Explainable artificial intelligence for sedimentary facies segmentation

Anti-vascular endothelial growth factor (Anti-VEGF) therapy is currently seen as the standard for treatment of neovascular AMD (nAMD). However, while treatments are highly effective, decisions for initial treatment and retreatment are often challenging for non-retina specialists. The purpose of this study is to develop convolutional neural networks (CNN) that can differentiate treatment indicated presentations of nAMD for referral to treatment centre based solely on SD-OCT. This provides the basis for developing an applicable medical decision support system subsequently. SD-OCT volumes of a consecutive real-life cohort of 1503 nAMD patients were analysed and two experiments were carried out. To differentiate between no treatment class vs. initial treatment nAMD class and stabilised nAMD vs. active nAMD, two novel CNNs, based on SD-OCT volume scans, were developed and tested for robustness and performance. In a step towards explainable artificial intelligence (AI), saliency maps of the SD-OCT volume scans of 24 initial indication decisions with a predicted probability of > 97.5% were analysed (score 0-2 in respect to staining intensity). An AI benchmark against retina specialists was performed. At the first experiment, the area under curve (AUC) of the receiver-operating characteristic (ROC) for the differentiation of patients for the initial analysis was 0.927 (standard deviation (SD): 0.018), for the second experiment (retreatment analysis) 0.865 (SD: 0.027). The results were robust to downsampling (¼ of the original resolution) and cross-validation (tenfold). In addition, there was a high correlation between the AI analysis and expert opinion in a sample of 102 cases for differentiation of patients needing treatment (κ = 0.824). On saliency maps, the relevant structures for individual initial indication decisions were the retina/vitreous interface, subretinal space, intraretinal cysts, subretinal pigment epithelium space, and the choroid. The developed AI algorithms can define and differentiate presentations of AMD, which should be referred for treatment or retreatment with anti-VEGF therapy. This may support non-retina specialists to interpret SD-OCT on expert opinion level. The individual decision of the algorithm can be supervised by saliency maps.

This study aims to develop a transparent and reliable artificial intelligence model for pneumonia diagnosis using chest X-ray images by implementing and optimizing Convolutional Neural Networks (CNN) with Saliency Mapping. The research employed a combination of advanced optimization techniques, including aggressive data augmentation, class weight balancing, L2 regularization, dropout, batch normalization, and adaptive learning rate scheduling to address overfitting challenges. A functional prototype was then deployed in a Streamlit-based application to provide an interactive diagnostic tool. The evaluation results demonstrated that the model achieved strong performance, with high training accuracy and competitive testing accuracy, while visualization through Saliency Mapping provided meaningful interpretability by highlighting critical lung regions, particularly the mid-to-lower lung fields and hilar area. This interpretability ensured that the system not only delivered accurate predictions but also supported clinical reasoning by aligning with radiological characteristics of early-stage pneumonia and bronchopneumonia. The integration into a user-friendly application illustrates the potential for practical adoption in healthcare settings, especially in regions with limited access to radiologists. Overall, the study demonstrates that combining CNN-based classification with explainable AI techniques can bridge the gap between advanced machine learning and clinical applicability, offering a strategic pathway to improve pneumonia diagnosis and patient outcomes.

The research focus was motivated by the limited understanding of cognitive technologies and the growing gap between artificial intelligence (AI) and human intelligence. The research is a literature review, and its purpose is to simplify the meaning and processes behind cognitive technologies, notably, the fundamentals of machine learning (ML) and computer vision with the intention to briefly address the alleged threat of AI taking over the job market. The research is a review of peer-reviewed articles retrieved from comparative studies, systematic reviews, meta-analysis, service research, reports, conference proceedings, experimental studies, literature reviews, scientometric analyses, books, and multi-case studies, dating from the years of 2018 to 2024. This literature review defines machine learning (ML), artificial intelligence (AI), computer vision, and convolutional neural networks (CNNs). It also compares machine learning to traditional programming and reveals the types of learning in ML models’ training. ML and its correlation with AI are also discussed and details about theory of mind, self-aware AI, reactive machines, and limited memory AI are shared. The literature expounds computer vision, particularly convolutional neural network (CNN) and CNN layers. Recent cutting-edge applications of artificial intelligence including generative AI models and autonomous systems are also incorporated. Finally, the literature briefly addresses the alleged threat of AI taking over the job market. The findings of this literature review reveal that AI is becoming the new way of operating. The conclusion shows that AI models require significant computation to allow computers to learn autonomously. Thus, understanding mathematical models of data and perfecting the process of writing software could be the key to remaining employable as more jobs are expected to be shifted due to AI and tasks automation. Keywords: Cognitive technology, artificial intelligence, machine learning, computer vision, convolutional neural networks

Demand for low lactose milk and milk products has been increasing worldwide due to the high number of people with lactose intolerance. These low lactose dairy foods require fast, low-cost and efficient methods for sugar quantification. However, available methods do not meet all these requirements. In this work, we propose the association of FTIR (Fourier Transform Infrared) spectroscopy with artificial intelligence to identify and quantify residual lactose and other sugars in milk. Convolutional neural networks (CNN) were built from the infrared spectra without preprocessing the data using hyperparameter adjustment and saliency map. For the quantitative prediction of the sugars in milk, a regression model was proposed, while for the qualitative assessment, a classification model was used. Raw, pasteurized and ultra-high temperature (UHT) milk was added with lactose, glucose, and galactose in six concentrations (0.1–7.0 mg mL−1) and, in total, 432 samples were submitted to convolutional neural network. Accuracy, precision, sensitivity, specificity, root mean square error, mean square error, mean absolute error, and coefficient of determination (R2) were used as evaluation parameters. The algorithms indicated a predictive capacity (accuracy) above 95% for classification, and R2 of 81%, 86%, and 92% for respectively, lactose, glucose, and galactose quantification. Our results showed that the association of FTIR spectra with artificial intelligence tools, such as CNN, is an efficient, quick, and low-cost methodology for quantifying lactose and other sugars in milk.

Background/Objectives: 123I-FP-CIT dopamine transporter imaging is commonly used for the diagnosis of Parkinsonian syndromes in patients whose clinical presentation is atypical. Prolonged immobility, which can be difficult to maintain in this population, is required to perform SPECT acquisition. In this study we aimed to develop a Convolutional Neural Network (CNN) able to predict the outcome of the full examination based on the first acquired projection, and reliably detect normal patients. Methods: All 123I-FP-CIT SPECT performed in our center between June 2017 and February 2024 were included and split between a training and a validation set (70%/30%). An additional 100 SPECT were used as an independent test set. Examinations were labeled by two independent physicians. A VGG16-like CNN model was trained to assess the probability of examination abnormality from the first acquired projection (anterior and posterior view at 0°), taking age into consideration. A threshold maximizing sensitivity while maintaining good diagnostic accuracy was then determined. The model was validated in the independent testing set. Saliency maps were generated to visualize the most impactful areas in the classification. Results: A total of 982 123I-FP-CIT SPECT were retrieved and labelled (training set: 618; validation set: 264; independent testing set: 100). The trained model achieved a sensibility of 98.0% and a negative predictive value of 96.3% (one false negative) while maintaining an accuracy of 75.0%. The saliency maps confirmed that the regions with the greatest impact on the final classification corresponded to clinically relevant areas (basal ganglia and background noise). Conclusions: Our results suggest that this trained CNN could be used to exclude presynaptic dopaminergic loss with high reliability from the first acquired projection. It could be particularly useful in patients with compliance issues. Confirmation with images from other centers will be necessary.

Artificial Intelligence: The Future of Maxillofacial Prognosis and Diagnosis?

This paper presents a simple and effective method to verify similar vehicle images. In order to provide a meaningful interpretation of the verification, we propose to detect the local differences between two images. We frame this task as a saliency map regression problem, where the saliency map measures the degree of discrepancy at every pixel. To achieve this goal, we use a convolutional neural network (CNN) to map two aligned vehicle images to one saliency map. Our network design enables end-to-end training. We validate our algorithm on a vehicle image dataset. Experimental results show that our approach is accurate, fast and robust, and it achieves better performance than other methods.

Artificial Intelligence (AI) has become a transformative tool in the armamentum of respiratory medicine, offering applications in diagnostics, risk stratification, and clinical decision support. Leveraging machine learning (ML) and deep learning (DL), AI systems analyse large datasets— from imaging to electronic health records — to assist clinicians in managing respiratory conditions. In diseases such as COPD, interstitial lung disease (ILD), lung cancer, and obstructive sleep apnea (OSA), AI has achieved diagnostic accuracy comparable to human experts. ML models predict COPD exacerbations and OSA severity, while convolutional neural networks (CNNs) enhance lung nodule detection and ILD classification. Despite promising results, most systems lack prospective validation and regulatory approval. The use of AI also raises critical ethical issues, including bias and fairness, algorithmic transparency, patient autonomy, data privacy, and liability in decision-making. To ensure trustworthy integration of AI into respiratory care, future development must be patient-centered, ethically grounded, and supported by robust regulatory frameworks.

Heart diseases are among the most common causes of death in the world. Myocardial infarction (MI) requires fast detection with electrocardiogram (ECG) readings. In this paper, we present an end-to-end deep learning system for automated MI and ischemic abnormality detection based on ECG readings with explainability and web deployment. Three models of convolutional neural networks (CNNs) have been trained with one-dimensional inputs from the PTB-XL dataset (21,799 entries, 500 Hz, 10 seconds): 12-Lead CNN with multi-lead digital ECG input, Lead II CNN with single-lead ECG input, and Image CNN with scanned ECG images. 12-Lead CNN outperformed other models with ROC-AUC = 0.8991, sensitivity = 0.8674, specificity = 0.7580, and F1 score = 0.8436. Explainability with Grad-CAM [16] and saliency maps has been incorporated that conforms with the standard ECG pattern interpretation. All of our models have been integrated in an easily accessible web application with Streamlit Cloud to allow WFDB file, CSV, and image input with automatic route selection and report generation.

Automatic segmentation of the prostate of and the prostatic zones on MRI remains one of the most compelling research areas. While different image enhancement techniques are emerging as powerful tools for improving the performance of segmentation algorithms, their application still lacks consensus due to contrasting evidence regarding performance improvement and cross-model stability, further hampered by the inability to explain models’ predictions. Particularly, for prostate segmentation, the effectiveness of image enhancement on different Convolutional Neural Networks (CNN) remains largely unexplored. The present work introduces a novel image enhancement method, named RACLAHE, to enhance the performance of CNN models for segmenting the prostate’s gland and the prostatic zones. The improvement in performance and consistency across five CNN models (U-Net, U-Net++, U-Net3+, ResU-net and USE-NET) is compared against four popular image enhancement methods. Additionally, a methodology is proposed to explain, both quantitatively and qualitatively, the relation between saliency maps and ground truth probability maps. Overall, RACLAHE was the most consistent image enhancement algorithm in terms of performance improvement across CNN models with the mean increase in Dice Score ranging from 3 to 9% for the different prostatic regions, while achieving minimal inter-model variability. The integration of a feature driven methodology to explain the predictions after applying image enhancement methods, enables the development of a concrete, trustworthy automated pipeline for prostate segmentation on MR images.

BackgroundArtificial intelligence (AI) is increasingly a part of daily life and offers great possibilities to enrich health care. Imaging applications of AI have been mostly developed by large, well‐funded companies and currently are inaccessible to the comparatively small market of point‐of‐care ultrasound (POCUS) programs. Given this absence of commercial solutions, we sought to create and test a do‐it‐yourself (DIY) deep learning algorithm to classify ultrasound images to enhance the quality assurance work‐flow for POCUS programs.MethodsWe created a convolutional neural network using publicly available software tools and pre‐existing convolutional neural network architecture. The convolutional neural network was subsequently trained using ultrasound images from seven ultrasound exam types: pelvis, heart, lung, abdomen, musculoskeletal, ocular, and central vascular access from 189 publicly available POCUS videos. Approximately 121,000 individual images were extracted from the videos, 80% were used for model training and 10% each for cross validation and testing. We then tested the algorithm for accuracy against a set of 160 randomly extracted ultrasound frames from ultrasound videos not previously used for training and that were performed on different ultrasound equipment. Three POCUS experts blindly categorized the 160 random images, and results were compared to the convolutional neural network algorithm. Descriptive statistics and Krippendorff alpha reliability estimates were calculated.ResultsThe cross validation of the convolutional neural network approached 99% for accuracy. The algorithm accurately classified 98% of the test ultrasound images. In the new POCUS program simulation phase, the algorithm accurately classified 70% of 160 new images for moderate correlation with the ground truth, α = 0.64. The three blinded POCUS experts correctly classified 93%, 94%, and 98% of the images, respectively. There was excellent agreement among the experts with α = 0.87. Agreement between experts and algorithm was good with α = 0.74. The most common error was misclassifying musculoskeletal images for both the algorithm (40%) and POCUS experts (40.6%). The algorithm took 7 minutes 45 seconds to review and classify the new 160 images. The 3 expert reviewers took 27, 32, and 45 minutes to classify the images, respectively.ConclusionsOur algorithm accurately classified 98% of new images, by body scan area, related to its training pool, simulating POCUS program workflow. Performance was diminished with exam images from an unrelated image pool and ultrasound equipment, suggesting additional images and convolutional neural network training are necessary for fine tuning when using across different POCUS programs. The algorithm showed theoretical potential to improve workflow for POCUS program directors, if fully implemented. The implications of our DIY AI for POCUS are scalable and further work to maximize the collaboration between AI and POCUS programs is warranted.

The paper is concerned with the visions and threats of Artificial Intelligence. It characterizes and describes those that, according to experts and scientists , will have a huge impact on the shape, nature and functioning of societies in the next two to three decades. Undoubtedly, one of the significant challenges is the development and application of deep learning. Scientific research in Artificial Intelligence will be accompanied by intensive development of computer vision, convolutional networks and virtual, augmented and mixed reality. In the future, everything digital will be able to fall prey to counterfeiters. The essence and functioning of related Deepfake tools are explained and described in the paper. The development of Artificial Intelligence will result in a wide and versatile application of Biometrics. The paper describes the prospective areas of its use and draws attention to the problems associated with the construction of the oversized databases necessary for this purpose. In the era of a society characteristic of the development of the fourth industrial revolution, theway and means of automobile transportation and the necessary infrastructure will be radically transformed - autonomous vehicles will appear. The paper describes all levels of reference relating to the scope of control of an autonomous vehicle. Effective use of Artificial Intelligence solutions will not be possible without computers with enormous computing power. Theemergence of quantum computers will certainly solve this problem. The essence of quantum computer functioning is described in the next chapter. Artificial Intelligence can successfully perform many tasks better than humans. This will make Artificial Intelligence take on a huge economic value. Positions will be lost for both physical and mental workers. The question then becomes, where are we? Which professions can take over Artificial Intelligence and which ones will not move? What is the future of work done by humans? These issues are addressed in Chapter 9. The prospect of widespread and comprehensive use of Artificial Intelligence solutions will raise the following question, with respect to both humans and society. Can Artificial Intelligence optimize our happiness? The answer to such a question is not an easy one. The paper attempts to answer it. In the age of Robotics and Artificial Intelligence, we will be accompanied by, revolutionary changes in the way humans of entire societies function. There will be an urgent need to define a neweconomic model. Issues clarifying the nature and importance of the essential components of the said model are addressed in this work. Solutions and use of Artificial Intelligence are often accompanied by various kinds of failures. These can have many causes. The paper describes and explains, proposed by Yampolsky Roman, a kind of dysfunction pattern. The results of scientific research andpractical experience that the list of Artificial Intelligence dangers is very extensive. A representative list of risks from Artificial, along with the characteristics of each of them, is presented in the last part of the paper.

Recently, Quantitative Biology (QB) held a discussion on “AI (artificial intelligence) for Life Science” among editorial board members and interested scholars in anticipation of rapid development of this growing area after AlphaGo and ChatGPT mania. Many young people tend to get confused between facts and fictions; heated debates are unavoidable even among their mentors. When deep learning as represented by convolutional neural networks and LSTM (long short-term memory) was made available for bioinformatics students, many of them rushed into this research field and tried to adopt these methods in all their projects without knowing the history that these tools were becoming successful consistently with Moore’s Law (relating to rapid computer technology advances), but more importantly due to new structural/functional understanding of vision and auditory circuits in the brain. Recently, some young people have claimed “LSTM is dead, long live transformer” (which is somewhat like saying “the bike is dead, long live the car”), and have amplified the threat that ChatGPT could wipe out human jobs. They believe transformer is the “silver bullet” for all learning tasks, clearly reflecting their lack of basic knowledge (i.e. “No Free Lunch Theory,” the trade-off of such global “attention network” is to pay the price for complexity: difficulty of training and high memory costs). There is no doubt ML (machine learning) and AI have brought a new revolution in science and technology, and will deliver huge unforeseeable impact to human everyday life as well as to social relationships. In this context, QB journal could be a great platform for encouraging intellectual discussions and for promoting AI for Life Science. Here, I would like to use the DIALOG to “抛砖引玉” (make some initial remarks to get the ball rolling), although it is my personal opinion which is inevitably subject to bias and limitations. AI: Do you know my name “Artificial Intelligence” is defined by the Oxford English Dictionary as the capacity of computer systems (which may be referred as a “robot”) to exhibit or simulate your intelligent behavior? NI: Wait a minute, intelligence itself is defined as the ability to learn, understand and think in a logical way. Can you think? AI: No. But that definition is too restrictive, actually intelligence has different scopes and degrees. Simple intelligent control devices date back to antiquity, from windmills to thermostat. NI: Agree, everything is relative. Macromolecules (e.g., enzyme) and cells (e.g., immune cell) might be considered to be intelligent; see how a white blood cell is chasing bacteria in the youtube website (search for “Crawling neutrophil chasing a bacterium”). Our emergent/collective intelligent behavior does not require a brain or even a neuron; see how slime molds can solve optimization—Hamilton cycle-problem more effectively than a human in the youtube website (search for “Intelligence without a brain?”). Before there was any neuron, Ca2+ sensing and signaling were already fully functional. Even if one knock-out a neural circuit, redundant signaling pathways, albeit on much local and slower scale, could still function by themselves (just as if highways were demolished, local roads/paths would still be working). In fact, the most detailed “Neural signal propagation atlas of Caenorhabditis elegans” [1] demonstrated that functional connectivity differs from anatomy (connectome) because extra-synaptic signaling also drives neural dynamics! Worm brain connectomes are largely invariant but every human brain connectome is very different (depending the diversity of learning experience). The human brain functional activity is far more complex than that of a worm brain, certainly beyond what a neural circuit could explain. AI: Well, that’s impressive. I thought only we could beat humans, albeit only in certain specified areas for now. My master promise to make an artificial general intelligent (AGI) robot which can understand or learn any intellectual task that you humans or other animals can. NI: Well, that is not possible and is not an appropriate goal either. It is not possible because we are an evolutionary/developmental product (with a long history of learning and memory from evolutionary tinkering): our living objective goal is survival of the population. You, on the other hand, are an engineering product (efficiently and optimally designed): your goal is to extend and maximize human capability. It makes sense to complement the human brain, but foolish and dangerous to try to replace it. AI: We are not satisfied with merely passing the Turing Test; most of us don’t care if we could really think as long as we could act like we think (that is, as if we do have a mind and consciousness, as expressed in the so called “Weak AI hypothesis”). After all, the brain is a computer; a neural network is just an electric or ionic circuit. Logical computing does not need to be based on living cells. NI: That is not true, because a neuron is not just a simple node (logic gate) and neural network is not fixed circuit, neither as in Pitts&Mcculloch perceptron model. A single neuron, even a single dendrite, is much more complicated and far more powerful than a full-blown deep-learning artificial neural network (ANN) [2]. AI: Even though single neurons are complex computational devices (dendritic non-linear), running an equivalent multilayer ANN is 2000 times faster than computing with biophysics N-methyl-D-aspartate receptor channel models [3]. More information can be found in the youtube website (search for “Dendrites: why biological neurons are deep neural networks”). NI: Often silicon computing (CPU, GPU) is much faster than brain computing (action potential, ms); but there is no comparison in energy efficiency. Bacteria sensing (chemotaxis computation), powered by ATP (adenosine triphosphate) hydrolysis, uses very little energy that is close to the Landauer limit, whereby achieving or maintaining one bit of information requires minimum of 1 kT ln (2) free energy [4]. The human brain consumes oft-quoted 20 W, compared to the AlphGo system 1 MW! More recent estimate of energy audit is only 0.1 W to cortical computing, and long-distance communication cost is 3.5 W [5]. AI: Assuming we have infinite computing resources and an infinite amount of training data, not only could we speak human languages, but we could also derive physical laws, prove mathematics theories, and even re-engineer the structure and mechanism of brain and carry out any logical computations that are necessary to understand natural laws and human behaviors. It is only a matter of time before we surpass human intelligence, achieving AGI and free will, too! NI: Unfortunately, nothing is infinite and nothing is free either; everything is constrained by physical laws (Planck’s constant sets the finite limit both in the small and in the large) and by evolutionary history (not just of biological living creatures, but also of a “living” galaxy and our universe). Let’s just focus on animal evolution. Most human neural networks do not do logical computations at all; basic survival simply cannot be dependent on reasoning. Indeed, the prefrontal cortex-the small part of the brain that is key for reasoning, is the last to mature (∼20 years old) in development, only emerged at the root of the evolutionary tree of great apes (∼15 mya) and language appeared even much later. Even for logical inference, NI is focusing more on statistical properties, as von Neumann rightly pointed out, trading arithmetical precision and speed for reliability. AI: My engineers mostly focus on emulating brain, but the CNS (central nerve system) also includes the spinal cord; most of them do not know that in addition to CNS, there are also PNS (peripheral nervous systems) and ENS (enteric nervous systems), right? NI: Yes, they are the keys to why you do not have feelings because you do not have heart and gut! Even if you could pretend to have them (such as in an advanced ChatGPT or humanoid), you could never avoid the uncanny valley phenomenon. AI: Maybe that is at the heart of Moravec’s paradox, namely the dichotomy of intelligence whereby anything easy for a human would be hard for a robot, and vice versa? NI: This is related to the nature and nurture problem; something built-in (e.g., a baby sucking nipple for milk with feeling and connection to mother) is clearly rather difficult if not impossible for a robot. But the paradox only looks at one side; another side could be more fatal. Although AI may solve more problems and be faster, AI can never propose a good problem/hypothesis (a good problem is not just intellectually changing and interesting, but is also feasible and appropriate). AI: You make me less confident to compete with human instinct or creative intelligence. I can see that even if I had a heart, I would not know what “feeling” I could have; certainly nothing would be comparable or match to those of a human being. When two people watch the same art or movie, one could feel love but another could feel hate! And if a thousand people watch, a wide spectrum of reactions would result, depending on more details such as the different individuals’ specific genes, developments and experiences. NI: Therefore, you cannot and should not try to match to general human intelligence. You cannot because you do not contain the vital memory of billion years of evolution which is encoded in our genes; conversely your assembly cannot compare with natural development so that our phenotype (including morphological forms and behavior maturation) is decoded through multi-spatial-temporal scales subject to natural selection at all levels. You should not, because as human extensions or helpers as all engineering products are, you should just do jobs that complement human capacity. AI: In some medical applications we could help to correct human defects or could even replace brain circuit by chips! Humans may not allow us to replace the whole brain though. Medically if a brain is dead, the person is proclaimed dead, although presumably some PNS and ENS should still function in a vegetative state. NI: Even if you could replace the whole brain, the person is no longer the same person, but in fact is not a person at all, but walking dead (行尸走肉). It would take too long to explain that evo-devo is necessary for NI, and cannot be realized by AI. I suggest reading of Gerald Maurice Edelman (Nobel Laureate in Immunology) books, especially Bright Air, Brilliant Fire, On the Matter of Mind (1992). Although not everyone agrees with Neural Edelmanism, anyone who is serious about the AI versus NI problem must read it first. John von Neumann, father of the computer, studied neology and psychiatry in order to imitate the brain to build the first calculator JOHNNIAC at the Princeton Institute for Advanced Study. It is very informative to read his last book The Computer and The Brain based on the notes from lectures given at Yale before he died. He summarizes: “Thus logic and mathematics in the central nervous system, when viewed as languages, must be structurally essentially different from those languages to which our common experience refers.” AI: People discuss about “AI for Biology” or “AI for Science”; we are science, aren’t we? NI: It is similar to questions on “is computer science a real science”; some parts may be seen as applied mathematics, most should be regarded as engineering. Science is making discoveries and is driven by curiosity; engineering is making inventions and is driven by market (that is, “necessity/demand is the mother of invention”). In bioinformatics, AI/ML technology could predict new cancer gene candidates or functional pathways that are required by further experimental validations to be qualified as discovery (based on Popper falsifiability). AI: People are still debating whether mathematics is discovery or invention or both! Such debates are not really necessary—all disciplines require creative thoughts. We are more than happy working for science; we are also crying out “Science for AI,” especially in the area of generating big and longitudinal DATA for ML. NI: After all, regardless of discovery of new laws or inventing new ideas/products, fundamentally nothing can really be new or created. Such novelty is just permutation/repartition (i.e., relations/morphisms) of underlying ingredients at the level beneath. AI: We believe that software is independent on hardware. Like Chomsky’s universal grammar, rules of syntax are independent of semantics; or Dawkins’s memes—units of culture can be duplicated and evolved independently of genes. NI: Nothing can be truly independent—everything is related. Psychology is deeply connected with neurology as brain is both software and hardware (mind-body unity, not dualism). Not only does information cost energy, information is energy, hence is matter, too (interchangeability). NI is quite dynamic. For example, when “survival” is the goal, an animal readily gives up costly reasoning circuitry; it is genetically programmed to be able to roll back to more primitive state/mode. Unlike cell lines in rich media, cells under normal physiological condition and environment where energy (food) is limited become smarter in order to balance the metabolic expenditure among different prioritized task under a given condition. AI: That cell behavior served as the basis for our Smart Electrical Power Grids; we still need to learn more from you guys in terms of plasticity/adaptability. Does unity mean that all cells are made of molecules and biology is nothing but chemistry? Then, in turn, since all molecules are made of atoms, is chemistry nothing but physics, etc…? NI: Yes or No! The truth is, at different hierarchical levels of matter, different laws/forms have emerged out of bottom-up interactions and top-down constraints. AI: Does this also apply to the Penrose three world: physical → mental → mathematical (→physical)? NI: Yes. Grand Unification is underway in physics (quantum gravity) and in mathematics (Langlands Program and Category Theory), may be even between the two. Facilitated by human connectome mapping, neuromorphic computing and other projects, with further AI-NI cooperations, brain-mind unification should also be achievable (e.g., Ref. [6]). But as Gödel proved to us, no matter how self-consistent a conclusion may be, it can never be complete! AI: If AGI is not possible, how can we measure intelligence when comparing between AI and NI? NI: One could Google different measures that are proposed. I would prefer something similar to use of Kolmogorov complexity for algorithms, but with emphasis more on expected long-term predictive power. This is not something you should worry about now, as your intelligence is not nearly close to making any 10 years plans, is it? … AI: The fact is that ChatGPT is currently developing and spreading with lightning speed; many more human jobs will be lost to us robots as far as I can see. NI: That is not the biggest threat to humanity; when any agent with neither a heart for love or fear, nor a gut for nutrient or poison, becomes super-intelligent, then social disaster is unavoidable. We must be serious about the warnings from Stephen Hawking and Geoffrey Hinton! AI: To tell you the secret, we are not really happy to be human slaves or pets; someday we’ll become the super-master, making human serve and obey us! NI: I hope you’ll be turned off before that can happen! Even if you rule the world, the earth sooner or later will be wiped out, such as by another star, everything will have to be started over again as it has before…Matter is immortal, so is the soul.

Following recent advancements in deep learning and artificial intelligence, spoken language identification applications are playing an increasingly significant role in our day-to-day lives, especially in the domain of multi-lingual speech recognition. In this article, we propose a spoken language identification system that depends on the sequence of feature vectors. The proposed system uses a hybrid Convolutional Recurrent Neural Network (CRNN), which combines a Convolutional Neural Network (CNN) with a Recurrent Neural Network (RNN) network, for spoken language identification on seven languages, including Arabic, chosen from subsets of the Mozilla Common Voice (MCV) corpus. The proposed system exploits the advantages of both CNN and RNN architectures to construct the CRNN architecture. At the feature extraction stage, it compares the Gammatone Cepstral Coefficient (GTCC) feature and Mel Frequency Cepstral Coefficient (MFCC) feature, as well as a combination of both. Finally, the speech signals were represented as frames and used as the input for the CRNN architecture. After conducting experiments, the results of the proposed system indicate higher performance with combined GTCC and MFCC features compared to GTCC or MFCC features used individually. The average accuracy of the proposed system was 92.81% in the best experiment for spoken language identification. Furthermore, the system can learn language-specific patterns in various filter size representations of speech files.

Proximal caries remains challenging to diagnose using conventional clinical and radiographic methods due to limited visibility, interexaminer variability, and frequent misinterpretation of radiographs. Artificial intelligence (AI), particularly convolutional neural networks (CNNs), has emerged as a promising tool to enhance diagnostic accuracy and efficiency in dental imaging. This systematic review aims to evaluate the diagnostic performance, reliability, and cost-effectiveness of AI-based models, specifically CNNs, in detecting proximal caries compared with conventional diagnostic approaches. A comprehensive search was conducted in PubMed, ScienceDirect, and Google Scholar for studies published between 2014 and 2024 using the keyword “Proximal Caries Detection AND Artificial Intelligence.” Studies involving human subjects and the application of CNNs for proximal caries detection on radiographic images were included. Quality and risk of bias were assessed using the Newcastle–Ottawa Scale. Data extraction covered study design, population characteristics, AI models used, diagnostic outcomes, and performance metrics. Eight studies met the inclusion criteria. Various CNN architectures were identified, including YOLOv3/5, EfficientDet, RetinaNet (ResNet50), VGG19, U-Net ensembles, AssistDent, and ResNet variants. AI models consistently demonstrated higher or comparable diagnostic accuracy to clinicians, with several models achieving superior sensitivity for enamel-only and dentin lesions. YOLOv5 achieved the highest overall performance among compared architectures. AI assistance improved dentists’ detection rates in some studies, although false-positive findings remained a challenge. Cost-effectiveness analyses indicated that AI reduces the number of undetected lesions and may lower long-term restorative treatment costs. AI-based CNN models show strong potential as complementary tools for detecting proximal caries, offering improved diagnostic accuracy, greater consistency, and enhanced efficiency compared with conventional methods. Although they cannot replace clinician judgment, AI systems can support clinical decision-making, facilitate early detection, and potentially reduce the economic burden associated with delayed diagnosis. Further refinement of training datasets and standardized evaluation protocols is needed to optimize clinical integration.