The number of people with glaucoma worldwide in 2010 and 2020

The global healthcare sector continues to grow rapidly and is reflected as one of the fastest-growing sectors in the fourth industrial revolution (4.0). The majority of the healthcare industry still uses labor-intensive, time-consuming, and error-prone traditional, manual, and manpower-based methods. This review addresses the current paradigm, the potential for new scientific discoveries, the technological state of preparation, the potential for supervised machine learning (SML) prospects in various healthcare sectors, and ethical issues. The effectiveness and potential for innovation of disease diagnosis, personalized medicine, clinical trials, non-invasive image analysis, drug discovery, patient care services, remote patient monitoring, hospital data, and nanotechnology in various learning-based automation in healthcare along with the requirement for explainable artificial intelligence (AI) in healthcare are evaluated. In order to understand the potential architecture of non-invasive treatment, a thorough study of medical imaging analysis from a technical point of view is presented. This study also represents new thinking and developments that will push the boundaries and increase the opportunity for healthcare through AI and SML in the near future. Nowadays, SML-based applications require a lot of data quality awareness as healthcare is data-heavy, and knowledge management is paramount. Nowadays, SML in biomedical and healthcare developments needs skills, quality data consciousness for data-intensive study, and a knowledge-centric health management system. As a result, the merits, demerits, and precautions need to take ethics and the other effects of AI and SML into consideration. The overall insight in this paper will help researchers in academia and industry to understand and address the future research that needs to be discussed on SML in the healthcare and biomedical sectors.

https://www.mdpi.com/2075-4418/12/10/2549/pdf?version=1666682164

Demystifying Supervised Learning in Healthcare 4.0: A New Reality of Transforming Diagnostic Medicine

Glaucoma is one of the leading severe retinal disease which damages the optic nerve head on the retinal part of the eye irreversibly. Once the person is diagnosed with glaucoma, it cannot be treated entirely, but it can be controlled. If glaucoma is not diagnosed in time, it will lead to vision loss by damaging the Optic Nerve Head. The glaucoma detection is performed based on the optic disc and optic cup parameters on the retinal part of the eye. In the existing system, many image processing and machine learning techniques used for the segmentation and classification of optic disc and optic cup. To improve the precision of diagnosis, the existing techniques used need an improvement. This article helps readers with more information about the existing methods applied for the diagnosis of glaucoma, it also lists the research gaps and technical challenges to improve the accuracy of segmentation and classification methods.

/pdf/a-review-on-the-optic-disc-and-optic-cup-segmentation-and-29qyxutpz0.pdf

A Review on the optic disc and optic cup segmentation and classification approaches over retinal fundus images for detection of glaucoma

Glaucoma is an optic nerve disease that damages the optic nerves and can cause blindness if it remains untreated. CDR (Cup-to-Disc Diameter Ratio) is one of the factors with which we can determine the presence of Glaucoma. The detection is carried out using an existing pipeline in which segmentation of optic disc and cup is carried out first followed by CDR calculation based on which a prediction is made. A threshold-based algorithm was used for segmenting the Optic Disc. For the cup region, a modified region growing algorithm was applied. The segmentations were followed by infilling blood vessels and morphological operations. The CDR value calculated from the segmented images was fed to an SVM model to classify. Cup segmentation is a challenging and hard problem. There are many algorithms that tackle the same. The proposed method approaches this challenge with a novel method for segmenting the optic cup. The results show that the proposed approach could accurately predict the presence of Glaucoma with less computational requirements.

Glaucoma Detection from Retinal Fundus Images

Preclinical magnetic resonance imaging (MRI) is a critical component in a co-clinical research pipeline. Importantly, segmentation of tumors in MRI is a necessary step in tumor phenotyping and assessment of response to therapy. However, manual segmentation is time-intensive and suffers from inter- and intra- observer variability and lack of reproducibility. This study aimed to develop an automated pipeline for accurate localization and delineation of TNBC PDX tumors from preclinical T1w and T2w MR images using a deep learning (DL) algorithm and to assess the sensitivity of radiomic features to tumor boundaries. We tested five network architectures including U-Net, dense U-Net, Res-Net, recurrent residual UNet (R2UNet), and dense R2U-Net (D-R2UNet), which were compared against manual delineation by experts. To mitigate bias among multiple experts, the simultaneous truth and performance level estimation (STAPLE) algorithm was applied to create consensus maps. Performance metrics (F1-Score, recall, precision, and AUC) were used to assess the performance of the networks. Multi-contrast D-R2UNet performed best with F1-score = 0.948; however, all networks scored within 1-3% of each other. Radiomic features extracted from D-R2UNet were highly corelated to STAPLE-derived features with 67.13% of T1w and 53.15% of T2w exhibiting correlation ρ ≥ 0.9 (p ≤ 0.05). D-R2UNet-extracted features exhibited better reproducibility relative to STAPLE with 86.71% of T1w and 69.93% of T2w features found to be highly reproducible (CCC ≥ 0.9, p ≤ 0.05). Finally, 39.16% T1w and 13.9% T2w features were identified as insensitive to tumor boundary perturbations (Spearman correlation (-0.4 ≤ ρ ≤ 0.4). We developed a highly reproducible DL algorithm to circumvent manual segmentation of T1w and T2w MR images and identified sensitivity of radiomic features to tumor boundaries.

https://www.mdpi.com/2072-6694/13/15/3795/pdf

Deep Learning Segmentation of Triple-Negative Breast Cancer (TNBC) Patient Derived Tumor Xenograft (PDX) and Sensitivity of Radiomic Pipeline to Tumor Probability Boundary.

The automatic retinal image analysis is emerging as one of the most important primary screening tools for early detection and treatment for eye diseases. Glaucoma is a severe human eye disease leading to the permanent loss of vision. The manual examination of optic nerve head of the retina using Color Fundus Imaging (CFI) is a standard procedure used for predicting glaucoma, but the detection and diagnosis varies widely across different ophthalmologists. In this paper we present an automatic technique for the segmentation of the cup region from the optical disc(OD) region in RGB channels to calculate the parameters used for the predictive analysis of glaucoma. The accurate segmentation of the cup region and the optical disc from the retinal fundus image serves as an important step for the calculation of cup-to-disc area ratio (ACDR). The quantitative evaluation of this predictive analysis is done on a freely available database with a result accuracy of 83.168%.

Automatic Evaluation and Predictive Analysis of Optic Nerve Head for the Detection of Glaucoma

Automatic evaluation of the retinal fundus image is regarded as one of the most important future tools for early detection and treatment of progressive eye diseases like glaucoma. Glaucoma leads to progressive degeneration of vision which is characterized by shape deformation of the optic cup associated with focal notching, wherein the degeneration of the blood vessels results in the formation of a notch along the neuroretinal rim. In this study, we have developed a methodology for automated prediction of glaucoma based on feature analysis of the focal notching along the neuroretinal rim and cup to disc ratio values. This procedure has three phases: the first phase segments the optic disc and cup by suppressing the blood vessels with dynamic thresholding; the second phase computes the neuroretinal rim width to detect the presence and direction of notching by the conventional ISNT rule apart from calculating the cup-to-disc ratio from the color fundus image (CFI); the third phase uses linear support vector based machine learning algorithm by integrating extracted parameters as features for classification of CFIs into glaucomatous or normal. The algorithm outputs have been evaluated on a freely available database of 101 images, each marked with decision of five glaucoma expert ophthalmologists, thereby returning an accuracy rate of 87.128%.

https://link.springer.com/content/pdf/10.1134/S1054661819040230.pdf

Predictive Diagnosis of Glaucoma Based on Analysis of Focal Notching along the Neuro-Retinal Rim Using Machine Learning

Deep Learning networks have established themselves as providing state of art performance for semantic segmentation These techniques are widely applied specifically to medical detection, segmentation and classification The advent of the U-Net based architecture has become particularly popular for this application In this paper we present the Dense Recurrent Residual Convolutional Neural Network(Dense R2U CNN) which is a synthesis of Recurrent CNN, Residual Network and Dense Convolutional Network based on the U-Net model architecture The residual unit helps training deeper network, while the dense recurrent layers enhances feature propagation needed for segmentation The proposed model tested on the benchmark Lung Lesion dataset showed better performance on segmentation tasks than its equivalent models

Densely Connected Recurrent Residual (Dense R2UNet) Convolutional Neural Network for Segmentation of Lung CT Images.

The advent of various bandwidth-hungry applications now-a-days has increased the spectrum demand, thereby resulting in spectrum scarcity. Cognitive Radio Networks (CRN), proposed by the researchers, is a probable solution to the problem. CRN allows licensed Primary Users (PUs) to partly lease their unutilized spectrum to the opportunistic Secondary Users (SU) for effective Channel Utilization (CU) and enhanced Quality of Service (QoS). Now, use of buffers is a common approach to provide improved QoS to the SUs. However, if the waiting time of the SUs in the buffers exceed their time-out interval, the QoS degrades instead of improving. Thus, in this work, firstly, a CRN has been modeled using two buffers, namely, the New Queue (NQ) and the Pre-empted Queue (PQ). The NQ holds the newly requesting SUs while the PQ holds the SUs pre-empted by the PUs. Next, a model to determine the dynamic length of buffers has been proposed. It works based on the prior activity of the end-users and the requesting SU's waiting threshold. The model ensures service to user if it is admitted in the network. Otherwise, it is blocked or dropped. Blocking or dropping of the calls in this case provides a chance to the SUs to transmit via other base stations. The system is modeled using a multidimensional Continuous Time Markov Chain (CTMC) model. The dynamic queue helps to restrict the Level of Impatience (LOI) to 19.90% for the New Queue SUs and 14.93% for Preempted Queue SUs while achieving 99.33% CU.

Kaushik Dutta

Papers

Deep Learning Segmentation of Triple-Negative Breast Cancer (TNBC) Patient Derived Tumor Xenograft (PDX) and Sensitivity of Radiomic Pipeline to Tumor Probability Boundary.

Automatic Evaluation and Predictive Analysis of Optic Nerve Head for the Detection of Glaucoma

Predictive Diagnosis of Glaucoma Based on Analysis of Focal Notching along the Neuro-Retinal Rim Using Machine Learning

Densely Connected Recurrent Residual (Dense R2UNet) Convolutional Neural Network for Segmentation of Lung CT Images.

Dynamic Queuing Model for the Secondary Users in a Cognitive Radio Network for Improvement of QoS