Traumatic brain injury (TBI) is a major problem with an estimated cost of $76 billion per year in the US alone. The Center for Disease Control and Prevention (CDC) documented 2.53 million TBI-related emergency department visits, with approximately 288,000 TBI-related hospitalizations and 56,800 TBI-related deaths in 2014 in the US. The lack of FDA-approved treatment strategies for TBI drives the need for novel therapeutic and preventative measures. In a quest to reduce TBI-related injuries and deaths, automotive companies have focused their efforts to make safer cars for both occupants and pedestrians. Computational finite element (FE) models have been used to advance research efforts in automotive safety systems engineering in hopes of ameliorating the burden caused by TBI. The current use of FE models in the automotive industry focuses on predicting stresses and strains that occur during the accident itself to predict primary injury. However, contemporary models lack the appropriate mechanical properties required to make accurate predictions of brain tissue deformation after injury and lack the ability to model secondary injuries such as cerebral edema (brain swelling). With cerebral edema being a major cause of death and disability after TBI, and with the pattern and magnitude of cerebral edema being dependent on the initiating strain field in brain tissue during TBI, automotive safety systems could be further improved if 1) FE head models contained more accurate mechanical properties and 2) if FE models could simulate secondary injuries such as cerebral edema. Therefore, the driving purpose of this thesis is two-fold: 1) to determine the mechanical properties of different regions of the brain and 2) to present a new computational methodology that allows for modeling of cerebral edema to better predict patient outcome following TBI. The use of FE models requires appropriate constitutive formulations and associated parameters to accurately model and predict the initial mechanical response of the brain to injury loading conditions. Since patient outcome is dependent on the resulting strain field within brain tissue post-injury, accurate modeling of brain tissue deformation is important for testing the efficacy of engineered automotive safety systems using FE simulations. To address this need, the first aim of this thesis employed an inverse FE approach to characterize mechanical properties of the human hippocampus (CA1, CA3, dentate gyrus), cortex white matter, and cortex gray matter. Anatomical regions were significantly different in their mechanical properties. Although no sex dependency was observed, there were trends indicating that some male brain regions were generally stiffer than corresponding female regions. In addition, mechanical properties were not dependent on age within the examined age range (4-58 years old). Ultimately, this study provides a structure-specific description of fresh human brain tissue mechanical properties, which will be an important step toward explicitly modeling the heterogeneity of brain tissue deformation during TBI using FE modeling. Fatal brain injuries may also result from physiological changes in the brain that occur after the primary injury that immediately occurs during head injury. Secondary injuries such as cerebral edema are associated with poor outcome. Despite the severe consequences of cerebral edema, its mechanism is not fully understood. The second aim of this thesis, therefore, was to elucidate the driving mechanism of cerebral edema by demonstrating that cleavage of intracellular fixed-charge density (FCD) reduces brain swelling pressure and to measure the FCD content of rat and pig brain tissue. Thin brain samples were placed into a confined pressure chamber, and FCD content was calculated from measured swelling pressure and the Gibbs-Donnan equation. We observed that cleavage of FCD using enzymes reduced swelling pressure in rat brain tissue samples and determined that pig cortex gray matter contains more FCD than pig cortex white matter. These results demonstrate that cerebral edema may occur in accordance with principles of triphasic swelling biomechanics and demonstrates the plausibility of computationally modeling cerebral edema with triphasic material formulations. Cerebral edema leads to increased intracranial pressure (ICP) as the brain swells within the fixed volume of the skull, and there is overwhelming evidence of ICP as a powerful predictor of patient outcome following TBI. Current industry standards of patient outcome evaluation use tissue-level metrics solely from primary injury such as maximum principal strain (MPS) or cumulative strain damage measure (CSDM), but these methods can be improved especially in regards to predicting mortality. Therefore, the third aim of this thesis was to develop a new FE head model and computational methodology incorporating triphasic swelling biomechanics to simulate brain swelling following impact to improve patient outcome predictions. Patient outcome was predicted by simulating swelling and calculating the resulting ICP, which is a strong indicator of patient mortality. Calculating ICP in addition to predicting primary injury metrics such as MPS and CSDM may allow automotive safety engineers to make better predictions of patient outcome following TBI so they can develop better safety systems. Another common indicator of poor outcome following TBI is acute subdural hematoma (ASDH). ASDH is an intracranial bleed that often results from TBI because of stretching and tearing of the bridging veins which causes blood to collect in the innermost layer of the dura. Despite the poor prognosis associated with the presence of ASDH following TBI, the mechanism as to why its presence is associated with a higher likelihood of death remains uncertain. Current state of the art FE head models used in automotive safety engineering efforts do not consider ASDH, which may drastically reduce their effectiveness in predicting patient outcome following TBI. Therefore, the fourth and final aim of this thesis was to incorporate ASDH into our FE head model of swelling and elucidate the underlying secondary brain injury mechanism of ASDH that contributes to increased mortality in hopes of increasing the efficacy of current FE models to predict patient outcome and ultimately design better safety systems. Using our novel FE head model and methodology from aim 3, we showed that the higher likelihood of death associated with the presence of ASDH may be caused by exacerbated ischemic injury which increases ICP, demonstrating that modeling of ASDH is necessary for accurately modeling patient outcome following TBI. Despite decades of TBI research and FE head model improvements, more work is required to enhance the biofidelity of these models to better predict patient outcome. The work in this thesis is important, as it introduces a new tool that will allow automotive safety engineers to incorporate cerebral edema and ASDH, both of which may drastically influence patient outcome following TBI, into models of head injury to allow for better predictions of patient outcome. It is hoped that the work in this thesis lays the foundation for future work that aids in the design of improved automotive safety systems that will save countless human lives.

Os objetivos do estudo foram correlacionar a razão entre a circunferência abdominal e altura (CA/A) e o índice de massa corpórea (IMC) com as variáveis cardiometabólicas e inflamatórias em escolares de seis a 10 anos; avaliar a frequência de sobrepeso/obesidade e alterações cardiometabólicas e comparar o desempenho dos referenciais de índice de massa corpórea (IMC) do Centers for Disease Control and Prevention 2000 (CDC) e Organização Mundial de Saúde 2007 (OMS) no diagnóstico de sobrepeso/obesidade e alterações cardiometabólicas. Métodos: estudo de corte transversal, que incluiu 175 crianças, provenientes do Centro de Referência para Tratamento da Criança e do Adolescente (CRTCA), em Campos, Rio de Janeiro. As crianças foram divididas segundo os escores z do CDC e OMS em: não obesas (z do IMC <1) e sobrepeso/obesidade (z do IMC > 1). As variáveis cardiometabólicas analisadas foram: pressão arterial sistólica (PAS) e diastólica (PAD), glicose, lipoproteínas de baixa e alta densidades (LDL e HDL, respectivamente), triglicerídeos (TG), HOMA-IR. Como variáveis inflamatórias, analisamos proteína C reativa ultra-sensível (PCR) e leucometria. Resultados: a média da CA/A do grupo sobrepeso/obesidade foi maior que a do não obeso (0,58 ± 0,007 e 0,45 ± 0,004, respectivamente, p< 0,0001). Houve correlação significativa da CA/A com os escores z do IMC (r = 0,88, p < 0,0001), PAS (r= 0,51, p<0,0001), PAD (r= 0,49, p<0,0001), HOMA-IR (r=0,83, p<0,0001), HDL (r = -0,28, p< 0,0002), TG (r= 0,26, p<0,0006), LDL (r= 0,25, p<0,0008) e PCR (r= 0,51, p<0,0001). Contudo, a CA/A não se correlacionou com glicemia nem leucócitos. A sensibilidade da CA/A se equivaleu à do IMC no diagnóstico das alterações cardiometabólicas. A sensibilidade mais elevada da CA/A foi para o diagnóstico de alteração da PAS (80,0 %), PAD (76,6%) e HOMA-IR (92,6%). O ponto de corte superior a 0,47 foi sensível para o diagnóstico de resistência insulínica, mas acima de 0,50, para os demais distúrbios cardiometabólicos. A frequência de sobrepeso/obesidade nos escolares foi igual a 49,7%. Com exceção de hipertrigliceridemia, todas as outras alterações cardiometabólicas foram mais frequentes no grupo sobrepeso/obesidade (aumento de PA, p<0,0001; glicemia de jejum alterada, p < 0,0048; aumento de LDL, p< 0,015 e redução do HDL, p<0,0001). O referencial da OMS 2007 reclassificou 11 crianças a mais como obesas que o CDC, que apresentaram médias de escores z de PAS (1,71 ± 1,54), PAD (2,64 ± 1,83) e HOMA-IR (1,84 ± 0,98) semelhantes às médias das obesas (PAS = 1,25 ± 2,04; PAD = 1,94 ± 1,19 e HOMA-IR = 2,09 ± 1,12), mas superiores às médias das classificadas como sobrepeso (PAS = 0,49 ± 1,34, p < 0,023; PAD = 1,45 ± 0,97, p < 0,04 e HOMA-IR = 1,24 ± 0,67, p < 0,04 ). Conclusões: a razão CA/A foi tão sensível quanto IMC da OMS 2007 no diagnóstico do risco cardiometabólico e inflamatório. O referencial da OMS 2007 foi o mais sensível não só para o rastreamento de sobrepeso/obesidade, como também para pressão arterial elevada e resistência insulínica, em escolares de seis a 10 anos / This study aims to correlate the waist-to-height ratio (WHtR) and the body mass index (BMI) with the cardiometabolic and inflammatory variables in 6-10 year-old school children; to evaluated the frequency of overweight/obesity and cardiometabolic disturbances, and to compare the 2000 Centers for Disease Control and Prevention (CDC) and 2007 World Health Organization (WHO) body mass index (BMI) references in the diagnosis of overweight/obesity and the cardiometabolic disturbances. Methods: a cross-sectional study which included 175 subjects, selected from the Reference Center for the Treatment of Children and Adolescents, in Campos, Rio de Janeiro. The subjects were classified according to the 2000 CDC and 2007 OMS BMI z scores as non obese (BMI < 1) and overweight/obese ones (BMI > 1). The analized cardiometabolic variables were systolic and diastolic blood pressure (SBP and DBP respectively), fasting glycemia, low and high density lipoproteins (LDL and HDL respectively), trigliceride (TG), homeostatic model assessment (HOMA-IR). As inflammatory markers we analized the ultra-sensitive Creactive protein (CRP) and the leucocyte count. Results: the WHtR mean of the overweight/obese group was higher than that of the non obese ones (0,58 ± 0,007 and 0,45 ± 0,004, respectively,p < 0,0001). There was correlation between the WHtR and BMI z score (r = 0,88, p < 0,0001), SBP (r = 0,51, p < 0,0001), DBP (r = 0,49, p < 0,0001), HOMA-IR (r = 0,83, p < 0,0001), HDL (r = -0,28, p < 0,0002, TG (r= 0,26, p < 0,0006), LDL (r = 0,25, p < 0,0008), and CRP (r = 0, 51, p < 0.0001). However, the WHtR was neither correlated with glycemia nor with the leucocyte count. The WHtR sensitivity was equivalent to that of the BMI in the diagnosis of all cardiometabolic variables. The highest WHtR sensitivity was to diagnose the SBP (80,0%), DBP (76,6%) and HOMA-IR (92,6%) alterations. The WHtR cut-off higher than 0,47 pointed out to insulin resistance diagnosis, but higher than 0,5, it did to the other metabolic disturbances. The frequency of overweight/obesity was 49,7% in these school children. Except for hypertriglyceridemia, all the remaining cardiometabolic disturbances were more frequent in the overweight/obese group. The 2007 WHO BMI reference reclassified 11 children more as obese than the 2000 CDC, who had means of SBP (1,71 ± 1,54) and DBP z scores (2,64 ± 1,83) and HOMA-IR (1,84 ± 0,98) similar to those of the obese ones (SBP = 1,25 ± 20,4; DBP = 1,94 ± 1,1 and HOMA-IR = 2,09 ± 1,12), but higher than those of the classified as overweight (SBP= 0,49 ± 1,34, p<0,023; DBP= 1,45 ± 0,97, p<0,04 and HOMA-IR= 1,24 ± 0,67, p<0,04). Conclusions: the WHtR was so sensitive as the 2007 WHO BMI z score in diagnosing the cardiometabolic and inflammatory risk. The 2007 WHO reference was the most sensitive not only to screen obesity, but also the high blood pressure and insulin resistance, in 6-10-year-old children

Os objetivos do estudo foram correlacionar a razão entre a circunferência abdominal e altura (CA/A) e o índice de massa corpórea (IMC) com as variáveis cardiometabólicas e inflamatórias em escolares de seis a 10 anos; avaliar a frequência de sobrepeso/obesidade e alterações cardiometabólicas e comparar o desempenho dos referenciais de índice de massa corpórea (IMC) do Centers for Disease Control and Prevention 2000 (CDC) e Organização Mundial de Saúde 2007 (OMS) no diagnóstico de sobrepeso/obesidade e alterações cardiometabólicas. Métodos: estudo de corte transversal, que incluiu 175 crianças, provenientes do Centro de Referência para Tratamento da Criança e do Adolescente (CRTCA), em Campos, Rio de Janeiro. As crianças foram divididas segundo os escores z do CDC e OMS em: não obesas (z do IMC <1) e sobrepeso/obesidade (z do IMC > 1). As variáveis cardiometabólicas analisadas foram: pressão arterial sistólica (PAS) e diastólica (PAD), glicose, lipoproteínas de baixa e alta densidades (LDL e HDL, respectivamente), triglicerídeos (TG), HOMA-IR. Como variáveis inflamatórias, analisamos proteína C reativa ultra-sensível (PCR) e leucometria. Resultados: a média da CA/A do grupo sobrepeso/obesidade foi maior que a do não obeso (0,58 ± 0,007 e 0,45 ± 0,004, respectivamente, p< 0,0001). Houve correlação significativa da CA/A com os escores z do IMC (r = 0,88, p < 0,0001), PAS (r= 0,51, p<0,0001), PAD (r= 0,49, p<0,0001), HOMA-IR (r=0,83, p<0,0001), HDL (r = -0,28, p< 0,0002), TG (r= 0,26, p<0,0006), LDL (r= 0,25, p<0,0008) e PCR (r= 0,51, p<0,0001). Contudo, a CA/A não se correlacionou com glicemia nem leucócitos. A sensibilidade da CA/A se equivaleu à do IMC no diagnóstico das alterações cardiometabólicas. A sensibilidade mais elevada da CA/A foi para o diagnóstico de alteração da PAS (80,0 %), PAD (76,6%) e HOMA-IR (92,6%). O ponto de corte superior a 0,47 foi sensível para o diagnóstico de resistência insulínica, mas acima de 0,50, para os demais distúrbios cardiometabólicos. A frequência de sobrepeso/obesidade nos escolares foi igual a 49,7%. Com exceção de hipertrigliceridemia, todas as outras alterações cardiometabólicas foram mais frequentes no grupo sobrepeso/obesidade (aumento de PA, p<0,0001; glicemia de jejum alterada, p < 0,0048; aumento de LDL, p< 0,015 e redução do HDL, p<0,0001). O referencial da OMS 2007 reclassificou 11 crianças a mais como obesas que o CDC, que apresentaram médias de escores z de PAS (1,71 ± 1,54), PAD (2,64 ± 1,83) e HOMA-IR (1,84 ± 0,98) semelhantes às médias das obesas (PAS = 1,25 ± 2,04; PAD = 1,94 ± 1,19 e HOMA-IR = 2,09 ± 1,12), mas superiores às médias das classificadas como sobrepeso (PAS = 0,49 ± 1,34, p < 0,023; PAD = 1,45 ± 0,97, p < 0,04 e HOMA-IR = 1,24 ± 0,67, p < 0,04 ). Conclusões: a razão CA/A foi tão sensível quanto IMC da OMS 2007 no diagnóstico do risco cardiometabólico e inflamatório. O referencial da OMS 2007 foi o mais sensível não só para o rastreamento de sobrepeso/obesidade, como também para pressão arterial elevada e resistência insulínica, em escolares de seis a 10 anos / This study aims to correlate the waist-to-height ratio (WHtR) and the body mass index (BMI) with the cardiometabolic and inflammatory variables in 6-10 year-old school children; to evaluated the frequency of overweight/obesity and cardiometabolic disturbances, and to compare the 2000 Centers for Disease Control and Prevention (CDC) and 2007 World Health Organization (WHO) body mass index (BMI) references in the diagnosis of overweight/obesity and the cardiometabolic disturbances. Methods: a cross-sectional study which included 175 subjects, selected from the Reference Center for the Treatment of Children and Adolescents, in Campos, Rio de Janeiro. The subjects were classified according to the 2000 CDC and 2007 OMS BMI z scores as non obese (BMI < 1) and overweight/obese ones (BMI > 1). The analized cardiometabolic variables were systolic and diastolic blood pressure (SBP and DBP respectively), fasting glycemia, low and high density lipoproteins (LDL and HDL respectively), trigliceride (TG), homeostatic model assessment (HOMA-IR). As inflammatory markers we analized the ultra-sensitive Creactive protein (CRP) and the leucocyte count. Results: the WHtR mean of the overweight/obese group was higher than that of the non obese ones (0,58 ± 0,007 and 0,45 ± 0,004, respectively,p < 0,0001). There was correlation between the WHtR and BMI z score (r = 0,88, p < 0,0001), SBP (r = 0,51, p < 0,0001), DBP (r = 0,49, p < 0,0001), HOMA-IR (r = 0,83, p < 0,0001), HDL (r = -0,28, p < 0,0002, TG (r= 0,26, p < 0,0006), LDL (r = 0,25, p < 0,0008), and CRP (r = 0, 51, p < 0.0001). However, the WHtR was neither correlated with glycemia nor with the leucocyte count. The WHtR sensitivity was equivalent to that of the BMI in the diagnosis of all cardiometabolic variables. The highest WHtR sensitivity was to diagnose the SBP (80,0%), DBP (76,6%) and HOMA-IR (92,6%) alterations. The WHtR cut-off higher than 0,47 pointed out to insulin resistance diagnosis, but higher than 0,5, it did to the other metabolic disturbances. The frequency of overweight/obesity was 49,7% in these school children. Except for hypertriglyceridemia, all the remaining cardiometabolic disturbances were more frequent in the overweight/obese group. The 2007 WHO BMI reference reclassified 11 children more as obese than the 2000 CDC, who had means of SBP (1,71 ± 1,54) and DBP z scores (2,64 ± 1,83) and HOMA-IR (1,84 ± 0,98) similar to those of the obese ones (SBP = 1,25 ± 20,4; DBP = 1,94 ± 1,1 and HOMA-IR = 2,09 ± 1,12), but higher than those of the classified as overweight (SBP= 0,49 ± 1,34, p<0,023; DBP= 1,45 ± 0,97, p<0,04 and HOMA-IR= 1,24 ± 0,67, p<0,04). Conclusions: the WHtR was so sensitive as the 2007 WHO BMI z score in diagnosing the cardiometabolic and inflammatory risk. The 2007 WHO reference was the most sensitive not only to screen obesity, but also the high blood pressure and insulin resistance, in 6-10-year-old children

This project examines the role of immunization registries and their effect on a health care delivery system. Recent efforts to attain coverage of child populations by recommended vaccines have included initiatives by federal and state agencies, as well as private foundations, to develop and implement statewide community-based childhood immunization registries.

Black American women have the highest screening rates for cervical cancer among all the ethnic groups in the United States. Even though evidence from the literature suggests that the number of deaths from cervical cancer in the United States could be reduced by preventive screening, this particular minority population still suffers disproportionately higher mortality from the disease than the other minority and majority populations in the United States. This study was proposed to investigate cancer screening disparities among different subpopulations of women residing in the United States during 1999, and to recommend public health interventions that could potentially increase cervical cancer screening rates, thereby decreasing differential mortality rates for cervical cancer among these subpopulations. The Preventive Health Model in conjunction with data from the 1999 Behavioral Risk Factor Surveillance System was used to identify the covariates of cervical cancer screening behavior in an ethnically diverse population of American women residing in the United States during the specified timeframe. Univariate, bivariate and multivariable logistic regression procedures were used to evaluate the association between each one of the independent variables and the dependent variable (compliance with the 1999 cervical screening guidelines of the American Cancer Society). One of the major findings of this study was that Black, White and Hispanic American women were more similar in their screening behavior than dissimilar. The study also showed that the disparity in cervical cancer screening behavior in this population is in age, rather than in ethnic origin. Black, White and Hispanic American women of child-bearing age (18-44 years) were more likely to be compliant with the 1999 cervical cancer screening guidelines of the American Cancer Society, than Black, White and Hispanic American women who were not of child-bearing age (45 to 64 years). Implications for public health intervention studies are discussed, and recommendations made for future research in this area of cervical cancer screening behavior.

The global transmission of Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) has resulted in over 677 million infections and 6.88 million tragic deaths worldwide as of March 10th, 2023. During the pandemic, the ability to effectively combat SARS-CoV-2 had been hindered by the lack of rapid, reliable, and cost-effective testing platforms for readily screening patients, discerning incubation stages, and accounting for variants. The limited knowledge of the viral pathogenesis further hindered rapid diagnosis and long-term clinical management of this complex disease. While effective in the short term, measures such as social distancing and lockdowns have resulted in devastating economic loss, in addition to material and psychological hardships. Therefore, successfully reopening society during a pandemic depends on frequent, reliable testing, which can result in the timely isolation of highly infectious cases before they spread or become contagious. Viral loads, and consequently an individual's infectiousness, change throughout the progression of the illness. These dynamics necessitate frequent testing to identify when an infected individual can safely interact with non-infected individuals. Thus, scalable, accurate, and rapid serial testing is a cornerstone of an effective pandemic response, a prerequisite for safely reopening society, and invaluable for early containment of epidemics. Given the significant challenges posed by the pandemic, the power of artificial intelligence (AI) can be harnessed to create new diagnostic methods and be used in conjunction with serial tests. With increasing utilization of at-home lateral flow immunoassay (LFIA) tests, the National Institutes of Health (NIH) and Centers for Disease Control and Prevention (CDC) have consistently raised concerns about a potential underreporting of actual SARS-CoV-2-positive cases. When AI is paired with serial tests, it could instantly notify, automatically quantify, aid in real-time contact tracing, and assist in isolating infected individuals. Moreover, the computer vision-assisted methodology can help objectively diagnose conditions, especially in cases where subjective LFIA tests are employed. Recent advances in the interdisciplinary scientific fields of machine learning and biomedical engineering support a unique opportunity to design AI-based strategies for pandemic preparation and response. Deep learning algorithms are transforming the interpretation and analysis of image data when used in conjunction with biomedical imaging modalities such as MRI, Xray, CT scans, confocal microscopes, etc. These advances have enabled researchers to carry out real-time viral infection diagnostics that were previously thought to be impossible. The objective of this thesis is to use SARS-CoV-2 as a model virus and investigate the potential of applying multi-class instance segmentation deep learning and other machine learning strategies to build pandemic preparedness for rapid, in-depth, and longitudinal diagnostic platforms. This thesis encompasses three research tasks: 1) computer vision-assisted rapid serial testing, 2) infected cell phenotyping, and 3) diagnosing the long-term consequences of infection (i.e., long-term COVID). The objective of Task 1 is to leverage the power of AI, in conjunction with smartphones, to rapidly and simultaneously diagnose COVID-19 infections for millions of people across the globe. AI not only makes it possible for rapid and simultaneous screenings of millions but can also aid in the identification and contact tracing of individuals who may be carriers of the virus. The technology could be used, for example, in university settings to manage the entry of students into university buildings, ensuring that only students who test negative for the virus are allowed within campus premises, while students who test positive are placed in quarantine until they recover. The technology could also be used in settings where strict adherence to COVID-19 prevention protocols is compromised, for example, in an Emergency Room. This technology could also help with CDC’s concern on growing incidences of underreporting positive COVID-19 cases with growing utilization of at-home LFIA tests. AI can address issues that arise from relying solely on the visual interpretation of LFIA tests to make accurate diagnoses. One problem is that LFIA test results may be subjective or ambiguous, especially when the test line of the LFIA displays faint color, indicating a low analyte abundance. Therefore, reaching a decisive conclusion regarding the patient's diagnosis becomes challenging. Additionally, the inclusion of a secondary source for verifying the test results could potentially increase the test's cost, as it may require the purchase of complementary electronic gadgets. To address these issues, our innovation would be accurately calibrated with appropriate sensitivity markers, ensuring increased accuracy of the diagnostic test and rapid acquisition of test results from the simultaneous classification of millions of LFIA tests as either positive or negative. Furthermore, the designed network architecture can be utilized to detect other LFIA-based tests, such as early pregnancy detection, HIV LFIA detection, and LFIA-based detection of other viruses. Such minute advances in machine learning and artificial intelligence can be leveraged on many different scales and at various levels to revolutionize the health sector. The motivating purpose of Task 2 is to design a highly accurate instance segmentation network architecture not only for the analysis of SARS-CoV-2 infected cells but also one that yields the highest possible segmentation accuracy for all applications in biomedical sciences. For example, the designed network architecture can be utilized to analyze macrophages, stem cells, and other types of cells. Task 3 focuses on conducting studies that were previously considered computationally impossible. The invention will assist medical researchers and dentists in automatically calculating alveolar crest height (ACH) in teeth using over 500 dental Xrays. This will help determine if patients diagnosed with COVID-19 by a positive PCR test exhibited more alveolar bone loss and had greater bone loss in the two years preceding their COVID-positive test when compared to a control group without a positive COVID-19 test. The contraction of periodontal disease results in higher levels of transmembrane serine protease 2 (TMPRSS2) within the buccal cavity, which is instrumental in enabling the entry of SARS-CoV-2. Gum inflammation, a symptom of periodontal disease, can lead to alterations in the ACH of teeth within the oral mucosa. Through this innovation, we can calculate ACHs of various teeth and, therefore, determine the correlation between ACH and the risk of contracting SARS-CoV-2 infection. Without the invention, extensive manpower and time would be required to make such calculations and gather data for further research into the effects of SARS-CoV-2 infection, as well as other related biological phenomena within the human body. Furthermore, the novel network framework can be modified and used to calculate dental caries and other periodontal diseases of interest.