared to RF and KNN as a result of its effectiveness in modelling detailed spatial dependencies present in seismic images.

ObjectivesCrohn’s disease (CD), ulcerative colitis (UC), intestinal Behçet’s disease (BD), intestinal tuberculosis (ITB), and primary intestinal lymphoma (PIL) are major intestinal disorders that frequently present with mucosal ulceration. Accurate differentiation among these conditions is challenging due to overlapping clinical, endoscopic, and imaging characteristics. Accordingly, this study aimed to develop an artificial intelligence (AI)-assisted endoscopic diagnostic system to accurately identify these five diseases.MethodsThis multicenter prospective study used endoscopic images from patients diagnosed with pathologically confirmed CD, UC, BD, ITB, and PIL to develop an AI system that uses convolutional neural networks (CNNs) and transformer architectures. It was validated across multiple centers compared with endoscopist performance, and assessed prospectively. In addition, clinical data were integrated to construct a comprehensive diagnostic model.ResultsInternal validation revealed that the AI system achieved an accuracy of 96.8%, with sensitivities for the five ulcerative diseases ranging from 76.9% to 97.8%. In the multicenter test (Test A + Test B3), diagnostic accuracy reached 83.4%, outperforming endoscopists. Prospective evaluation revealed that AI system demonstrated significantly higher accuracy than senior endoscopists (83.4% versus 59.4%, P < 0.001). Moreover, the optimal comprehensive model, which combined clinical and endoscopic data, achieved an accuracy of 76.3%.ConclusionsAn AI-assisted endoscopic diagnostic system that accurately differentiates CD, UC, BD, ITB, and PIL was developed, which may contribute to improving diagnostic precision for colorectal ulcerative diseases.Supplementary InformationThe online version contains supplementary material available at 10.1007/s00384-025-05029-y.