Convolutional neural networks: an overview and application in radiology

Addressing docking pose selection with structure-based deep learning: Recent advances, challenges and opportunities

Molecular docking is a widely used technique in drug discovery to predict the binding mode of a given ligand to its target. However, the identification of the near-native binding pose in docking experiments still represents a challenging task as the scoring functions currently employed by docking programs are parametrized to predict the binding affinity, and, therefore, they often fail to correctly identify the ligand native binding conformation. Selecting the correct binding mode is crucial to obtaining meaningful results and to conveniently optimizing new hit compounds. Deep learning (DL) algorithms have been an area of a growing interest in this sense for their capability to extract the relevant information directly from the protein-ligand structure. Our review aims to present the recent advances regarding the development of DL-based pose selection approaches, discussing limitations and possible future directions. Moreover, a comparison between the performances of some classical scoring functions and DL-based methods concerning their ability to select the correct binding mode is reported. In this regard, two novel DL-based pose selectors developed by us are presented.

Artificial intelligence for skin permeability prediction: deep learning

BACKGROUND AND OBJECTIVE

Researchers have put in significant laboratory time and effort in measuring the permeability coefficient (Kp) of xenobiotics. To develop alternative approaches to this labour-intensive procedure, predictive models have been employed by scientists to describe the transport of xenobiotics across the skin. Most quantitative structure-permeability relationship (QSPR) models are derived statistically from experimental data. Recently, artificial intelligence-based computational drug delivery has attracted tremendous interest. Deep learning is an umbrella term for machine-learning algorithms consisting of deep neural networks (DNNs). Distinct network architectures, like convolutional neural networks (CNNs), feedforward neural networks (FNNs), and recurrent neural networks (RNNs), can be employed for prediction.

METHODS

In this project, we used a convolutional neural network, feedforward neural network, and recurrent neural network to predict skin permeability coefficients from a publicly available database reported by Cheruvu et al. The dataset contains 476 records of 145 chemicals, xenobiotics, and pharmaceuticals, administered on the human epidermis in vitro from aqueous solutions of constant concentration either saturated in infinite dose quantities or diluted. All the computations were conducted with Python under Anaconda and Jupyterlab environment after importing the required Python, Keras, and Tensorflow modules.

RESULTS

We used a convolutional neural network, feedforward neural network, and recurrent neural network to predict log kp.

CONCLUSION

This research work shows that deep learning networks can be successfully used to digitally screen and predict the skin permeability of xenobiotics.

Marine oil spill detection and segmentation in SAR data with two steps Deep Learning framework

Marine oil spills pose significant ecological and economic threats worldwide, requiring effective decision-making tools. In this study, the optimal parameters, and configurations for Deep Learning models in oil spill classification and segmentation using Sentinel-1 SAR imagery were identified. First, a new Sentinel-1 image dataset was created. Ninety CNN configurations were explored for classification by varying the number of convolutional layers, filters, hidden layers, and neurons in each layer. For segmentation tasks, MLP and U-Net models were evaluated with variations in convolutional layers, filters, and incorporation of IoU and Focal Loss. The results indicated that a CNN model with six layers, 32 filters, and two hidden layers achieved 99 % classification accuracy. For segmentation, the U-Net model with more layers and filters using Focal Loss achieved 99 % accuracy and 96 % IoU. Therefore, a CNN and U-Net framework was proposed that achieves an overall accuracy of 95 % and an IoU of 90 %.

Revolutionizing disease diagnosis and management: Open-access magnetic resonance imaging datasets a challenge for artificial intelligence driven liver iron quantification

Artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL) techniques, such as convolutional neural networks (CNNs), have emerged as transformative technologies with vast potential in healthcare. Body iron load is usually assessed using slightly invasive blood tests (serum ferritin, serum iron, and serum transferrin). Serum ferritin is widely used to assess body iron and drive medical management; however, it is an acute phase reactant protein offering wrong interpretation in the setting of inflammation and distressed patients. Magnetic resonance imaging is a non-invasive technique that can be used to assess liver iron. The ML and DL algorithms can be used to enhance the detection of minor changes. However, a lack of open-access datasets may delay the advancement of medical research in this field. In this letter, we highlight the importance of standardized datasets for advancing AI and CNNs in medical imaging. Despite the current limitations, embracing AI and CNNs holds promise in revolutionizing disease diagnosis and treatment.

Selection of convolutional neural network model for bladder tumor classification of cystoscopy images and comparison with humans

PURPOSE

An investigation of various convolutional neural network (CNN)-based deep learning algorithms was conducted to select the appropriate artificial intelligence (AI) model for calculating the diagnostic performance of bladder tumor classification on cystoscopy images, with the performance of the selected model to be compared against that of medical students and urologists.

METHODS

A total of 3,731 cystoscopic images that contained 2,191 tumor images were obtained from 543 bladder tumor cases and 219 normal cases were evaluated. A total of 17 CNN models were trained for tumor classification with various hyperparameters. The diagnostic performance of the selected AI model was compared with the results obtained from urologists and medical students by using the receiver operating characteristic (ROC) curve graph and metrics.

RESULTS

EfficientNetB0 was selected as the appropriate AI model. In the test results, EfficientNetB0 achieved a balanced accuracy of 81%, sensitivity of 88%, specificity of 74%, and an AUC of 92%. In contrast, human-derived diagnostic statistics for the test data showed an average balanced accuracy of 75%, sensitivity of 94%, and specificity of 55%. Specifically, urologists had an average balanced accuracy of 91%, sensitivity of 95%, and specificity of 88%, while medical students had an average balanced accuracy of 69%, sensitivity of 94%, and specificity of 44% Conclusions: Among the various AI models, we suggest that EfficientNetB0 is an appropriate AI classification model for determining the presence of bladder tumors in cystoscopic images. EfficientNetB0 showed the highest performance among several models and showed high accuracy and specificity compared to medical student. This AI technology will be helpful for less experienced urologists or non-urologists in making diagnoses. Image-based deep learning classifies bladder cancer using cystoscopy images and shows promise for generalized applications in biomedical image analysis and clinical decision-making.

A guide to artificial intelligence for cancer researchers

Artificial intelligence (AI) has been commoditized. It has evolved from a specialty resource to a readily accessible tool for cancer researchers. AI-based tools can boost research productivity in daily workflows, but can also extract hidden information from existing data, thereby enabling new scientific discoveries. Building a basic literacy in these tools is useful for every cancer researcher. Researchers with a traditional biological science focus can use AI-based tools through off-the-shelf software, whereas those who are more computationally inclined can develop their own AI-based software pipelines. In this article, we provide a practical guide for non-computational cancer researchers to understand how AI-based tools can benefit them. We convey general principles of AI for applications in image analysis, natural language processing and drug discovery. In addition, we give examples of how non-computational researchers can get started on the journey to productively use AI in their own work.

Morphometric Analysis of Lateral Cervical Lymph Node Metastasis in Papillary Thyroid Carcinoma Using Digital Pathology

Digital pathology uses digitized images for cancer research. We aimed to assess morphometric parameters using digital pathology for predicting recurrence in patients with papillary thyroid carcinoma (PTC) and lateral cervical lymph node (LN) metastasis. We analyzed 316 PTC patients and assessed the longest diameter and largest area of metastatic focus in LNs using a whole slide imaging scanner. In digital pathology assessment, the longest diameters and largest areas of metastatic foci in LNs were positively correlated with traditional optically measured diameters (R = 0.928 and R2 = 0.727, p < 0.001 and p < 0.001, respectively). The optimal cutoff diameter was 8.0 mm in both traditional microscopic (p = 0.009) and digital pathology (p = 0.016) evaluations, with significant differences in progression-free survival (PFS) observed at this cutoff (p = 0.006 and p = 0.002, respectively). The predictive area's cutoff was 35.6 mm2 (p = 0.005), which significantly affected PFS (p = 0.015). Using an 8.0-mm cutoff in traditional microscopic evaluation and a 35.6-mm2 cutoff in digital pathology showed comparable predictive results using the proportion of variation explained (PVE) methods (2.6% vs. 2.4%). Excluding cases with predominant cystic changes in LNs, the largest metastatic areas by digital pathology had the highest PVE at 3.9%. Furthermore, high volume of LN metastasis (p = 0.001), extranodal extension (p = 0.047), and high ratio of metastatic LNs (p = 0.006) were associated with poor prognosis. Both traditional microscopic and digital pathology evaluations effectively measured the longest diameter of metastatic foci in LNs. Moreover, digital pathology offers limited advantages in predicting PFS of patients with lateral cervical LN metastasis of PTC, especially those without predominant cystic changes in LNs.

The Use of Deep Learning Software in the Detection of Voice Disorders: A Systematic Review

OBJECTIVE

To summarize the use of deep learning in the detection of voice disorders using acoustic and laryngoscopic input, compare specific neural networks in terms of accuracy, and assess their effectiveness compared to expert clinical visual examination.

DATA SOURCES

Embase, MEDLINE, and Cochrane Central.

REVIEW METHODS

Databases were screened through November 11, 2023 for relevant studies. The inclusion criteria required studies to utilize a specified deep learning method, use laryngoscopy or acoustic input, and measure accuracy of binary classification between healthy patients and those with voice disorders.

RESULTS

Thirty-four studies met the inclusion criteria, with 18 focusing on voice analysis, 15 on imaging analysis, and 1 both. Across the 18 acoustic studies, 21 programs were used for identification of organic and functional voice disorders. These technologies included 10 convolutional neural networks (CNNs), 6 multilayer perceptrons (MLPs), and 5 other neural networks. The binary classification systems yielded a mean accuracy of 89.0% overall, including 93.7% for MLP programs and 84.5% for CNNs. Among the 15 imaging analysis studies, a total of 23 programs were utilized, resulting in a mean accuracy of 91.3%. Specifically, the twenty CNNs achieved a mean accuracy of 92.6% compared to 83.0% for the 3 MLPs.

CONCLUSION

Deep learning models were shown to be highly accurate in the detection of voice pathology, with CNNs most effective for assessing laryngoscopy images and MLPs most effective for assessing acoustic input. While deep learning methods outperformed expert clinical exam in limited comparisons, further studies integrating external validation are necessary.

DeepOCR: A multi-species deep-learning framework for accurate identification of open chromatin regions in livestock

A wealth of experimental evidence has suggested that open chromatin regions (OCRs) are involved in many critical biological activities, such as DNA replication, enhancer activity, and gene transcription. Accurately identifying OCRs in livestock species can provide critical insights into the distribution and characteristics of OCRs for disease treatment in livestock, thereby improving animal welfare. However, most current machine-learning methods for OCR prediction were originally designed for a limited number of model organisms, such as humans and some model organisms, and thus their performance on non-model organisms, specifically livestock, is often unsatisfactory. To bridge this gap, we propose DeepOCR, a lightweight depth-separable residual network model for predicting OCRs in livestock, including chicken, cattle, and sheep. DeepOCR integrates a single convolution layer and two improved residue structure blocks to extract and learn important features from the input DNA sequences. A fully connected layer was also employed to further process the extracted features and improve the robustness of the entire network. Our benchmarking experiments demonstrated superior prediction performance of DeepOCR compared to state-of-the-art approaches on testing datasets of the three species. The source code of DeepOCR is freely available for academic purposes at https://github.com/jasonzhao371/DeepOCR/. We anticipate DeepOCR servers as a practical and reliable computational tool for OCR-related studies in livestock species.

Applications and challenges of neural networks in otolaryngology (Review)

Artificial Intelligence (AI) has become a topic of interest that is frequently debated in all research fields. The medical field is no exception, where several unanswered questions remain. When and how this field can benefit from AI support in daily routines are the most frequently asked questions. The present review aims to present the types of neural networks (NNs) available for development, discussing their advantages, disadvantages and how they can be applied practically. In addition, the present review summarizes how NNs (combined with various other features) have already been applied in studies in the ear nose throat research field, from assisting diagnosis to treatment management. Although the answer to this question regarding AI remains elusive, understanding the basics and types of applicable NNs can lead to future studies possibly using more than one type of NN. This approach may bypass the actual limitations in accuracy and relevance of information generated by AI. The proposed studies, the majority of which used convolutional NNs, obtained accuracies varying 70-98%, with a number of studies having the AI trained on a limited number of cases (<100 patients). The lack of standardization in AI protocols for research negatively affects data homogeneity and transparency of databases.

Deep Learning for Automated Image Segmentation of the Middle Ear: A Scoping Review

OBJECTIVE

Convolutional neural networks (CNNs) have revolutionized medical image segmentation in recent years. This scoping review aimed to carry out a comprehensive review of the literature describing automated image segmentation of the middle ear using CNNs from computed tomography (CT) scans.

DATA SOURCES

A comprehensive literature search, generated jointly with a medical librarian, was performed on Medline, Embase, Scopus, Web of Science, and Cochrane, using Medical Subject Heading terms and keywords. Databases were searched from inception to July 2023. Reference lists of included papers were also screened.

REVIEW METHODS

Ten studies were included for analysis, which contained a total of 866 scans which were used in model training/testing. Thirteen different architectures were described to perform automated segmentation. The best Dice similarity coefficient (DSC) for the entire ossicular chain was 0.87 using ResNet. The highest DSC for any structure was the incus using 3D-V-Net at 0.93. The most difficult structure to segment was the stapes, with the highest DSC of 0.84 using 3D-V-Net.

CONCLUSIONS

Numerous architectures have demonstrated good performance in segmenting the middle ear using CNNs. To overcome some of the difficulties in segmenting the stapes, we recommend the development of an architecture trained on cone beam CTs to provide improved spatial resolution to assist with delineating the smallest ossicle.

IMPLICATIONS FOR PRACTICE

This has clinical applications for preoperative planning, diagnosis, and simulation.

Intra and inter-regional functional connectivity of the human brain due to Task-Evoked fMRI Data classification through CNN & LSTM

BACKGROUND AND PURPOSE

Olfaction is an early marker of neurodegenerative disease. Standard olfactory function is essential due to the importance of olfaction in human life. The psychophysical evaluation assesses the olfactory function commonly. It is patient-reported, and results rely on the patient's answers and collaboration. However, methodological difficulties attributed to the psychophysical evaluation of olfactory-related cerebral areas led to limited assessment of olfactory function in the human brain.

MATERIALS AND METHODS

The current study utilized clustering approaches to assess olfactory function in fMRI data and used brain activity to parcellate the brain with homogeneous properties. Deep neural network architecture based on ResNet convolutional neural networks (CNN) and Long Short-Term Model (LSTM) designed to classify healthy with olfactory disorders subjects.

RESULTS

The fMRI result obtained by k-means unsupervised machine learning model was within the expected outcome and similar to those found with the conn toolbox in detecting active areas. There was no significant difference between the means of subjects and every subject. Proposing a CRNN deep learning model to classify fMRI data in two different healthy and with olfactory disorders groups leads to an accuracy score of 97 %.

CONCLUSIONS

The K-means unsupervised algorithm can detect the active regions in the brain and analyze olfactory function. Classification results prove the CNN-LSTM architecture using ResNet provides the best accuracy score in olfactory fMRI data. It is the first attempt conducted on olfactory fMRI data in detail until now.

Enhancing bladder cancer diagnosis through transitional cell carcinoma polyp detection and segmentation: an artificial intelligence powered deep learning solution

Background

Bladder cancer, specifically transitional cell carcinoma (TCC) polyps, presents a significant healthcare challenge worldwide. Accurate segmentation of TCC polyps in cystoscopy images is crucial for early diagnosis and urgent treatment. Deep learning models have shown promise in addressing this challenge.

Methods

We evaluated deep learning architectures, including Unetplusplus_vgg19, Unet_vgg11, and FPN_resnet34, trained on a dataset of annotated cystoscopy images of low quality.

Results

The models showed promise, with Unetplusplus_vgg19 and FPN_resnet34 exhibiting precision of 55.40 and 57.41%, respectively, suitable for clinical application without modifying existing treatment workflows.

Conclusion

Deep learning models demonstrate potential in TCC polyp segmentation, even when trained on lower-quality images, suggesting their viability in improving timely bladder cancer diagnosis without impacting the current clinical processes.

Detection of milk adulteration using coffee ring effect and convolutional neural network

A low-cost and effective method is reported to identify water and synthetic milk adulteration of cow's milk using coffee ring patterns. The cow's milk samples were diluted with tap water (TW), distilled water (DW) and mineral water (MW) and drop cast onto glass slides to observe coffee ring patterns. The area of the ring, total particle area and average particle diameter were extracted from these patterns. For each ring, the ratio of total particle area versus total ring area was calculated. The area ratio, regardless of water adulterants, follows an exponential model with respect to average particle diameter. Unlike TW, the ratio for DW and MW adulterated milk are clustered and classified together with respect to the particle diameter. These results were independent of dilution level and are used for adulterant classification. The ring of milk adulterated using synthetic milk gave multiple concentric rings, flower-like structures, and oil globules throughout the dilution level. An Alexnet model was used to classify water and synthetic milk adulterants in authentic milk. The trained model could achieve 96.7% and 95.8% accuracy for binary and tertiary classification respectively. These results enable us to distinguish synthetic milk from pure milk and segregate DW and MW with respect to TW adulterated milk.

A comparative analysis of different augmentations for brain images

Deep learning (DL) requires a large amount of training data to improve performance and prevent overfitting. To overcome these difficulties, we need to increase the size of the training dataset. This can be done by augmentation on a small dataset. The augmentation approaches must enhance the model's performance during the learning period. There are several types of transformations that can be applied to medical images. These transformations can be applied to the entire dataset or to a subset of the data, depending on the desired outcome. In this study, we categorize data augmentation methods into four groups: Absent augmentation, where no modifications are made; basic augmentation, which includes brightness and contrast adjustments; intermediate augmentation, encompassing a wider array of transformations like rotation, flipping, and shifting in addition to brightness and contrast adjustments; and advanced augmentation, where all transformation layers are employed. We plan to conduct a comprehensive analysis to determine which group performs best when applied to brain CT images. This evaluation aims to identify the augmentation group that produces the most favorable results in terms of improving model accuracy, minimizing diagnostic errors, and ensuring the robustness of the model in the context of brain CT image analysis.

The innovation of AI-based software in oral diseases: clinical-histopathological correlation diagnostic accuracy primary study

BACKGROUND

Machine learning (ML) through artificial intelligence (AI) could provide clinicians and oral pathologists to advance diagnostic problems in the field of potentially malignant lesions, oral cancer, periodontal diseases, salivary gland disease, oral infections, immune-mediated disease, and others. AI can detect micro-features beyond human eyes and provide solution in critical diagnostic cases.

OBJECTIVE

The objective of this study was developing a software with all needed feeding data to act as AI-based program to diagnose oral diseases. So our research question was: Can we develop a Computer-Aided Software for accurate diagnosis of oral diseases based on clinical and histopathological data inputs?

METHOD

The study sample included clinical images, patient symptoms, radiographic images, histopathological images and texts for the oral diseases of interest in the current study (premalignant lesions, oral cancer, salivary gland neoplasms, immune mediated oral mucosal lesions, oral reactive lesions) total oral diseases enrolled in this study was 28 diseases retrieved from the archives of oral maxillofacial pathology department. Total 11,200 texts and 3000 images (2800 images were used for training data to the program and 100 images were used as test data to the program and 100 cases for calculating accuracy, sensitivity& specificity).

RESULTS

The correct diagnosis rates for group 1 (software users), group 2 (microscopic users) and group 3 (hybrid) were 87%, 90.6, 95% respectively. The reliability for inter-observer value was done by calculating Cronbach's alpha and interclass correlation coefficient. The test revealed for group 1, 2 and 3 the following values respectively 0.934, 0.712 & 0.703. All groups showed acceptable reliability especially for Diagnosis Oral Diseases Software (DODS) that revealed higher reliability value than other groups. However, The accuracy, sensitivity & specificity of this software was lower than those of oral pathologists (master's degree).

CONCLUSION

The correct diagnosis rate of DODS was comparable to oral pathologists using standard microscopic examination. The DODS program could be utilized as diagnostic guidance tool with high reliability & accuracy.

Using artificial intelligence to study atherosclerosis from computed tomography imaging: A state-of-the-art review of the current literature

With the enormous progress in the field of cardiovascular imaging in recent years, computed tomography (CT) has become readily available to phenotype atherosclerotic coronary artery disease. New analytical methods using artificial intelligence (AI) enable the analysis of complex phenotypic information of atherosclerotic plaques. In particular, deep learning-based approaches using convolutional neural networks (CNNs) facilitate tasks such as lesion detection, segmentation, and classification. New radiotranscriptomic techniques even capture underlying bio-histochemical processes through higher-order structural analysis of voxels on CT images. In the near future, the international large-scale Oxford Risk Factors And Non-invasive Imaging (ORFAN) study will provide a powerful platform for testing and validating prognostic AI-based models. The goal is the transition of these new approaches from research settings into a clinical workflow. In this review, we present an overview of existing AI-based techniques with focus on imaging biomarkers to determine the degree of coronary inflammation, coronary plaques, and the associated risk. Further, current limitations using AI-based approaches as well as the priorities to address these challenges will be discussed. This will pave the way for an AI-enabled risk assessment tool to detect vulnerable atherosclerotic plaques and to guide treatment strategies for patients.

Detecting Parkinson's disease from shoe-mounted accelerometer sensors using convolutional neural networks optimized with modified metaheuristics

Neurodegenerative conditions significantly impact patient quality of life. Many conditions do not have a cure, but with appropriate and timely treatment the advance of the disease could be diminished. However, many patients only seek a diagnosis once the condition progresses to a point at which the quality of life is significantly impacted. Effective non-invasive and readily accessible methods for early diagnosis can considerably enhance the quality of life of patients affected by neurodegenerative conditions. This work explores the potential of convolutional neural networks (CNNs) for patient gain freezing associated with Parkinson's disease. Sensor data collected from wearable gyroscopes located at the sole of the patient's shoe record walking patterns. These patterns are further analyzed using convolutional networks to accurately detect abnormal walking patterns. The suggested method is assessed on a public real-world dataset collected from parents affected by Parkinson's as well as individuals from a control group. To improve the accuracy of the classification, an altered variant of the recent crayfish optimization algorithm is introduced and compared to contemporary optimization metaheuristics. Our findings reveal that the modified algorithm (MSCHO) significantly outperforms other methods in accuracy, demonstrated by low error rates and high Cohen's Kappa, precision, sensitivity, and F1-measures across three datasets. These results suggest the potential of CNNs, combined with advanced optimization techniques, for early, non-invasive diagnosis of neurodegenerative conditions, offering a path to improve patient quality of life.

Convolutional Neural Network to Classify Infrared Thermal Images of Fractured Wrists in Pediatrics

Convolutional neural network (CNN) models were devised and evaluated to classify infrared thermal (IRT) images of pediatric wrist fractures. The images were recorded from 19 participants with a wrist fracture and 21 without a fracture (sprain). The injury diagnosis was by X-ray radiography. For each participant, 299 IRT images of their wrists were recorded. These generated 11,960 images (40 participants × 299 images). For each image, the wrist region of interest (ROI) was selected and fast Fourier transformed (FFT) to obtain a magnitude frequency spectrum. The spectrum was resized to 100 × 100 pixels from its center as this region represented the main frequency components. Image augmentations of rotation, translation and shearing were applied to the 11,960 magnitude frequency spectra to assist with the CNN generalization during training. The CNN had 34 layers associated with convolution, batch normalization, rectified linear unit, maximum pooling and SoftMax and classification. The ratio of images for the training and test was 70:30, respectively. The effects of augmentation and dropout on CNN performance were explored. Wrist fracture identification sensitivity and accuracy of 88% and 76%, respectively, were achieved. The CNN model was able to identify wrist fractures; however, a larger sample size would improve accuracy.

Fundamentals for predicting transcriptional regulations from DNA sequence patterns

Cell-type-specific regulatory elements, cataloged through extensive experiments and bioinformatics in large-scale consortiums, have enabled enrichment analyses of genetic associations that primarily utilize positional information of the regulatory elements. These analyses have identified cell types and pathways genetically associated with human complex traits. However, our understanding of detailed allelic effects on these elements' activities and on-off states remains incomplete, hampering the interpretation of human genetic study results. This review introduces machine learning methods to learn sequence-dependent transcriptional regulation mechanisms from DNA sequences for predicting such allelic effects (not associations). We provide a concise history of machine-learning-based approaches, the requirements, and the key computational processes, focusing on primers in machine learning. Convolution and self-attention, pivotal in modern deep-learning models, are explained through geometrical interpretations using dot products. This facilitates understanding of the concept and why these have been used for machine learning for DNA sequences. These will inspire further research in this genetics and genomics field.

Applications of Artificial Intelligence in Acute Abdominal Imaging

Artificial intelligence (AI) is a rapidly growing field with significant implications for radiology. Acute abdominal pain is a common clinical presentation that can range from benign conditions to life-threatening emergencies. The critical nature of these situations renders emergent abdominal imaging an ideal candidate for AI applications. CT, radiographs, and ultrasound are the most common modalities for imaging evaluation of these patients. For each modality, numerous studies have assessed the performance of AI models for detecting common pathologies, such as appendicitis, bowel obstruction, and cholecystitis. The capabilities of these models range from simple classification to detailed severity assessment. This narrative review explores the evolution, trends, and challenges in AI applications for evaluating acute abdominal pathologies. We review implementations of AI for non-traumatic and traumatic abdominal pathologies, with discussion of potential clinical impact, challenges, and future directions for the technology.

Sub-photon accuracy noise reduction of a single shot coherent diffraction pattern with an atomic model trained autoencoder

Single-shot imaging with femtosecond X-ray lasers is a powerful measurement technique that can achieve both high spatial and temporal resolution. However, its accuracy has been severely limited by the difficulty of applying conventional noise-reduction processing. This study uses deep learning to validate noise reduction techniques, with autoencoders serving as the learning model. Focusing on the diffraction patterns of nanoparticles, we simulated a large dataset treating the nanoparticles as composed of many independent atoms. Three neural network architectures are investigated: neural network, convolutional neural network and U-net, with U-net showing superior performance in noise reduction and subphoton reproduction. We also extended our models to apply to diffraction patterns of particle shapes different from those in the simulated data. We then applied the U-net model to a coherent diffractive imaging study, wherein a nanoparticle in a microfluidic device is exposed to a single X-ray free-electron laser pulse. After noise reduction, the reconstructed nanoparticle image improved significantly even though the nanoparticle shape was different from the training data, highlighting the importance of transfer learning.

NTSM: a non-salient target segmentation model for oral mucosal diseases

BACKGROUND

Oral mucosal diseases are similar to the surrounding normal tissues, i.e., their many non-salient features, which poses a challenge for accurate segmentation lesions. Additionally, high-precision large models generate too many parameters, which puts pressure on storage and makes it difficult to deploy on portable devices.

METHODS

To address these issues, we design a non-salient target segmentation model (NTSM) to improve segmentation performance while reducing the number of parameters. The NTSM includes a difference association (DA) module and multiple feature hierarchy pyramid attention (FHPA) modules. The DA module enhances feature differences at different levels to learn local context information and extend the segmentation mask to potentially similar areas. It also learns logical semantic relationship information through different receptive fields to determine the actual lesions and further elevates the segmentation performance of non-salient lesions. The FHPA module extracts pathological information from different views by performing the hadamard product attention (HPA) operation on input features, which reduces the number of parameters.

RESULTS

The experimental results on the oral mucosal diseases (OMD) dataset and international skin imaging collaboration (ISIC) dataset demonstrate that our model outperforms existing state-of-the-art methods. Compared with the nnU-Net backbone, our model has 43.20% fewer parameters while still achieving a 3.14% increase in the Dice score.

CONCLUSIONS

Our model has high segmentation accuracy on non-salient areas of oral mucosal diseases and can effectively reduce resource consumption.

A hybrid framework for glaucoma detection through federated machine learning and deep learning models

BACKGROUND

Glaucoma, the second leading cause of global blindness, demands timely detection due to its asymptomatic progression. This paper introduces an advanced computerized system, integrates Machine Learning (ML), convolutional neural networks (CNNs), and image processing for accurate glaucoma detection using medical imaging data, surpassing prior research efforts.

METHOD

Developing a hybrid glaucoma detection framework using CNNs (ResNet50, VGG-16) and Random Forest. Models analyze pre-processed retinal images independently, and post-processing rules combine predictions for an overall glaucoma impact assessment.

RESULT

The hybrid framework achieves a significant 95.41% accuracy, with precision and recall at 99.37% and 88.37%, respectively. The F1 score, balancing precision and recall, reaches a commendable 93.52%. These results highlight the robustness and effectiveness of the hybrid framework in accurate glaucoma diagnosis.

CONCLUSION

In summary, our research presents an innovative hybrid framework combining CNNs and traditional ML models for glaucoma detection. Using ResNet50, VGG-16, and Random Forest in an ensemble approach yields remarkable accuracy, precision, recall, and F1 score. These results showcase the methodology's potential to enhance glaucoma diagnosis, emphasizing its promising role in early detection and preventing irreversible vision loss. The integration of ML and DNNs in medical imaging analysis suggests a valuable path for future advancements in ophthalmic healthcare.

Intelligent classification of cardiotocography based on a support vector machine and convolutional neural network: Multiscene research

OBJECTIVE

To propose a computerized system utilizing multiscene analysis based on a support vector machine (SVM) and convolutional neural network (CNN) to assess cardiotocography (CTG) intelligently.

METHODS

We retrospectively collected 2542 CTG records of singleton pregnancies delivered at the maternity ward of the First Affiliated Hospital of Xi'an Jiaotong University from October 10, 2020, to August 7, 2021. CTG records were divided into five categories (baseline, variability, acceleration, deceleration, and normality). Apart from the category of normality, the other four different categories of abnormal data correspond to four scenes. Each scene was divided into training and testing sets at 9:1 or 7:3. We used three computer algorithms (dynamic threshold, SVM, and CNN) to learn and optimize the system. Accuracy, sensitivity, and specificity were performed to evaluate performance.

RESULTS

The global accuracy, sensitivity, and specificity of the system were 93.88%, 93.06%, and 94.33%, respectively. In acceleration and deceleration scenes, when the convolution kernel was 3, the test data set reached the highest performance.

CONCLUSION

The multiscene research model using SVM and CNN is a potential effective tool to assist obstetricians in classifying CTG intelligently.

The development and validation of a milk feeding behavior alert from automated feeder data to classify calves at risk for a diarrhea bout: A diagnostic accuracy study

The objective of this diagnostic accuracy study was to develop and validate an alert to identify calves at risk for a diarrhea bout using milk feeding behavior data (behavior) from automated milk feeders (AMF). We enrolled Holstein calves (n = 259) as a convenience sample size from 2 facilities that were health scored daily preweaning and offered either 10 or 15 L/d of milk replacer. For alert development, 132 calves were enrolled and the ability of milk intake, drinking speed, and rewarded visits collected from AMF to identify calves at risk for diarrhea was tested. Alerts that had high diagnostic accuracy in the alert development phase were validated using a holdout validation strategy of 127 different calves from the same facilities (all offered 15 L/d) for -3 to 1 d relative to diarrhea diagnosis. We enrolled calves that were either healthy or had a first diarrheal bout (loose feces ≥2 d or watery feces ≥1 d). Relative change and rolling dividends for each milk feeding behavior were calculated for each calf from the previous 2 d. Logistic regression models and receiver operator curves (ROC) were used to assess the diagnostic ability for relative change and rolling dividends behavior relative to alert d) to classify calves at risk for a diarrhea bout from -2 to 0 d relative to diagnosis. To maximize sensitivity (Se), alert thresholds were based on ROC optimal classification cutoff. Diagnostic accuracy was met when the alert had a moderate area under the ROC curve (≥0.70), high accuracy (Acc; ≥0.80), high Se (≥0.80), and very high precision (Pre; ≥0.85). For alert development, deviations in rolling dividend milk intake with drinking speed had the best performance (10 L/d: ROC area under the curve [AUC] = 0.79, threshold ≤0.70; 15 L/d: ROC AUC = 0.82, threshold ≤0.60). Our diagnostic criteria were only met in calves offered 15 L/d (10 L/d: Se 75%, Acc 72%, Pre 92%, specificity [Sp] 55% vs. 15 L/d: Se 91%, Acc 91%, Pre 89%, Sp 73%). For holdout validation, rolling dividend milk intake with drinking speed met diagnostic criteria for one facility (threshold ≤0.60, Se 86%, Acc 82%, Pre 94%, Sp 50%). However, no milk feeding behavior alerts met diagnostic criteria for the second facility due to poor Se (relative change milk intake -0.36 threshold, Se 71%, Acc 70%, and Pre 97%). We suggest that changes in milk feeding behavior may indicate diarrhea bouts in dairy calves. Future research should validate this alert in commercial settings; furthermore, software updates, support, and new analytics might be required for on-farm application to implement these types of alerts.

Geographical discrimination of Asian red pepper powders using 1H NMR spectroscopy and deep learning-based convolution neural networks

This study investigated an innovative approach to discriminate the geographical origins of Asian red pepper powders by analyzing one-dimensional 1H NMR spectra through a deep learning-based convolution neural network (CNN). 1H NMR spectra were collected from 300 samples originating from China, Korea, and Vietnam and used as input data. Principal component analysis - linear discriminant analysis and support vector machine models were employed for comparison. Bayesian optimization was used for hyperparameter optimization, and cross-validation was performed to prevent overfitting. As a result, all three models discriminated the origins of the test samples with over 95 % accuracy. Specifically, the CNN models achieved a 100 % accuracy rate. Gradient-weighted class activation mapping analysis verified that the CNN models recognized the origins of the samples based on variations in metabolite distributions. This research demonstrated the potential of deep learning-based classification of 1H NMR spectra as an accurate and reliable approach for determining the geographical origins of various foods.

Anatomically aware dual-hop learning for pulmonary embolism detection in CT pulmonary angiograms

Pulmonary Embolisms (PE) represent a leading cause of cardiovascular death. While medical imaging, through computed tomographic pulmonary angiography (CTPA), represents the gold standard for PE diagnosis, it is still susceptible to misdiagnosis or significant diagnosis delays, which may be fatal for critical cases. Despite the recently demonstrated power of deep learning to bring a significant boost in performance in a wide range of medical imaging tasks, there are still very few published researches on automatic pulmonary embolism detection. Herein we introduce a deep learning based approach, which efficiently combines computer vision and deep neural networks for pulmonary embolism detection in CTPA. Our method brings novel contributions along three orthogonal axes: (1) automatic detection of anatomical structures; (2) anatomical aware pretraining, and (3) a dual-hop deep neural net for PE detection. We obtain state-of-the-art results on the publicly available multicenter large-scale RSNA dataset.

Prognostic Value of a Combined Nomogram Model Integrating 3-Dimensional Deep Learning and Radiomics for Head and Neck Cancer

OBJECTIVE

The preoperative prediction of the overall survival (OS) status of patients with head and neck cancer (HNC) is significant value for their individualized treatment and prognosis. This study aims to evaluate the impact of adding 3D deep learning features to radiomics models for predicting 5-year OS status.

METHODS

Two hundred twenty cases from The Cancer Imaging Archive public dataset were included in this study; 2212 radiomics features and 304 deep features were extracted from each case. The features were selected by univariate analysis and the least absolute shrinkage and selection operator, and then grouped into a radiomics model containing Positron Emission Tomography /Computed Tomography (PET/CT) radiomics features score, a deep model containing deep features score, and a combined model containing PET/CT radiomics features score +3D deep features score. TumorStage model was also constructed using initial patient tumor node metastasis stage to compare the performance of the combined model. A nomogram was constructed to analyze the influence of deep features on the performance of the model. The 10-fold cross-validation of the average area under the receiver operating characteristic curve and calibration curve were used to evaluate performance, and Shapley Additive exPlanations (SHAP) was developed for interpretation.

RESULTS

The TumorStage model, radiomics model, deep model, and the combined model achieved areas under the receiver operating characteristic curve of 0.604, 0.851, 0.840, and 0.895 on the train set and 0.571, 0.849, 0.832, and 0.900 on the test set. The combined model showed better performance of predicting the 5-year OS status of HNC patients than the radiomics model and deep model. The combined model was shown to provide a favorable fit in calibration curves and be clinically useful in decision curve analysis. SHAP summary plot and SHAP The SHAP summary plot and SHAP force plot visually interpreted the influence of deep features and radiomics features on the model results.

CONCLUSIONS

In predicting 5-year OS status in patients with HNC, 3D deep features could provide richer features for combined model, which showed outperformance compared with the radiomics model and deep model.

Evaluation of the structural integrity of different spinal cord tracts with magnetization transfer ratio in degenerative cervical myelopathy

PURPOSE

Degenerative cervical myelopathy (DCM) is a common cause of spinal cord dysfunction. In this study, we explored the potential of magnetization transfer ratio (MTR) for evaluating the structural integrity of spinal cord tracts in patients with clinically significant DCM.

METHODS

Fifty-three patients with DCM and 41 patients with cervical radiculopathy were evaluated using high-resolution cervical spinal cord magnetic resonance imaging (MRI), which included the magnetization transfer technique. MRI data were analyzed with the Spinal Cord Toolbox (v5.5); MTR values in each spinal tract were calculated and compared between groups after correction for patient age and sex. Correlations between MTR values and patients' clinical disability rate were also evaluated.

RESULTS

A statistically significant reduction in the average MTR of the spinal cord white matter, as well as the MTR of the ventral columns and lateral funiculi, was revealed in the DCM group (adjusted p < 0.01 for all comparisons). Furthermore, reductions in MTR values in the fasciculus cuneatus, spinocerebellar, rubrospinal, and reticulospinal tracts were found in patients with DCM (adjusted p < 0.01 for all comparisons). Positive correlations between the JOA score and the MTR within the ventral columns of the spinal cord (R = 0.38, adjusted p < 0.05) and the ventral spinocerebellar tract (R = 0.41, adjusted p < 0.05) were revealed.

CONCLUSION

The findings of our study indicate that demyelination in patients with DCM primarily affects the spinal tracts of the extrapyramidal system, and the extent of these changes is related to the severity of the condition.

Super-resolution techniques for biomedical applications and challenges

Super-resolution (SR) techniques have revolutionized the field of biomedical applications by detailing the structures at resolutions beyond the limits of imaging or measuring tools. These techniques have been applied in various biomedical applications, including microscopy, magnetic resonance imaging (MRI), computed tomography (CT), X-ray, electroencephalogram (EEG), ultrasound, etc. SR methods are categorized into two main types: traditional non-learning-based methods and modern learning-based approaches. In both applications, SR methodologies have been effectively utilized on biomedical images, enhancing the visualization of complex biological structures. Additionally, these methods have been employed on biomedical data, leading to improvements in computational precision and efficiency for biomedical simulations. The use of SR techniques has resulted in more detailed and accurate analyses in diagnostics and research, essential for early disease detection and treatment planning. However, challenges such as computational demands, data interpretation complexities, and the lack of unified high-quality data persist. The article emphasizes these issues, underscoring the need for ongoing development in SR technologies to further improve biomedical research and patient care outcomes.

Rapid and accurate identification of marine bacteria spores at a single-cell resolution by laser tweezers Raman spectroscopy and deep learning

Marine bacteria have been considered as important participants in revealing various carbon/sulfur/nitrogen cycles of marine ecosystem. Thus, how to accurately identify rare marine bacteria without a culture process is significant and valuable. In this work, we constructed a single-cell Raman spectra dataset from five living bacteria spores and utilized convolutional neural network to rapidly, accurately, nondestructively identify bacteria spores. The optimal CNN architecture can provide a prediction accuracy of five bacteria spore as high as 94.93% ± 1.78%. To evaluate the classification weight of extracted spectra features, we proposed a novel algorithm by occluding fingerprint Raman bands. Based on the relative classification weight arranged from large to small, four Raman bands located at 1518, 1397, 1666, and 1017 cm-1 mostly contribute to producing such high prediction accuracy. It can be foreseen that, LTRS combined with CNN approach have great potential for identifying marine bacteria, which cannot be cultured under normal condition.

Using neural networks to autonomously assess adequacy in intraoperative cholangiograms

BACKGROUND

Intraoperative cholangiography (IOC) is a contrast-enhanced X-ray acquired during laparoscopic cholecystectomy. IOC images the biliary tree whereby filling defects, anatomical anomalies and duct injuries can be identified. In Australia, IOC are performed in over 81% of cholecystectomies compared with 20 to 30% internationally (Welfare AIoHa in Australian Atlas of Healthcare Variation, 2017). In this study, we aim to train artificial intelligence (AI) algorithms to interpret anatomy and recognise abnormalities in IOC images. This has potential utility in (a) intraoperative safety mechanisms to limit the risk of missed ductal injury or stone, (b) surgical training and coaching, and (c) auditing of cholangiogram quality.

METHODOLOGY

Semantic segmentation masks were applied to a dataset of 1000 cholangiograms with 10 classes. Classes corresponded to anatomy, filling defects and the cholangiogram catheter instrument. Segmentation masks were applied by a surgical trainee and reviewed by a radiologist. Two convolutional neural networks (CNNs), DeeplabV3+ and U-Net, were trained and validated using 900 (90%) labelled frames. Testing was conducted on 100 (10%) hold-out frames. CNN generated segmentation class masks were compared with ground truth segmentation masks to evaluate performance according to a pixel-wise comparison.

RESULTS

The trained CNNs recognised all classes.. U-Net and DeeplabV3+ achieved a mean F1 of 0.64 and 0.70 respectively in class segmentation, excluding the background class. The presence of individual classes was correctly recognised in over 80% of cases. Given the limited local dataset, these results provide proof of concept in the development of an accurate and clinically useful tool to aid in the interpretation and quality control of intraoperative cholangiograms.

CONCLUSION

Our results demonstrate that a CNN can be trained to identify anatomical structures in IOC images. Future performance can be improved with the use of larger, more diverse training datasets. Implementation of this technology may provide cholangiogram quality control and improve intraoperative detection of ductal injuries or ductal injuries.

CECT: Controllable ensemble CNN and transformer for COVID-19 image classification

The COVID-19 pandemic has resulted in hundreds of million cases and numerous deaths worldwide. Here, we develop a novel classification network CECT by controllable ensemble convolutional neural network and transformer to provide a timely and accurate COVID-19 diagnosis. The CECT is composed of a parallel convolutional encoder block, an aggregate transposed-convolutional decoder block, and a windowed attention classification block. Each block captures features at different scales from 28 × 28 to 224 × 224 from the input, composing enriched and comprehensive information. Different from existing methods, our CECT can capture features at both multi-local and global scales without any sophisticated module design. Moreover, the contribution of local features at different scales can be controlled with the proposed ensemble coefficients. We evaluate CECT on two public COVID-19 datasets and it reaches the highest accuracy of 98.1% in the intra-dataset evaluation, outperforming existing state-of-the-art methods. Moreover, the developed CECT achieves an accuracy of 90.9% on the unseen dataset in the inter-dataset evaluation, showing extraordinary generalization ability. With remarkable feature capture ability and generalization ability, we believe CECT can be extended to other medical scenarios as a powerful diagnosis tool. Code is available at https://github.com/NUS-Tim/CECT.

Artificial intelligence in coronary artery calcium score: rationale, different approaches, and outcomes

Almost 35 years after its introduction, coronary artery calcium score (CACS) not only survived technological advances but became one of the cornerstones of contemporary cardiovascular imaging. Its simplicity and quantitative nature established it as one of the most robust approaches for atherosclerotic cardiovascular disease risk stratification in primary prevention and a powerful tool to guide therapeutic choices. Groundbreaking advances in computational models and computer power translated into a surge of artificial intelligence (AI)-based approaches directly or indirectly linked to CACS analysis. This review aims to provide essential knowledge on the AI-based techniques currently applied to CACS, setting the stage for a holistic analysis of the use of these techniques in coronary artery calcium imaging. While the focus of the review will be detailing the evidence, strengths, and limitations of end-to-end CACS algorithms in electrocardiography-gated and non-gated scans, the current role of deep-learning image reconstructions, segmentation techniques, and combined applications such as simultaneous coronary artery calcium and pulmonary nodule segmentation, will also be discussed.

Quantifying lung fissure integrity using a three-dimensional patch-based convolutional neural network on CT images for emphysema treatment planning

Purpose

Evaluation of lung fissure integrity is required to determine whether emphysema patients have complete fissures and are candidates for endobronchial valve (EBV) therapy. We propose a deep learning (DL) approach to segment fissures using a three-dimensional patch-based convolutional neural network (CNN) and quantitatively assess fissure integrity on CT to evaluate it in subjects with severe emphysema.

Approach

From an anonymized image database of patients with severe emphysema, 129 CT scans were used. Lung lobe segmentations were performed to identify lobar regions, and the boundaries among these regions were used to construct approximate interlobar regions of interest (ROIs). The interlobar ROIs were annotated by expert image analysts to identify voxels where the fissure was present and create a reference ROI that excluded non-fissure voxels (where the fissure is incomplete). A CNN configured by nnU-Net was trained using 86 CT scans and their corresponding reference ROIs to segment the ROIs of left oblique fissure (LOF), right oblique fissure (ROF), and right horizontal fissure (RHF). For an independent test set of 43 cases, fissure integrity was quantified by mapping the segmented fissure ROI along the interlobar ROI. A fissure integrity score (FIS) was then calculated as the percentage of labeled fissure voxels divided by total voxels in the interlobar ROI. Predicted FIS (p-FIS) was quantified from the CNN output, and statistical analyses were performed comparing p-FIS and reference FIS (r-FIS).

Results

The absolute percent error mean (±SD) between r-FIS and p-FIS for the test set was 4.0% (± 4.1 % ), 6.0% (± 9.3 % ), and 12.2% (± 12.5 % ) for the LOF, ROF, and RHF, respectively.

Conclusions

A DL approach was developed to segment lung fissures on CT images and accurately quantify FIS. It has potential to assist in the identification of emphysema patients who would benefit from EBV treatment.

CGO-ensemble: Chaos game optimization algorithm-based fusion of deep neural networks for accurate Mpox detection

The rising global incidence of human Mpox cases necessitates prompt and accurate identification for effective disease control. Previous studies have predominantly delved into traditional ensemble methods for detection, we introduce a novel approach by leveraging a metaheuristic-based ensemble framework. In this research, we present an innovative CGO-Ensemble framework designed to elevate the accuracy of detecting Mpox infection in patients. Initially, we employ five transfer learning base models that integrate feature integration layers and residual blocks. These components play a crucial role in capturing significant features from the skin images, thereby enhancing the models' efficacy. In the next step, we employ a weighted averaging scheme to consolidate predictions generated by distinct models. To achieve the optimal allocation of weights for each base model in the ensemble process, we leverage the Chaos Game Optimization (CGO) algorithm. This strategic weight assignment enhances classification outcomes considerably, surpassing the performance of randomly assigned weights. Implementing this approach yields notably enhanced prediction accuracy compared to using individual models. We evaluate the effectiveness of our proposed approach through comprehensive experiments conducted on two widely recognized benchmark datasets: the Mpox Skin Lesion Dataset (MSLD) and the Mpox Skin Image Dataset (MSID). To gain insights into the decision-making process of the base models, we have performed Gradient Class Activation Mapping (Grad-CAM) analysis. The experimental results showcase the outstanding performance of the CGO-ensemble, achieving an impressive accuracy of 100% on MSLD and 94.16% on MSID. Our approach significantly outperforms other state-of-the-art optimization algorithms, traditional ensemble methods, and existing techniques in the context of Mpox detection on these datasets. These findings underscore the effectiveness and superiority of the CGO-Ensemble in accurately identifying Mpox cases, highlighting its potential in disease detection and classification.

Deep Transfer Learning Using Real-World Image Features for Medical Image Classification, with a Case Study on Pneumonia X-ray Images

Deep learning has profoundly influenced various domains, particularly medical image analysis. Traditional transfer learning approaches in this field rely on models pretrained on domain-specific medical datasets, which limits their generalizability and accessibility. In this study, we propose a novel framework called real-world feature transfer learning, which utilizes backbone models initially trained on large-scale general-purpose datasets such as ImageNet. We evaluate the effectiveness and robustness of this approach compared to models trained from scratch, focusing on the task of classifying pneumonia in X-ray images. Our experiments, which included converting grayscale images to RGB format, demonstrate that real-world-feature transfer learning consistently outperforms conventional training approaches across various performance metrics. This advancement has the potential to accelerate deep learning applications in medical imaging by leveraging the rich feature representations learned from general-purpose pretrained models. The proposed methodology overcomes the limitations of domain-specific pretrained models, thereby enabling accelerated innovation in medical diagnostics and healthcare. From a mathematical perspective, we formalize the concept of real-world feature transfer learning and provide a rigorous mathematical formulation of the problem. Our experimental results provide empirical evidence supporting the effectiveness of this approach, laying the foundation for further theoretical analysis and exploration. This work contributes to the broader understanding of feature transferability across domains and has significant implications for the development of accurate and efficient models for medical image analysis, even in resource-constrained settings.

Recent advances in nanomaterial-based biosensor for periodontitis detection

Periodontitis, a chronic inflammatory condition caused by bacteria, often causes gradual destruction of the components that support teeth, such as the alveolar bone, cementum, periodontal ligament, and gingiva. This ultimately results in teeth becoming loose and eventually falling out. Timely identification has a crucial role in preventing and controlling its progression. Clinical measures are used to diagnose periodontitis. However, now, there is a hunt for alternative diagnostic and monitoring methods due to the progress of technology. Various biomarkers have been assessed using multiple bodily fluids as sample sources. Furthermore, conventional periodontal categorization factors do not provide significant insights into the present disease activity, severity and amount of tissue damage, future development, and responsiveness to treatment. In recent times, there has been a growing utilization of nanoparticle (NP)-based detection strategies to create quick and efficient detection assays. Every single one of these platforms leverages the distinct characteristics of NPs to identify periodontitis. Plasmonic NPs include metal NPs, quantum dots (QDs), carbon base NPs, and nanozymes, exceptionally potent light absorbers and scatterers. These find application in labeling, surface-enhanced spectroscopy, and color-changing sensors. Fluorescent NPs function as photostable and sensitive instruments capable of labeling various biological targets. This article presents a comprehensive summary of the latest developments in the effective utilization of various NPs to detect periodontitis.

The effect of hair removal and filtering on melanoma detection: a comparative deep learning study with AlexNet CNN

Melanoma is the most aggressive and prevalent form of skin cancer globally, with a higher incidence in men and individuals with fair skin. Early detection of melanoma is essential for the successful treatment and prevention of metastasis. In this context, deep learning methods, distinguished by their ability to perform automated and detailed analysis, extracting melanoma-specific features, have emerged. These approaches excel in performing large-scale analysis, optimizing time, and providing accurate diagnoses, contributing to timely treatments compared to conventional diagnostic methods. The present study offers a methodology to assess the effectiveness of an AlexNet-based convolutional neural network (CNN) in identifying early-stage melanomas. The model is trained on a balanced dataset of 10,605 dermoscopic images, and on modified datasets where hair, a potential obstructive factor, was detected and removed allowing for an assessment of how hair removal affects the model's overall performance. To perform hair removal, we propose a morphological algorithm combined with different filtering techniques for comparison: Fourier, Wavelet, average blur, and low-pass filters. The model is evaluated through 10-fold cross-validation and the metrics of accuracy, recall, precision, and the F1 score. The results demonstrate that the proposed model performs the best for the dataset where we implemented both a Wavelet filter and hair removal algorithm. It has an accuracy of 91.30%, a recall of 87%, a precision of 95.19%, and an F1 score of 90.91%.

Diagnosis of retinal damage using Resnet rescaling and support vector machine (Resnet-RS-SVM): a case study from an Indian hospital

PURPOSE

This study aims to address the challenge of identifying retinal damage in medical applications through a computer-aided diagnosis (CAD) approach. Data was collected from four prominent eye hospitals in India for analysis and model development.

METHODS

Data was collected from Silchar Medical College and Hospital (SMCH), Aravind Eye Hospital (Tamil Nadu), LV Prasad Eye Hospital (Hyderabad), and Medanta (Gurugram). A modified version of the ResNet-101 architecture, named ResNet-RS, was utilized for retinal damage identification. In this modified architecture, the last layer's softmax function was replaced with a support vector machine (SVM). The resulting model, termed ResNet-RS-SVM, was trained and evaluated on each hospital's dataset individually and collectively.

RESULTS

The proposed ResNet-RS-SVM model achieved high accuracies across the datasets from the different hospitals: 99.17% for Aravind, 98.53% for LV Prasad, 98.33% for Medanta, and 100% for SMCH. When considering all hospitals collectively, the model attained an accuracy of 97.19%.

CONCLUSION

The findings demonstrate the effectiveness of the ResNet-RS-SVM model in accurately identifying retinal damage in diverse datasets collected from multiple eye hospitals in India. This approach presents a promising advancement in computer-aided diagnosis for improving the detection and management of retinal diseases.

Convolutional neural network algorithm trained on lumbar spine radiographs to predict outcomes of transforaminal epidural steroid injection for lumbosacral radicular pain from spinal stenosis

Little is known about the therapeutic outcomes of transforaminal epidural steroid injection (TFESI) in patients with lumbosacral radicular pain due to lumbar spinal stenosis (LSS). Using lumbar spine radiographs as input data, we trained a convolutional neural network (CNN) to predict therapeutic outcomes after lumbar TFESI in patients with lumbosacral radicular pain caused by LSS. We retrospectively recruited 193 patients for this study. The lumbar spine radiographs included anteroposterior, lateral, and bilateral (left and right) oblique views. We cut each lumbar spine radiograph image into a square shape that included the vertebra corresponding to the level at which the TFESI was performed and the vertebrae juxta below and above that level. Output data were divided into "favorable outcome" (≥ 50% reduction in the numeric rating scale [NRS] score at 2 months post-TFESI) and "poor outcome" (< 50% reduction in the NRS score at 2 months post-TFESI). Using these input and output data, we developed a CNN model for predicting TFESI outcomes. The area under the curve of our model was 0.920. Its accuracy was 87.2%. Our CNN model has an excellent capacity for predicting therapeutic outcomes after lumbar TFESI in patients with lumbosacral radicular pain induced by LSS.

A systematic review of artificial intelligence tools for chronic pulmonary embolism on CT pulmonary angiography

Background

Chronic pulmonary embolism (PE) may result in pulmonary hypertension (CTEPH). Automated CT pulmonary angiography (CTPA) interpretation using artificial intelligence (AI) tools has the potential for improving diagnostic accuracy, reducing delays to diagnosis and yielding novel information of clinical value in CTEPH. This systematic review aimed to identify and appraise existing studies presenting AI tools for CTPA in the context of chronic PE and CTEPH.

Methods

MEDLINE and EMBASE databases were searched on 11 September 2023. Journal publications presenting AI tools for CTPA in patients with chronic PE or CTEPH were eligible for inclusion. Information about model design, training and testing was extracted. Study quality was assessed using compliance with the Checklist for Artificial Intelligence in Medical Imaging (CLAIM).

Results

Five studies were eligible for inclusion, all of which presented deep learning AI models to evaluate PE. First study evaluated the lung parenchymal changes in chronic PE and two studies used an AI model to classify PE, with none directly assessing the pulmonary arteries. In addition, a separate study developed a CNN tool to distinguish chronic PE using 2D maximum intensity projection reconstructions. While another study assessed a novel automated approach to quantify hypoperfusion to help in the severity assessment of CTEPH. While descriptions of model design and training were reliable, descriptions of the datasets used in training and testing were more inconsistent.

Conclusion

In contrast to AI tools for evaluation of acute PE, there has been limited investigation of AI-based approaches to characterising chronic PE and CTEPH on CTPA. Existing studies are limited by inconsistent reporting of the data used to train and test their models. This systematic review highlights an area of potential expansion for the field of AI in medical image interpretation.There is limited knowledge of A systematic review of artificial intelligence tools for chronic pulmonary embolism in CT. This systematic review provides an assessment on research that examined deep learning algorithms in detecting CTEPH on CTPA images, the number of studies assessing the utility of deep learning on CTPA in CTEPH was unclear and should be highlighted.

Automated detection and classification of concealed objects using infrared thermography and convolutional neural networks

This paper presents a study on the effectiveness of a convolutional neural network (CNN) in classifying infrared images for security scanning. Infrared thermography was explored as a non-invasive security scanner for stand-off and walk-through concealed object detection. Heat generated by human subjects radiates off the clothing surface, allowing detection by an infrared camera. However, infrared lacks in penetration capability compared to longer electromagnetic waves, leading to less obvious visuals on the clothing surface. ResNet-50 was used as the CNN model to automate the classification process of thermal images. The ImageNet database was used to pre-train the model, which was further fine-tuned using infrared images obtained from experiments. Four image pre-processing approaches were explored, i.e., raw infrared image, subject cropped region-of-interest (ROI) image, K-means, and Fuzzy-c clustered images. All these approaches were evaluated using the receiver operating characteristic curve on an internal holdout set, with an area-under-the-curve of 0.8923, 0.9256, 0.9485, and 0.9669 for the raw image, ROI cropped, K-means, and Fuzzy-c models, respectively. The CNN models trained using various image pre-processing approaches suggest that the prediction performance can be improved by the removal of non-decision relevant information and the visual highlighting of features.

Development and web deployment of prediction model for pulmonary arterial pressure in chronic thromboembolic pulmonary hypertension using machine learning

BACKGROUND AND PURPOSE

Mean pulmonary artery pressure (mPAP) is a key index for chronic thromboembolic pulmonary hypertension (CTEPH). Using machine learning, we attempted to construct an accurate prediction model for mPAP in patients with CTEPH.

METHODS

A total of 136 patients diagnosed with CTEPH were included, for whom mPAP was measured. The following patient data were used as explanatory variables in the model: basic patient information (age and sex), blood tests (brain natriuretic peptide (BNP)), echocardiography (tricuspid valve pressure gradient (TRPG)), and chest radiography (cardiothoracic ratio (CTR), right second arc ratio, and presence of avascular area). Seven machine learning methods including linear regression were used for the multivariable prediction models. Additionally, prediction models were constructed using the AutoML software. Among the 136 patients, 2/3 and 1/3 were used as training and validation sets, respectively. The average of R squared was obtained from 10 different data splittings of the training and validation sets.

RESULTS

The optimal machine learning model was linear regression (averaged R squared, 0.360). The optimal combination of explanatory variables with linear regression was age, BNP level, TRPG level, and CTR (averaged R squared, 0.388). The R squared of the optimal multivariable linear regression model was higher than that of the univariable linear regression model with only TRPG.

CONCLUSION

We constructed a more accurate prediction model for mPAP in patients with CTEPH than a model of TRPG only. The prediction performance of our model was improved by selecting the optimal machine learning method and combination of explanatory variables.

Hemodynamic property incorporated brain tumor segmentation by deep learning and density-based analysis of dynamic susceptibility contrast-enhanced magnetic resonance imaging (MRI)

Background

Magnetic resonance imaging (MRI) is a primary non-invasive imaging modality for tumor segmentation, leveraging its exceptional soft tissue contrast and high resolution. Current segmentation methods typically focus on structural MRI, such as T1-weighted post-contrast-enhanced or fluid-attenuated inversion recovery (FLAIR) sequences. However, these methods overlook the blood perfusion and hemodynamic properties of tumors, readily derived from dynamic susceptibility contrast (DSC) enhanced MRI. This study introduces a novel hybrid method combining density-based analysis of hemodynamic properties in time-dependent perfusion imaging with deep learning spatial segmentation techniques to enhance tumor segmentation.

Methods

First, a U-Net convolutional neural network (CNN) is employed on structural images to delineate a region of interest (ROI). Subsequently, Hierarchical Density-Based Scans (HDBScan) are employed within the ROI to augment segmentation by exploring intratumoral hemodynamic heterogeneity through the investigation of tumor time course profiles unveiled in DSC MRI.

Results

The approach was tested and evaluated using a cohort of 513 patients from the open-source University of Pennsylvania glioblastoma database (UPENN-GBM) dataset, achieving a 74.83% Intersection over Union (IoU) score when compared to structural-only segmentation. The algorithm also exhibited increased precision and localized predictions of heightened segmentation boundary complexity, resulting in a 146.92% increase in contour complexity (ICC) compared to the reference standard provided by the UPENN-GBM dataset. Importantly, segmenting tumors with the developed new approach uncovered a negative correlation of the tumor volume with the scores in the Karnofsky Performance Scale (KPS) clinically used for assessing the functional status of patients (-0.309), which is not observed with the prevailing segmentation standard.

Conclusions

This work demonstrated that including hemodynamic properties of tissues from DSC MRI can improve existing structural or morphological feature-based tumor segmentation techniques with additional information on tumor biology and physiology. This approach can also be applied to other clinical indications that use perfusion MRI for diagnosis or treatment monitoring.

Predicting drug activity against cancer through genomic profiles and SMILES

Due to the constant increase in cancer rates, the disease has become a leading cause of death worldwide, enhancing the need for its detection and treatment. In the era of personalized medicine, the main goal is to incorporate individual variability in order to choose more precisely which therapy and prevention strategies suit each person. However, predicting the sensitivity of tumors to anticancer treatments remains a challenge. In this work, we propose two deep neural network models to predict the impact of anticancer drugs in tumors through the half-maximal inhibitory concentration (IC50). These models join biological and chemical data to apprehend relevant features of the genetic profile and the drug compounds, respectively. In order to predict the drug response in cancer cell lines, this study employed different DL methods, resorting to Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs). In the first stage, two autoencoders were pre-trained with high-dimensional gene expression and mutation data of tumors. Afterward, this genetic background is transferred to the prediction models that return the IC50 value that portrays the potency of a substance in inhibiting a cancer cell line. When comparing RSEM Expected counts and TPM as methods for displaying gene expression data, RSEM has been shown to perform better in deep models and CNNs model can obtain better insight in these types of data. Moreover, the obtained results reflect the effectiveness of the extracted deep representations in the prediction of the IC50 value that portrays the potency of a substance in inhibiting a tumor, achieving a performance of a mean squared error of 1.06 and surpassing previous state-of-the-art models.

Application of deep learning in radiation therapy for cancer

In recent years, with the development of artificial intelligence, deep learning has been gradually applied to clinical treatment and research. It has also found its way into the applications in radiotherapy, a crucial method for cancer treatment. This study summarizes the commonly used and latest deep learning algorithms (including transformer, and diffusion models), introduces the workflow of different radiotherapy, and illustrates the application of different algorithms in different radiotherapy modules, as well as the defects and challenges of deep learning in the field of radiotherapy, so as to provide some help for the development of automatic radiotherapy for cancer.

Influence of intraoral scanning coverage on the accuracy of digital implant impressions - An in vitro study

OBJECTIVES

To evaluate the influence of intraoral scanning coverage (IOSC) on digital implant impression accuracy in various partially edentulous situations and predict the optimal IOSC.

METHODS

Five types of resin models were fabricated, each simulating single or multiple tooth loss scenarios with inserted implants and scan bodies. IOSC was subgrouped to cover two, four, six, eight, ten, and twelve teeth, as well as full arch. Each group underwent ten scans. A desktop scanner served as the reference. Accuracy was evaluated by measuring the Root mean square error (RMSE) values of scan bodies. A convolutional neural network (CNN) was trained to predict the optimal IOSC with different edentulous situations. Statistical analysis was performed using one-way ANOVA and Tukey's test.

RESULTS

For single-tooth-missing situations, in anterior sites, significantly better accuracy was observed in groups with IOSC ranging from four teeth to full arch (p < 0.05). In premolar sites, IOSC spanning four to six teeth were more accurate (p < 0.05), while in molar sites, groups with IOSC encompassing two to eight teeth exhibited better accuracy (p < 0.05). For multiple-teeth-missing situations, IOSC covering four, six, and eight teeth, as well as full arch showed better accuracy in anterior gaps (p < 0.05). In posterior gaps, IOSC of two, four, six or eight teeth were more accurate (p < 0.05). The CNN predicted distinct optimal IOSC for different edentulous scenarios.

CONCLUSIONS

Implant impression accuracy can be significantly impacted by IOSC in different partially edentulous situations. The selection of IOSC should be customized to the specific dentition defect condition.

CLINICAL SIGNIFICANCE

The number of teeth scanned can significantly affect digital implant impression accuracy. For missing single or four anterior teeth, scan at least four or six neighboring teeth is acceptable. In lateral cases, two neighboring teeth may suffice, but extending over ten teeth, including contralateral side, might deteriorate the scan.