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

General General

EG-TransUNet: a transformer-based U-Net with enhanced and guided models for biomedical image segmentation.

In BMC bioinformatics

Although various methods based on convolutional neural networks have improved the performance of biomedical image segmentation to meet the precision requirements of medical imaging segmentation task, medical image segmentation methods based on deep learning still need to solve the following problems: (1) Difficulty in extracting the discriminative feature of the lesion region in medical images during the encoding process due to variable sizes and shapes; (2) difficulty in fusing spatial and semantic information of the lesion region effectively during the decoding process due to redundant information and the semantic gap. In this paper, we used the attention-based Transformer during the encoder and decoder stages to improve feature discrimination at the level of spatial detail and semantic location by its multihead-based self-attention. In conclusion, we propose an architecture called EG-TransUNet, including three modules improved by a transformer: progressive enhancement module, channel spatial attention, and semantic guidance attention. The proposed EG-TransUNet architecture allowed us to capture object variabilities with improved results on different biomedical datasets. EG-TransUNet outperformed other methods on two popular colonoscopy datasets (Kvasir-SEG and CVC-ClinicDB) by achieving 93.44% and 95.26% on mDice. Extensive experiments and visualization results demonstrate that our method advances the performance on five medical segmentation datasets with better generalization ability.

Pan Shaoming, Liu Xin, Xie Ningdi, Chong Yanwen

2023-Mar-07

Channel spatial attention, Medical image segmentation, Progressive enhancement module, Self-attention, Semantic guidance attention, Transformer

General General

Deep learning for improving PET/CT attenuation correction by elastic registration of anatomical data.

In European journal of nuclear medicine and molecular imaging ; h5-index 66.0

BACKGROUND : For PET/CT, the CT transmission data are used to correct the PET emission data for attenuation. However, subject motion between the consecutive scans can cause problems for the PET reconstruction. A method to match the CT to the PET would reduce resulting artifacts in the reconstructed images.

PURPOSE : This work presents a deep learning technique for inter-modality, elastic registration of PET/CT images for improving PET attenuation correction (AC). The feasibility of the technique is demonstrated for two applications: general whole-body (WB) imaging and cardiac myocardial perfusion imaging (MPI), with a specific focus on respiratory and gross voluntary motion.

MATERIALS AND METHODS : A convolutional neural network (CNN) was developed and trained for the registration task, comprising two distinct modules: a feature extractor and a displacement vector field (DVF) regressor. It took as input a non-attenuation-corrected PET/CT image pair and returned the relative DVF between them-it was trained in a supervised fashion using simulated inter-image motion. The 3D motion fields produced by the network were used to resample the CT image volumes, elastically warping them to spatially match the corresponding PET distributions. Performance of the algorithm was evaluated in different independent sets of WB clinical subject data: for recovering deliberate misregistrations imposed in motion-free PET/CT pairs and for improving reconstruction artifacts in cases with actual subject motion. The efficacy of this technique is also demonstrated for improving PET AC in cardiac MPI applications.

RESULTS : A single registration network was found to be capable of handling a variety of PET tracers. It demonstrated state-of-the-art performance in the PET/CT registration task and was able to significantly reduce the effects of simulated motion imposed in motion-free, clinical data. Registering the CT to the PET distribution was also found to reduce various types of AC artifacts in the reconstructed PET images of subjects with actual motion. In particular, liver uniformity was improved in the subjects with significant observable respiratory motion. For MPI, the proposed approach yielded advantages for correcting artifacts in myocardial activity quantification and potentially for reducing the rate of the associated diagnostic errors.

CONCLUSION : This study demonstrated the feasibility of using deep learning for registering the anatomical image to improve AC in clinical PET/CT reconstruction. Most notably, this improved common respiratory artifacts occurring near the lung/liver border, misalignment artifacts due to gross voluntary motion, and quantification errors in cardiac PET imaging.

Schaefferkoetter Joshua, Shah Vijay, Hayden Charles, Prior John O, Zuehlsdorff Sven

2023-Mar-08

Artificial intelligence, Attenuation correction, Deep learning, Elastic registration, PET/CT

General General

Noble metal catalyst detection in rocks using machine-learning: The future to low-cost, green energy materials?

In Scientific reports ; h5-index 158.0

Carbon capture and catalytic conversion to methane is promising for carbon-neutral energy production. Precious metals catalysts are highly efficient; yet they have several significant drawbacks including high cost, scarcity, environmental impact from the mining and intense processing requirements. Previous experimental studies and the current analytical work show that refractory grade chromitites (chromium rich rocks with Al2O3 > 20% and Cr2O3 + Al2O3 > 60%) with certain noble metal concentrations (i.e., Ir: 17-45 ppb, Ru: 73-178 ppb) catalyse Sabatier reactions and produce abiotic methane; a process which has not been investigated at the industrial scale. Thus, a natural source (chromitites) hosting noble metals might be used instead of concentrating noble metals for catalysis. Stochastic machine-learning algorithms show that among the various phases, the noble metal alloys are natural methanation catalysts. Such alloys form when pre-existing platinum group minerals (PGM) are chemically destructed. Chemical destruction of existing PGM results to mass loss forming locally a nano-porous surface. The chromium-rich spinel phases, hosting the PGM inclusions, are subsequently a second-tier support. The current work is the first multi-disciplinary research showing that noble metal alloys within chromium-rich rocks are double-supported, Sabatier catalysts. Thus, such sources could be a promising material in the search of low-cost, sustainable materials for green energy production.

Ifandi Elena, Lai Daphne Teck Ching, Kalaitzidis Stavros, Abu Bakar Muhammad Saifullah, Grammatikopoulos Tassos, Lai Chun-Kit, Tsikouras Basilios

2023-Mar-07

General General

Differentially expressed discriminative genes and significant meta-hub genes based key genes identification for hepatocellular carcinoma using statistical machine learning.

In Scientific reports ; h5-index 158.0

Hepatocellular carcinoma (HCC) is the most common lethal malignancy of the liver worldwide. Thus, it is important to dig the key genes for uncovering the molecular mechanisms and to improve diagnostic and therapeutic options for HCC. This study aimed to encompass a set of statistical and machine learning computational approaches for identifying the key candidate genes for HCC. Three microarray datasets were used in this work, which were downloaded from the Gene Expression Omnibus Database. At first, normalization and differentially expressed genes (DEGs) identification were performed using limma for each dataset. Then, support vector machine (SVM) was implemented to determine the differentially expressed discriminative genes (DEDGs) from DEGs of each dataset and select overlapping DEDGs genes among identified three sets of DEDGs. Enrichment analysis was performed on common DEDGs using DAVID. A protein-protein interaction (PPI) network was constructed using STRING and the central hub genes were identified depending on the degree, maximum neighborhood component (MNC), maximal clique centrality (MCC), centralities of closeness, and betweenness criteria using CytoHubba. Simultaneously, significant modules were selected using MCODE scores and identified their associated genes from the PPI networks. Moreover, metadata were created by listing all hub genes from previous studies and identified significant meta-hub genes whose occurrence frequency was greater than 3 among previous studies. Finally, six key candidate genes (TOP2A, CDC20, ASPM, PRC1, NUSAP1, and UBE2C) were determined by intersecting shared genes among central hub genes, hub module genes, and significant meta-hub genes. Two independent test datasets (GSE76427 and TCGA-LIHC) were utilized to validate these key candidate genes using the area under the curve. Moreover, the prognostic potential of these six key candidate genes was also evaluated on the TCGA-LIHC cohort using survival analysis.

Hasan Md Al Mehedi, Maniruzzaman Md, Shin Jungpil

2023-Mar-07

Cardiology Cardiology

A transparent artificial intelligence framework to assess lung disease in pulmonary hypertension.

In Scientific reports ; h5-index 158.0

Recent studies have recognized the importance of characterizing the extent of lung disease in pulmonary hypertension patients by using Computed Tomography. The trustworthiness of an artificial intelligence system is linked with the depth of the evaluation in functional, operational, usability, safety and validation dimensions. The safety and validation of an artificial tool is linked to the uncertainty estimation of the model's prediction. On the other hand, the functionality, operation and usability can be achieved by explainable deep learning approaches which can verify the learning patterns and use of the network from a generalized point of view. We developed an artificial intelligence framework to map the 3D anatomical models of patients with lung disease in pulmonary hypertension. To verify the trustworthiness of the framework we studied the uncertainty estimation of the network's prediction, and we explained the learning patterns of the network. Therefore, a new generalized technique combining local explainable and interpretable dimensionality reduction approaches (PCA-GradCam, PCA-Shape) was developed. Our open-source software framework was evaluated in unbiased validation datasets achieving accurate, robust and generalized results.

Mamalakis Michail, Dwivedi Krit, Sharkey Michael, Alabed Samer, Kiely David, Swift Andrew J

2023-Mar-07

General General

Key therapeutic targets implicated at the early stage of hepatocellular carcinoma identified through machine-learning approaches.

In Scientific reports ; h5-index 158.0

Hepatocellular carcinoma (HCC) is the most frequent type of primary liver cancer. Early-stage detection plays an essential role in making treatment decisions and identifying dominant molecular mechanisms. We utilized machine learning algorithms to find significant mRNAs and microRNAs (miRNAs) at the early and late stages of HCC. First, pre-processing approaches, including organization, nested cross-validation, cleaning, and normalization were applied. Next, the t-test/ANOVA methods and binary particle swarm optimization were used as a filter and wrapper method in the feature selection step, respectively. Then, classifiers, based on machine learning and deep learning algorithms were utilized to evaluate the discrimination power of selected features (mRNAs and miRNAs) in the classification step. Finally, the association rule mining algorithm was applied to selected features for identifying key mRNAs and miRNAs that can help decode dominant molecular mechanisms in HCC stages. The applied methods could identify key genes associated with the early (e.g., Vitronectin, thrombin-activatable fibrinolysis inhibitor, lactate dehydrogenase D (LDHD), miR-590) and late-stage (e.g., SPRY domain containing 4, regucalcin, miR-3199-1, miR-194-2, miR-4999) of HCC. This research could establish a clear picture of putative candidate genes, which could be the main actors at the early and late stages of HCC.

Hosseiniyan Khatibi Seyed Mahdi, Najjarian Farima, Homaei Rad Hamed, Ardalan Mohammadreza, Teshnehlab Mohammad, Zununi Vahed Sepideh, Pirmoradi Saeed

2023-Mar-07