The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study

Application of Artificial Intelligence to Automate the Reconstruction of Muscle Cross-Sectional Area Obtained by Ultrasound

PURPOSE

Manual reconstruction (MR) of the vastus lateralis (VL) muscle cross-sectional area (CSA) from sequential ultrasound (US) images is accessible, is reproducible, and has concurrent validity with magnetic resonance imaging. However, this technique requires numerous controls and procedures during image acquisition and reconstruction, making it laborious and time-consuming. The aim of this study was to determine the concurrent validity of VL CSA assessments between MR and computer vision-based automated reconstruction (AR) of CSA from sequential images of the VL obtained by US.

METHODS

The images from each sequence were manually rotated to align the fascia between images and thus visualize the VL CSA. For the AR, an artificial neural network model was utilized to segment areas of interest in the image, such as skin, fascia, deep aponeurosis, and femur. This segmentation was crucial to impose necessary constraints for the main assembly phase. At this stage, an image registration application, combined with differential evolution, was employed to achieve appropriate adjustments between the images. Next, the VL CSA obtained from the MR ( n = 488) and AR ( n = 488) techniques was used to determine their concurrent validity.

RESULTS

Our findings demonstrated a low coefficient of variation (CV) (1.51%) for AR compared with MR. The Bland-Altman plot showed low bias and close limits of agreement (+1.18 cm 2 , -1.19 cm 2 ), containing more than 95% of the data points.

CONCLUSIONS

The AR technique is valid compared with MR when measuring VL CSA in a heterogeneous sample.

Unveiling the potential of machine learning in cost-effective degradation of pharmaceutically active compounds: A stirred photo-reactor study

In this study, neural networks and support vector regression (SVR) were employed to predict the degradation over three pharmaceutically active compounds (PhACs): Ibuprofen (IBP), diclofenac (DCF), and caffeine (CAF) within a stirred reactor featuring a flotation cell with two non-concentric ultraviolet lamps. A total of 438 datapoints were collected from published works and distributed into 70% training and 30% test datasets while cross-validation was utilized to assess the training reliability. The models incorporated 15 input variables concerning reaction kinetics, molecular properties, hydrodynamic information, presence of radiation, and catalytic properties. It was observed that the Support Vector Regression (SVR) presented a poor performance as the ε hyperparameter ignored large error over low concentration levels. Meanwhile, the Artificial Neural Networks (ANN) model was able to provide rough estimations on the expected degradation of the pollutants without requiring information regarding reaction rate constants. The multi-objective optimization analysis suggested a leading role due to ozone kinetic for a rapid degradation of the contaminants and most of the results required intensification with hydrogen peroxide and Fenton process. Although both models were affected by accuracy limitations, this work provided a lightweight model to evaluate different Advanced Oxidation Processes (AOPs) by providing general information regarding the process operational conditions as well as know molecular and catalytic properties.

Improved prostate cancer diagnosis using a modified ResNet50-based deep learning architecture

Prostate cancer, the most common cancer in men, is influenced by age, family history, genetics, and lifestyle factors. Early detection of prostate cancer using screening methods improves outcomes, but the balance between overdiagnosis and early detection remains debated. Using Deep Learning (DL) algorithms for prostate cancer detection offers a promising solution for accurate and efficient diagnosis, particularly in cases where prostate imaging is challenging. In this paper, we propose a Prostate Cancer Detection Model (PCDM) model for the automatic diagnosis of prostate cancer. It proves its clinical applicability to aid in the early detection and management of prostate cancer in real-world healthcare environments. The PCDM model is a modified ResNet50-based architecture that integrates faster R-CNN and dual optimizers to improve the performance of the detection process. The model is trained on a large dataset of annotated medical images, and the experimental results show that the proposed model outperforms both ResNet50 and VGG19 architectures. Specifically, the proposed model achieves high sensitivity, specificity, precision, and accuracy rates of 97.40%, 97.09%, 97.56%, and 95.24%, respectively.

Optimizing classification of diseases through language model analysis of symptoms

This paper investigated the use of language models and deep learning techniques for automating disease prediction from symptoms. Specifically, we explored the use of two Medical Concept Normalization-Bidirectional Encoder Representations from Transformers (MCN-BERT) models and a Bidirectional Long Short-Term Memory (BiLSTM) model, each optimized with a different hyperparameter optimization method, to predict diseases from symptom descriptions. In this paper, we utilized two distinct dataset called Dataset-1, and Dataset-2. Dataset-1 consists of 1,200 data points, with each point representing a unique combination of disease labels and symptom descriptions. While, Dataset-2 is designed to identify Adverse Drug Reactions (ADRs) from Twitter data, comprising 23,516 rows categorized as ADR (1) or Non-ADR (0) tweets. The results indicate that the MCN-BERT model optimized with AdamP achieved 99.58% accuracy for Dataset-1 and 96.15% accuracy for Dataset-2. The MCN-BERT model optimized with AdamW performed well with 98.33% accuracy for Dataset-1 and 95.15% for Dataset-2, while the BiLSTM model optimized with Hyperopt achieved 97.08% accuracy for Dataset-1 and 94.15% for Dataset-2. Our findings suggest that language models and deep learning techniques have promise for supporting earlier detection and more prompt treatment of diseases, as well as expanding remote diagnostic capabilities. The MCN-BERT and BiLSTM models demonstrated robust performance in accurately predicting diseases from symptoms, indicating the potential for further related research.

Evaluation of the Photoplethysmogram-Based Deep Learning Model for Continuous Respiratory Rate Estimation in Surgical Intensive Care Unit

The respiratory rate (RR) is a significant indicator to evaluate a patient's prognosis and status; however, it requires specific instrumentation or estimates from other monitored signals. A photoplethysmogram (PPG) is extensively used in clinical environments as well as in intensive care units (ICUs) to primarily monitor peripheral circulation while capturing indirect information about intrathoracic pressure changes. This study aims to apply and evaluate several deep learning models using a PPG for the continuous and accurate estimation of the RRs of patients. The dataset was collected twice for 2 min each in 100 patients aged 18 years and older from the surgical intensive care unit of a tertiary referral hospital. The BIDMC and CapnoBase public datasets were also analyzed. The collected dataset was preprocessed and split according to the 5-fold cross-validation. We used seven deep learning models, including our own Dilated Residual Neural Network, to check how accurately the RR estimates match the ground truth using the mean absolute error (MAE). As a result, when validated using the collected dataset, our model showed the best results with a 1.2628 ± 0.2697 MAE on BIDMC and RespNet and with a 3.1268 ± 0.6363 MAE on our dataset, respectively. In conclusion, RR estimation using PPG-derived models is still challenging and has many limitations. However, if there is an equal amount of data from various breathing groups to train, we expect that various models, including our Dilated ResNet model, which showed good results, can achieve better results than the current ones.

Adapting the pre-trained convolutional neural networks to improve the anomaly detection and classification in mammographic images

Mortality from breast cancer (BC) is among the top causes of cancer death in women. BC can be effectively treated when diagnosed early, improving the likelihood that a patient will survive. BC masses and calcification clusters must be identified by mammography in order to prevent disease effects and commence therapy at an early stage. A mammography misinterpretation may result in an unnecessary biopsy of the false-positive results, lowering the patient's odds of survival. This study intends to improve breast mass detection and identification in order to provide better therapy and reduce mortality risk. A new deep-learning (DL) model based on a combination of transfer-learning (TL) and long short-term memory (LSTM) is proposed in this study to adequately facilitate the automatic detection and diagnosis of the BC suspicious region using the 80-20 method. Since DL designs are modelled to be problem-specific, TL applies the knowledge gained during the solution of one problem to another relevant problem. In the presented model, the learning features from the pre-trained networks such as the squeezeNet and DenseNet are extracted and transferred with the features that have been extracted from the INbreast dataset. To measure the proposed model performance, we selected accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC) as our metrics of choice. The classification of mammographic data using the suggested model yielded overall accuracy, sensitivity, specificity, precision, and AUC values of 99.236%, 98.8%, 99.1%, 96%, and 0.998, respectively, demonstrating the model's efficacy in detecting breast tumors.

PPG Signals-Based Blood-Pressure Estimation Using Grid Search in Hyperparameter Optimization of CNN-LSTM

Researchers commonly use continuous noninvasive blood-pressure measurement (cNIBP) based on photoplethysmography (PPG) signals to monitor blood pressure conveniently. However, the performance of the system still needs to be improved. Accuracy and precision in blood-pressure measurements are critical factors in diagnosing and managing patients' health conditions. Therefore, we propose a convolutional long short-term memory neural network (CNN-LSTM) with grid search ability, which provides a robust blood-pressure estimation system by extracting meaningful information from PPG signals and reducing the complexity of hyperparameter optimization in the proposed model. The multiparameter intelligent monitoring for intensive care III (MIMIC III) dataset obtained PPG and arterial-blood-pressure (ABP) signals. We obtained 75,226 signal segments, with 60,180 signals allocated for training data, 12,030 signals allocated for the validation set, and 15,045 signals allocated for the test data. During training, we applied five-fold cross-validation with a grid-search method to select the best model and determine the optimal hyperparameter settings. The optimized configuration of the CNN-LSTM layers consisted of five convolutional layers, one long short-term memory (LSTM) layer, and two fully connected layers for blood-pressure estimation. This study successfully achieved good accuracy in assessing both systolic blood pressure (SBP) and diastolic blood pressure (DBP) by calculating the standard deviation (SD) and the mean absolute error (MAE), resulting in values of 7.89 ± 3.79 and 5.34 ± 2.89 mmHg, respectively. The optimal configuration of the CNN-LSTM provided satisfactory performance according to the standards set by the British Hypertension Society (BHS), the Association for the Advancement of Medical Instrumentation (AAMI), and the Institute of Electrical and Electronics Engineers (IEEE) for blood-pressure monitoring devices.