The Application of Artificial Intelligence to Cancer Research: A Comprehensive Guide.

Advancements in AI have notably changed cancer research, improving patient care by enhancing detection, survival prediction, and treatment efficacy. This review covers the role of Machine Learning, Soft Computing, and Deep Learning in oncology, explaining key concepts and algorithms (like SVM, Naïve Bayes, and CNN) in a clear, accessible manner. It aims to make AI advancements understandable to a broad audience, focusing on their application in diagnosing, classifying, and predicting various cancer types, thereby underlining AI's potential to better patient outcomes. Moreover, we present a tabular summary of the most significant advances from the literature, offering a time-saving resource for readers to grasp each study's main contributions. The remarkable benefits of AI-powered algorithms in cancer care underscore their potential for advancing cancer research and clinical practice. This review is a valuable resource for researchers and clinicians interested in the transformative implications of AI in cancer care.

Impact of Foliar Fungicide Application on the Culturable Fungal Endophyte Community of Soybean Seed in the Midwest United States.

The purpose of our study was to determine whether the application of quinone outside inhibitor (QoI) and pyrazole-carboxamide fungicides as a tank mix would impact the endophyte community of soybean seed. Field trials during 2018 in Iowa, South Dakota, and Wisconsin, U.S.A., investigated the impact of a single combination fungicide spray at early pod set in soybeans. The composition of culturable endophytic fungi in mature soybean seed was assessed on three cultivars per state, with maturity groups (MGs) ranging from 1.1 to 4.7. An unusually wet 2018 season delayed harvest, which led to a high level of fungal growth in grain. The survey included 1,080 asymptomatic seeds that were disinfested and individually placed on 5-cm-diameter Petri plates of acidified water agar. The survey yielded 721 fungal isolates belonging to 24 putative species in seven genera; taxa were grouped into genera based on a combination of morphological and molecular evidence. The dominant genera encountered in the survey were Alternaria, Diaporthe, and Fusarium. The study showed that the fungicide treatment reduced the incidence of Fusarium in Wisconsin seed, increased the incidence of Diaporthe in seed from all states, and had no impact on the incidence of Alternaria. This is one of the first attempts to characterize the diversity of seed endophytes in soybean and the first to characterize the impacts of fungicide spraying on these endophyte communities across three states. Our study provides evidence that the impact of a fungicide spray on soybean seed endophyte communities may be influenced by site, weather, and cultivar maturity group.

Cycling-Induced Capacity Increase of Bulk and Artificially Layered LiTaO3 Anodes in Lithium-Ion Batteries.

Tantalum-based oxide electrodes have recently drawn much attention as promising anode materials owing to their hybrid Li+ storage mechanism. However, the utilization of LiTaO3 electrode materials that can deliver a high theoretical capacity of 568 mAh g-1 has been neglected. Herein, we prepare a layered LiTaO3 electrode formed artificially by restacking LiTaO3 nanosheets using a facile synthesis method and investigate the Li+ storage performance of this electrode compared with its bulk counterpart. The designed artificially layered anode reaches specific capacities of 474, 290, and 201 mAh g-1, respectively, at 56 (>500 cycles), 280 (>1000 cycles), and 1120 mAg-1 (>2000 cycles) current densities. We also determine that the Li+ storage capacity of the layered LiTaO3 demonstrates a cycling-induced capacity increase after a certain number of cycles. Adopting various characterization techniques on LiTaO3 electrodes before and after electrochemical cycling, we attribute the origin of the cycling-induced improvement of the Li+ storage capacity in these electrodes to the amorphization of the electrode after cycling, formation of metallic tantalum during the partially irreversible conversion mechanism, lower activation overpotential of electrodes due to the formation of Li-rich species by the lithium insertion mechanism, and finally the intrinsic piezoelectric behavior of LiTaO3 that can regulate Li+ diffusion kinetics.

DeeP4med: deep learning for P4 medicine to predict normal and cancer transcriptome in multiple human tissues.

BACKGROUND: P4 medicine (predict, prevent, personalize, and participate) is a new approach to diagnosing and predicting diseases on a patient-by-patient basis. For the prevention and treatment of diseases, prediction plays a fundamental role. One of the intelligent strategies is the design of deep learning models that can predict the state of the disease using gene expression data. RESULTS: We create an autoencoder deep learning model called DeeP4med, including a Classifier and a Transferor that predicts cancer's gene expression (mRNA) matrix from its matched normal sample and vice versa. The range of the F1 score of the model, depending on tissue type in the Classifier, is from 0.935 to 0.999 and in Transferor from 0.944 to 0.999. The accuracy of DeeP4med for tissue and disease classification was 0.986 and 0.992, respectively, which performed better compared to seven classic machine learning models (Support Vector Classifier, Logistic Regression, Linear Discriminant Analysis, Naive Bayes, Decision Tree, Random Forest, K Nearest Neighbors). CONCLUSIONS: Based on the idea of DeeP4med, by having the gene expression matrix of a normal tissue, we can predict its tumor gene expression matrix and, in this way, find effective genes in transforming a normal tissue into a tumor tissue. Results of Differentially Expressed Genes (DEGs) and enrichment analysis on the predicted matrices for 13 types of cancer showed a good correlation with the literature and biological databases. This led that by using the gene expression matrix, to train the model with features of each person in a normal and cancer state, this model could predict diagnosis based on gene expression data from healthy tissue and be used to identify possible therapeutic interventions for those patients.

A deep convolutional neural network for segmentation of whole-slide pathology images identifies novel tumour cell-perivascular niche interactions that are associated with poor survival in glioblastoma.

BACKGROUND: Glioblastoma is the most aggressive type of brain cancer with high-levels of intra- and inter-tumour heterogeneity that contribute to its rapid growth and invasion within the brain. However, a spatial characterisation of gene signatures and the cell types expressing these in different tumour locations is still lacking. METHODS: We have used a deep convolutional neural network (DCNN) as a semantic segmentation model to segment seven different tumour regions including leading edge (LE), infiltrating tumour (IT), cellular tumour (CT), cellular tumour microvascular proliferation (CTmvp), cellular tumour pseudopalisading region around necrosis (CTpan), cellular tumour perinecrotic zones (CTpnz) and cellular tumour necrosis (CTne) in digitised glioblastoma histopathological slides from The Cancer Genome Atlas (TCGA). Correlation analysis between segmentation results from tumour images together with matched RNA expression data was performed to identify genetic signatures that are specific to different tumour regions. RESULTS: We found that spatially resolved gene signatures were strongly correlated with survival in patients with defined genetic mutations. Further in silico cell ontology analysis along with single-cell RNA sequencing data from resected glioblastoma tissue samples showed that these tumour regions had different gene signatures, whose expression was driven by different cell types in the regional tumour microenvironment. Our results further pointed to a key role for interactions between microglia/pericytes/monocytes and tumour cells that occur in the IT and CTmvp regions, which may contribute to poor patient survival. CONCLUSIONS: This work identified key histopathological features that correlate with patient survival and detected spatially associated genetic signatures that contribute to tumour-stroma interactions and which should be investigated as new targets in glioblastoma. The source codes and datasets used are available in GitHub: https://github.com/amin20/GBM_WSSM .

Effects of Zr substitution on soot combustion over cubic fluorite-structured nanoceria: Soot-ceria contact and interfacial oxygen evolution.

Ceria is widely used as a catalyst for soot combustion, but effects of Zr substitution on the reaction mechanism is ambiguous. The present work elucidates effects of Zr substitution on soot combustion over cubic fluorite-structured nanoceria. The nanostructured CeO2, Ce0.92Zr0.08O2, and Ce0.84Zr0.16O2 composed of 5-6 nm crystallites display Tm-CO2 (the temperature at maximum CO2 yield) at 383, 355, and 375°C under 10 vol.% O2/N2, respectively. The size of agglomerate decreases from 165.5 to 51.9-57.3 nm, which is beneficial for the soot-ceria contact. Moreover, Zr increases the amount of surface oxygen vacancies, generating more active oxygen (O2- and O-) for soot oxidation. Thus, the activities of Ce0.92Zr0.08O2 and Ce0.84Zr0.16O2 in soot combustion are better than that of CeO2. Although oxygen vacancies promote the migration of lattice O2-, the enriched surface Zr also inhibits the mobility of lattice O2-. Therefore, the Tm-CO2 of Ce0.84Zr0.16O2 is higher than that of Ce0.92Zr0.08O2. Based on reaction kinetic study, soot in direct contact with ceria preferentially decomposes with low activation energy, while the oxidation of isolated soot occurs through diffusion with high activation energy. The obtained findings provide new understanding on the soot combustion over nanoceria.

The Application of Deep Convolutional Neural Networks to Brain Cancer Images: A Survey.

In recent years, improved deep learning techniques have been applied to biomedical image processing for the classification and segmentation of different tumors based on magnetic resonance imaging (MRI) and histopathological imaging (H&E) clinical information. Deep Convolutional Neural Networks (DCNNs) architectures include tens to hundreds of processing layers that can extract multiple levels of features in image-based data, which would be otherwise very difficult and time-consuming to be recognized and extracted by experts for classification of tumors into different tumor types, as well as segmentation of tumor images. This article summarizes the latest studies of deep learning techniques applied to three different kinds of brain cancer medical images (histology, magnetic resonance, and computed tomography) and highlights current challenges in the field for the broader applicability of DCNN in personalized brain cancer care by focusing on two main applications of DCNNs: classification and segmentation of brain cancer tumors images.

Mesoporous Crystalline Niobium Oxide with a High Surface Area: A Solid Acid Catalyst for Alkyne Hydration.

A mesoporous crystalline niobium oxide with tunable pore sizes was synthesized via the sol-gel-based inverse micelle method. The material shows a surface area of 127 m2/g, which is the highest surface area reported so far for crystalline niobium oxide synthesized by soft template methods. The material also has a monomodal pore size distribution with an average pore diameter of 5.6 nm. A comprehensive characterization of niobium oxide was performed using powder X-ray diffraction, Brunauer-Emmett-Teller, thermogravimetric analysis, scanning electron microscopy, transmission electron microscopy, UV-vis, and X-ray photoelectron spectroscopy. The material acts as an environmentally friendly, solid acid catalyst toward hydration of alkynes under with excellent catalytic activity (99% conversion, 99% selectivity, and 4.39 h-1 TOF). Brønsted acid sites present in the catalyst were found to be responsible for the high catalytic activity. The catalyst was reusable up to five cycles without a significant loss of the activity.

DeepSurvNet: deep survival convolutional network for brain cancer survival rate classification based on histopathological images.

Histopathological whole slide images of haematoxylin and eosin (H&E)-stained biopsies contain valuable information with relation to cancer disease and its clinical outcomes. Still, there are no highly accurate automated methods to correlate histolopathological images with brain cancer patients' survival, which can help in scheduling patients therapeutic treatment and allocate time for preclinical studies to guide personalized treatments. We now propose a new classifier, namely, DeepSurvNet powered by deep convolutional neural networks, to accurately classify in 4 classes brain cancer patients' survival rate based on histopathological images (class I, 0-6 months; class II, 6-12 months; class III, 12-24 months; and class IV, >24 months survival after diagnosis). After training and testing of DeepSurvNet model on a public brain cancer dataset, The Cancer Genome Atlas, we have generalized it using independent testing on unseen samples. Using DeepSurvNet, we obtained precisions of 0.99 and 0.8 in the testing phases on the mentioned datasets, respectively, which shows DeepSurvNet is a reliable classifier for brain cancer patients' survival rate classification based on histopathological images. Finally, analysis of the frequency of mutations revealed differences in terms of frequency and type of genes associated to each class, supporting the idea of a different genetic fingerprint associated to patient survival. We conclude that DeepSurvNet constitutes a new artificial intelligence tool to assess the survival rate in brain cancer. Graphical abstract A DCNN model was generated to accurately predict survival rates of brain cancer patients (classified in 4 different classes) accurately. After training the model using images from H&E stained tissue biopsies from The Cancer Genome Atlas database (TCGA, left), the model can predict for each patient, based on a histological image (top right), its survival class accurately (bottom right).

Syntheses of ZnO with Different Morphologies: Catalytic Activity toward Coumarin Synthesis via the Knoevenagel Condensation Reaction.

Heterogeneous catalysts are preferred in fine chemical industries due to their easy recovery and reusability. Here, we report an easily scalable method of ZnO catalysts for coumarin synthesis. Nanocrystalline ZnO particles with diverse morphologies and crystallite sizes were prepared using different solvents. The change in morphology results in changes in band gaps, defects, basicity, and textural properties (surface areas, pore volumes, and pore sizes). The catalytic performances of the synthesized ZnO materials were tested using coumarin synthesis via the Knoevenagel condensation. The catalyst synthesized using methanol shows the highest activity and selectivity (conversion of 74%, selectivity of 94%) with a turnover number of 14.69. The increased activity of the ZnO synthesized in methanol is attributed to the combined effects of moderate basicity and relatively high textural properties of the sample.

Synthesis of Large Mesoporous-Macroporous and High Pore Volume, Mixed Crystallographic Phase Manganese Oxide, Mn2O3/Mn3O4 Sponge.

The controlled synthesis of mixed crystallographic phase Mn2O3/Mn3O4 sponge material by varying heating rates and isothermal segments provides valuable information about the morphological and physical properties of the obtained sample. The well-characterized Mn2O3/Mn3O4 sponge and applicability of difference in reactivity of H2 and CO2 desorbed during the synthesis provide new developments in the synthesis of metal oxide materials with unique morphological and surface properties. We report the preparation of a Mn2O3/Mn3O4 sponge using a metal nitrate salt, water, and Dextran, a biopolymer consisting of glucose monomers. The Mn2O3/Mn3O4 sponge prepared at 1 °C·min-1 heating rate to 500 °C and held isothermally for 1 h consisted of large mesopores-macropores (25.5 nm, pore diameter) and a pore volume of 0.413 mL/g. Furthermore, the prepared Mn2O3/Mn3O4 and 5 mol %-Fe-Mn2O3/Mn3O4 sponges provide potential avenues in the development of solid-state catalyst materials for alcohol and amine oxidation reactions.

Synthesis and Electrocatalytic Activity of Ammonium Nickel Phosphate, [NH4]NiPO4·6H2O, and ß-Nickel Pyrophosphate, ß-Ni2P2O7: Catalysts for Electrocatalytic Decomposition of Urea.

Electrocatalytic decomposition of urea for the production of hydrogen, H2, for clean energy applications, such as in fuel cells, has several potential advantages such as reducing carbon emissions in the energy sector and environmental applications to remove urea from animal and human waste facilities. The study and development of new catalyst materials containing nickel metal, the active site for urea decomposition, is a critical aspect of research in inorganic and materials chemistry. We report the synthesis and application of [NH4]NiPO4·6H2O and ß-Ni2P2O7 using in situ prepared [NH4]2HPO4. The [NH4]NiPO4·6H2O is calcined at varying temperatures and tested for electrocatalytic decomposition of urea. Our results indicate that [NH4]NiPO4·6H2O calcined at 300 °C with an amorphous crystal structure and, for the first time applied for urea electrocatalytic decomposition, had the greatest reported electroactive surface area (ESA) of 142 cm2/mg and an onset potential of 0.33 V (SCE) and was stable over a 24-h test period.

A novel and reliable computational intelligence system for breast cancer detection.

Cancer is the second important morbidity and mortality factor among women and the most incident type is breast cancer. This paper suggests a hybrid computational intelligence model based on unsupervised and supervised learning techniques, i.e., self-organizing map (SOM) and complex-valued neural network (CVNN), for reliable detection of breast cancer. The dataset used in this paper consists of 822 patients with five features (patient's breast mass shape, margin, density, patient's age, and Breast Imaging Reporting and Data System assessment). The proposed model was used for the first time and can be categorized in two stages. In the first stage, considering the input features, SOM technique was used to cluster the patients with the most similarity. Then, in the second stage, for each cluster, the patient's features were applied to complex-valued neural network and dealt with to classify breast cancer severity (benign or malign). The obtained results corresponding to each patient were compared to the medical diagnosis results using receiver operating characteristic analyses and confusion matrix. In the testing phase, health and disease detection ratios were 94 and 95%, respectively. Accordingly, the superiority of the proposed model was proved and can be used for reliable and robust detection of breast cancer.

Fractionated stereotactic conformal radiotherapy following conservative surgery in the control of craniopharyngiomas.

PURPOSE: To describe the technique and results of stereotactically guided conformal radiotherapy (SCRT) in patients with craniopharyngioma after conservative surgery. METHODS AND MATERIALS: Thirty-nine patients with craniopharyngioma aged 3-68 years (median age 18 years) were treated with SCRT between June 1994 and January 2003. All patients were referred for radiotherapy after undergoing one or more surgical procedures. Treatment was delivered in 30-33 daily fractions over 6-6.5 weeks to a total dose of 50 Gy using 6 MV photons. Outcome was assessed prospectively. RESULTS: At a median follow-up of 40 months (range 3-88 months) the 3- and 5-year progression-free survival (PFS) was 97% and 92%, and 3- and 5-year survival 100%. Two patients required further debulking surgery for progressive disease 8 and 41 months after radiotherapy. Twelve patients (30%) had acute clinical deterioration due to cystic enlargement of craniopharyngioma following SCRT and required cyst aspiration. One patient with severe visual impairment prior to radiotherapy had visual deterioration following SCRT. Seven out of 10 patients with a normal pituitary function before SCRT had no endocrine deficits following treatment. CONCLUSION: SCRT as a high-precision technique of localized RT is suitable for the treatment of incompletely excised craniopharyngioma. The local control, toxicity and survival outcomes are comparable to results reported following conventional external beam RT. Longer follow-up is required to assess long-term efficacy and toxicity, particularly in terms of potential reduction in treatment related late toxicity.