Current Medical Imaging - Volume 19, Issue 5, 2023

Hyperspectral Imaging (HSI) is a pertinent technique to provide meaningful information about unique objects in the medical field. This paper discusses the basic principles, imaging methods, comparisons, and advances in the medical applications of HSI to accentuate the importance of HSI in the medical field. To date, there are numerous tools and methods to fix the problems, but reliable medical HSI tools and methods need to be studied. The enactment and analytical competencies of HSI for medical imaging are discussed. Specifically, the recent successes and limitations of HSI in biomedical are presented to offer the readers an insight into its current potential for medical research. Lastly, we have discussed the future challenges concerning medical applications and possible ways to overcome these limitations.

Background: Radiological diagnosis of thoracic nerve diseases is difficult because they are rare, and nerves cannot be seen directly on radiological images. The major nerves of the thorax can be listed as the phrenic, vagus, recurrent laryngeal, long thoracic nerve pairs, sympathetic chains, costal nerves, and brachial plexus. Diseases of thoracic nerves have various causes, including traumatic injury, neuromuscular diseases, infection, compression, radiation, drugs, and tumors. Objective: This pictorial review aims to describe the anatomic locations of the major thoracic nerves on radiological images, comprehensively describe the causes of thoracic nerve diseases and define the clinical signs and primary and secondary imaging findings of dysfunction of the thoracic nerves. Methods: This paper was designed to illustrate primary and secondary imaging findings of nerve diseases. Firstly, the normal anatomy of nerves is shown with diagrams. Secondly, we explained primary and secondary imaging features with variable radiological methods, including chest X-Ray, magnetic resonance imaging, and computed tomography. Conclusion: Primary findings of nerve diseases can be detected if radiologists are familiar with the courses of the nerves on radiological images. Knowledge of the normal functions of the nerves can aid in diagnosing thoracic nerve diseases identified from secondary imaging findings such as diaphragmatic elevation, muscular atrophy, and winged scapula. It is essential to know the normal anatomy, function, and possible causes of thoracic nerve diseases to make a correct diagnosis and apply the prompt treatment.

Background: In 2019, a series of novel pneumonia cases later known as Coronavirus Disease 2019(COVID-19) were reported in Wuhan, China. Chest computed tomography (CT) has played a key role in the management and prognostication of COVID-19 patients. CT has demonstrated 98% sensitivity in detecting COVID-19, including identifying lung abnormalities that are suggestive of COVID-19, even among asymptomatic individuals. Methods: We conducted a comprehensive literature review of 17 published studies, focusing on three subgroups, pediatric patients, pregnant women, and patients over 60 years old, to identify key characteristics of chest CT in COVID-19 patients. Results: Our comprehensive review of the 17 studies concluded that the main CT imaging finding is ground glass opacities (GGOs) regardless of patient age. We also identified that crazy paving pattern, reverse halo sign, smooth or irregular septal thickening, and pleural thickening may serve as indicators of disease progression. Lesions on CT scans were dominantly distributed in the peripheral zone with multilobar involvement, specifically concentrated in the lower lobes. In the patients over 60 years old, the proportion of substantial lobe involvement was higher than the control group and crazy paving signs, bronchodilation, and pleural thickening were more commonly present. Conclusion: Based on all 17 studies, CT findings in COVID-19 have shown a predictable pattern of evolution over the disease. These studies have proven that CT may be an effective approach for early screening and detection of COVID-19.

The accurate assessment or diagnosis of breast cancer depends on image acquisition and image analysis and interpretation. The expert radiologist makes image interpretation, and this process has been greatly benefited by computer technology. For image acquisition, various imaging modalities have been developed and used over the years. This research examines several imaging modalities and their associated benefits and drawbacks. Commonly used parameters such as sensitivity and specificity are also offered to evaluate the usefulness of different imaging modalities. The main focus of the research is on mammograms. Despite the availability of breast cancer datasets of imaging modalities such as MRI, ultrasounds, and thermograms, mammogram datasets are used mainly by the domain researcher. They are considered an international gold standard for the early detection of breast cancer. We discussed and analyzed widely used and publicly available mammogram repositories. We further discussed some common key constraints related to mammogram datasets to develop the deep learningbased computer-aided diagnosis (CADx) systems for breast cancer. The ideas for their improvements have also been presented.

Background: Peripheral lymphedema represents a debilitating condition affecting the lymphatic system of the limbs resulting from impaired drainage and excessive lymphatic fluid accumulation in the interstitial spaces. Lymphoscintigraphy is the imaging modality of first choice to investigate patients with peripheral lymphedema. Nevertheless, in recent times, magnetic resonance imaging (MRI) techniques have also been applied to assess patients with lymphedema. Objective: The present systematic review aims to appraise the evidence by providing a head-to-head comparison between lymphoscintigraphy and MRI techniques in peripheral lymphedema. Methods: A systematic literature search was performed using the PubMed database and Cochrane Central Register of Controlled Trials (CENTRAL). The eligibility criteria for the articles to be included in the qualitative synthesis were: 1) a study cohort or a subset of patients with a clinical diagnosis of peripheral lymphedema (either upper or lower limb); 2) execution of both MR imaging and lymphoscintigraphy in the same subset of patients. The methodological quality of the studies was assessed by an investigator using the “Quality Assessment of Diagnostic Accuracy Studies” tool, v. 2 (QUADAS-2). Results: Overall, 11 studies were ultimately included in the quantitative analysis. No meta-analysis was performed due to the heterogeneous patient samples, the different study aims of the retrieved literature, and the limited number of available articles. In the diagnosis of upper limb extremity lymphedema, the sensitivity of MRI techniques appears superior to that of lymphoscintigraphy. Comparative studies in the lower limbs are still scarce but suggest that MRI may increase the diagnostic accuracy for lymphedema. Conclusion: The available literature on patients with lymphedema evaluated with both lymphoscintigraphy and MRI does not allow definite conclusions on the superiority of one imaging technique over the other. Further studies, including well-selected patient samples, are still necessary to compare the accuracy of these imaging modalities. Since MRI techniques seem to provide complementary findings to lymphoscintigraphy, it would be conceivable to acquire both imaging exams in patients with peripheral lymphedema. Furthermore, studies evaluating the clinical impact of adding MRl to the diagnostic workup are warranted.

Background: The Non-Small Cell Variant of Lung Cancer (NSCLC) has a poorer prognosis. It is typically diagnosed through non-invasive imaging. Of particular note has been FDGPET/ CT, which has been investigated across various settings with differing results. Objective: This study is to pool the available information on the diagnostic performance of 18-F FDG PET/CT for detecting NSCLC recurrence. Methods: A systematic literature search was conducted across electronic databases for studies published before May 2021. The QUADAS tool was applied to assess study quality, and a metaanalysis was performed to retrieve pooled estimates. Chi-squared tests and I2 statistics were used to assess heterogeneity. Egger’s test and funnel plots were used to assess publication bias. Results: The literature search yielded 20 studies featuring data on 1,973 patients. The majority of the studies had a low bias risk. The pooled sensitivity and specificity were 96% (95% CI: 91%- 98%) and 93% (95% CI: 89%-95%), respectively. The LRP and LRN estimates were in the left upper quadrant of the LR scattergram, indicating that F18-FDG PET/CT can be utilized for both confirmation and exclusion. The AUC was 0.98 (95% CI: 0.92-0.99). Fagan’s nomogram showed that F18-FDG PET/CT had good clinical utility for recurrent NSCLC diagnosis. There was considerable between-study variability (p=0.02). The funnel plot was asymmetrical, indicating the possibility of publication bias. Conclusion: This meta-analysis found FDG-PET/CT to be highly accurate for identifying NSCLC recurrence. However, more studies assessing this modality across different patient situations are required to strengthen the argument for changing international guidelines and practices.

Background: Chest High-Resolution Computed Tomography (HRCT) is mandatory for patients with confirmed Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) infection and a high Respiratory Rate (RR) because sublobar consolidation is the likely pathological pattern in addition to Ground Glass Opacities (GGOs). Objective: The present study determined the correlation between the percentage extent of typical pulmonary lesions on HRCT, as a representation of severity, and the RR and peripheral oxygen saturation level (SpO2), as measured through pulse oximetry, in patients with Reverse Transcriptase Polymerase Chain Reaction (RT-PCR)-confirmed primary (noncomplicated) SARS-CoV-2 pneumonia. Methods: The present retrospective study was conducted in 332 adult patients who presented with dyspnea and hypoxemia and were admitted to Prince Mohammed bin Abdulaziz Hospital, Riyadh, Saudi Arabia between May 15, 2020 and December 15, 2020. All the patients underwent chest HRCT. Of the total, 198 patients with primary noncomplicated SARS-CoV-2 pneumonia were finally selected based on the typical chest HRCT patterns. The main CT patterns, GGO and sublobar consolidation, were individually quantified as a percentage of the total pulmonary involvement through algebraic summation of the percentage of the 19 pulmonary segments affected. Additionally, the statistical correlation strength between the total percentage pulmonary involvement and the age, initial RR, and percentage SpO2 of the patients was determined. Results: The mean ± Standard Deviation (SD) age of the 198 patients was 48.9 ± 11.4 years. GGO magnitude alone exhibited a significant weak positive correlation with patients’ age (r = 0.2; p = 0.04). Sublobar consolidation extent exhibited a relatively stronger positive correlation with RR than GGO magnitude (r = 0.23; p = 0.002). A relatively stronger negative correlation was observed between the GGO extent and SpO2 (r = - 0.38; p = 0.002) than that between sublobar consolidation and SpO2 (r = - 0.2; p = 0.04). An increase in the correlation strength was demonstrated with increased case segregation with GGO extent (r = - 0.34; p = 0.01). Conclusion: The correlation between the magnitudes of typical pulmonary lesion patterns, particularly GGO, which exhibited an incremental correlation pattern on chest HRCT, and the SpO2 percentage, may allow the establishment of an artificial intelligence program to differentiate primary SARS-CoV-2 pneumonia from other complications and associated pathology influencing SpO2.

Background: Several diagnostic methods were proposed and evaluated for the COVID-19 disease. However, published studies have reported different diagnostic values for these methods. Aims: The present study aimed to evaluate the diagnostic performance and accuracy of CT in the novel coronavirus disease (COVID-19) and developed and presented a Corona CT severity index. Methods: In this retrospective study, CT diagnostic performance was measured based on sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and diagnostic accuracy, and RT-PCR was regarded as a standard. Patients’ CT reports were evaluated by a radiologist, and scoring and calculating of the CT severity index were performed. Results: Of 208 patients, 82 showed positive, and 126 showed negative RT-PCR results with a positive frequency of 39.4% (95% CI, 32.7-46.4). The chest CT scan related to 136 patients indicated COVID- 19, whereas the initial RT-PCR assays of 56 patients were negative. Considering RT-PCR results as the reference standard, the sensitivity, specificity, and accuracy of chest CT to indicate COVID-19 infection were 100%, 55.6% (95% CI 46.4-64.4%), and 72.8% (95% CI 66.2-78.8%), respectively. The severity of pulmonary involvement was assigned with different grades. For 60.7% of patients with severity grades of 2 to 6, who showed the involvement of at least one lung lobe in CT, PCR retrieved negative results. Conclusion: CT scan shows an acceptable sensitivity as well as a consistently better specificity to identify COVID-19 pneumonia than PCR. It may be considered a major method to identify COVID-19 in epidemic locations.

Background: Hydronephrosis is a common condition, and the correct diagnosis of hydronephrosis is necessary to improve the early diagnosis rates of pediatric hydronephrosis. Objective: The objective of this study is to explore and analyze the diagnostic value of dynamic contrast- enhanced magnetic resonance imaging (DCE-MRI) analyzed using the Tofts model in children with unilateral hydronephrosis. Methods: We retrospectively selected data from 88 children with unilateral hydronephrosis treated in our hospital from September 2018 to October 2020. Routine and DCE-MR renal image indexes were collected and their pharmacokinetic variables were calculated based on the Tofts model to compare kinetic parameters of affected and normal kidney. We compared the renal parenchymal thickness and other renal function indexes in children with different degrees of hydronephrosis, and drew receiver operating characteristic (ROC) curves to evaluate the diagnostic value of this approach in children with hydronephrosis. Results: The K^trans, Kep, and Ve values in the diseased kidneys were lower than those in the normal ones (P<0.05). The thickness of the healthy renal parenchyma in children with severe hydronephrosis was higher than in children with moderate and mild hydronephrosis, but the renal parenchyma thickness and the thickness ratio of renal parenchyma on the affected side were lower than those in children with moderate and mild hydronephrosis (P<0.05). Sensitivity, specificity and accuracy of DCE-MRI and Tofts model in the diagnosis of hydronephrosis in children were higher than those of a single DCE-MRI (P<0.05). The area under the ROC curve for the DCE-MRI and Tofts model approach for the diagnosis of hydronephrosis in children was 0.789 (95% CI, 0.72-0.859), and the sensitivity and specificity were 86.36% and 71.59%, respectively. Conclusion: DCE-MRI and Tofts model can provide a clear picture of renal morphology, and renal function evaluation parameters. They have high sensitivity and specificity in the diagnosis of hydronephrosis in children.

Background: The whole world has been severely affected due to the COVID-19 pandemic. The rapid and large-scale spread has caused immense pressure on the medical sector hence increasing the chances of false detection due to human errors and mishandling of reports. At the time of outbreaks of COVID-19, there is a crucial shortage of test kits as well. Quick diagnostic testing has become one of the main challenges. For the detection of COVID-19, many Artificial Intelligence based methodologies have been proposed, a few had suggested integration of the model on a public usable platform, but none had executed this on a working application as per our knowledge. Objective: Keeping the above comprehension in mind, the objective is to provide an easy-to-use platform for COVID-19 identification. This work would be a contribution to the digitization of health facilities. This work is a fusion of deep learning classifiers and medical images to provide a speedy and accurate identification of the COVID-19 virus by analyzing the user's CT scan images of the lungs. It will assist healthcare workers in reducing their workload and decreasing the possibility of false detection. Methods: In this work, various models like Resnet50V2 and Resnet101V2, an adjusted rendition of ResNet101V2 with Feature Pyramid Network, have been applied for classifying the CT scan images into the categories: normal or COVID-19 positive. Results: A detailed analysis of all three models' performances have been done on the SARS-CoV-2 dataset with various metrics like precision, recall, F1-score, ROC curve, etc. It was found that Resnet50V2 achieves an accuracy of 96.79%, whereas Resnet101V2 achieves an accuracy of 97.79%. An accuracy of 98.19% has been obtained by ResNet101V2 with Feature Pyramid Network. As Res- Net101V2 with Feature Pyramid Network is showing better results, thus, it is further incorporated into a working application that takes CT images as input from the user and feeds into the trained model and detects the presence of COVID-19 infection. Conclusion: A mobile application integrated with the deeper variant of ResNet, i.e., ResNet101V2 with FPN checks the presence of COVID-19 in a faster and accurate manner. People can use this application on their smart mobile devices. This automated system would assist healthcare workers as well, which ultimately reduces their workload and decreases the possibility of false detection.

Purpose: To reduce breast tumor size before surgery, Neoadjuvant Chemotherapy (NAC) is applied systematically to patients with local breast cancer. However, with the existing clinical protocols, it is not yet possible to have an early prediction of the effect of chemotherapy on a breast tumor. Predicting the response to chemotherapy could reduce toxicity and delay effective treatment. Computational analysis of Dynamic Contrast-Enhanced Magnetic Resonance Images (DCE-MRI) through Deep Convolution Neural Network (CNN) has proved a significant performance in classifying responders and no responder’s patients. This study intends to present a new explainable Deep Learning (DL) model predicting the breast cancer response to chemotherapy based on multiple MRI inputs. Material and Methods: In this study, a cohort of 42 breast cancer patients who underwent chemotherapy was used to train and validate the proposed DL model. This dataset was provided by the Jules Bordet institute of radiology in Brussels, Belgium. 14 external subjects were used to validate the DL model to classify responding or non-responding patients on temporal DCE-MRI volumes. The model performance was assessed by the Area Under the receiver operating characteristic Curve (AUC), accuracy, and features map visualization according to pathological complete response (Ground truth). Results: The developed deep learning architecture was able to predict the responding breast tumors to chemotherapy treatment in the external validation dataset with an AUC of 0.93 using parallel learning MRI images acquired at different moments. The visual results showed that the most important extracted features from non-responding tumors are in the peripheral and external tumor regions. The model proposed in this study is more efficient compared to those proposed in the literature. Conclusion: Even with a limited training dataset size, the developed multi-input CNN model using DCE-MR images acquired before and following the first chemotherapy was able to predict responding and non-responding tumors with higher accuracy. Thanks to the visualization of the extracted characteristics by the DL model on the responding and non-responding tumors, the latter could be used henceforth in clinical analysis after its evaluation based on more extra data.