Current Medical Imaging - Volume 18, Issue 2, 2022

Objective: Coronavirus-related disease, a deadly illness, has raised public health issues worldwide. The majority of individuals infected are multiplying. The government is taking aggressive steps to quarantine people, people exposed to infection, and clinical trials for treatment. Subsequently recommends critical care for the aged, children, and health-care personnel. While machine learning methods have been previously used to augment clinical decisions, there is now a demand for “Emergency ML.” With rapidly growing datasets, there also remain important considerations when developing and validating ML models. Methods: This paper reviews the recent study that applies machine-learning technology addressing Corona virus-related disease issues' challenges in different perspectives. The report also discusses various treatment trials and procedures on Corona virus-related disease infected patients providing insights to physicians and the public on the current treatment challenges. Results: The paper provides the individual with insights into certain precautions to prevent and control the spread of this deadly disease. Conclusion: This review highlights the utility of evidence-based machine learning prediction tools in several clinical settings, and how similar models can be deployed during the Corona virus-related disease pandemic to guide hospital frontlines and health-care administrators to make informed decisions about patient care and managing hospital volume. Further, the clinical trials conducted so far for infected patients with Corona virus-related disease addresses their results to improve community alertness from the viewpoint of a well-known saying, “prevention is always better.”

COVID-19 is a global pandemic that has affected many countries in a short span of time. People worldwide are susceptible to this deadly disease. To control the prevailing havoc of coronavirus, researchers are adopting techniques like plasma therapy, proning, medicines, etc. To stop the rapid spread of COVID-19, contact tracing is one of the important ways to check the infected people. This paper explains the various challenges people and health practitioners are facing due to COVID-19. In this paper, various ways with which the impact of COVID-19 can be controlled using IoT technology have been discussed. A six-layer architecture of IoT solutions for containing the deadly COVID-19 has been proposed. In addition to this, the role of machine learning techniques for diagnosing COVID-19 has been discussed in this paper, and a quick explanation of the unmanned aerial vehicle (UAVs) applications for contact tracing has also been specified. From the study conducted, it is evident that IoT solutions can be used in various ways for restricting the impact of COVID-19. Furthermore, IoT can be used in the healthcare sector to assure people's safety and good health with minimal costs.

The outbreak of COVID-19 has led to a global health emergency. Emerging from China, it has now been declared as a pandemic. Owing to the fast pace at which it spreads, its control and prevention have now become the greatest challenge. The inner structural analysis of the virus is an important area of research for the invention of the potential drug. The countries are following different strategies and policies to fight against COVID-19; various schemes have also been employed to cope up with the economic crisis. While the government is struggling to balance between the public health sector and the economic collapse, the researchers and medicine practitioners are inclined towards obtaining treatment and early detection of the deadly disease. Further, the impact of COVID-19 on Dentistry is alarming and posing severe threats to the professionals as well. Now, the technology is helping the countries fight against the disease. ML and AI based applications are substantially aiding the process of detection and diagnosis of novel coronavirus. Science of Robotics is another approach followed with an aim to improve patient care.

The use of a navigation system allows precise resection of a tumor and accurate reconstruction of the resultant defect thereby sparing important anatomical structures and preserving function. It is an “image-based” system where the imaging (computed tomography and magnetic resonance imaging) is required to supply the software with data. The fusion of the preoperative imaging provides pre-operative information about local anatomy and the extent of the tumor so that it allows accurate preoperative planning. Accurate pre-operative imaging is mandatory in order to minimize CATS errors, thus performing accurate tumor resections.

Age, location of the tumor, and detailed patient history can narrow the differential diagnosis of spinal bone lesions, including metastasis and primary benign and malignant bone tumors. Computed tomography and magnetic resonance imaging are both crucial in evaluating the characteristics of spinal bone tumors. Growth speed and Lodwick margin description can differentiate malignant from benign tumors to a certain degree. Positron emission tomography has a limited ability to differentiate malignant from benign tumors. A biopsy is often required for a definitive diagnosis. To select the optimal treatment for spinal metastasis, neurological status by epidural spinal cord compression grade (axial T2-weighted magnetic resonance image), radiosensitivity of tumor histology, mechanical instability by Spine Instability Neoplastic Score (sagittal and axial computed tomography image), and systemic disease should be evaluated by a multidisciplinary team. This review article summarizes the role of imaging for diagnosis and treatment of spinal bone tumors.

Giant cell tumour of bone (GCTB) typically occurs in young adults from 20-40 years old. Although the majority of lesions are located in the epi-metaphyses of the long bones, approximately one third of tumours are located in the axial skeleton, of which only 4% in the sacrum. Sacral tumours tend to be large at the time of presentation, and they present with aggressive features such as marked cortical destruction and an associated soft tissue component. The 2020 World Health Organisation classification of Soft Tissue and Bone Tumours describes GCTB as a neoplasm which is locally aggressive and rarely metastasizing. The tumour contains three different cell types: neoplastic mononuclear stromal cells, macrophages and osteoclast-like giant cells. Two tumour subtypes were defined: conventional GCTB and malignant GCTB. Only 1-4% of GCTB is malignant. In this review article, we will discuss imaging findings at the time of diagnosis to guide the musculoskeletal radiologist in reporting these tumours. In addition, imaging for response evaluation after various treatment options will be addressed, such as surgery, radiotherapy, embolization and denosumab. Specific findings will be presented per imaging modality and illustrated by cases from our tertiary sarcoma referral center. Common postoperative and post-radiotherapy findings in GCTB of the sacrum on MRI will be discussed.

The diagnosis of sacral neoplasms is often delayed because they tend to remain clinically silent for a long time. Imaging is useful at all stages of the management of sacral bone tumors, i.e., from the detection of the neoplasm to the long-term follow-up. Radiographs are recommended as the modality of choice to begin the imaging workup of a patient with known or suspected sacral pathology. More sensitive examinations, such as Computerized Tomography (CT), magnetic resonance (MRI), or scintigraphy, are often necessary. The morphological features of the lesions on CT and MRI help orientate the diagnosis. Although some imaging characteristics are helpful to limit the differential diagnosis, an imaging-guided biopsy is often ultimately required to establish a specific diagnosis. Imaging is of paramount importance even in the long-term follow-up, in order to assess any residual tumor when surgical resection remains incomplete, to assess the efficacy of adjuvant chemotherapy and radiotherapy, and to detect recurrence.

Vertebral fractures are a common condition occurring in the context of osteoporosis and malignancy. These entities affect a group of patients in the same age range; clinical features may be indistinct and symptoms non-existing, and thus present challenges to diagnosis. In this article, we review the use and accuracy of different imaging modalities available to characterize vertebral fracture etiology, from well-established classical techniques to the role of new and advanced imaging techniques and the prospective use of artificial intelligence. We also address the role of imaging in treatment. In the context of osteoporosis, the importance of opportunistic diagnosis is highlighted. In the near future, the use of automated computer-aided diagnostic algorithms applied to different imaging techniques may be really useful to aid in diagnosis.

Spinal epidural lipomatosis (SEL) is defined as the abnormal accumulation of unencapsulated adipose tissue in the spinal epidural space. SEL can be asymptomatic or can cause a wide range of symptoms, the most common of which is neurogenic claudication. Several other neurological manifestations may also occur, above all myelopathy and radicular symptoms. The spinal level most frequently involved in patients with SEL is the lumbar one, followed by the thoracic one. Imaging plays a key role in the disease assessment. MRI is considered the most effective and sensitive modality for diagnosing and staging SEL. Anyway, also CT scan can diagnose SEL. The diagnosis may be incidental (in mild-moderate disease) or may be taken into account in cases with neurological symptoms (in moderate-severe disease). There are some recognized risk factors for SEL, the most common of which are exogenous steroid use and obesity. Recent studies have found an association between SEL and obesity, hyperlipidemia and liver fat deposition. As a matter of fact, SEL can be considered the spinal hallmark of metabolic syndrome. Risk factors control represents the initial treatment strategy in patients with SEL (e.g. weight loss, steroid therapy suspension). Surgical decompression may be required when conservative treatment fails or when the patient develops acute/severe neurological symptoms.

Spondylodiscitis is an infectious process that requires numerous health care professionals to be clearly diagnosed and eventually successfully treated. It implies a variety of microbiological agents and conditions; during the diagnostic workup, it is difficult to correctly identify them, and the clinician has to rapidly choose the correct treatment to avoid permanent injuries to the patient. In this context, we conducted a review to better understand the most suitable use of Positron Emission Tomography with 18-Fluoro-deossi-glucose (FDG PET) in a patient suspected of spondylodiscitis, based on current guidelines and literature.. We wanted to review the role of FDG PET in the spondylodiscitis diagnosis and follow up in the context of the current guidelines.

Spinal Infection (SI) is an infection of vertebral bodies, intervening disc, and/or adjoining para-spinal tissue. It represents less than 10% of all skeletal infections. There are numerous factors that predispose to developing a SI. Due to the low specificity of signs, delayed diagnosis is common. Hence, SI may be associated with poor outcomes. Diagnosis of SI must be supported by clinicopathological and radiological findings. MRI is a reliable modality of choice. Treatment options vary according to the site of the infection, disease progression, neurology, presence of instability, and general condition of the subject. Conservative treatment (orthosis/ bed-rest + antibiotics) is recommended during the early course with no/ lesser degree of neurological involvement and to medically unfit patients. Nevertheless, when conservative measures alone fail, surgical interventions must be considered. The use of concomitant antimicrobial drugs intravenously during initial duration followed by oral administration is a necessity. Controversies exist regarding the optimal duration of antimicrobial therapy, yet never given less than six weeks. Heterogeneity in clinical picture and associated co-morbidities with a range of treatment modalities are available; however, a common applicable guideline for SI does not exist. Managing SI must be tailored on a case-to-case basis.

Purpose: To describe the magnetic resonance characteristics of radial scars/complex sclerosing lesions (RS/CSL) of the breast using the current BI-RADS lexicon. To investigate the value of diffusion weighted imaging to predict malignancy. Patients and Methods: From 2010 to 2017, we have found 25 women with architectural distortion at mammography who underwent surgical resection with a final hystopathologic report of RS/CSL. For the description of MRI findings, we adhered to BI-RADS classification (5th edition). Results: The final pathological diagnosis was: “pure” RS/CSL in 7 cases (28%), RS/CSL with associated high risk lesions in 12 (48%) and 6 cases (24%) were associated with malignancy. Magnetic resonance findings: four of 25 negative or focus. Five of 25 mass enhancement: irregular, non circumscribed spiculated mass with heterogeneous or rim enhancement and most with type II curves. Sixteen of 25 non mass enhancement: focal or linear distribution and heterogeneous internal enhancement most with type I curves. Six of 25 had cancer associated with the complex sclerosing lesion. All six showed non-mass enhancement. Two cases with invasive breast carcinoma had ADC values under 1.15 x10^-3 mm/s while most of the rest had the values above. Conclusion: Most RS/CSL showed enhancement at MR. The predominant pattern was a non-mass, focal, heterogeneous internal enhancement with type 1 curves. All cases with associated cancer showed non mass enhancement. Invasive breast cancers had ADC values < 1.15 10-3 s/mm2.

Background: In some patients with cochlear implants, bony resorption at the internal receiver- stimulator site can be observed on postoperative computed tomography. Therefore, it is essential to elucidate the effects of the internal receiver-stimulator on the scalp and bony bed over time. Objective: We aimed to evaluate how the internal receiver-stimulator of a cochlear implant device changed the thickness of the surrounding scalp and skull over time using computed tomography. Methods: This retrospective study evaluated patients who underwent cochlear implantation and received two computed tomography scans postoperatively for different indications at a tertiary referral centre. The main outcomes were scalp thickness and bony bed depth. Results: Fourteen ears were included in this study. There was very good inter-rater reliability among the two readers who evaluated the computed tomography of the included patients, with a Cronbach’s alpha of 0.94. The mean scalp thickness over the internal receiver-stimulator was 6.02 (+/-2.4) mm in the first scan and decreased with no significant change to 5.62 mm (+/-1.64) in the second scan (p = 0.59, paired t-test). The mean depth of the bony bed increased significantly from 1.39 mm (+/-0.93) to 2.62 mm (+/-1.24) (p = 0.03). Conclusion: There was no change in the thickness of the scalp overlying the internal receiver-stimulator indicating that the scalp was more resistant than the bony skull to the tensile pressure exerted by the internal receiver-stimulator. In contrast, the bony bed depth of the internal receiver-stimulator increased over time. This can result in decreased internal receiver-stimulator protrusion and decreased risk of device displacement and migration.

Background: The liver is the most common site for rectal cancer metastases. Recommended standard pre-treatment workups have involved Computed Tomography (CT) for abdominal metastases, however, few hospitals have replaced this with Magnetic Resonance Imaging (MRI). Introduction: The aim of this study was to compare MRI with CT as an index examination of the liver in the pre-treatment workup in usual care. The primary endpoint was the need for supplementary liver investigations. Methods: Consecutive patients from two hospitals during 2013-2015 were identified in the Regional Swedish Colorectal Cancer Register and included in this retrospective study. Hospital records and radiology reports were reviewed. Inconclusive reports were re-evaluated by two radiologists. Results: A total of 320 patients were included, and 293 were available for analysis. Some 175 and 118 patients had undergone CT and MRI respectively, as their index pre-treatment liver examination. Thirty-four (19.4%) in the CT group and 6 (5.1%) patients in the MRI group underwent supplementary liver investigation due to inconclusive index examination (RR 3.82, 95% CI: 1.66; 8.81, p=0.0017). Median time (q1; q3) from index examination to start of treatment was 50 (36; 68) days in the CT group and 34 (27; 45) days in the MRI group. Conclusion: This retrospective study of two modalities within usual care found that MRI of the liver as index radiological workup before treatment for rectal cancer was associated with fewer supplementary liver investigations and a shorter time to start of treatment. Based on these findings, a prospective trial should be undertaken before implementing MRI as a standard. Clinicaltrials.gov Registration Number: NCT03463616.

Background: Hepatic portal venous gas [HPVG] is not a common finding in daily practice. It is usually associated with mesenteric ischemia and bowel necrosis in adults. Combination of intratumoral gas in metastatic liver lesions with HPVG is quite rare and thought to be associated with chemotherapy-induced necrosis and infection of the necrotized metastasis Objective: Here we present a case of gastric adenocarcinoma with portal venous and intratumoral gas in metastatic liver lesions due to the infected necrosis. Case Presentation:The patient was presented to the emergency room with severe abdominal pain and septic condition after the second round of chemotherapy. Hepatic portal venous and intratumoral gas in metastatic liver lesions due to the infected necrosis of liver metastasis was detected in computed tomography images. There were no findings of mesenteric ischemia both clinically and radiologically. Massive intratumoral infected necrosis in metastatic liver lesions and fistulization to the right portal vein branches were detected on abdominopelvic CT. Secondary infection of the necrotic metastases and fistulization to portal vein branches was believed to cause the air in metastatic liver masses and portal venous gas. Conclusion:Infected necrosis of metastatic liver lesions and fistulizations to the portal venous structures is extremely rare. Clinicians and radiologists should be aware of such a rare complication because early detection is crucial for patient management.