Current Medical Imaging - Volume 19, Issue 13, 2023

Background: Cancer is a deadly disease. It is crucial to diagnose cancer in its early stages. This can be done with medical imaging. Medical imaging helps us scan and view internal organs. The analysis of these images is a very important task in the identification and classification of cancer. Over the past years, the occurrence of cancer has been increasing, so has been the load on the medical fraternity. Fortunately, with the growth of Artificial Intelligence in the past decade, many tools and techniques have emerged which may help doctors in the analysis of medical images. Methodology: This is a systematic study covering various tools and techniques used for medical image analysis in the field of cancer detection. It focuses on machine learning and deep learning technologies, their performances, and their shortcomings. Also, the various types of imaging techniques and the different datasets used have been discussed extensively. This work also discusses the various preprocessing techniques that have been performed on medical images for better classification. Results: A total of 270 studies from 5 different publications and 5 different conferences have been included and compared on the above-cited parameters. Conclusion: Recommendations for future work have been given towards the end.

Background: As a new high-resolution three-dimensional CT imaging technology, the essential reference range of CT values in Cone-beam breast computed tomography (CBBCT) has not been established to date. Purpose: To determine the reference range of computed tomography (CT) values in CBBCT for clinical breast examination. Materials and Methods: In total, 913 cases (1167 lateral) were subject to CBBCT. CT values of the glandular tissue, fat and different quadrants and different distances of CBBCT images were analyzed. The nipple and muscle were also evaluated. Results: A total of 672 lateral breasts were included in the normal group for investigation. The reference range of the absolute CT value of the chest wall muscle is -136.68~43.36 HU. The reference range of the absolute CT value of the nipple is 176.39~334.02 HU. The reference range of the absolute CT value of fat is -190.4~-63.67HU, and of glandular tissue is -12.2~199.07HU. Conclusion: Our results firstly established the baseline CT values of Non-contrast CBBCT in female breasts, which will benefit cancer screening and lesion locating. The closer the normal breast fat and glandular tissue is to the nipple, the greater the CT value. The older the age, the lower the density. The CT values of fat are unstable in a distance of less than 5 cm, and the CT values of glandular tissues are relatively stable. The difference between the upper and lower quadrants is significant in the same lateral breast and the same section.

Background: Developing a reliable predictive tool of disease severity in COVID-19 infection is important to help triage patients and ensure the appropriate utilization of health-care resources. Objective: To develop, validate, and compare three CT scoring systems (CTSS) to predict severe disease on initial diagnosis of COVID-19 infection. Methods: One hundred and twenty and 80 symptomatic adults with confirmed COVID-19 infection who presented to emergency department were evaluated retrospectively in the primary and validation groups, respectively. All patients had non-contrast CT chest within 48 hours of admission. Three lobarbased CTSS were assessed and compared. The simple lobar system was based on the extent of pulmonary infiltration. Attenuation corrected lobar system (ACL) assigned further weighting factor based on attenuation of pulmonary infiltrates. Attenuation and volume-corrected lobar system incorporated further weighting factor based on proportional lobar volume. The total CT severity score (TSS) was calculated by adding individual lobar scores. The disease severity assessment was based on Chinese National Health Commission guidelines. Disease severity discrimination was assessed by the area under the receiver operating characteristic curve (AUC). Results: The ACL CTSS demonstrated the best predictive and consistent accuracy of disease severity with an AUC of 0.93(95%CI:0.88-0.97) in the primary cohort and 0.97 (95%CI:0.91.5-1) in the validation group. Applying a TSS cut-off value of 9.25, the sensitivities were 96.4% and 100% and the specificities were 75% and 91% in the primary and validation groups, respectively. Conclusion: The ACL CTSS showed the highest accuracy and consistency in predicting severe disease on initial diagnosis of COVID-19. This scoring system may provide frontline physicians with a triage tool to guide admission, discharge, and early detection of severe illness.

Objectives: To differentiate the primary small-cell lung cancer (SCLC) and non-small-cell lung cancer (NSCLC) for patients with brain metastases (BMs) based on a deep learning (DL) model using contrast-enhanced magnetic resonance imaging (MRI) T1 weighted (T1CE) images. Methods: Out of 711 patients with BMs of lung cancer origin (SCLC 232, NSCLC 479), the MRI datasets of 192 patients (lesions’ widths and heights > 30 pixels) with BMs from lung cancer (73 SCLC and 119 NSCLC) confirmed pathologically were enrolled, retrospectively. A typical convolutional neural network ResNet18 was applied for the automatic classification of BMs lesions from lung cancer based on T1CE images, with training and testing groups randomized per patient to eliminate learning bias. A 5-fold cross-validation was performed to evaluate the classification of the model. The receiver operating characteristic (ROC) curve, accuracy, precision, recall and f1 score were calculated. Results: For a 5-fold cross-validation test, the DL model achieved AUCs of 0.8019 and 0.8024 for SCLC and NSCLC patients with BMs, respectively, and a mean overall accuracy of 0.7515±0.04. The DL model performed well in differentiating the primary SCLC and NSCLC with BMs. Conclusion: The proposed DL model is feasible and effective in differentiating the pathological subtypes of SCLC and NSCLC causing BMs, which may be used as a new tool for oncologists to diagnose noninvasively BMs and guide therapy based on the imaging structure of tumors.

Background: During X-ray computed tomography (CT) scans, the metal implants in the patient's body will produce severe artifacts, which reduce the image quality and interferes with the doctor's judgment. Therefore, it is necessary to develop an algorithm for removing metal artifacts in CT images and reconstructing high-quality images. Objective: In this article, we proposed a generative adversarial networks (GANs)-based metal artifact reduction algorithm for the image domain, Res-U-Net GANs. This method can effectively suppress noise and remove metal artifacts in CT images. Methods: Our new approach includes a generator and a discriminator. The generator contains several residual blocks, a U-Net structure and skip connections. And a weighted joint loss function is also used for training. These structures can reduce metal artifacts in images, improve image quality, and restore implant details. Results: We use SSIM, PSNR and RMSE to evaluate the performance of the proposed method. The mean SSIM, PSNR and RMSE of the testing set images are 0.977, 39.044 and 0.011, respectively. And the trained model which is compiled and encapsulated, also show excellent performance in processing clinical data sets, which can remove metal artifacts in clinical CT images. Conclusion: We consider that the proposed algorithm can remove metal artifacts in CT images and restore image details, which is very helpful for radiologists.

Background: The assessment of collaterals before endovascular thrombectomy (EVT) therapy play a pivotal role in clinical decision-making for acute stroke patients. Objective: To investigate the correlation between hypoperfusion intensity ratio (HIR), collaterals on digital subtraction angiography (DSA), and infarct growth in acute stroke patients who underwent EVT therapy. Methods: Patients with acute ischemic stroke (AIS) who underwent EVT therapy were enrolled retrospectively. HIR was assessed through magnetic resonance imaging (MRI) and was defined as the Tmax > 10 s lesion volume divided by the Tmax > 6 s lesion volume. Collaterals were assessed on DSA using the American Society of Interventional and Therapeutic Neuroradiology/Society of Interventional Radiology (ASITN/SIR) scale. Good collaterals were defined as ASITN/SIR score 3–4 and poor collaterals were defined as ASITN/SIR score 0–2. Spearman’s rank correlation analysis was used to evaluate the correlation between HIR, collaterals, infarct growth, and functional outcome. Results: A total of 115 patients were included. Patients with good collateral (n = 59) had smaller HIR (0.29 ± 0.07 vs. 0.52 ± 0.14; t = 10.769, P < 0.001) and infarct growth (8.47 ± 2.40 vs. 14.37 ± 5.28; t = 7.652, P < 0.001) than those with poor collateral (n = 56). Discussion: The ROC analyses showed that the optimal cut-off value of HIR was 0.40, and the sensitivity and specificity for predicting good collateral were 85.70% and 96.61%, respectively. With the optimal cut-off value, patients with HIR < 0.4 (n = 67) had smaller infarct growth (8.86 ± 2.59 vs. 14.81 ± 5.52; t = 6.944, P < 0.001) than those with HIR ≥ 0.4 (n = 48). Spearman’s rank correlation analysis showed that HIR had a correlation with ASITN/SIR score (r = -0.761, P < 0.001), infarct growth (r = 0.567, P < 0.001), and mRS at 3 months (r = -0.627, P < 0.001). Conclusion: HIR < 0.4 is significantly correlated with good collateral status and small infarct growth. Evaluating HIR before treatment may be useful for guiding EVT and predicting the functional outcome of AIS patients.

Background: Breast cancer (BC) is one of the most severe diseases in women. Therefore, a premature diagnosis is necessary for timely detection and treatment execution. Clinical-level diagnosis of BC is normally performed with imaging techniques, and Ultrasound-Imaging (UI) is one of the noninvasive imaging techniques frequently executed to diagnose BC. Aims: This research aims to develop an efficient deep-learning framework to detect BC from UI with better accuracy. Methods: The executed method consists of the following stages: (i) Data collection and preprocessing, (ii) Deep-features mining with pre-trained VGG16, (iii) Image enhancement using Discrete Wavelet Transform (DWT) and Local Binary Pattern (LBP), (iv) Firefly-algorithm (FA) supported feature reduction, and (v) Feature integration and classification. Results: The proposed work is tested and executed using 1680 test images (840 benign and 840 malignant) of dimension pixels and implements a binary classifier with 5-fold cross-validation to separate the UI database into the healthy/cancer class. Conclusion: This work implemented FA-supported feature reduction. Moreover, it was found that this scheme helps to achieve a classification accuracy of 98.21% with the KNN classifier.

Background: Infrared thermal imaging technology was used to observe the changes in infrared radiation temperature at acupoints in rats caused by chronic myocardial ischemia injury. Objective: This study aims to compare the difference of body surface infrared radiation temperature information of three groups of acupoints: bilateral Neiguan (PC6), bilateral Yanglingquan (GB33), and bilateral Sham Acupoints (SA) in the pathological state of myocardial ischemia injury, and to explore the relationship between acupoints and viscera state. Methods: SPF adult Wistar male rats (n = 20) were randomly divided into a control (CTL; n = 10) and an isoproterenol group (ISO; n = 10). Chronic myocardial injury was induced in rats by subcutaneous injection of isoproterenol hydrochloride for 14 d. On the second day after the establishment of the model, the serum levels of cardiac troponin (cTnI) and creatine kinase isoenzyme (CK-MB) were measured by enzyme-linked immunosorbent assay (ELISA). The morphological changes of the myocardial tissue in the two groups were observed by hematoxylin-eosin (HE) staining and their pathological scores were evaluated, which was then used to determine the myocardial ischemic injury. Two days before and after the establishment of the model, the electrocardiograms (ECG) of the two groups of rats were recorded by the (ECG) data acquisition system, and the infrared thermal imaging platform was used to detect the temperature of the six acupoints. Results: 1. After subcutaneous injection of isoproterenol hydrochloride for 14 days, the ST segment of the ECG decreased in the ISO group compared with that of the CTL group; 2. Myocardial tissue injury was serious in the ISO group compared to the CTL group; 3. Serum cTn-I and CK-MB were significantly increased (P <0 01) in the ISO group, compared to that in the CTL group; 4. The infrared radiation temperature on the body surface of bilateral Neiguan (PC6) acupoints decreased significantly in the ISO group, compared to that of the CTL group. Conclusion: Infrared thermal imaging technology can be used to detect the changes in the energy state of acupoints. Chronic myocardial ischemic injury can cause a decrease in IR temperature on the body surface of bilateral Neiguan (PC6) acupoints, suggesting that visceral diseases can lead to changes in the energy metabolism of acupoints.

Introduction: Traumatic spinal root injury caused by shoulder dislocation may involve the brachial plexus or, in some cases, a single nerve. The degree of severity of the injury depends on many patient-specific factors as well as the mechanism of injury. It is essential to suspect this type of lesion by means of a thorough physical examination in order to have better patient outcomes. Case Presentation: We presented the subtle magnetic resonance imaging (MRI) findings in a 35-yearold male with left shoulder trauma and dislocation after falling off a bicycle. He complained of decreased muscle strength and sensitivity in the C8 dermatome. Atrophy of the hypothenar region and flexion deformity of the 4^th and ^5th digits were noted. Magnetic resonance imaging findings were consistent with a partial preganglionic C8 motor root lesion. We found T2 increased signal intensity and thinning of the intradural segment of the C8 motor nerve root and low signal in the sequence of a multi- echo gradient recalled echo (GRE). Conclusion: MRI is a noninvasive tool that allows a detailed anatomical characterization of the nerves. In brachial plexus injuries, the use of the GRE sequence is useful to identify the lesions, even if they are subtle; however, some lesions may go unnoticed. It is important to note that these patients require an interdisciplinary group to reach a correct diagnosis, which is vital to establish the appropriate treatment and follow-up.

Background: Aberrant origin of the distal anterior cerebral artery (ACA) arising from the middle cerebral artery (MCA) is extremely rare. Case Presentation: A 74-year-old woman with a sudden onset of left-sided weakness was admitted to the emergency department. Angiography revealed an unusual course of the distal ACA originating from the MCA with bilateral obstruction of the proximal segment of the ACA and simultaneous occurrence of infarction in the ACA and MCA territories. Conclusion: Knowledge of a rare vascular variation or anomaly could help understand brain imaging, which has an unusual involvement of vascular territories, performed in patients with acute ischemic stroke.

Background: Sarcoidosis is a systemic non-caseous necrotizing granulomatous disease with unknown etiology. It can involve multiple organs throughout the body, most commonly affecting lungs and/or bilateral hilar lymph nodes. Sjögren's syndrome is a multi-system autoimmune disease. The main clinical symptoms include dry mouth and dry eyes. The combination of the two diseases with the involvement of multiple systems is very rare, and the final diagnosis is mainly based on the comprehensive judgment of clinical history, imaging manifestations and pathological examination. Case Presentation: We report a case of multiple sarcoidosis (lung, hilar, mediastinal, inguinal, liver, and spleen) with Sjögren syndrome. The patient had a dry mouth, dry eyes, and bilateral parotid gland enlargement. The first computed tomography (CT) scan of the chest and abdomen showed multiple nodules in the lungs, multiple enlarged lymph nodes, and low-density shadows in the liver and spleen. After a one-year interval, the re-examination showed that the lung lesions increased with bead-like changes, and the lymph nodes shrunk. Through pathological puncture and comprehensive judgment, considering the coexistence of the two diseases, the patient improved after hormone therapy and was finally diagnosed. Conclusion: Multisystem sarcoidosis combined with Sjögren's syndrome has rarely been reported in the literature. This case has multiple imaging examinations, pathological data and a follow-up review after treatment. The dynamic changes in different periods will help us to better understand the situation of sarcoidosis and explore the connection between the two diseases so as to reduce misdiagnosis.

Introduction: Retroperitoneal localization is an extremely rare presentation of interdigitating dendritic cell sarcoma (IDCS), the primary neoplasm of the antigen-presenting interdigitating dendritic cells. Case Presentation: We report an incidentally found isolated retroperitoneal IDCS in a 59-year-old female patient with no prior symptoms. The patient was initially misdiagnosed since the tissue samples obtained by tru-cut biopsies were diffusely positive for S-100, and the radiological features were similar to neurogenic tumors. However, additional immunohistochemical staining in the excisional biopsy specimen revealed IDCS as the correct diagnosis. Conclusion: The correct diagnosis may not always be achieved with tru-cut biopsy evaluations in the retroperitoneal masses. Immunophenotyping and radiological features can occasionally be perplexing. In these cases, an accurate diagnosis can be achieved by excisional biopsy and additional immunohistochemical staining.