Medical Datasets Research Articles

Advances in medical data modeling: A new logarithmic beta generated family of distributions with theory and inference

This paper introduces a novel logarithmic beta generated family of distributions, designed specifically for the nuanced analysis of medical data. Through meticulous development, we have establish a comprehensive suite of distributional properties, including quantiles, moments, and hazard rate functions. Central to our contributions is the exploration of the power function distribution, a pivotal sub-model within this innovative family, demonstrating unparalleled flexibility across a broad spectrum of data types. Our investigation delves into seven prominent parameter estimation techniques, rigorously assessing their efficacy through both simulation studies and real-life medical datasets. This comparative analysis highlights the superior performance of the proposed model against existing standards, particularly through improved goodness-of-fit measures across four distinct medical science lifetime datasets. The findings highlight the new model's dominance in capturing complex data patterns, attributable to its adaptable density and hazard rate functions. These attributes significantly enhance modeling capabilities, paving the way for more precise and reliable medical research outcomes. The study concludes by emphasizing the model's potential in advancing statistical methodologies for medical science, backed by theoretical and empirical validations of its superior performance and versatility.

WSPolyp-SAM: Weakly Supervised and Self-Guided Fine-Tuning of SAM for Colonoscopy Polyp Segmentation

Ensuring precise segmentation of colorectal polyps holds critical importance in the early diagnosis and treatment of colorectal cancer. Nevertheless, existing deep learning-based segmentation methods are fully supervised, requiring extensive, precise, manual pixel-level annotation data, which leads to high annotation costs. Additionally, it remains challenging to train large-scale segmentation models when confronted with limited colonoscopy data. To address these issues, we introduce the general segmentation foundation model—the Segment Anything Model (SAM)—into the field of medical image segmentation. Fine-tuning the foundation model is an effective approach to tackle sample scarcity. However, current SAM fine-tuning techniques still rely on precise annotations. To overcome this limitation, we propose WSPolyp-SAM, a novel weakly supervised approach for colonoscopy polyp segmentation. WSPolyp-SAM utilizes weak annotations to guide SAM in generating segmentation masks, which are then treated as pseudo-labels to guide the fine-tuning of SAM, thereby reducing the dependence on precise annotation data. To improve the reliability and accuracy of pseudo-labels, we have designed a series of enhancement strategies to improve the quality of pseudo-labels and mitigate the negative impact of low-quality pseudo-labels. Experimental results on five medical image datasets demonstrate that WSPolyp-SAM outperforms current fully supervised mainstream polyp segmentation networks on the Kvasir-SEG, ColonDB, CVC-300, and ETIS datasets. Furthermore, by using different amounts of training data in weakly supervised and fully supervised experiments, it is found that weakly supervised fine-tuning can save 70% to 73% of annotation time costs compared to fully supervised fine-tuning. This study provides a new perspective on the combination of weakly supervised learning and SAM models, significantly reducing annotation time and offering insights for further development in the field of colonoscopy polyp segmentation.

VTHSC-MIR: Vision Transformer Hashing with Supervised Contrastive learning based medical image retrieval

In past few years, deep learning based medical image analysis technologies have significantly improved computer-assisted tasks like detecting, diagnosing, and predicting medical outcomes. The monitoring and diagnosis of ailments such as cancer and COVID-19 rely primarily on retrieving medical images. As the medical databases size is increasing rapidly it causes difficulty in managing and querying them. The main challenge lies in achieving superior retrieval performance while handling the intricacies of medical imaging datasets. To tackle this, we propose a novel end-to-end trainable framework for medical image retrieval using a vision transformer hashing with Supervised Contrastive (VTHSC) learning. Leveraging the self-attention mechanism of transformers and supervised contrastive loss, our model surpasses existing hashing-based retrieval methods. Focusing on the most recent COVID-19 and breast cancer datasets, we aim to efficiently retrieve relevant medical images from large datasets. Using the ImageNet-pretrained ViT as its backbone network, the VTHSC model incorporates a hashing head combined with a supervised contrastive loss and employs joint loss optimization. The VTHSC model is subsequently fine- tuned for a retrieval task, employing four different hashing frameworks: Deep Supervised Hashing (DSH), GreedyHash, Improved Deep Hashing Network (IDHN), and Deep Polarized Network (DPN). Our model achieves outstanding Mean Average Precision (MAP) scores of 98.9 for the BreakHis dataset and 96.03 for the COVID dataset. Notably, the VTHSC model surpasses several competing hashing-based retrieval methods by a substantial gain in terms of performance across various metrics such as precision, recall, and Top-6 retrieved images retrieval performance on the two benchmark medical image datasets.

CellMarkerPipe: cell marker identification and evaluation pipeline in single cell transcriptomes

Assessing marker genes from all cell clusters can be time-consuming and lack systematic strategy. Streamlining this process through a unified computational platform that automates identification and benchmarking will greatly enhance efficiency and ensure a fair evaluation. We therefore developed a novel computational platform, cellMarkerPipe (https://github.com/yao-laboratory/cellMarkerPipe), for automated cell-type specific marker gene identification from scRNA-seq data, coupled with comprehensive evaluation schema. CellMarkerPipe adaptively wraps around a collection of commonly used and state-of-the-art tools, including Seurat, COSG, SC3, SCMarker, COMET, and scGeneFit. From rigorously testing across diverse samples, we ascertain SCMarker’s overall reliable performance in single marker gene selection, with COSG showing commendable speed and comparable efficacy. Furthermore, we demonstrate the pivotal role of our approach in real-world medical datasets. This general and opensource pipeline stands as a significant advancement in streamlining cell marker gene identification and evaluation, fitting broad applications in the field of cellular biology and medical research.

A Review of Semantic Medical Image Segmentation Based on Different Paradigms

In recent years, with the widespread application of medical images, the rapid and accurate identification of these regions of interest in a large number of medical images has received widespread attention. This article provides a review of medical image segmentation methods based on deep learning. Firstly, an overview of medical image segmentation methods was provided in the relevant knowledge, segmentation types, segmentation processes, and image processing applications. Secondly, the applications of supervised, semi supervised, and unsupervised methods in medical image segmentation were discussed, and their advantages, disadvantages, and applicable scenarios were revealed through the application of a large number of specific segmentation examples in practical scenarios. Finally, the commonly used medical image segmentation datasets and evaluation indicators were introduced, and the current medical image segmentation methods were summarized and prospected. This review provides a comprehensive and in-depth understanding for researchers in the field of medical image segmentation, and provides valuable references for the design and implementation of future related work.

Enhancing Medical Image Retrieval with UMLS-Integrated CNN-Based Text Indexing.

In recent years, Convolutional Neural Network (CNN) models have demonstrated notable advancements in various domains such as image classification and Natural Language Processing (NLP). Despite their success in image classification tasks, their potential impact on medical image retrieval, particularly in text-based medical image retrieval (TBMIR) tasks, has not yet been fully realized. This could be attributed to the complexity of the ranking process, as there is ambiguity in treating TBMIR as an image retrieval task rather than a traditional information retrieval or NLP task. To address this gap, our paper proposes a novel approach to re-ranking medical images using a Deep Matching Model (DMM) and Medical-Dependent Features (MDF). These features incorporate categorical attributes such as medical terminologies and imaging modalities. Specifically, our DMM aims to generate effective representations for query and image metadata using a personalized CNN, facilitating matching between these representations. By using MDF, a semantic similarity matrix based on Unified Medical Language System (UMLS) meta-thesaurus, and a set of personalized filters taking into account some ranking features, our deep matching model can effectively consider the TBMIR task as an image retrieval task, as previously mentioned. To evaluate our approach, we performed experiments on the medical ImageCLEF datasets from 2009 to 2012. The experimental results show that the proposed model significantly enhances image retrieval performance compared to the baseline and state-of-the-art approaches.

The effect of noise removal filters on classifying different types of medical images

The number of studies on medical image processing with artificial intelligence-supported systems and the resulting diagnosis and classification of diseases has increased significantly as deep learning technology has developed. Doctors and specialists can save time and energy using the most successful deep learning models to classify medical images. This study aims to optimize various models and filters with grid search to increase classification success in medical images. Hybrid models were created by combining Vgg16, EfficientNetB0, ResNet50, and ResNet50v2 models with support vector machine classifiers. The models were trained and tested on three medical datasets: lung nodules, histopathological images for breast cancer as PatchCamelyon, and diagnosis of eye diseases as Retinal Fundus Multi-disease Image Dataset. The results demonstrated the optimized models' effectiveness compared to literature studies regarding various performance metrics. The proposed approaches present saliency maps and reveal the effects of filters on model success through comprehensive experiments on medical image datasets.

DSTAN: A Deformable Spatial-temporal Attention Network with Bidirectional Sequence Feature Refinement for Speckle Noise Removal in Thyroid Ultrasound Video.

Thyroid ultrasound video provides significant value for thyroid diseases diagnosis, but the ultrasound imaging process is often affected by the speckle noise, resulting in poor quality of the ultrasound video. Numerous video denoising methods have been proposed to remove noise while preserving texture details. However, existing methods still suffer from the following problems: (1) relevant temporal features in the low-contrast ultrasound video cannot be accurately aligned and effectively aggregated by simple optical flow or motion estimation, resulting in the artifacts and motion blur in the video; (2) fixed receptive field in spatial features integration lacks the flexibility of aggregating features in the global region of interest and is susceptible to interference from irrelevant noisy regions. In this work, we propose a deformable spatial-temporal attention denoising network to remove speckle noise in thyroid ultrasound video. The entire network follows the bidirectional feature propagation mechanism to efficiently exploit the spatial-temporal information of the whole video sequence. In this process, two modules are proposed to address the above problems: (1) a deformable temporal attention module (DTAM) is designed after optical flow pre-alignment to further capture and aggregate relevant temporal features according to the learned offsets between frames, so that inter-frame information can be better exploited even with the imprecise flow estimation under the low contrast of ultrasound video; (2) a deformable spatial attention module (DSAM) is proposed to flexibly integrate spatial features in the global region of interest through the learned intra-frame offsets, so that irrelevant noisy information can be ignored and essential information can be precisely exploited. Finally, all these refined features are rectified and merged through residual convolution blocks to recover the clean video frames. Experimental results on our thyroid ultrasound video (US-V) dataset and the DDTI dataset demonstrate that our proposed method exceeds 1.2 1.3dB on PSNR and has clearer texture detail compared to other state-of-the-art methods. In the meantime, the proposed model can also assist thyroid nodule segmentation methods to achieve more accurate segmentation effect, which provides an important basis for thyroid diagnosis. In the future, the proposed model can be improved and extended to other medical image sequence datasets, including CT and MRI slice denoising. The code and datasets are provided at https://github.com/Meta-MJ/DSTAN .

An interpretable ensemble structure with a non-iterative training algorithm to improve the predictive accuracy of healthcare data analysis

The modern development of healthcare is characterized by a set of large volumes of tabular data for monitoring and diagnosing the patient's condition. In addition, modern methods of data engineering allow the synthesizing of a large number of features from an image or signals, which are presented in tabular form. The possibility of high-precision and high-speed processing of such large volumes of medical data requires the use of artificial intelligence tools. A linear machine learning model cannot accurately analyze such data, and traditional bagging, boosting, or stacking ensembles typically require significant computing power and time to implement. In this paper, the authors proposed a method for the analysis of large sets of medical data, based on a designed linear ensemble method with a non-iterative learning algorithm. The basic node of the new ensemble is an extended-input SGTM neural-like structure, which provides high-speed data processing at each level of the ensemble. Increasing prediction accuracy is ensured by dividing the large dataset into parts, the analysis of which is carried out in each node of the ensemble structure and taking into account the output signal from the previous level of the ensemble as an additional attribute on the next one. Such a design of a new ensemble structure provides both a significant increase in the prediction accuracy for large sets of medical data analysis and a significant reduction in the duration of the training procedure. Experimental studies on a large medical dataset, as well as a comparison with existing machine learning methods, confirmed the high efficiency of using the developed ensemble structure when solving the prediction task.

Reinforcement Learning in Latent Heterogeneous Environments

Reinforcement Learning holds great promise for data-driven decision-making in various social contexts, including healthcare, education, and business. However, classical methods that focus on the mean of the total return may yield misleading results when dealing with heterogeneous populations typically found in large-scale datasets. To address this issue, we introduce the K-Value Heterogeneous Markov Decision Process, a framework designed to handle sequential decision problems with latent population heterogeneity. Within this framework, we propose auto-clustered policy evaluation for estimating the value of a given policy and auto-clustered policy iteration for estimating the optimal policy within a parametric policy class. Our auto-clustered algorithms can automatically identify homogeneous subpopulations while simultaneously estimating the action value function and the optimal policy for each subgroup. We establish convergence rates and construct confidence intervals for the estimators. Simulation results support our theoretical findings, and an empirical study conducted on a real medical dataset confirms the presence of value heterogeneity and validates the advantages of our novel approach. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.

Stitched vision transformer for age-related macular degeneration detection using retinal optical coherence tomography images.

Age-related macular degeneration (AMD) is an eye disease that leads to the deterioration of the central vision area of the eye and can gradually result in vision loss in elderly individuals. Early identification of this disease can significantly impact patient treatment outcomes. Furthermore, given the increasing elderly population globally, the importance of automated methods for rapidly monitoring at-risk individuals and accurately diagnosing AMD is growing daily. One standard method for diagnosing AMD is using optical coherence tomography (OCT) images as a non-invasive imaging technology. In recent years, numerous deep neural networks have been proposed for the classification of OCT images. Utilizing pre-trained neural networks can speed up model deployment in related tasks without compromising accuracy. However, most previous methods overlook the feasibility of leveraging pre-existing trained networks to search for an optimal architecture for AMD staging on a new target dataset. In this study, our objective was to achieve an optimal architecture in the efficiency-accuracy trade-off for classifying retinal OCT images. To this end, we employed pre-trained medical vision transformer (MedViT) models. MedViT combines convolutional and transformer neural networks, explicitly designed for medical image classification. Our approach involved pre-training two distinct MedViT models on a source dataset with labels identical to those in the target dataset. This pre-training was conducted in a supervised manner. Subsequently, we evaluated the performance of the pre-trained MedViT models for classifying retinal OCT images from the target Noor Eye Hospital (NEH) dataset into the normal, drusen, and choroidal neovascularization (CNV) classes in zero-shot settings and through five-fold cross-validation. Then, we proposed a stitching approach to search for an optimal model from two MedViT family models. The proposed stitching method is an efficient architecture search algorithm known as stitchable neural networks. Stitchable neural networks create a candidate model in search space for each pair of stitchable layers by inserting a linear layer between them. A pair of stitchable layers consists of layers, each selected from one input model. While stitchable neural networks had previously been tested on more extensive and general datasets, this study demonstrated that stitching networks could also be helpful in smaller medical datasets. The results of this approach indicate that when pre-trained models were available for OCT images from another dataset, it was possible to achieve a model in 100 epochs with an accuracy of over 94.9% in classifying images from the NEH dataset. The results of this study demonstrate the efficacy of stitchable neural networks as a fine-tuning method for OCT image classification. This approach not only leads to higher accuracy but also considers architecture optimization at a reasonable computational cost.

Improving the performance and interpretability on medical datasets using graphical ensemble feature selection.

A major hindrance towards using Machine Learning (ML) on medical datasets is the discrepancy between a large number of variables and small sample sizes. While multiple feature selection techniques have been proposed to avoid the resulting overfitting, overall ensemble techniques offer the best selection robustness. Yet, current methods designed to combine different algorithms generally fail to leverage the dependencies identified by their components. Here, we propose Graphical Ensembling (GE), a graph-theory-based ensemble feature selection technique designed to improve the stability and relevance of the selected features. Relying on four datasets, we show that GE increases classification performance with fewer selected features. For example, on rheumatoid arthritis patient stratification, GE outperforms the baseline methods by 9% Balanced Accuracy while relying on fewer features. We use data on sub-cellular networks to show that the selected features (proteins) are closer to the known disease genes, and the uncovered biological mechanisms are more diversified. By successfully tackling the complex correlations between biological variables, we anticipate that GE will improve the medical applications of ML. https://github.com/ebattistella/auto_machine_learning.

Beyond singular prototype: A prototype splitting strategy for few-shot medical image segmentation

In the realm of medical image semantic segmentation, few-shot learning, characterized by its efficient data utilization and flexible generalization capabilities, has been garnering increasing attention. The mainstream methods currently employ prototype-based approaches, which extract semantic knowledge from the annotated support images to guide the segmentation of the query image via masked global average pooling. However, such masked global average pooling leads to severe information loss, which is more problematic for medical images with large numbers of highly heterogeneous background categories. In this work, we propose a prototype splitting module (PSM) to effectively address the issue of semantic information loss in few-shot medical image segmentation. Specifically, PSM iteratively splits the support image masks into set of sub-masks containing segmented regions and unsegmented regions in a self-guided manner. This maximally retains the information within the original semantic classes and better extracts the representations of those classes. Additionally, we devise a multi-level cross attention module (MCAM) that transfers the foreground information from the support images to the query images across different levels to facilitate final segmentation prediction. We validate our method on multiple modal and multi-semantic medical image datasets. Results demonstrate that our approach achieves superior performance over existing state-of-the-art methods. The code has been released on https://github.com/fdngh/PSMnet.

Few-Shot Medical Image Segmentation via Generating Multiple Representative Descriptors.

Automatic medical image segmentation has witnessed significant development with the success of large models on massive datasets. However, acquiring and annotating vast medical image datasets often proves to be impractical due to the time consumption, specialized expertise requirements, and compliance with patient privacy standards, etc. As a result, Few-shot Medical Image Segmentation (FSMIS) has become an increasingly compelling research direction. Conventional FSMIS methods usually learn prototypes from support images and apply nearest-neighbor searching to segment the query images. However, only a single prototype cannot well represent the distribution of each class, thus leading to restricted performance. To address this problem, we propose to Generate Multiple Representative Descriptors (GMRD), which can comprehensively represent the commonality within the corresponding class distribution. In addition, we design a Multiple Affinity Maps based Prediction (MAMP) module to fuse the multiple affinity maps generated by the aforementioned descriptors. Furthermore, to address intra-class variation and enhance the representativeness of descriptors, we introduce two novel losses. Notably, our model is structured as a dual-path design to achieve a balance between foreground and background differences in medical images. Extensive experiments on four publicly available medical image datasets demonstrate that our method outperforms the state-of-the-art methods, and the detailed analysis also verifies the effectiveness of our designed module.

Multibranch CNN With MLP-Mixer-Based Feature Exploration for High-Performance Disease Diagnosis.

Deep learning-based diagnosis is becoming an indispensable part of modern healthcare. For high-performance diagnosis, the optimal design of deep neural networks (DNNs) is a prerequisite. Despite its success in image analysis, existing supervised DNNs based on convolutional layers often suffer from their rudimentary feature exploration ability caused by the limited receptive field and biased feature extraction of conventional convolutional neural networks (CNNs), which compromises the network performance. Here, we propose a novel feature exploration network named manifold embedded multilayer perceptron (MLP) mixer (ME-Mixer), which utilizes both supervised and unsupervised features for disease diagnosis. In the proposed approach, a manifold embedding network is employed to extract class-discriminative features; then, two MLP-Mixer-based feature projectors are adopted to encode the extracted features with the global reception field. Our ME-Mixer network is quite general and can be added as a plugin to any existing CNN. Comprehensive evaluations on two medical datasets are performed. The results demonstrate that their approach greatly enhances the classification accuracy in comparison with different configurations of DNNs with acceptable computational complexity.

Hybrid optimal feature selection approach for internet of things based medical data analysis for prognosis

<p>Healthcare is very important application domain in internet of things (IoT). The aim is to provide a novel combined feature selection (FS) methods like univariate (UV) with tree-based methods (TB), recursive feature elimination (RFE) with least absolute shrinkage selection operator (LASSO), mutual information (MI) with genetic algorithm (GA) and embedded methods (EM) with univariate has been applied to internet of medical things (IoMT)based heart disease dataset. The well-suited machine learning algorithms for IoT medical data are logistic regression (LR) and support vector machine (SVM). Each combined method has been applied to the machine learning algorithms to find the best classifier for prognosis. The various performance metrices has been calculated for all the combined feature selection methods for logistic regression and support vector machine and found that for precise classification could be done using recursive elimination feature selection method with LASSO applied to logistic regression achieved a better performance than all other combined methods with high accuracy, sensitivity and high area under curve. Decision has been taken by data analytics that RFE+LASSO using LR feature selection method will provide an overall better performance for IoT based medical heart disease dataset after comparing all other combined methods with LR and SVM classifiers<em>. </em></p>

Frame rate improvement in coherent plane-wave compounding using null subtraction imaging

Coherent plane-wave compounding (CPWC) has attracted significant attention in preclinical research and clinical diagnosis. However, a trade-off exists in CPWC between the image quality and frame rate. Null subtraction imaging (NSI), as a novel beamforming method, can realize high-quality imaging with enhanced lateral resolution and suppressed grating lobes. This study explores NSI to reduce the number of emissions while preserving the imaging quality. The performance of the proposed method is assessed using the Plane-Wave Imaging Challenge in Medical Ultrasound datasets, including phantom and in vivo datasets. The results verify the potential of NSI in terms of frame rate improvement compared to the conventional delay and sum beamforming method. NSI with 5 and 15 plane-wave emissions is evaluated. For example, for the experimental phantom datasets, NSI with 15 plane-wave emissions improves the lateral full-width at half maximum by 0.10 in comparison to DAS with 75 plane-wave emissions. Moreover, the corresponding contrast ratio and generalized contrast-to-noise ratio increase from 25.11 to 31.19 dB and 0.63 to 0.68, respectively, indicating contrast improvement. Thus, compared to DAS with 75 plane-wave emissions, the proposed method accelerates data acquisition by a factor of 5, resulting in remarkable frame rate improvement.

Robust Semi-Supervised 3D Medical Image Segmentation With Diverse Joint-Task Learning and Decoupled Inter-Student Learning.

Semi-supervised segmentation is highly significant in 3D medical image segmentation. The typical solutions adopt a teacher-student dual-model architecture, and they constrain the two models' decision consistency on the same segmentation task. However, the scarcity of medical samples can lower the diversity of tasks, reducing the effectiveness of consistency constraint. The issue can further worsen as the weights of the models gradually become synchronized. In this work, we have proposed to construct diverse joint-tasks using masked image modelling for enhancing the reliability of the consistency constraint, and develop a novel architecture consisting of a single teacher but multiple students to enjoy the additional knowledge decoupled from the synchronized weights. Specifically, the teacher and student models 'see' varied randomly-masked versions of an input, and are trained to segment the same targets but reconstruct different missing regions concurrently. Such joint-task of segmentation and reconstruction can have the two learners capture related but complementary features to derive instructive knowledge when constraining their consistency. Moreover, two extra students join the original one to perform an inter-student learning. The three students share the same encoding but different decoding designs, and learn decoupled knowledge by constraining their mutual consistencies, preventing themselves from suboptimally converging to the biased predictions of the dictatorial teacher. Experimental on four medical datasets show that our approach performs better than six mainstream semi-supervised methods. Particularly, our approach achieves at least 0.61% and 0.36% higher Dice and Jaccard values, respectively, than the most competitive approach on our in-house dataset. The code will be released at https://github.com/zxmboshi/DDL.

Evaluation of conventional and quantum computing for predicting mortality based on small early-onset colorectal cancer data

BackgroundQuantum computing integrated with machine learning (ML) offers novel solutions in various fields, including healthcare. The synergy between quantum computing and ML in classification exploits unique data patterns. Despite theoretical advantages, the empirical application and effectiveness of quantum computing on small medical datasets remains underexplored. MethodThis retrospective study from a tertiary hospital used data on early-onset colorectal cancer with 93 features and 1501 patients from 2008 to 2020 to predict mortality. We compared quantum support vector machine (QSVM) models with classical SVM models in terms of number of features, number of training sets, and outcome ratio. We evaluated the model based on the area under the curve in the receiver operating characteristic curve (AUROC). ResultsWe observed a mortality rate of 7.6 % (96 of 1253 subjects). We generated the mortality prediction model using 11 clinical variables, including cancer stage and chemotherapy history. We found that the AUROC difference between the conventional and quantum methods was the maximum for the top 11 variables. We also showed the AUROC in QSVM (mean [standard deviation], 0.863 [0.102]) outperformed all the number of trials in the conventional SVM (0.723 [0.231]). Compared to the conventional SVM, the QSVM showed robust performance, consistent with the AUROC, even in the unbalanced case. ConclusionOur study highlights the potential of quantum computing to improve predictive modeling in healthcare, especially for rare diseases with limited available data. The advantages of quantum computing, such as the exploration of Hilbert space, contributed to the superior predictive performance compared to conventional methods.

Automated feature selection using improved migrating birds optimization for enhanced medical diagnosis

The feature selection task is a crucial phase in data analysis, aiming to identify a minimized set of relevant features for the target class, thereby eliminating irrelevant and redundant attributes used for model training. While population-based feature selection approaches offer prominent solutions for classification performance, their computational time can be prohibitive. To mitigate delays and optimize resource utilization, this study adopts machine learning operations (MLOps). MLOps involves the seamless transition of experimental Machine Learning models into production, serving them to end users and automating the feature selection phase. This paper introduces a novel feature selection method based on improved migrating bird optimization and its automated variant integrated into MLOps. Experiments conducted on six medical datasets validate the effectiveness of our proposed feature selection method in improving the outcomes of medical diagnosis systems. The results showcase satisfactory performance in terms of classification compared to concurrent feature selection algorithms.