Cogn Sci. 2024 Sep;48(9):e13492. doi: 10.1111/cogs.13492.

ABSTRACT

Early number skills represent critical milestones in children's cognitive development and are shaped over years of interacting with quantities and numerals in various contexts. Several connectionist computational models have attempted to emulate how certain number concepts may be learned, represented, and processed in the brain. However, these models mainly used highly simplified inputs and focused on limited tasks. We expand on previous work in two directions: First, we train a model end-to-end on video demonstrations in a synthetic environment with multimodal visual and language inputs. Second, we use a more holistic dataset of 35 tasks, covering enumeration, set comparisons, symbolic digits, and seriation. The order in which the model acquires tasks reflects input length and variability, and the resulting trajectories mostly fit with findings from educational psychology. The trained model also displays symbolic and non-symbolic size and distance effects. Using techniques from interpretability research, we investigate how our attention-based model integrates cross-modal representations and binds them into context-specific associative networks to solve different tasks. We compare models trained with and without symbolic inputs and find that the purely non-symbolic model employs more processing-intensive strategies to determine set size.

PMID:39226225 | DOI:10.1111/cogs.13492

IEEE J Biomed Health Inform. 2024 Sep 3;PP. doi: 10.1109/JBHI.2024.3454000. Online ahead of print.

ABSTRACT

Breast cancer, as a malignant tumor disease, has maintained high incidence and mortality rates over the years. Ultrasonography is one of the primary methods for diagnosing early-stage breast cancer. However, correctly interpreting breast ultrasound images requires massive time from physicians with specialized knowledge and extensive experience. Recently, deep learning-based method have made significant advancements in breast tumor segmentation and classification due to their powerful fitting capabilities. However, most existing methods focus on performing one of these tasks separately, and often failing to effectively leverage information from specific tumor-related areas that hold considerable diagnostic value. In this study, we propose a multi-task network with local-global feature interaction and multiple tumoral region guidance for breast ultrasound-based tumor segmentation and classification. Specifically, we construct a dual-stream encoder, paralleling CNN and Transformer, to facilitate hierarchical interaction and fusion of local and global features. This architecture enables each stream to capitalize on the strengths of the other while preserving its unique characteristics. Moreover, we design a multi-tumoral region guidance module to explicitly learn long-range non-local dependencies within intra-tumoral and peri-tumoral regions from spatial domain, thus providing interpretable cues beneficial for classification. Experimental results on two breast ultrasound datasets show that our network outperforms state-of-the-art methods in tumor segmentation and classification tasks. Compared with the second-best competitive method, our network improves the diagnosis accuracy from 73.64% to 80.21% on a large external validation dataset, which demonstrates its superior generalization capability.

PMID:39226204 | DOI:10.1109/JBHI.2024.3454000

IEEE J Biomed Health Inform. 2024 Sep 3;PP. doi: 10.1109/JBHI.2024.3453956. Online ahead of print.

ABSTRACT

Drug-drug interaction (DDI) can trigger many adverse effects in patients and has emerged as a threat to medicine and public health. Therefore, it is important to predict potential drug interactions since it can provide combination strategies of drugs for systematic and effective treatment. Existing deep learning-based methods often rely on DDI functional networks, or use them as an important part of the model information source. However, it is difficult to discover the interactions of a new drug. To address the above limitations, we propose a geometric molecular graph representation learning model (Mol-DDI) for DDI prediction based on the basic assumption that structure determines function. Mol-DDI only considers the covalent and non-covalent bond information of molecules, then it uses the pre-training idea of large-scale models to learn drug molecular representations and predict drug interactions during the fine-tuning process. Experimental results show that the Mol-DDI model outperforms others on the three datasets and performs better in predicting new drug interaction experiments.

PMID:39226203 | DOI:10.1109/JBHI.2024.3453956

Clin Exp Dermatol. 2024 Sep 3:llae361. doi: 10.1093/ced/llae361. Online ahead of print.

ABSTRACT

BACKGROUND: Medical research, driven by advancing technologies like Artificial Intelligence (AI), is transforming healthcare. Dermatology, known for its visual nature, benefits from AI, especially in dermatopathology with digitized slides. This review explores into AI's role, challenges, opportunities, and future potential in enhancing dermatopathological diagnosis and care.

MATERIALS AND METHODOLOGY: Adhering to PRISMA and Cochrane Handbook standards, this systematic review explored AI's function in dermatopathology. It employed an interdisciplinary method, encompassing diverse study types and comprehensive database searches. Inclusion criteria encompassed peer-reviewed articles from 2000 to 2023, with a focus on practical AI use in dermatopathology.

RESULTS: Numerous studies have investigated AI's potential in dermatopathology. We reviewed 112 papers. Notable applications include AI classifying histopathological images of nevi and melanomas, although challenges exist regarding subtype differentiation and generalizability. AI achieved high accuracy in melanoma recognition from formalin-fixed paraffin-embedded samples but faced limitations due to small datasets. Deep learning algorithms showed diagnostic accuracy for specific skin conditions, but challenges persisted, such as small sample sizes and the need for prospective validation.

CONCLUSION: This systematic review underscores AI's potential in enhancing dermatopathology for better diagnosis and patient care. Addressing challenges like limited datasets and potential biases is essential. Future directions involve expanding datasets, conducting validation studies, promoting interdisciplinary collaboration, and creating patient-centred AI tools to enhance dermatopathology's accuracy, accessibility, and patient-focused care.

PMID:39226138 | DOI:10.1093/ced/llae361

Environ Sci Technol. 2024 Sep 3. doi: 10.1021/acs.est.4c03088. Online ahead of print.

ABSTRACT

The environment faces increasing anthropogenic impacts, resulting in a rapid increase in environmental issues that undermine the natural capital essential for human wellbeing. These issues are complex and often influenced by various factors represented by data with different modalities. While machine learning (ML) provides data-driven tools for addressing the environmental issues, the current ML models in environmental science and engineering (ES&E) often neglect the utilization of multimodal data. With the advancement in deep learning, multimodal learning (MML) holds promise for comprehensive descriptions of the environmental issues by harnessing data from diverse modalities. This advancement has the potential to significantly elevate the accuracy and robustness of prediction models in ES&E studies, providing enhanced solutions for various environmental modeling tasks. This perspective summarizes MML methodologies and proposes potential applications of MML models in ES&E studies, including environmental quality assessment, prediction of chemical hazards, and optimization of pollution control techniques. Additionally, we discuss the challenges associated with implementing MML in ES&E and propose future research directions in this domain.

PMID:39226136 | DOI:10.1021/acs.est.4c03088

Transl Vis Sci Technol. 2024 Sep 3;13(9):3. doi: 10.1167/tvst.13.9.3.

ABSTRACT

PURPOSE: We evaluated the features predicting visual acuity (VA) after one year in neovascular age-related macular degeneration (nAMD) patients.

METHODS: A total of 527 eyes of 506 patients were included. Machine learning (ML) models were trained to predict VA deterioration beyond a logarithm of the minimum angle of resolution of 1.0 after 1 year based on the sequential addition of multimodal data. BaseM models used clinical data (age, sex, treatment regimen, and VA), SegM models included fluid volumes from optical coherence tomography (OCT) images, and RawM models used probabilities of visual deterioration (hereafter probability) from deep learning classifiers trained on baseline OCT (OCT0) and OCT after three loading doses (OCT3), fluorescein angiography, and indocyanine green angiography. We applied SHapley Additive exPlanations (SHAP) for machine learning model interpretation.

RESULTS: The RawM model based on the probability of OCT0 outperformed the SegM model (area under the receiver operating characteristic curve of 0.95 vs. 0.91). Adding probabilities from OCT3, fluorescein angiography, and indocyanine green angiography to RawM showed minimal performance improvement, highlighting the practicality of using raw OCT0 data for predicting visual outcomes. Applied SHapley Additive exPlanations analysis identified VA after 3 months and OCT3 probability values as the most influential features over quantified fluid segments.

CONCLUSIONS: Integrating multimodal data to create a visual predictive model yielded accurate, interpretable predictions. This approach allowed the identification of crucial factors for predicting VA in patients with nAMD.

TRANSLATIONAL RELEVANCE: Interpreting a predictive model for 1-year VA in patients with nAMD from multimodal data allowed us to identify crucial factors for predicting VA.

PMID:39226064 | DOI:10.1167/tvst.13.9.3

Transl Vis Sci Technol. 2024 Sep 3;13(9):5. doi: 10.1167/tvst.13.9.5.

ABSTRACT

PURPOSE: The purpose of this study was to develop deep learning models for surgical video analysis, capable of identifying minimally invasive glaucoma surgery (MIGS) and locating the trabecular meshwork (TM).

METHODS: For classification of surgical steps, we had 313 video files (265 for cataract surgery and 48 for MIGS procedures), and for TM segmentation, we had 1743 frames (1110 for TM and 633 for no TM). We used transfer learning to update a classification model pretrained to recognize standard cataract surgical steps, enabling it to also identify MIGS procedures. For TM localization, we developed three different models: U-Net, Y-Net, and Cascaded. Segmentation accuracy for TM was measured by calculating the average pixel error between the predicted and ground truth TM locations.

RESULTS: Using transfer learning, we developed a model which achieved 87% accuracy for MIGS frame classification, with area under the receiver operating characteristic curve (AUROC) of 0.99. This model maintained a 79% accuracy for identifying 14 standard cataract surgery steps. The overall micro-averaged AUROC was 0.98. The U-Net model excelled in TM segmentation with an Intersection over union (IoU) score of 0.9988 and an average pixel error of 1.47.

CONCLUSIONS: Building on prior work developing computer vision models for cataract surgical video, we developed models that recognize MIGS procedures and precisely localize the TM with superior performance. Our work demonstrates the potential of transfer learning for extending our computer vision models to new surgeries without the need for extensive additional data collection.

TRANSLATIONAL RELEVANCE: Computer vision models in surgical videos can underpin the development of systems offering automated feedback for trainees, improving surgical training and patient care.

PMID:39226062 | DOI:10.1167/tvst.13.9.5

Neurol Sci. 2024 Sep 3. doi: 10.1007/s10072-024-07731-1. Online ahead of print.

ABSTRACT

BACKGROUND: Various machine learning (ML) models based on resting-state functional MRI (Rs-fMRI) have been developed to facilitate differential diagnosis of mild cognitive impairment (MCI) and Alzheimer's disease (AD). However, the diagnostic accuracy of such models remains understudied. Therefore, we conducted this systematic review and meta-analysis to explore the diagnostic accuracy of Rs-fMRI-based radiomics in differentiating MCI from AD.

METHODS: PubMed, Embase, Cochrane, and Web of Science were searched from inception up to February 8, 2024, to identify relevant studies. Meta-analysis was conducted using a bivariate mixed-effects model, and sub-group analyses were carried out by the types of ML tasks (binary classification and multi-class classification tasks).

FINDINGS: In total, 23 studies, comprising 5,554 participants were enrolled in the study. In the binary classification tasks (twenty studies), the diagnostic accuracy of the ML model for AD was 0.99 (95%CI: 0.34 ~ 1.00), with a sensitivity of 0.94 (95%CI: 0.89 ~ 0.97) and a specificity of 0.98 (95%CI: 0.95 ~ 1.00). In the multi-class classification tasks (six studies), the diagnostic accuracy of the ML model was 0.98 (95%CI: 0.98 ~ 0.99) for NC, 0.96 (95%CI: 0.96 ~ 0.96) for early mild cognitive impairment (EMCI), 0.97 (95%CI: 0.96 ~ 0.97) for late mild cognitive impairment (LMCI), and 0.95 (95%CI: 0.95 ~ 0.95) for AD.

CONCLUSIONS: The Rs-fMRI-based ML model can be adapted to multi-class classification tasks. Therefore, multi-center studies with large samples are needed to develop intelligent application tools to promote the development of intelligent ML models for disease diagnosis.

PMID:39225837 | DOI:10.1007/s10072-024-07731-1

Neuroradiology. 2024 Sep 3. doi: 10.1007/s00234-024-03451-7. Online ahead of print.

ABSTRACT

OBJECTIVE: Research into the effectiveness and applicability of deep learning, radiomics, and their integrated models based on Magnetic Resonance Imaging (MRI) for preoperative differentiation between Primary Central Nervous System Lymphoma (PCNSL) and Glioblastoma (GBM), along with an exploration of the interpretability of these models.

MATERIALS AND METHODS: A retrospective analysis was performed on MRI images and clinical data from 261 patients across two medical centers. The data were split into a training set (n = 153, medical center 1) and an external test set (n = 108, medical center 2). Radiomic features were extracted using Pyradiomics to build the Radiomics Model. Deep learning networks, including the transformer-based MobileVIT Model and Convolutional Neural Networks (CNN) based ConvNeXt Model, were trained separately. By applying the "late fusion" theory, the radiomics model and deep learning model were fused to produce the optimal Max-Fusion Model. Additionally, Shapley Additive exPlanations (SHAP) and Grad-CAM were employed for interpretability analysis.

RESULTS: In the external test set, the Radiomics Model achieved an Area under the receiver operating characteristic curve (AUC) of 0.86, the MobileVIT Model had an AUC of 0.91, the ConvNeXt Model demonstrated an AUC of 0.89, and the Max-Fusion Model showed an AUC of 0.92. The Delong test revealed a significant difference in AUC between the Max-Fusion Model and the Radiomics Model (P = 0.02).

CONCLUSION: The Max-Fusion Model, combining different models, presents superior performance in distinguishing PCNSL and GBM, highlighting the effectiveness of model fusion for enhanced decision-making in medical applications.

CLINICAL RELEVANCE STATEMENT: The preoperative non-invasive differentiation between PCNSL and GBM assists clinicians in selecting appropriate treatment regimens and clinical management strategies.

PMID:39225815 | DOI:10.1007/s00234-024-03451-7

Soft Matter. 2024 Sep 3. doi: 10.1039/d4sm00483c. Online ahead of print.

ABSTRACT

Deep learning-based optical flow (DLOF) extracts features in adjacent video frames with deep convolutional neural networks. It uses those features to estimate the inter-frame motions of objects. We evaluate the ability of optical flow to quantify the spontaneous flows of microtubule (MT)-based active nematics under different labeling conditions, and compare its performance to particle image velocimetry (PIV). We obtain flow velocity ground truths either by performing semi-automated particle tracking on samples with sparsely labeled filaments, or from passive tracer beads. DLOF produces more accurate velocity fields than PIV for densely labeled samples. PIV cannot reliably distinguish contrast variations at high densities, particularly along the nematic director. DLOF overcomes this limitation. For sparsely labeled samples, DLOF and PIV produce comparable results, but DLOF gives higher-resolution fields. Our work establishes DLOF as a versatile tool for measuring fluid flows in a broad class of active, soft, and biophysical systems.

PMID:39225732 | DOI:10.1039/d4sm00483c

Med Phys. 2024 Sep 3. doi: 10.1002/mp.17381. Online ahead of print.

ABSTRACT

BACKGROUND: Patients may undergo anatomical changes during radiotherapy, leading to an underdosing of the target or overdosing of the organs at risk (OARs).

PURPOSE: This study developed a deep-learning method to predict the tumor response of patients with nasopharyngeal carcinoma (NPC) during treatment. This method can predict the anatomical changes of a patient.

METHODS: The participants included 230 patients with NPC. The data included planning computed tomography (pCT) and routine cone-beam CT (CBCT) images. The CBCT image quality was improved to the CT level using an advanced method. A long short-term memory network-generative adversarial network (LSTM-GAN) is proposed, which can harness the forecasting ability of LSTM and the generation ability of GAN. Four models were trained to predict the anatomical changes that occurred in weeks 3-6 and named LSTM-GAN-week 3 to LSTM-GAN-week 6. The pCT and CBCT were used as input, and the tumor target volumes (TVs) and OARs were delineated on the predicted and real images (ground truth). Finally, the models were evaluated using contours and dosimetry parameters.

RESULTS: The proposed method predicted the anatomical changes, with a dice similarity coefficient above 0.94 and 0.90 for the TVs and surrounding OARs, respectively. The dosimetry parameters were close between the prediction and ground truth. The deviations in the prescription, minimum, and maximum doses of the tumor targets were below 0.5 Gy. For serial organs (brain stem and spinal cord), the deviations in the maximum dose were below 0.6 Gy. For parallel organs (bilateral parotid glands), the deviations in the mean dose were below 0.8 Gy.

CONCLUSION: The proposed method can predict the tumor response to radiotherapy in the future such that adaptation can be scheduled on time. This study provides a proactive mechanism for planning adaptation, which can enable personalized treatment and save clinical time by anticipating and preparing for treatment strategy adjustments.

PMID:39225585 | DOI:10.1002/mp.17381

Med Phys. 2024 Sep 3. doi: 10.1002/mp.17368. Online ahead of print.

ABSTRACT

BACKGROUND: Deep learning is the primary method for conducting automated analysis of SPECT bone scintigrams. The lack of available large-scale data significantly hinders the development of well-performing deep learning models, as the performance of a deep learning model is positively correlated with the size of the dataset used. Therefore, there is an urgent demand for an automated data generation method to enlarge the dataset of SPECT bone scintigrams.

PURPOSE: We introduce a deep learning-based generation model that can generate realistic but not identical samples from the original SPECT bone scintigrams.

METHODS: Following the generative adversarial learning architecture, a bone metastasis scintigram generation model christened BMS-Gen is proposed. First, BMS-Gen takes multiple input conditions and employs multi-receptive field learning to ensure that the generated samples are as realistic as possible. Second, BMS-Gen adopts generative adversarial learning to retain the diversity of the generated samples. Last, BMS-Gen uses a two-stage training strategy to improve the quality of the generated samples.

RESULTS: Experimental evaluation conducted on a set of clinical data of SPECT BM scintigrams has shown the performance of the proposed BMS-Gen, achieving the best overall scores of 1678.0, 69.33, and 19.51 for FID (Fréchet Inception Distance), MSE (Mean Square Error), and PSNR (Peak Signal-to-Noise Ratio) metrics. The introduction of samples generated by BMS-Gen contributes a maximum (minimum) increase of 3.01% (0.15%) on the F-1 score and a maximum (minimum) increase of 6.83% (2.21%) on the DSC score for the image classification and segmentation tasks, respectively.

CONCLUSIONS: The proposed BMS-Gen model can be used as a promising tool for augmenting the data of bone scintigrams, greatly facilitating the development of deep learning-based automated analysis of SPECT bone scintigrams.

PMID:39225550 | DOI:10.1002/mp.17368

Isotopes Environ Health Stud. 2024 Sep 3:1-20. doi: 10.1080/10256016.2024.2396302. Online ahead of print.

ABSTRACT

Stable isotope techniques are precise methods for studying various aspects of hydrology, such as precipitation characteristics. However, understanding the variations in the stable isotope content in precipitation is challenging in Iran due to numerous climatic and geographic factors. To address this, forty-two precipitation sampling stations were selected across Iran to assess the fractional importance of these climatic and geographic parameters influencing stable isotopes. Additionally, deep learning models were employed to simulate the stable isotope content, with missing data initially addressed using the predictive mean matching (PMM) method. Subsequently, the recursive feature elimination (RFE) technique was applied to identify influential parameters impacting Iran's precipitation stable isotope content. Following this, long short-term memory (LSTM) and deep neural network (DNN) models were utilized to predict stable isotope values in precipitation. Interpolated maps of these values across Iran were developed using inverse distance weighting (IDW), while an interpolated reconstruction error (RE) map was generated to quantify deviations between observed and predicted values at study stations, offering insights into model precision. Validation using evaluation metrics demonstrated that the model based on DNN exhibited higher accuracy. Furthermore, RE maps confirmed acceptable accuracy in simulating the stable isotope content, albeit with minor weaknesses observed in simulation maps. The methodology outlined in this study holds promise for application in regions worldwide characterized by diverse climatic conditions.

PMID:39225427 | DOI:10.1080/10256016.2024.2396302

Hum Brain Mapp. 2024 Sep;45(13):e70005. doi: 10.1002/hbm.70005.

ABSTRACT

There has been extensive evidence that aging affects human brain function. However, there is no complete picture of what brain functional changes are mostly related to normal aging and how aging affects brain function similarly and differently between males and females. Based on resting-state brain functional connectivity (FC) of 25,582 healthy participants (13,373 females) aged 49-76 years from the UK Biobank project, we employ deep learning with explainable AI to discover primary FCs related to progressive aging and reveal similarity and difference between females and males in brain aging. Using a nested cross-validation scheme, we conduct 4200 deep learning models to classify all paired age groups on the main data for females and males separately and then extract gender-common and gender-specific aging-related FCs. Next, we validate those FCs using additional 21,000 classifiers on the independent data. Our results support that aging results in reduced brain functional interactions for both females and males, primarily relating to the positive connectivity within the same functional domain and the negative connectivity between different functional domains. Regions linked to cognitive control show the most significant age-related changes in both genders. Unique aging effects in males and females mainly involve the interaction between cognitive control and the default mode, vision, auditory, and frontoparietal domains. Results also indicate females exhibit faster brain functional changes than males. Overall, our study provides new evidence about common and unique patterns of brain aging in females and males.

PMID:39225381 | DOI:10.1002/hbm.70005

Adv Sci (Weinh). 2024 Sep 3:e2403143. doi: 10.1002/advs.202403143. Online ahead of print.

ABSTRACT

Measurements of the refractive index of liquids are in high demand in numerous fields such as agriculture, food and beverages, and medicine. However, conventional ellipsometric refractive index measurements are too expensive and labor-intensive for consumer devices, while Abbe refractometry is limited to the measurement at a single wavelength. Here, a new approach is proposed using machine learning to unlock the potential of colorimetric metasurfaces for the real-time measurement of the dispersive refractive index of liquids over the entire visible spectrum. The platform with a proof-of-concept experiment for measuring the concentration of glucose is further demonstrated, which holds a profound impact in non-invasive medical sensing. High-index-dielectric metasurfaces are designed and fabricated, while their experimentally measured reflectance and reflected colors, through microscopy and a standard smartphone, are used to train deep-learning models to provide measurements of the dispersive background refractive index with a resolution of ≈10-4, which is comparable to the known index as measured with ellipsometry. These results show the potential of enabling the unique optical properties of metasurfaces with machine learning to create a platform for the quick, simple, and high-resolution measurement of the dispersive refractive index of liquids, without the need for highly specialized experts and optical procedures.

PMID:39225343 | DOI:10.1002/advs.202403143

J Int Med Res. 2024 Sep;52(9):3000605241274576. doi: 10.1177/03000605241274576.

ABSTRACT

OBJECTIVE: We developed a few-shot learning (FSL) framework for the diagnosis of osteopenia and osteoporosis in knee X-ray images.

METHODS: Computer vision models containing deep convolutional neural networks were fine-tuned to enable generalization from natural images (ImageNet) to chest X-ray images (normal vs. pneumonia, base images). Then, a series of automated machine learning classifiers based on the Euclidean distances of base images were developed to make predictions for novel images (normal vs. osteopenia vs. osteoporosis). The performance of the FSL framework was compared with that of junior and senior radiologists. In addition, the gradient-weighted class activation mapping algorithm was used for visual interpretation.

RESULTS: In Cohort #1, the mean accuracy (0.728) and sensitivity (0.774) of the FSL models were higher than those of the radiologists (0.512 and 0.448). A diagnostic pipeline of FSL model (first)-radiologists (second) achieved better performance (0.653 accuracy, 0.582 sensitivity, and 0.816 specificity) than radiologists alone. In Cohort #2, the diagnostic pipeline also showed improved performance.

CONCLUSIONS: The FSL framework yielded practical performance with respect to the diagnosis of osteopenia and osteoporosis in comparison with radiologists. This retrospective study supports the use of promising FSL methods in computer-aided diagnosis tasks involving limited samples.

PMID:39225007 | DOI:10.1177/03000605241274576

Nucl Med Commun. 2024 Sep 3. doi: 10.1097/MNM.0000000000001891. Online ahead of print.

ABSTRACT

PURPOSE: This study demonstrates the feasibility and benefits of using a deep learning-based approach for attenuation correction in [68Ga]Ga-PSMA PET scans.

METHODS: A dataset of 700 prostate cancer patients (mean age: 67.6 ± 5.9 years, range: 45-85 years) who underwent [68Ga]Ga-PSMA PET/computed tomography was collected. A deep learning model was trained to perform attenuation correction on these images. Quantitative accuracy was assessed using clinical data from 92 patients, comparing the deep learning-based attenuation correction (DLAC) to computed tomography-based PET attenuation correction (PET-CTAC) using mean error, mean absolute error, and root mean square error based on standard uptake value. Clinical evaluation was conducted by three specialists who performed a blinded assessment of lesion detectability and overall image quality in a subset of 50 subjects, comparing DLAC and PET-CTAC images.

RESULTS: The DLAC model yielded mean error, mean absolute error, and root mean square error values of -0.007 ± 0.032, 0.08 ± 0.033, and 0.252 ± 125 standard uptake value, respectively. Regarding lesion detection and image quality, DLAC showed superior performance in 16 of the 50 cases, while in 56% of the cases, the images generated by DLAC and PET-CTAC were found to have closely comparable quality and lesion detectability.

CONCLUSION: This study highlights significant improvements in image quality and lesion detection capabilities through the integration of DLAC in [68Ga]Ga-PSMA PET imaging. This innovative approach not only addresses challenges such as bladder radioactivity but also represents a promising method to minimize patient radiation exposure by integrating low-dose computed tomography and DLAC, ultimately improving diagnostic accuracy and patient outcomes.

PMID:39224922 | DOI:10.1097/MNM.0000000000001891

Nucl Med Commun. 2024 Sep 3. doi: 10.1097/MNM.0000000000001892. Online ahead of print.

ABSTRACT

OBJECTIVE: The accuracy of automatic tumor segmentation in PET/computed tomography (PET/CT) images is crucial for the effective treatment and monitoring of Hodgkin lymphoma. This study aims to address the challenges faced by certain segmentation algorithms in accurately differentiating lymphoma from normal organ uptakes due to PET image resolution and tumor heterogeneity.

MATERIALS AND METHODS: Variants of the encoder-decoder architectures are state-of-the-art models for image segmentation. Among these kinds of architectures, U-Net is one of the most famous and predominant for medical image segmentation. In this study, we propose a fully automatic approach for Hodgkin lymphoma segmentation that combines U-Net and DenseNet architectures to reduce network loss for very small lesions, which is trained using the Tversky loss function. The hypothesis is that the fusion of these two deep learning models can improve the accuracy and robustness of Hodgkin lymphoma segmentation. A dataset with 141 samples was used to train our proposed network. Also, to test and evaluate the proposed network, we allocated two separate datasets of 20 samples.

RESULTS: We achieved 0.759 as the mean Dice similarity coefficient with a median value of 0.767, and interquartile range (0.647-0.837). A good agreement was observed between the ground truth of test images against the predicted volume with precision and recall scores of 0.798 and 0.763, respectively.

CONCLUSION: This study demonstrates that the integration of U-Net and DenseNet architectures, along with the Tversky loss function, can significantly enhance the accuracy of Hodgkin lymphoma segmentation in PET/CT images compared to similar studies.

PMID:39224914 | DOI:10.1097/MNM.0000000000001892

Digit Health. 2024 Aug 30;10:20552076241277171. doi: 10.1177/20552076241277171. eCollection 2024 Jan-Dec.

ABSTRACT

OBJECTIVE: The COVID-19 pandemic has spurred an increased interest in online healthcare and a surge in usage of online healthcare platforms, leading to a proliferation of user-generated online physician reviews. Yet, distinguishing between genuine and fake reviews poses a significant challenge. This study aims to address the challenges delineated above by developing a reliable and effective fake review detection model leveraging deep learning approaches based on a fake review dataset tailored to the context of Chinese online medical platforms.

METHODS: Inspired by prior research, this paper adopts a crowdsourcing approach to assemble the fake review dataset for Chinese online medical platforms. To develop the fake review detection models, classical machine learning models, along with deep learning models such as Convolutional Neural Network and Bidirectional Encoder Representations from Transformers, were applied.

RESULTS: Our experimental deep learning model exhibited superior performance in identifying fake reviews on online medical platforms, achieving a precision of 98.36% and an F2-Score of 97.97%. Compared to the traditional machine learning models (i.e., logistic regression, support vector machine, random forest, ridge regression), this represents an 8.16% enhancement in precision and a 7.7% increase in F2-Score.

CONCLUSION: Overall, this study provides a valuable contribution toward the development of an effective fake physician review detection model for online medical platforms.

PMID:39224794 | PMC:PMC11367699 | DOI:10.1177/20552076241277171

Cureus. 2024 Aug 2;16(8):e66036. doi: 10.7759/cureus.66036. eCollection 2024 Aug.

ABSTRACT

With technological advancements, artificial intelligence (AI) has progressed to become a ubiquitous part of human life. Its aspects in otorhinolaryngology are varied and are continuously evolving. Currently, AI has applications in hearing aids, imaging technologies, interpretation of auditory brain stem systems, and many more in otology. In rhinology, AI is seen to impact navigation, robotic surgeries, and the determination of various anomalies. Detection of voice pathologies and imaging are some areas of laryngology where AI is being used. This review gives an outlook on the diverse elements, applications, and advancements of AI in otorhinolaryngology. The various subfields of AI including machine learning, neural networks, and deep learning are also discussed. Clinical integration of AI and otorhinolaryngology has immense potential to revolutionize the healthcare system and improve the standards of patient care. The current applications of AI and its future scopes in developing this field are highlighted in this review.

PMID:39224718 | PMC:PMC11366564 | DOI:10.7759/cureus.66036