Current Medical Imaging - Volume 18, Issue 9, 2022

Background: The task of identifying a tumor in the brain is a complex problem that requires sophisticated skills and inference mechanisms to accurately locate the tumor region. The complex nature of the brain tissue makes the problem of locating, segmenting, and ultimately classifying Magnetic Resonance (MR) images a complex problem. The aim of this review paper is to consolidate the details of the most relevant and recent approaches proposed in this domain for the binary and multi-class classification of brain tumors using brain MR images. Objective: In this review paper, a detailed summary of the latest techniques used for brain MR image feature extraction and classification is presented. A lot of research papers have been published recently with various techniques proposed for identifying an efficient method for the correct recognition and diagnosis of brain MR images. The review paper allows researchers in the field to familiarize themselves with the latest developments and be able to propose novel techniques that have not yet been explored in this research domain. In addition, the review paper will facilitate researchers who are new to machine learning algorithms for brain tumor recognition to understand the basics of the field and pave the way for them to be able to contribute to this vital field of medical research. Results: In this paper, the review is performed for all recently proposed methods for both feature extraction and classification. It also identifies the combination of feature extraction methods and classification methods that, when combined, would be the most efficient technique for the recognition and diagnosis of brain tumor from MR images. In addition, the paper presents the performance metrics, particularly the recognition accuracy, of selected research published between 2017-2021.

Background: Physical inspection is a simple way to diagnose oral cancer. Most cases of oral cancer, on the contrary, are diagnosed late, resulting in needless mortality and morbidity. While highrisk screening populations appears to be helpful, these people are often found in areas with minimal access to health care. In this paper, we have reviewed several aspects related to oral cancer, such as its cause, the risk factors associated with it, India's oral cancer situation at the moment, various screening methods, and the ability of artificial intelligence in the detection and classification purpose. Oral cancer results can be enhanced by combining imaging and artificial intelligence approaches for better detection and diagnosis. Objective: This paper aims to cover the various oral cancer screening detection techniques that use Artificial Intelligence (AI). Methods: In this paper, we have covered the imaging methods that are used in screening oral cancer and, after that, the potential of AI for the detection of oral cancer. Conclusion: This paper covers some of the main concepts regarding oral cancer and various AI methods used to detect it.

Background: The quantitative susceptibility mapping (QSM) technique can be used to quantitatively evaluate the cerebral iron deposition of the deep gray matter structure (DGM) in clinical practice. However, it could be significantly important to assess the reproducibility of the susceptibility values at different magnetic resonance (MR) scanners before the QSM technique can be widely used in clinical applications. Objective: This study aimed to assess the reproducibility of susceptibility value of the deep gray matter structure (DGM) at two different MR systems with the same magnetic strength. Methods: Raw data of 21 normal subjects (M/F = 7/14, median age 29 (21, 63) years) were acquired from a 3D multi-echo enhanced gradient recalled echo sequence at two different 3.0T MR systems, and STI software was used to reconstruct the magnetic susceptibility images. Brain structural images were used to be coregistered with magnitude images to generate normalized parameters and normalized susceptibility images. Voxel-based intraclass correlation coefficient (VB-ICC) was used to evaluate the reproducibility of susceptibility value of DGM at different 3.0T MR systems. Results: DGM with ICC > 0.75 is located in the bilateral posterior putamen and globus pallidus, bilateral red nuclei, and left dental nucleus. DGM with 0.6 < ICC < 0.75 is mainly located in the bilateral anterior putamen and globus pallidus, the margin of the bilateral red nuclei, right dental nucleus, and the margin of the left dental nucleus. DGM with 0.4 < ICC < 0.6 is located in anterior parts of the bilateral putamen, bilateral globus pallidus and substantia nigra, the margin of the bilateral dental nuclei, and the inferior part of the right dental nucleus. Conclusion: DGM presented regional dependent reproducibility of susceptibility value at two different 3.0T MR systems based on VB-ICC analysis.

Objective: This study investigates the association of the liver and spleen signal intensity on MRI with anemia in patients with gynecologic cancer. Methods: 332 patients with gynecological cancer and 78 healthy women underwent MRI examination. Liver and spleen MRI parameters and laboratory tests were obtained within 1 week. The signal intensity ratios of liver and spleen to the paraspinal muscle were calculated on gradient-echo T1-weighted images (T1WI) and T2-weighted images (T2WI) in both patients and healthy women, respectively. Results: The ratios of liver and spleen to paraspinal muscle on T1WI and T2WI were lower in patients than in the healthy women, respectively (P<0.0001). The ratios of the liver and spleen to paraspinal muscle on T1WI and T2WI decreased with the increasing stage of anemia and decreasing hemoglobin levels (P<0.001). The ratios of the liver to paraspinal muscle on T1WI, spleen to paraspinal muscle on T1WI, and the liver and spleen to paraspinal muscle on T2WI could predict anemia stage≥1 (AUC=0.576, 0.643, 0.688, and 0.756, respectively), ≥2 (AUC=0.743, 0.714, 0.891, and 0.922, respectively) and 3 (AUC=0.851, 0.822, 0.854, and 0.949, respectively). Conclusion: T2WI-based spleen signal intensity ratios showed the highest potential for non-invasive evaluation of anemia in gynecological cancer.

Background: This paper presents an improved radar-based imaging system for breast cancer detection that features p-slot ultrawideband antennae in a 32-array set-up. The improved reconstruction algorithm incorporates the phase coherence factor (PCF) into the conventional delay and sum (DAS) beamforming algorithm, thus effectively suppressing noise arising from the side- and gratinglobe interferences. Methods: The system is tested by using several breast models fabricated from chemical mixtures formulated on the basis of realistic human tissues. Each model is placed in a hemispherical breast radome that was fabricated from polylactide material and surrounded by 32 p-slot antennae mounted in four concentric layers. These antennae are connected to an 8.5 GHz vector network analyser through two 16-channel multiplexers that automatically switch different combinations of transmitter and receiver pairs in a sequential manner. Results: The system can accurately detect 5 mm tumours in a complex and homogeneously dense 3D breast model with an average signal-to-clutter ratio and full-width half-maximum of 7.0 dB and 2.3 mm, respectively. These values are more competitive than the values of other beamforming algorithms, even with contrasts as low as 1:2. Conclusion: The proposed PCF-weighted DAS is the best-performing algorithm amongst the tested beamforming techniques. This research paves the way for a clinical trial involving human subjects. Our laboratory is planning such a trial as part of future work.

Purpose: We evaluated brain iron content in a healthy pediatric population using quantitative susceptibility mapping (QSM). Methods: From June 2018 to December 2019, healthy subjects aged 2-18 years old (200 males, 200 females) with no anatomical abnormalities were assessed. All of the children underwent 3D T1 anatomical MRIs in addition to the sequence scans of enhanced T2 star-weighted angiography (ESWAN). The ESWAN sequence images were obtained with software to attain quantitative susceptibility mapping of the entire brain. The magnetic susceptibility values in the same brain region were compared across different age groups. The magnetic susceptibility values expressed in the same age group were compared across sexes, brain sides, and brain regions. Results: The magnetic susceptibility value of each brain region increased with age, and the magnetic susceptibility value expressed by each brain region demonstrated a positive correlation with the children’s age (r=0.63, P<0.05). No dramatic difference in magnetic susceptibility was observed between the brain’s left side and right side in the children within the age range ≥2-<6; however, among the children within the age range ≥6-<18, the magnetic susceptibility values expressed by the left putamen nucleus, globus pallidus, and substantia nigra were higher than those expressed by the same regions on the right side (P<0.05). Conclusion: Quantitative susceptibility mapping can be used to evaluate the content of iron in each brain region of normal children.

Aim: We aimed to investigate the magnetic resonance imaging (MRI) features of benign, atypical, or malignant papillary breast lesions and to assess the additional value of diffusion-weighted imaging (DWI) and turbo inversion recovery magnitude (TIRM) sequences to routine breast MRI. Background: Differentiation between benign and malignant papillary breast lesions is essential for patient management. However, morphologic features and enhancement patterns of malignant papillary lesions may overlap with those of benign papilloma. Methods: Seventy-two papillary breast lesions (50 benign, 22 atypical or malignant) were included in the current study, retrospectively. We divided the patients into two groups: benign papillary breast lesions and atypical or malignant papillary breast lesions. Morphologic, dynamic, turbo inversion recovery magnitude (TIRM) values and diffusion features of the papillary lesions were compared between two groups. Results: Benign papillary lesions were smaller in size (p=0.006 and p=0.005, for radiologists 1 and 2 respectively), closer to the areola (p=0.045 and 0.049 for radiologist 1 and 2 respectively), and had higher ADC values (p=0.001 for two radiologists) than the atypical or malignant group. ROC curves showed diagnostic accuracy for ADC (AUC=0.770 and 0.762, p & amp; lt; 0.0001 for two radiologists), and showed a cut-off value of ≤ 957 x 10-6 mm^2/s (radiologist 1) and ≤ 910 x 10-6 mm^2/s (radiologist 2). Conclusion: MRI is a useful method for differentiation between benign and malignant papillary breast lesions. Centrally located, lesser in size, and higher ADC values should be considered benign, whereas peripherally located, larger in size, and lower ADC values should be considered malignant.

Background: Triple negative breast cancers are considered the worst prognosis in breast cancer. Dynamic contrast enhanced magnetic resonance imaging has been widely used in the diagnosis of breast cancer since it is more sensitive to breast cancer. However, few studies report the MRI characteristics of triple negative breast cancers. Objective: The study aimed to evaluate the imaging finding in triple negative breast cancers compared with non-TNBC and attempt to predict it. Methods: 223 patients with a preoperative diagnosis of breast cancer were enrolled in the study. Dynamic contrast enhanced magnetic resonance imaging was performed before being diagnosed with breast cancer, and histopathological assessment was confirmed after biopsy or operation. The patients were divided into 2 groups based on immunohistochemistry, namely the triple negative breast cancers or non-triple negative breast cancers. Results: The 2 groups demonstrated significant differences regarding the tumor size, margin, outline, burr sign, enhancement, inverted nipple(P<0.05). A multivariate logistic regression analysis was performed to further validate the association of these features, however, only margin [odds ratio (OR), 0.038; 95% confidence interval (CI), 0.014-0.100; <0.001], outline [odds ratio (OR), 0.039; 95% confidence interval (CI), 0.008-0.200; <0.001], burr sign [odds ratio (OR), 2.786; 95% confidence interval (CI), 1.225-6.333; 0.014], and enhancement [odds ratio (OR), 0.131; 95% confidence interval (CI), 0.037-0.457; P=0.001] were associated with TNBC. Conclusion: The results indicated that the specific dynamic contrast enhanced magnetic resonance imaging features can predict pathological results, with a consequent prognostic value.

Background: Anatomical imaging methods and histological examinations have limited clinical value for early monitoring of brain function damage after cardiac arrest (CA) in vivo. Objective: We aimed to assess the cerebral protective effects of hydrogen in rabbits with CA by using fluorodeoxyglucose-positron emission tomography/computed tomography (FDG-PET/CT). Methods: Male rabbits were divided into the hydrogen-treated (n=6), control (n=6), and sham (n=3) groups. Maximum standardized uptake values (SUVmax) were measured by FDG-PET/CT at baseline and post-resuscitation. Blood Ubiquitin C-terminal hydrolase-L1 (UCH-L1) and neuron-specific enolase (NSE) were measured before and after the operation. After surgical euthanasia, brain tissues were extracted for Nissl staining. Results: SUVmax values first decreased at 2 and 24 h after resuscitation before rising in the hydrogentreated and control groups. SUVmax values in the frontal, occipital, and left temporal lobes and in the whole brain were significantly different between the hydrogen and control groups at 2 and 24 h postresuscitation (P<0.05). The neurological deficit scores at 24 and 48 h were lower in the hydrogentreated group (P<0.05). At 24 h, the serum UCH-L1 and NSE levels were increased in the hydrogen and control groups (P<0.05), but not in the sham group. At 48 and 72 h post-CA, the plasma UCH-L1 and NSE levels in the hydrogen and control groups gradually decreased. Neuronal damage was smaller in the hydrogen group compared to the control group at 72 h. Conclusion: FDG-PET/CT could be used to monitor early cerebral damage, indicating a novel method for evaluating the protective effects of hydrogen on the brain after CA.

Background: BI-RADS classification facilitates the information related to diagnosis for radiologists. It allows radiologists to interpret mammograms accurately. Objective: We aimed to compare the diagnostic accuracy of the three modalities, USG, MG and MRI, with the BI-RADS classification system according to their imaging findings. Methods: This study included 82 patients who underwent Tru-Cut biopsy under the guidance of USG, MG, and MRI. Mammography, sonography and MRI were performed in the prone position. Results: Of the patients, 46.3%, 14.6%, and 39.0% were assessed in 4A, 4B, and 5 MRI BI-RADS categories, respectively. Based on the variable surgical/pathological diagnosis, 50%, 28.0%, and 22.0% of the patients were categorized as having malignant findings, benign findings, and infectioninflammation- mastitis, respectively. The determination of the endpoints for the parameter of long-axis diameter (mm) was found to be statistically significant according to ROC analysis as a gold standard based on specificity levels of benign and malignant findings (p<0.05). A significant correlation was detected between the gold standard and the categorical variable MRI BI-RADS (χ²=46.380, p<0.01). Conclusion: When the specificity and sensitivity of all three modalities in surgical/pathological diagnosis were compared, MRI was concluded to be superior to the other modalities and a valuable method for the prediction of lesion malignancy and determination of biopsy prediction and priority.

Introduction: Benign metastasizing leiomyoma (BML) is a rare disease and mostly affects females with a history of uterine leiomyoma, and particularly the presence of multiple leiomyomas in BML patients is extremely rare. Case Presentation: This paper reported the clinical and imaging data of a BML patient with multiple leiomyomas involving bilateral pulmonary, mediastinum, pericardium, spine, peritoneum, and left thigh. Multiple BML lesions exhibited consistent imaging examinations, significantly improving the delayed phase enhancement. After multi-stage targeted therapy for multiple systemic metastases and the development of drug resistance, the patient was treated with hysterectomy and bilateral adnexectomy along with letrozole-based endocrine therapy. BML lesions, both pulmonary and mediastinum, became significantly smaller than before. Conclusion: This paper aims to analyze the imaging and clinical features of multiple leiomyomas in this BML case, thus strengthening the understanding of the rare type of leiomyoma for effective preoperative diagnosis and clinical treatment. Furthermore, it is noteworthy that gynecologists should avoid the manifestation of BML when performing uterine fibroids surgery.

Background: The ectopic pancreas is an anatomically separate pancreatic tissue from normal glands with its own vascular and ductal system; it is most commonly found in the upper gastrointestinal tract. The ectopic pancreas is usually asymptomatic, but it can present with symptoms associated with complications, including bleeding, inflammation, and neoplasm without abnormalities in the normal pancreas. Case Presentation: We report a 31-year-old female with acute ectopic pancreatitis involving gastric antrum and proximal duodenum mimicking peptic ulcer disease, without pancreatitis in the normal pancreas. Conclusion: Ectopic pancreatitis is a rare condition and can mimic more common diseases depending on the anatomical location.

Background: Takotsubo cardiomyopathy (TCM) has some distinctive features like greater proportion of reverse-TCM and central nervous system disease as a prevalent triggering cause. We expose the case of a child with cardiogenic shock presenting an atypical echocardiographic TCM pattern on an echocardiography, after an acute neurologic trigger. We also include a systematic literature review of previously described cases of atypical-TCM in children. Case Report: A previously healthy 9 year-old boy with status epilepticus presented abrupt cardiogenic shock. The EKG showed signs of myocardial ischemia, cardiac biomarkers NT-proBNP (2756 pg/mL ) and Troponin I (1707 pg/mL ) , and the echocardiography exposed a dilated LV with severely reduced systolic function (LVEF 28%) along with hypokinetic mid-basal segments (circumferential ballooning), and preserved hypercontractile apical segments, with the normal origin of both coronary arterial systems. A presumptive diagnosis of “reverse”, “inverse” or atypical Takotsubo cardiomyopathy was built based on the echocardiographic findings, apart from the ACS-like EKG findings, the raised cardiac biomarkers, and the neurological trigger of the hyper catecholaminergic state. Despite cardiovascular improvement with supportive treatment, the patient eventually expired on day 2 after PICU admission due to neurological complications. As shown in our systematic review, only 19 similar cases have been reported to date. Conclusion: With the report of this unusual case, we aim to point out the fundamental role of bedside echocardiography as a diagnostic test for critically ill children presenting with ACS-like in the context of neurosurgical emergencies, where bedside echocardiography itself can accurately establish a presumptive diagnosis of TCM.

Background: Primary extramedullary plasmacytomas (EMP) are rare; however, secondary forms may be seen in ~10-15% of patients with systemic multiple myeloma (MM). The diagnosis of EMP is based on the demonstration of monoclonal plasma cells in the lesion, which requires tissue sampling. Case Presentation: We present a case of a 38 year old female with MM who underwent diagnostic US at our institute. Multiple focal liver lesions were detected, which were suspicious for EMP. She underwent fine needle aspiration cytology (FNAC) for diagnosis, following which she developed hemoperitoneum secondary to deranged clotting parameters (prothrombin time and platelet count). CT angiography revealed active hepatic capsular bleed. She was taken up for percutaneous embolisation, and the supplying vessel successfully embolised using gel foam particles. Conclusion: Complications may rarely occur in interventional procedures, particularly in patients with comorbidities. However, prompt diagnosis and management help prevent adverse outcomes.

Background: The situation created by global emergencies, such as the current global pandemic [1], has led in many parts of the world to the cessation of clinical practice in hospitals for medical and nursing students, although in medical education the contact with the patient and the practical practice of various medical techniques and procedures by contact is necessary. However, in situations of biological risk, it is natural to avoid any possibility of exposure for students. Materials and Methods: The objective of this paper is to analyze the possibility of creating low cost, modular telepresence robots, adapted for medical clinical practice and capable of allowing practicing students to interact remotely with patients, communicate with them, monitor them, help them move, and also to be able to measure parameters such as temperature using thermal vision, pulse measurement or, the ability of the limbs to move. The robot consists of a mobile stretcher, with the possibility of moving both with wheels and with the help of legs, which allows the patient to move without human assistance in areas with obstacles. The method of achieving this goal refers to the realization of several modular applications and each to solve specific tasks, and finally to be interconnected in a telepresence robot that makes possible the remote interaction of practicing students with patients. Results: The research results emerge both from the prototypes made and from the simulations and the results of measuring certain vital parameters sent by the telepresence robot via the internet to the medical team. Conclusion: The idea of modular integration of several individual applications is feasible and offers the advantage of easily adapting to patients with various ailments and medical needs.