Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Radiology Radiology

An easy-to-use artificial intelligence preoperative lymph node metastasis predictor (LN-MASTER) in rectal cancer based on a privacy-preserving computing platform: multicenter retrospective cohort study.

In International journal of surgery (London, England)

BACKGROUND : Although the surgical treatment strategy for rectal cancer (RC) is usually based on the preoperative diagnosis of lymph node metastasis (LNM), the accurate diagnosis of LNM has been a clinical challenge. In this study, we developed machine learning (ML) models to predict the LNM status before surgery based on a privacy-preserving computing platform (PPCP) and created a web tool to help clinicians with treatment-based decision-making in RC patients.

PATIENTS AND METHODS : A total of 6578 RC patients were enrolled in this study. ML models, including logistic regression, support vector machine, extreme gradient boosting (XGB), and random forest, were used to establish the prediction models. The areas under the receiver operating characteristic curves (AUCs) were calculated to compare the accuracy of the ML models with the US guidelines and clinical diagnosis of LNM. Last, model establishment and validation were performed in the PPCP without the exchange of raw data among different institutions.

RESULTS : LNM was detected in 1006 (35.3%), 252 (35.3%), 581 (32.9%), and 342 (27.4%) RC patients in the training, test, and external validation sets 1 and 2, respectively. The XGB model identified the optimal model with an AUC of 0.84 [95% confidence interval (CI), 0.83-0.86] compared with the logistic regression model (AUC, 0.76; 95% CI, 0.74-0.78), random forest model (AUC, 0.82; 95% CI, 0.81-0.84), and support vector machine model (AUC, 0.79; 95% CI, 0.78-0.81). Furthermore, the XGB model showed higher accuracy than the predictive factors of the US guidelines and clinical diagnosis. The predictive XGB model was embedded in a web tool (named LN-MASTER) to predict the LNM status for RC.

CONCLUSION : The proposed easy-to-use model showed good performance for LNM prediction, and the web tool can help clinicians make treatment-based decisions for patients with RC. Furthermore, PPCP enables state-of-the-art model development despite the limited local data availability.

Guan Xu, Yu Guanyu, Zhang Weiyuan, Wen Rongbo, Wei Ran, Jiao Shuai, Zhao Qing, Lou Zheng, Hao Liqiang, Liu Enrui, Gao Xianhua, Wang Guiyu, Zhang Wei, Wang Xishan

2023-Mar-17

General General

Anomaly detection using spatial and temporal information in multivariate time series.

In Scientific reports ; h5-index 158.0

Real-world industrial systems contain a large number of interconnected sensors that generate a significant amount of time series data during system operation. Performing anomaly detection on these multivariate time series data can timely find faults, prevent malicious attacks, and ensure these systems safe and reliable operation. However, the rarity of abnormal instances leads to a lack of labeled data, so the supervised machine learning methods are not applicable. Furthermore, most current techniques do not take full advantage of the spatial and temporal dependencies implied among multiple variables to detect anomalies. Hence, we propose STADN, a novel Anomaly Detection Network Using Spatial and Temporal Information. STADN models the relationship graph between variables for a graph attention network to capture the spatial dependency between variables and utilizes a long short-term memory network to mine the temporal dependency of time series to fully use the spatial and temporal information of multivariate time series. STADN predicts the future behavior of each sensor by combining the historical behavior of the sensor and its neighbors, then detects and locates anomalies according to the prediction error. Furthermore, we improve the proposed model's ability to discriminate anomaly and regularity and expand the prediction error gap between normal and abnormal instances by reconstructing the prediction errors. We conduct experiments on two real-world datasets, and the experimental results suggested that STADN achieves state-of-the-art outperformance.

Tian Zhiwen, Zhuo Ming, Liu Leyuan, Chen Junyi, Zhou Shijie

2023-Mar-16

Surgery Surgery

MDU-Net: multi-scale densely connected U-Net for biomedical image segmentation.

In Health information science and systems

Biomedical image segmentation plays a central role in quantitative analysis, clinical diagnosis, and medical intervention. In the light of the fully convolutional networks (FCN) and U-Net, deep convolutional networks (DNNs) have made significant contributions to biomedical image segmentation applications. In this paper, we propose three different multi-scale dense connections (MDC) for the encoder, the decoder of U-shaped architectures, and across them. Based on three dense connections, we propose a multi-scale densely connected U-Net (MDU-Net) for biomedical image segmentation. MDU-Net directly fuses the neighboring feature maps with different scales from both higher layers and lower layers to strengthen feature propagation in the current layer. Multi-scale dense connections, which contain shorter connections between layers close to the input and output, also make a much deeper U-Net possible. Besides, we introduce quantization to alleviate the potential overfitting in dense connections, and further improve the segmentation performance. We evaluate our proposed model on the MICCAI 2015 Gland Segmentation (GlaS) dataset. The three MDC improve U-Net performance by up to 1.8% on test A and 3.5% on test B in the MICCAI Gland dataset. Meanwhile, the MDU-Net with quantization obviously improves the segmentation performance of original U-Net.

Zhang Jiawei, Zhang Yanchun, Jin Yuzhen, Xu Jilan, Xu Xiaowei

2023-Dec

Deep learning, Image segmentation, Medical image analysis, Multi-scale feature

General General

Artificial intelligence-based optimization for chitosan nanoparticles biosynthesis, characterization and in‑vitro assessment of its anti-biofilm potentiality.

In Scientific reports ; h5-index 158.0

Chitosan nanoparticles (CNPs) are promising biopolymeric nanoparticles with excellent physicochemical, antimicrobial, and biological properties. CNPs have a wide range of applications due to their unique characteristics, including plant growth promotion and protection, drug delivery, antimicrobials, and encapsulation. The current study describes an alternative, biologically-based strategy for CNPs biosynthesis using Olea europaea leaves extract. Face centered central composite design (FCCCD), with 50 experiments was used for optimization of CNPs biosynthesis. The artificial neural network (ANN) was employed for analyzing, validating, and predicting CNPs biosynthesis using Olea europaea leaves extract. Using the desirability function, the optimum conditions for maximum CNPs biosynthesis were determined theoretically and verified experimentally. The highest experimental yield of CNPs (21.15 mg CNPs/mL) was obtained using chitosan solution of 1%, leaves extract solution of 100%, initial pH 4.47, and incubation time of 60 min at 53.83°C. The SEM and TEM images revealed that CNPs had a spherical form and varied in size between 6.91 and 11.14 nm. X-ray diffraction demonstrates the crystalline nature of CNPs. The surface of the CNPs is positively charged, having a Zeta potential of 33.1 mV. FTIR analysis revealed various functional groups including C-H, C-O, CONH2, NH2, C-OH and C-O-C. The thermogravimetric investigation indicated that CNPs are thermally stable. The CNPs were able to suppress biofilm formation by P. aeruginosa, S. aureus and C. albicans at concentrations ranging from 10 to 1500 µg/mL in a dose-dependent manner. Inhibition of biofilm formation was associated with suppression of metabolic activity, protein/exopolysaccharide moieties, and hydrophobicity of biofilm encased cells (r ˃ 0.9, P = 0.00). Due to their small size, in the range of 6.91 to 11.14 nm, CNPs produced using Olea europaea leaves extract are promising for applications in the medical and pharmaceutical industries, in addition to their potential application in controlling multidrug-resistant microorganisms, especially those associated with post COVID-19 pneumonia in immunosuppressed patients.

El-Naggar Noura El-Ahmady, Dalal Shimaa R, Zweil Amal M, Eltarahony Marwa

2023-Mar-16

Radiology Radiology

What Does DALL-E 2 Know About Radiology?

In Journal of medical Internet research ; h5-index 88.0

Generative models, such as DALL-E 2 (OpenAI), could represent promising future tools for image generation, augmentation, and manipulation for artificial intelligence research in radiology, provided that these models have sufficient medical domain knowledge. Herein, we show that DALL-E 2 has learned relevant representations of x-ray images, with promising capabilities in terms of zero-shot text-to-image generation of new images, the continuation of an image beyond its original boundaries, and the removal of elements; however, its capabilities for the generation of images with pathological abnormalities (eg, tumors, fractures, and inflammation) or computed tomography, magnetic resonance imaging, or ultrasound images are still limited. The use of generative models for augmenting and generating radiological data thus seems feasible, even if the further fine-tuning and adaptation of these models to their respective domains are required first.

Adams Lisa C, Busch Felix, Truhn Daniel, Makowski Marcus R, Aerts Hugo J W L, Bressem Keno K

2023-Mar-16

DALL-E, artificial intelligence, creating images from text, diagnostic imaging, generative model, image creation, image generation, machine learning, medical imaging, radiology, text-to-image, transformer language model, x-ray

General General

Unsupervised encoding selection through ensemble pruning for biomedical classification.

In BioData mining

BACKGROUND : Owing to the rising levels of multi-resistant pathogens, antimicrobial peptides, an alternative strategy to classic antibiotics, got more attention. A crucial part is thereby the costly identification and validation. With the ever-growing amount of annotated peptides, researchers leverage artificial intelligence to circumvent the cumbersome, wet-lab-based identification and automate the detection of promising candidates. However, the prediction of a peptide's function is not limited to antimicrobial efficiency. To date, multiple studies successfully classified additional properties, e.g., antiviral or cell-penetrating effects. In this light, ensemble classifiers are employed aiming to further improve the prediction. Although we recently presented a workflow to significantly diminish the initial encoding choice, an entire unsupervised encoding selection, considering various machine learning models, is still lacking.

RESULTS : We developed a workflow, automatically selecting encodings and generating classifier ensembles by employing sophisticated pruning methods. We observed that the Pareto frontier pruning is a good method to create encoding ensembles for the datasets at hand. In addition, encodings combined with the Decision Tree classifier as the base model are often superior. However, our results also demonstrate that none of the ensemble building techniques is outstanding for all datasets.

CONCLUSION : The workflow conducts multiple pruning methods to evaluate ensemble classifiers composed from a wide range of peptide encodings and base models. Consequently, researchers can use the workflow for unsupervised encoding selection and ensemble creation. Ultimately, the extensible workflow can be used as a plugin for the PEPTIDE REACToR, further establishing it as a versatile tool in the domain.

Spänig Sebastian, Michel Alexander, Heider Dominik

2023-Mar-16

Antimicrobial peptides, Biomedical classification, Encodings, Ensemble learning, Machine learning