Availability Of Advanced Equipment Research Articles

CerviCell-detector: An object detection approach for identifying the cancerous cells in pap smear images of cervical cancer

Cervical cancer is the second most commonly seen cancer in women. It affects the cervix portion of the vagina. The most preferred diagnostic test required for screening for cervical cancer is the pap smear test. Pap smear is a time-consuming test as it requires detailed analysis by expert cytologists. Cytologists can screen around 100 to 1000 slides depending upon the availability of advanced equipment. It requires substantial time and effort to carefully examine each slide, identify and classify cells, and make accurate diagnoses. Prolonged periods of visual inspection can increase the likelihood of human errors, such as overlooking abnormalities or misclassifying cells. The sheer volume of slides to be screened can exacerbate fatigue and impact diagnostic accuracy. Due to this reason Artificial intelligence (AI) based computer-aided diagnosis system for the classification and detection of pap smear images is needed. There are some AI-based solutions proposed in the literature, still, an effective and accurate system is under research. In this paper, we implement a state-of-the-art object detection model with a newly available CRIC dataset which follows the Bethesda system for nomenclature. Object detection models implemented are YOLOv5 which uses the CSPNet backbone, Faster R–CNN which has Region Proposal Network (RPN) and Detectron2 framework created by Facebook AI Research (FAIR) Group. ResNext model is implemented among the available models from Detectron2. The CRIC dataset is preprocessed and augmented using Roboflow tool. The performance measures of Average Precision and mean Average precision over the Intersection over Union (IoU) are used to evaluate the effectiveness of the models. The models performed better for two classes namely Normal and Abnormal compared to six classes from the Bethesda system. The highest mean Average Precision (mAP) is observed on the augmented dataset for YOLOv5 models for binary classification with 83 % mAP with IoU in the range of 0.50–0.95.

DeepCyto: a hybrid framework for cervical cancer classification by using deep feature fusion of cytology images

<abstract> <p>Cervical cancer is the second most commonly seen cancer in women. It affects the cervix portion of the vagina. The most preferred diagnostic test required for screening cervical cancer is the pap smear test. Pap smear is a time-consuming test as it requires detailed analysis by expert cytologists. Cytologists can screen around 100 to 1000 slides depending upon the availability of advanced equipment. Due to this reason Artificial intelligence (AI) based computer-aided diagnosis system for the classification of pap smear images is needed. There are some AI-based solutions proposed in the literature, still an effective and accurate system is under research. In this paper, the deep learning-based hybrid methodology namely DeepCyto is proposed for the classification of pap smear cytology images. The DeepCyto extracts the feature fusion vectors from pre-trained models and passes these to two workflows. Workflow-1 applies principal component analysis and machine learning ensemble to classify the pap smear images. Workflow-2 takes feature fusion vectors as an input and applies an artificial neural network for classification. The experiments are performed on three benchmark datasets namely Herlev, SipakMed, and LBCs. The performance measures of accuracy, precision, recall and F1-score are used to evaluate the effectiveness of the DeepCyto. The experimental results depict that Workflow-2 has given the best performance on all three datasets even with a smaller number of epochs. Also, the performance of the DeepCyto Workflow 2 on multi-cell images of LBCs is better compared to single cell images of other datasets. Thus, DeepCyto is an efficient method for accurate feature extraction as well as pap smear image classification.</p> </abstract>

Preparedness of Hospitals Post COVID-19 Era

COVID-19 is an unprecedented global crisis, but epidemics have increased in both frequency and reach due to globalisation, greater connectivity, and denser cities. The pace at which healthcare systems were able to respond and the transformation scale are incredible achievements. But they also serve to highlight how ill-equipped the world was for a pandemic of this kind. COVID-19 has shone a spotlight on systems and processes that had been fine-tuned over many decades, revealing flaws and vulnerabilities that we had overlooked, as well as glaring blind spots in our forecasting. During the outbreak of the current COVID-19 pandemic, there were several problems faced by healthcare providers worldwide. A few of these were the shortage of spaces to handle the patient surge, availability of advanced equipment, overburdened doctors and paramedical staff, quality of services, and awareness about disease prevention. It is believed that the world may have to live with such viruses indefinitely. There is a need for shifting, changing, and altering the design and construction of hospitals to tackle such pandemics. Future hospitals should have more flexibility and adaptability to handle pandemics and other outlier events that enable rapid preparedness of staff, facilities, and processes to manage an unprecedented influx of patients. In this article, we are trying to answer some of the biggest questions faced by experts: "what shall be the design of future healthcare institutions which are capable enough to handle such pandemics? What lessons can be learnt for the future design of hospitals, as well as other healthcare buildings? Do we need to adapt and refurbish preparing for a second, third or fourth wave of infections? What will the long-term impact be on building typologies and layouts, strategic planning and investment?" We discuss the following major issues and suggest themes that could affect the design of such institutions and clinical services delivered by them.

Quality improvement strategies to improve inpatient management of small and sick newborns across All Babies Count supported hospitals in rural Rwanda

BackgroundNeonatal mortality contributes to nearly half of child deaths globally and the majority of these deaths are preventable. Poor quality of care is a major driver of neonatal mortality in low- and middle-income countries. The All Babies Count (ABC) intervention was designed to reduce neonatal mortality through provision of equipment and supplies, training, mentorship, and data-driven quality improvement (QI) with peer-to-peer learning through learning collaborative sessions (LCS). We aim to describe the ABC scale-up in seven rural district hospitals from 2017 to 2019 focusing on the QI strategies implemented in hospital neonatal care units (NCUs) and the resultant neonatal care outcomes.MethodsA pre-post quasi experimental study was conducted in 7 rural hospitals in Rwanda in two phases. The baseline periods were April-June 2017 for Phase I and July-September 2017 for Phase II; with end-line data collected during the same periods in 2019. Data included facility audits of supplies and staffing, LCS surveys of QI skills, and reports of implemented QI change ideas. Data on NCU admissions and deaths were extracted from Health Management Information System (HMIS). Facility-reported change ideas were coded into common themes. Changes in post-post neonatal mortality were measured using Chi-squared tests.ResultsNCUs were run by a median of 1 nurse [interquartile range (IQR):1–2] at baseline and endline. Median NCU admissions increased from 121 [IQR: 77–155] to 137 [IQR: 79–184]. Availability of advanced equipment improved (syringe pumps: 57–100 %, vital sign monitors: 51–100 % and CPAP machine: 14–100 %). There were significant improvements in QI skills among NCU staff. All 7 NCUs (100 %) addressed non-adherence to protocol as a priority gap, 5 NCUs (86 %) also improved communication with families. NCU case fatality rate declined from 12.4 to 7.8 % (p = 0.001).ConclusionsThe ABC package of interventions combining the provision of essential equipment to NCU, clinical training and strong mentorship, QI coaching, and the LCS approach for peer-to-peer learning was associated with significant neonatal mortality reduction and services utilization in the intervention hospitals.