Infantile Cardiac Hemangioma: A Rare Case Presentation.

Cardiac hemangiomas are rare tumors of the heart which account for less than one-twentieth of all primary cardiac tumors. They can be seen in all age groups but are mostly diagnosed in neonates and children. Although cardiac hemangiomas are benign in nature they can present with features of congestive heart failure and occasionally be life-threatening. We present such a case in a two-month-old child who underwent successful surgical excision of the mass.

COVLIAS 3.0: cloud-based quantized hybrid UNet3+ deep learning for COVID-19 lesion detection in lung computed tomography.

Background and novelty: When RT-PCR is ineffective in early diagnosis and understanding of COVID-19 severity, Computed Tomography (CT) scans are needed for COVID diagnosis, especially in patients having high ground-glass opacities, consolidations, and crazy paving. Radiologists find the manual method for lesion detection in CT very challenging and tedious. Previously solo deep learning (SDL) was tried but they had low to moderate-level performance. This study presents two new cloud-based quantized deep learning UNet3+ hybrid (HDL) models, which incorporated full-scale skip connections to enhance and improve the detections. Methodology: Annotations from expert radiologists were used to train one SDL (UNet3+), and two HDL models, namely, VGG-UNet3+ and ResNet-UNet3+. For accuracy, 5-fold cross-validation protocols, training on 3,500 CT scans, and testing on unseen 500 CT scans were adopted in the cloud framework. Two kinds of loss functions were used: Dice Similarity (DS) and binary cross-entropy (BCE). Performance was evaluated using (i) Area error, (ii) DS, (iii) Jaccard Index, (iii) Bland-Altman, and (iv) Correlation plots. Results: Among the two HDL models, ResNet-UNet3+ was superior to UNet3+ by 17 and 10% for Dice and BCE loss. The models were further compressed using quantization showing a percentage size reduction of 66.76, 36.64, and 46.23%, respectively, for UNet3+, VGG-UNet3+, and ResNet-UNet3+. Its stability and reliability were proved by statistical tests such as the Mann-Whitney, Paired t-Test, Wilcoxon test, and Friedman test all of which had a p < 0.001. Conclusion: Full-scale skip connections of UNet3+ with VGG and ResNet in HDL framework proved the hypothesis showing powerful results improving the detection accuracy of COVID-19.

Imaging and MR Spectroscopy in Papillary Craniopharyngioma.

Sellar-suprasellar masses exhibit a diverse range of differential diagnoses and it is feasible to establish a preliminary diagnosis before surgery by evaluating conventional CT scans and contrast-enhanced MRI results. Nevertheless, certain cases may present with inconclusive findings, making it challenging to anticipate the underlying tissue composition accurately through imaging alone. Researchers have explored the application of Proton MR spectroscopy in analyzing suprasellar tumors, and their investigations have revealed that it can complement traditional MRI by enhancing the accuracy of preoperative diagnoses. In this context, we report three biopsy-proven cases of suprasellar papillary craniopharyngioma where the MRS spectra derived from the solid component exhibited noticeable lipid peaks alongside reduced levels of choline and NAA. These findings played a pivotal role in facilitating the correct preoperative identification of papillary craniopharyngioma.

Coexistence of neural tube defects and spinal arteriovenous shunts: a case series and review of literature.

BACKGROUND: Spinal arteriovenous shunts and spinal dysraphism both have a different underlying cause, disease spectrum and developmental process; hence, these entities rarely coexist in a patient. Here, we reported four cases of coexistence of adult-onset spinal arteriovenous shunt and spinal dysraphism in the same patient along with their therapeutic embolisation. Additionally, we conducted an extensive literature review to explore the potential theories and explanations for this coexistence. METHODS: We retrospectively searched our imaging database from January 2015 to December 2023 to identify instances of spinal arteriovenous shunts occurring in patients with spinal dysraphism or neural tube defect disorders. MRI and angiographic imaging, clinical presentation, treatment and follow-up were analysed. RESULTS: Four patients with arteriovenous fistula/shunt and spinal dysraphism were included in the study. The mean age of presentation was 35.5 years. The most common symptoms were sensory disturbance and motor weakness. Arteriovenous fistula or shunt was located at the lumber region in one patient and at the sacral region in three cases. Two patients have a prior history of surgery in first decade. Two patients were treated with glue embolisation. The internal iliac artery was a common feeder in all cases. CONCLUSIONS: The rare coexistence of neural tube defects with spinal vascular abnormalities should be considered when assessing a middle-aged patient with neural tube defect and myelopathy. Correct diagnosis can help in treatment planning and thereby improve prognosis.

Duplication of right vertebral artery in Klippel-Feil anomaly.

The duplicated origin of the vertebral artery (VA) is an uncommon anatomical variant, which is generally identified incidentally during angiography and can be misdiagnosed as dissection in the setting of posterior circulation stroke. Here, we describe a case of the right V1 VA duplication with embryological aspects in a patient with Klippel-Feil anomaly, which was diagnosed during preoperative evaluation. Surgeons must be aware to avoid vascular injury from a duplicated VA before head-neck and spinal surgery.

Preoperative Super-Selective Embolization versus "On-Clamp" Laparoscopic Partial Nephrectomy for T1 Renal Tumors- A Prospective Randomized Study.

To analyze and compare the intraoperative and post-operative outcomes of "on-clamp" laparoscopic partial nephrectomy (LPN) with "preoperative super-selective angioembolization" before LPN. This randomized clinical study was conducted at Gauhati Medical College Hospital, Guwahati, India, between November 2021 and November 2023. Adult patients of either gender diagnosed with T1 renal tumors were included in the study. All patients underwent diethylenetriamine pentaacetate scan preoperatively and at 1-month follow-up. The patients were randomized using a parallel group design with an allocation ratio of 1:1 to receive either preoperative angioembolization followed by LPN or conventional "on-clamp" LPN. Demographic and baseline parameters were recorded along with pre- and post-operative data. There was no significant difference between the two groups in terms of age (P = 0.11), gender distribution (P = 0.32), body mass index (P = 0.43), preoperative hemoglobin (P = 0.34), and preoperative estimated glomerular filtration rate (eGFR; P = 0.64). One patient in the embolization group required radical nephrectomy because of accidental backflow of glue into the renal artery during embolization whereas four patients required clamping due to inadequate embolization. Preoperative super-selective embolization yielded significantly less blood loss, compared to "on-clamp" LPN (145 [50.76 mL] vs. 261 [66.12 mL], P < 0.01). There was no significant difference between post-operative eGFR (at 1 month) between the two groups (P = 0.71). Preoperative embolization offers improved outcomes in the dissection plane, total operative time, and blood loss, compared to conventional "on-clamp" LPN but has no significant effect on change in eGFR.

In vitro inflammation and toxicity assessment of pre- and post-incinerated organomodified nanoclays to macrophages using high-throughput screening approaches.

BACKGROUND: Organomodified nanoclays (ONC), two-dimensional montmorillonite with organic coatings, are increasingly used to improve nanocomposite properties. However, little is known about pulmonary health risks along the nanoclay life cycle even with increased evidence of airborne particulate exposures in occupational environments. Recently, oropharyngeal aspiration exposure to pre- and post-incinerated ONC in mice caused low grade, persistent lung inflammation with a pro-fibrotic signaling response with unknown mode(s) of action. We hypothesized that the organic coating presence and incineration status of nanoclays determine the inflammatory cytokine secretary profile and cytotoxic response of macrophages. To test this hypothesis differentiated human macrophages (THP-1) were acutely exposed (0-20 µg/cm2) to pristine, uncoated nanoclay (CloisNa), an ONC (Clois30B), their incinerated byproducts (I-CloisNa and I-Clois30B), and crystalline silica (CS) followed by cytotoxicity and inflammatory endpoints. Macrophages were co-exposed to lipopolysaccharide (LPS) or LPS-free medium to assess the role of priming the NF-κB pathway in macrophage response to nanoclay treatment. Data were compared to inflammatory responses in male C57Bl/6J mice following 30 and 300 µg/mouse aspiration exposure to the same particles. RESULTS: In LPS-free media, CloisNa exposure caused mitochondrial depolarization while Clois30B exposure caused reduced macrophage viability, greater cytotoxicity, and significant damage-associated molecular patterns (IL-1α and ATP) release compared to CloisNa and unexposed controls. LPS priming with low CloisNa doses caused elevated cathepsin B/Caspage-1/IL-1ß release while higher doses resulted in apoptosis. Clois30B exposure caused dose-dependent THP-1 cell pyroptosis evidenced by Cathepsin B and IL-1ß release and Gasdermin D cleavage. Incineration ablated the cytotoxic and inflammatory effects of Clois30B while I-CloisNa still retained some mild inflammatory potential. Comparative analyses suggested that in vitro macrophage cell viability, inflammasome endpoints, and pro-inflammatory cytokine profiles significantly correlated to mouse bronchioalveolar lavage inflammation metrics including inflammatory cell recruitment. CONCLUSIONS: Presence of organic coating and incineration status influenced inflammatory and cytotoxic responses following exposure to human macrophages. Clois30B, with a quaternary ammonium tallow coating, induced a robust cell membrane damage and pyroptosis effect which was eliminated after incineration. Conversely, incinerated nanoclay exposure primarily caused elevated inflammatory cytokine release from THP-1 cells. Collectively, pre-incinerated nanoclay displayed interaction with macrophage membrane components (molecular initiating event), increased pro-inflammatory mediators, and increased inflammatory cell recruitment (two key events) in the lung fibrosis adverse outcome pathway.

The role of susceptibility-weighted imaging & contrast-enhanced MRI in the diagnosis of primary CNS vasculitis: a large case series.

Primary CNS Vasculitis (PCNSV) is a rare, diverse, and polymorphic CNS blood vessel inflammatory condition. Due to its rarity, clinical variability, heterogeneous imaging results, and lack of definitive laboratory markers, PCNSV diagnosis is challenging. This retrospective cohort analysis identified patients with histological diagnosis of PCNSV. Demographic data, clinical presentation, neuroimaging studies, and histopathologic findings were recorded. We enrolled 56 patients with a positive biopsy of CNS vasculitis. Most patients had cerebral hemisphere or brainstem symptoms. Most brain MRI lesions were bilateral, diffuse discrete to confluent white matter lesions. Frontal lobe lesions predominated, followed by inferior cerebellar lesions. Susceptibility-weighted imaging (SWI) hemorrhages in 96.4% (54/56) of patients, either solitary microhemorrhages or a combination of micro and macrohemorrhages. Contrast-enhanced T1-WIs revealed parenchymal enhancement in 96.3% (52/54 patients). The most prevalent pattern of enhancement observed was dot-linear (87%), followed by nodular (61.1%), perivascular (25.9%), and patchy (16.7%). Venulitis was found in 19 of 20 individuals in cerebral DSA. Hemorrhages in SWI and dot-linear enhancement pattern should be incorporated as MINOR diagnostic criteria to diagnose PCNSV accurately within an appropriate clinical context. Microhemorrhages in SWI and venulitis in DSA, should be regarded as a potential marker for PCNSV.

Cardiovascular disease/stroke risk stratification in deep learning framework: a review.

The global mortality rate is known to be the highest due to cardiovascular disease (CVD). Thus, preventive, and early CVD risk identification in a non-invasive manner is vital as healthcare cost is increasing day by day. Conventional methods for risk prediction of CVD lack robustness due to the non-linear relationship between risk factors and cardiovascular events in multi-ethnic cohorts. Few recently proposed machine learning-based risk stratification reviews without deep learning (DL) integration. The proposed study focuses on CVD risk stratification by the use of techniques mainly solo deep learning (SDL) and hybrid deep learning (HDL). Using a PRISMA model, 286 DL-based CVD studies were selected and analyzed. The databases included were Science Direct, IEEE Xplore, PubMed, and Google Scholar. This review is focused on different SDL and HDL architectures, their characteristics, applications, scientific and clinical validation, along with plaque tissue characterization for CVD/stroke risk stratification. Since signal processing methods are also crucial, the study further briefly presented Electrocardiogram (ECG)-based solutions. Finally, the study presented the risk due to bias in AI systems. The risk of bias tools used were (I) ranking method (RBS), (II) region-based map (RBM), (III) radial bias area (RBA), (IV) prediction model risk of bias assessment tool (PROBAST), and (V) risk of bias in non-randomized studies-of interventions (ROBINS-I). The surrogate carotid ultrasound image was mostly used in the UNet-based DL framework for arterial wall segmentation. Ground truth (GT) selection is vital for reducing the risk of bias (RoB) for CVD risk stratification. It was observed that the convolutional neural network (CNN) algorithms were widely used since the feature extraction process was automated. The ensemble-based DL techniques for risk stratification in CVD are likely to supersede the SDL and HDL paradigms. Due to the reliability, high accuracy, and faster execution on dedicated hardware, these DL methods for CVD risk assessment are powerful and promising. The risk of bias in DL methods can be best reduced by considering multicentre data collection and clinical evaluation.

Ensemble Deep Learning Derived from Transfer Learning for Classification of COVID-19 Patients on Hybrid Deep-Learning-Based Lung Segmentation: A Data Augmentation and Balancing Framework.

BACKGROUND AND MOTIVATION: Lung computed tomography (CT) techniques are high-resolution and are well adopted in the intensive care unit (ICU) for COVID-19 disease control classification. Most artificial intelligence (AI) systems do not undergo generalization and are typically overfitted. Such trained AI systems are not practical for clinical settings and therefore do not give accurate results when executed on unseen data sets. We hypothesize that ensemble deep learning (EDL) is superior to deep transfer learning (TL) in both non-augmented and augmented frameworks. METHODOLOGY: The system consists of a cascade of quality control, ResNet-UNet-based hybrid deep learning for lung segmentation, and seven models using TL-based classification followed by five types of EDL's. To prove our hypothesis, five different kinds of data combinations (DC) were designed using a combination of two multicenter cohorts-Croatia (80 COVID) and Italy (72 COVID and 30 controls)-leading to 12,000 CT slices. As part of generalization, the system was tested on unseen data and statistically tested for reliability/stability. RESULTS: Using the K5 (80:20) cross-validation protocol on the balanced and augmented dataset, the five DC datasets improved TL mean accuracy by 3.32%, 6.56%, 12.96%, 47.1%, and 2.78%, respectively. The five EDL systems showed improvements in accuracy of 2.12%, 5.78%, 6.72%, 32.05%, and 2.40%, thus validating our hypothesis. All statistical tests proved positive for reliability and stability. CONCLUSION: EDL showed superior performance to TL systems for both (a) unbalanced and unaugmented and (b) balanced and augmented datasets for both (i) seen and (ii) unseen paradigms, validating both our hypotheses.

Primary CNS vasculitis (PCNSV): a cohort study.

Primary CNS Vasculitis (PCNSV) is a rare inflammatory disorder affecting the blood vessels of the central nervous system. Patients present with a combination of headaches, seizures, and focal neurological deficits. There is usually a diagnostic delay. Treatment is based on observational studies and expert opinion. Our objective was to identify clinical, laboratory, neuroimaging, pathologic or management-related associations with 2 year outcome in patients with primary CNS vasculitis. We conducted a cohort study at a single tertiary care referral centre of prospectively (2018-2019) and retrospectively (2010-2018) identified individuals with primary CNS vasculitis (diagnosis was proven by either brain biopsy or cerebral digital subtraction angiography). Clinical, imaging and histopathologic findings, treatment, and functional outcomes were recorded. Univariate and stepwise multiple logistic regression were applied. P-value<0.05 was considered statistically significant. The main outcome measures were documentation of clinical improvement or worsening (defined by mRS scores) and identification of independent predictors of good functional outcome (mRS 0-2) at 2 years. We enrolled eighty-two biopsy and/or angiographically proven PCNSV cases. The median age at presentation was 34 years with a male predilection and a median diagnostic delay of 23 months. Most patients presented with seizures (70.7%). All patients had haemorrhages on MRI. Histologically lymphocytic subtype was the commonest. Corticosteroids with cyclophosphamide was the commonest medication used. The median mRS at follow-up of 2 years was 2 (0-3), and 65.2% of patients achieved a good functional outcome. Myelitis and longer duration of illness before diagnosis were associated with poorer outcomes. The presence of hemorrhages on SWI sequence of MRI might be a sensitive imaging marker. Treatment with steroids and another immunosuppressant probably reduced relapse rates in our cohort. We have described the third largest PCNSV cohort and multi-centre randomised controlled trials are required to study the relative efficacy of various immunosuppressants.Study registration: CTRI/2018/03/012721.

Multicenter Study on COVID-19 Lung Computed Tomography Segmentation with varying Glass Ground Opacities using Unseen Deep Learning Artificial Intelligence Paradigms: COVLIAS 1.0 Validation.

Variations in COVID-19 lesions such as glass ground opacities (GGO), consolidations, and crazy paving can compromise the ability of solo-deep learning (SDL) or hybrid-deep learning (HDL) artificial intelligence (AI) models in predicting automated COVID-19 lung segmentation in Computed Tomography (CT) from unseen data leading to poor clinical manifestations. As the first study of its kind, "COVLIAS 1.0-Unseen" proves two hypotheses, (i) contrast adjustment is vital for AI, and (ii) HDL is superior to SDL. In a multicenter study, 10,000 CT slices were collected from 72 Italian (ITA) patients with low-GGO, and 80 Croatian (CRO) patients with high-GGO. Hounsfield Units (HU) were automatically adjusted to train the AI models and predict from test data, leading to four combinations-two Unseen sets: (i) train-CRO:test-ITA, (ii) train-ITA:test-CRO, and two Seen sets: (iii) train-CRO:test-CRO, (iv) train-ITA:test-ITA. COVILAS used three SDL models: PSPNet, SegNet, UNet and six HDL models: VGG-PSPNet, VGG-SegNet, VGG-UNet, ResNet-PSPNet, ResNet-SegNet, and ResNet-UNet. Two trained, blinded senior radiologists conducted ground truth annotations. Five types of performance metrics were used to validate COVLIAS 1.0-Unseen which was further benchmarked against MedSeg, an open-source web-based system. After HU adjustment for DS and JI, HDL (Unseen AI) > SDL (Unseen AI) by 4% and 5%, respectively. For CC, HDL (Unseen AI) > SDL (Unseen AI) by 6%. The COVLIAS-MedSeg difference was < 5%, meeting regulatory guidelines.Unseen AI was successfully demonstrated using automated HU adjustment. HDL was found to be superior to SDL.

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans.

Background: The previous COVID-19 lung diagnosis system lacks both scientific validation and the role of explainable artificial intelligence (AI) for understanding lesion localization. This study presents a cloud-based explainable AI, the "COVLIAS 2.0-cXAI" system using four kinds of class activation maps (CAM) models. Methodology: Our cohort consisted of ~6000 CT slices from two sources (Croatia, 80 COVID-19 patients and Italy, 15 control patients). COVLIAS 2.0-cXAI design consisted of three stages: (i) automated lung segmentation using hybrid deep learning ResNet-UNet model by automatic adjustment of Hounsfield units, hyperparameter optimization, and parallel and distributed training, (ii) classification using three kinds of DenseNet (DN) models (DN-121, DN-169, DN-201), and (iii) validation using four kinds of CAM visualization techniques: gradient-weighted class activation mapping (Grad-CAM), Grad-CAM++, score-weighted CAM (Score-CAM), and FasterScore-CAM. The COVLIAS 2.0-cXAI was validated by three trained senior radiologists for its stability and reliability. The Friedman test was also performed on the scores of the three radiologists. Results: The ResNet-UNet segmentation model resulted in dice similarity of 0.96, Jaccard index of 0.93, a correlation coefficient of 0.99, with a figure-of-merit of 95.99%, while the classifier accuracies for the three DN nets (DN-121, DN-169, and DN-201) were 98%, 98%, and 99% with a loss of ~0.003, ~0.0025, and ~0.002 using 50 epochs, respectively. The mean AUC for all three DN models was 0.99 (p < 0.0001). The COVLIAS 2.0-cXAI showed 80% scans for mean alignment index (MAI) between heatmaps and gold standard, a score of four out of five, establishing the system for clinical settings. Conclusions: The COVLIAS 2.0-cXAI successfully showed a cloud-based explainable AI system for lesion localization in lung CT scans.

Eight pruning deep learning models for low storage and high-speed COVID-19 computed tomography lung segmentation and heatmap-based lesion localization: A multicenter study using COVLIAS 2.0.

BACKGROUND: COVLIAS 1.0: an automated lung segmentation was designed for COVID-19 diagnosis. It has issues related to storage space and speed. This study shows that COVLIAS 2.0 uses pruned AI (PAI) networks for improving both storage and speed, wiliest high performance on lung segmentation and lesion localization. METHOD: ology: The proposed study uses multicenter ∼9,000 CT slices from two different nations, namely, CroMed from Croatia (80 patients, experimental data), and NovMed from Italy (72 patients, validation data). We hypothesize that by using pruning and evolutionary optimization algorithms, the size of the AI models can be reduced significantly, ensuring optimal performance. Eight different pruning techniques (i) differential evolution (DE), (ii) genetic algorithm (GA), (iii) particle swarm optimization algorithm (PSO), and (iv) whale optimization algorithm (WO) in two deep learning frameworks (i) Fully connected network (FCN) and (ii) SegNet were designed. COVLIAS 2.0 was validated using "Unseen NovMed" and benchmarked against MedSeg. Statistical tests for stability and reliability were also conducted. RESULTS: Pruning algorithms (i) FCN-DE, (ii) FCN-GA, (iii) FCN-PSO, and (iv) FCN-WO showed improvement in storage by 92.4%, 95.3%, 98.7%, and 99.8% respectively when compared against solo FCN, and (v) SegNet-DE, (vi) SegNet-GA, (vii) SegNet-PSO, and (viii) SegNet-WO showed improvement by 97.1%, 97.9%, 98.8%, and 99.2% respectively when compared against solo SegNet. AUC > 0.94 (p < 0.0001) on CroMed and > 0.86 (p < 0.0001) on NovMed data set for all eight EA model. PAI <0.25 s per image. DenseNet-121-based Grad-CAM heatmaps showed validation on glass ground opacity lesions. CONCLUSIONS: Eight PAI networks that were successfully validated are five times faster, storage efficient, and could be used in clinical settings.

COVLIAS 1.0Lesion vs. MedSeg: An Artificial Intelligence Framework for Automated Lesion Segmentation in COVID-19 Lung Computed Tomography Scans.

Background: COVID-19 is a disease with multiple variants, and is quickly spreading throughout the world. It is crucial to identify patients who are suspected of having COVID-19 early, because the vaccine is not readily available in certain parts of the world. Methodology: Lung computed tomography (CT) imaging can be used to diagnose COVID-19 as an alternative to the RT-PCR test in some cases. The occurrence of ground-glass opacities in the lung region is a characteristic of COVID-19 in chest CT scans, and these are daunting to locate and segment manually. The proposed study consists of a combination of solo deep learning (DL) and hybrid DL (HDL) models to tackle the lesion location and segmentation more quickly. One DL and four HDL models­namely, PSPNet, VGG-SegNet, ResNet-SegNet, VGG-UNet, and ResNet-UNet­were trained by an expert radiologist. The training scheme adopted a fivefold cross-validation strategy on a cohort of 3000 images selected from a set of 40 COVID-19-positive individuals. Results: The proposed variability study uses tracings from two trained radiologists as part of the validation. Five artificial intelligence (AI) models were benchmarked against MedSeg. The best AI model, ResNet-UNet, was superior to MedSeg by 9% and 15% for Dice and Jaccard, respectively, when compared against MD 1, and by 4% and 8%, respectively, when compared against MD 2. Statistical tests­namely, the Mann−Whitney test, paired t-test, and Wilcoxon test­demonstrated its stability and reliability, with p < 0.0001. The online system for each slice was <1 s. Conclusions: The AI models reliably located and segmented COVID-19 lesions in CT scans. The COVLIAS 1.0Lesion lesion locator passed the intervariability test.

COVLIAS 1.0 vs. MedSeg: Artificial Intelligence-Based Comparative Study for Automated COVID-19 Computed Tomography Lung Segmentation in Italian and Croatian Cohorts.

(1) Background: COVID-19 computed tomography (CT) lung segmentation is critical for COVID lung severity diagnosis. Earlier proposed approaches during 2020-2021 were semiautomated or automated but not accurate, user-friendly, and industry-standard benchmarked. The proposed study compared the COVID Lung Image Analysis System, COVLIAS 1.0 (GBTI, Inc., and AtheroPointTM, Roseville, CA, USA, referred to as COVLIAS), against MedSeg, a web-based Artificial Intelligence (AI) segmentation tool, where COVLIAS uses hybrid deep learning (HDL) models for CT lung segmentation. (2) Materials and Methods: The proposed study used 5000 ITALIAN COVID-19 positive CT lung images collected from 72 patients (experimental data) that confirmed the reverse transcription-polymerase chain reaction (RT-PCR) test. Two hybrid AI models from the COVLIAS system, namely, VGG-SegNet (HDL 1) and ResNet-SegNet (HDL 2), were used to segment the CT lungs. As part of the results, we compared both COVLIAS and MedSeg against two manual delineations (MD 1 and MD 2) using (i) Bland-Altman plots, (ii) Correlation coefficient (CC) plots, (iii) Receiver operating characteristic curve, and (iv) Figure of Merit and (v) visual overlays. A cohort of 500 CROATIA COVID-19 positive CT lung images (validation data) was used. A previously trained COVLIAS model was directly applied to the validation data (as part of Unseen-AI) to segment the CT lungs and compare them against MedSeg. (3) Result: For the experimental data, the four CCs between COVLIAS (HDL 1) vs. MD 1, COVLIAS (HDL 1) vs. MD 2, COVLIAS (HDL 2) vs. MD 1, and COVLIAS (HDL 2) vs. MD 2 were 0.96, 0.96, 0.96, and 0.96, respectively. The mean value of the COVLIAS system for the above four readings was 0.96. CC between MedSeg vs. MD 1 and MedSeg vs. MD 2 was 0.98 and 0.98, respectively. Both had a mean value of 0.98. On the validation data, the CC between COVLIAS (HDL 1) vs. MedSeg and COVLIAS (HDL 2) vs. MedSeg was 0.98 and 0.99, respectively. For the experimental data, the difference between the mean values for COVLIAS and MedSeg showed a difference of <2.5%, meeting the standard of equivalence. The average running times for COVLIAS and MedSeg on a single lung CT slice were ~4 s and ~10 s, respectively. (4) Conclusions: The performances of COVLIAS and MedSeg were similar. However, COVLIAS showed improved computing time over MedSeg.

Inter-Variability Study of COVLIAS 1.0: Hybrid Deep Learning Models for COVID-19 Lung Segmentation in Computed Tomography.

Background: For COVID-19 lung severity, segmentation of lungs on computed tomography (CT) is the first crucial step. Current deep learning (DL)-based Artificial Intelligence (AI) models have a bias in the training stage of segmentation because only one set of ground truth (GT) annotations are evaluated. We propose a robust and stable inter-variability analysis of CT lung segmentation in COVID-19 to avoid the effect of bias. Methodology: The proposed inter-variability study consists of two GT tracers for lung segmentation on chest CT. Three AI models, PSP Net, VGG-SegNet, and ResNet-SegNet, were trained using GT annotations. We hypothesized that if AI models are trained on the GT tracings from multiple experience levels, and if the AI performance on the test data between these AI models is within the 5% range, one can consider such an AI model robust and unbiased. The K5 protocol (training to testing: 80%:20%) was adapted. Ten kinds of metrics were used for performance evaluation. Results: The database consisted of 5000 CT chest images from 72 COVID-19-infected patients. By computing the coefficient of correlations (CC) between the output of the two AI models trained corresponding to the two GT tracers, computing their differences in their CC, and repeating the process for all three AI-models, we show the differences as 0%, 0.51%, and 2.04% (all < 5%), thereby validating the hypothesis. The performance was comparable; however, it had the following order: ResNet-SegNet > PSP Net > VGG-SegNet. Conclusions: The AI models were clinically robust and stable during the inter-variability analysis on the CT lung segmentation on COVID-19 patients.