Digital colposcopy image analysis techniques requirements and their role in clinical diagnosis: a systematic review.

INTRODUCTION: Colposcopy is a medical procedure for detecting cervical lesions. Access to devices required for colposcopy procedures is limited in low- and middle-income countries. However, various existing digital imaging techniques based on artificial intelligence offer solutions to analyze colposcopy images and address accessibility challenges. METHODS: We systematically searched PubMed, National Library of Medicine, and Crossref, which met our inclusion criteria for our study. Various methods and research gaps are addressed, including how variability in images and sample size affect the accuracy of the methods. The quality and risk of each study were assessed following the QUADAS-2 guidelines. RESULTS: Development of image analysis and compression algorithms, and their efficiency are analyzed. Most of the studied algorithms have attained specificity, sensitivity, and accuracy which range from 86% to 95%, 75%-100%, and 100%, respectively, and these results were validated by the clinician to analyze the images quickly and thus minimize biases among the clinicians. CONCLUSION: This systematic review provides a comprehensive study on colposcopy image analysis stages and the advantages of utilizing digital imaging techniques to enhance image analysis and diagnostic procedures and ensure prompt consultations. Furthermore, compression techniques can be applied to send medical images over media for further analysis among periphery hospitals.

Geospatial analysis of contagious infection growth and cross-boundary transmission in non-vaccinated districts of North-East Indian states during the COVID-19 pandemic.

Background: During the initial phase of the COVID-19 pandemic, the Government of India implemented a nationwide lockdown, sealing borders across states and districts. The northeastern region of India, surrounded by three international borders and connected to mainland India by a narrow passage, faced particular isolation. This isolation resulted in these states forming a relatively closed population. Consequently, the availability of population-based data from Indian Council of Medical Research, tracked through national identification cards, offered a distinctive opportunity to understand the spread of the virus among non-vaccinated and non-exposed populations. This research leverages this dataset to comprehend the repercussions within isolated populations. Methods: The inter-district variability was visualized using geospatial analysis. The patterns do not follow any established grounded theories on disease spread. Out of 7.1 million total data weekly 0.35 million COVID-19-positive northeast data was taken from April 2020 to February 2021 including "date, test result, population density, area, latitude, longitude, district, and state" to identify the spread pattern using a modified reaction-diffusion model (MRD-Model) and Geographic Information System. Findings: The analysis of the closed population group revealed an initial uneven yet rapidly expanding geographical spread characterized by a high diffusion rate α approximately 0.4503 and a lower reaction rate ß approximately 0.0256, which indicated a slower growth trajectory of case numbers rather than exponential escalation. In the latter stages, COVID-19 incidence reached zero in numerous districts, while in others, the reported cases did not exceed 100. Interpretation: The MRD-Model effectively captured the disease transmission dynamics in the abovementioned setting. This enhanced understanding of COVID-19 spread in remote, isolated regions provided by the MRD modelling framework can guide targeted public health strategies for similar isolated areas. Funding: This study is Funded by Indian Council of Medical Research (ICMR).

Serial section histopathology image dataset of colon and pancreas tissue captured through light microscope.

Till date, histopathological examination of concerned tissue by light microscopy is considered to be the gold standard and most acceptable method for the final diagnosis of disease processes. Sometimes, examination of serial sections, i.e., consecutive sections obtained from a histopathologically processed tissue specimen using a microtome, plays a very vital role in comprehensive understanding of the tissue details, aiding in treatment planning, prognosis, and final diagnosis. In this study, the histopathological dataset showcased, focuses on images of serial sections from colonic and pancreatic tissues, captured through light microscopy. These sequential images might serve as a valuable resource for generating a three-dimensional representation of histological tissue samples. The resulting 3D reconstructed data obtained from the serial sections will provide detailed structural information at a high resolution. Although whole-slide imaging is considered a better option to get images of all sections on one slide at multiple desired magnifications and is obviously a more wanted option for 3D reconstruction of an entire tissue, its high cost poses a significant barrier. In this study, the dataset is prepared and collected from the histopathology division of the Department of Pathology, North Bengal Medical College, near Siliguri. It consisted of 168 serial section images of colon and pancreatic tissue captured at different magnifications. This comprehensive dataset will aid biomedical researchers in the field of histopathology analysis, an area that still holds potential for recent advancements, particularly in 3D reconstruction.

Tracing the COVID-19 spread pattern in India through a GIS-based spatio-temporal analysis of interconnected clusters.

Spatiotemporal analysis is a critical tool for understanding COVID-19 spread. This study examines the pattern of spatial distribution of COVID-19 cases across India, based on data provided by the Indian Council of Medical Research (ICMR). The research investigates temporal patterns during the first, second, and third waves in India for an informed policy response in case of any present or future pandemics. Given the colossal size of the dataset encompassing the entire nation's data during the pandemic, a time-bound convenience sampling approach was employed. This approach was carefully designed to ensure a representative sample from advancing timeframes to observe time-based patterns in data. Data were captured from March 2020 to December 2022, with a 5-day interval considered for downloading the data. We employ robust spatial analysis techniques, including the Moran's I index for spatial correlation assessment and the Getis Ord Gi* statistic for cluster identification. It was observed that positive COVID-19 cases in India showed a positive auto-correlation from May 2020 till December 2022. Moran's I index values ranged from 0.11 to 0.39. It signifies a strong trend over the last 3 years with [Formula: see text] of 0.74 on order 3 polynomial regression. It is expected that high-risk zones can have a higher number of cases in future COVID-19 waves. Monthly clusters of positive cases were mapped through ArcGIS software. Through cluster maps, high-risk zones were identified namely Kerala, Maharashtra, New Delhi, Tamil Nadu, and Gujarat. The observation is: high-risk zones mostly fall near coastal areas and hotter climatic zones, contrary to the cold Himalayan region with Montanne climate zone. Our aggregate analysis of 3 years of COVID-19 cases suggests significant patterns of interconnectedness between the Indian Railway network, climatic zones, and geographical location with COVID-19 spread. This study thereby underscores the vital role of spatiotemporal analysis in predicting and managing future COVID-19 waves as well as future pandemics for an informed policy response.

Fractal Dimension-Based Infection Detection in Chest X-ray Images.

The current ongoing trend of dimension detection of medical images is one of the challenging areas which facilitates several improvements in accurate measuring of clinical imaging based on fractal dimension detection methodologies. For medical diagnosis of any infection, detection of dimension is one of the major challenges due to the fractal shape of the medical object. Significantly improved outcome indicates that the performance of fractal dimension detection techniques is better than that of other state-of-the-art methods to extract diagnostically significant information from clinical image. Among the fractal dimension detection methodologies, fractal geometry has developed an efficient tool in medical image investigation. In this paper, a novel methodology of fractal dimension detection of medical images is proposed based on the concept of box counting technique to evaluate the fractal dimension. The proposed method has been evaluated and compared to other state-of-the-art approaches, and the results of the proposed algorithm graphically justify the mathematical derivation of the box counting approach in terms of Hurst exponent.

Time Efficient Image Encryption-Decryption for Visible and COVID-19 X-ray Images Using Modified Chaos-Based Logistic Map.

In this pandemic situation, radiological images are the biggest source of information in healthcare and, at the same time, one of the foremost troublesome sources to analyze. Clinicians now-a-days must depend to a great extent on therapeutic image investigation performed by exhausted radiologists and some of the time analyzed and filtered themselves. Due to an overflow of patients, transmission of these medical data becomes frequent and maintaining confidentiality turns out to be one of the most important aspects of security along with integrity and availability. Chaos-based cryptography has proven a useful technique in the process of medical image encryption. The specialty of using chaotic maps in image security is its capability to increase the unpredictability and this causes the encryption robust. There are large number of literature available with chaotic map; however, most of these are not useful in low-precision devices due to their time-consuming nature. Taking into consideration of all these facts, a modified encryption technique is proposed for 2D COVID-19 images without compromising security. The novelty of the encryption procedure lies in the proposed design which is split into mainly three parts. In the first part, a variable length gray level code is used to generate the secret key to confuse the intruder and subsequently it is used as the initial parameter of both the chaotic maps. In the second part, one-stage image pixels are shuffled using the address code obtained from the sorting transformation of the first logistic map. In the final stage, a complete diffusion is applied for the whole image using the second chaotic map to counter differential and statistical attack. Algorithm validation is done by experimentation with visual image and COVID-19 X-ray images. In addition, a quantitative analysis is carried out to ensure a negligible data loss between the original and the decrypted image. The strength of the proposed method is tested by calculating the various security parameters like correlation coefficient, NPCR, UACI, and key sensitivity. Comparison analysis shows the effectiveness for the proposed method. Implementation statistics shows time efficiency and proves more security with better unpredictability.