Surveillance After Surgical and Endovascular Treatment for Peripheral Artery Disease: a Dutch Survey.

OBJECTIVE: At present, there is no clear, optimal approach to surveillance after invasive treatment of peripheral artery disease (PAD) in terms of modality, duration, clinical benefit, and cost effectiveness. The ongoing debate on the clinical benefit and cost effectiveness of standard surveillance creates a clear knowledge gap and may result in overtreatment or undertreatment. In this study, a survey was conducted among vascular surgeons in the Netherlands to assess the currently applied surveillance programmes. METHODS: All vascular surgeons from the Dutch Society for Vascular Surgery received an online survey on follow up after open and endovascular revascularisation in patients with PAD. Surveillance was defined as at least one follow up visit after intervention with or without additional imaging or ankle brachial index (ABI) measurement. Ten types of PAD intervention were surveyed. RESULTS: Surveys were returned by 97 (46.2%) of 210 vascular surgeons, and 76% reported using a routine follow up protocol after an invasive intervention. Clinical follow up only is most commonly performed after femoral endarterectomy (53%). After peripheral bypass surgery, clinical follow up only is applied rarely (4 - 8%). In six of the 10 interventions surveyed, duplex ultrasound (DUS) was the most used imaging modality for follow up. After bypass surgery, 76 - 86% of vascular surgeons perform DUS with or without ABI measurement. After endovascular interventions, 21 - 60% performed DUS surveillance. Lifelong surveillance is most often applied after aortobifemoral bypass (57%). Surveillance frequency and duration vary greatly within the same intervention. Frequencies range from every three or six months to annually. Duration ranges from one time surveillance to lifelong follow up. CONCLUSION: There is significant practice variation in surveillance after surgical and endovascular treatment of patients with PAD in the Netherlands. Prospective studies to evaluate treatment outcomes and to define the clinical need and cost effectiveness of standardised surveillance programmes for patients with PAD are recommended.

Second Near-Infrared (NIR-II) Window for Imaging-Navigated Modulation of Brain Structure and Function.

For a long time, optical imaging of the deep brain with high resolution has been a challenge. Recently, with the advance in second near-infrared (NIR-II) bioimaging techniques and imaging contrast agents, NIR-II window bioimaging has attracted great attention to monitoring deeper biological or pathophysiological processes with high signal-to-noise ratio (SNR) and spatiotemporal resolution. Assisted with NIR-II bioimaging, the modulation of structure and function of brain is promising to be noninvasive and more precise. Herein, in this review, first the advantage of NIR-II light in brain imaging from the interaction between NIR-II and tissue is elaborated. Then, several specific NIR-II bioimaging technologies are introduced, including NIR-II fluorescence imaging, multiphoton fluorescence imaging, and photoacoustic imaging. Furthermore, the corresponding contrast agents are summarized. Next, the application of various NIR-II bioimaging technologies in visualizing the characteristics of cerebrovascular network and monitoring the changes of the pathology signals will be presented. After that, the modulation of brain structure and function based on NIR-II bioimaging will be discussed, including treatment of glioblastoma, guidance of cell transplantation, and neuromodulation. In the end, future perspectives that would help improve the clinical translation of NIR-II light are proposed.

Primary Site Identification of Soft-Tissue Mass: Things to Know in MRI Assessment.

The spectrum of soft-tissue mass is varied, including neoplastic and nonneoplastic/inflammatory lesions. However, soft-tissue tumors have similar imaging findings and, therefore, the diagnosis of soft-tissue mass is challenging. Although careful assessment of the internal characteristics on imaging can often narrow the differential diagnoses, the differential diagnosis may be out of the question if identification of the soft-tissue mass origin is missed. The purpose of this article is to review the imaging findings and the essential anatomy to identify the primary site of the soft-tissue mass, and discuss the associated potential pitfalls. In order not to fall into a pitfall, recognition of characteristic imaging findings indicating the origin of the soft-tissue mass and anatomical knowledge of the normal tissue distribution are necessary. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY STAGE: 3.

Clinical outcomes for intracoronary imaging strategies at different medical facilities in Japanese patients with coronary artery disease: the SAKURA imaging PCI Registry.

The relationships between intracoronary imaging modalities and outcomes among Japanese patients with coronary artery disease (CAD) based on the type of medical facility providing outpatient care remain unclear. In this multicenter prospective study (SAKURA PCI Registry), we aimed to investigate the clinical outcomes of patients with CAD who underwent percutaneous coronary intervention (PCI) between April 2015 and December 2018. In this registry, we investigated differences in patient characteristics, intracoronary imaging modalities, and clinical outcomes between two types of medical facilities. Of the 414 patients enrolled in this registry, 196 were treated at two university hospitals, and 218 were treated at five community hospitals (median follow-up 11.0 months). The primary endpoint was clinically relevant events (CREs), including a composite of all-cause death, non-fatal myocardial infarction, clinically driven target lesion revascularization, stent thrombosis, stroke, and major bleeding. Patients treated at university hospitals had higher rates of diabetes (50% vs. 38%, p = 0.015) and malignant tumors (12% vs. 6%, p = 0.015) and more frequent use of multiple intracoronary imaging modalities than patients treated at community hospitals (21% vs. 0.5%, p < 0.001). The Kaplan-Meier incidence of CREs at 1 year was comparable between university hospitals and community hospitals (8.8% vs. 7.3%, p = 0.527, log-rank test). Despite the relatively higher risk among patients in university hospitals with frequent use of multi-intracoronary imaging modalities, adverse clinical events appeared to be comparable between patients with CAD treated at university and community hospitals in Japan.

Endoscopic imaging modalities for diagnosing the invasion depth of superficial esophageal squamous cell carcinoma: a systematic review.

Endoscopic diagnosis of the invasion depth of superficial esophageal squamous cell carcinoma (ESCC) is an important determinant of the treatment strategy. The three endoscopic imaging modalities commonly used to predict the invasion depth of superficial ESCC in Japan are non-magnifying endoscopy (non-ME), magnifying endoscopy (ME), and endoscopic ultrasonography (EUS). However, which of these three modalities is most effective remains unclear. We performed a systematic review of the literature to compare the diagnostic accuracy of the three modalities for prediction of the invasion depth of superficial ESCC. We used Medical Subject Heading terms and free keywords to search the PubMed, Cochrane Central, and Ichushi databases to identify direct comparison studies published from January 2000 to August 2020. The results of direct comparison studies were used to compare the diagnostic accuracy of each modality. The primary outcome was defined as the proportion of overdiagnosis of pT1b-SM2/3 cancers, and the main secondary outcome was the proportion of underdiagnosis of pT1b-SM2/3 cancers. Other secondary outcomes were the sensitivity and specificity values of the modalities. Four articles were finally selected for qualitative evaluation. Although ME showed no significant advantages over non-ME in terms of sensitivity and specificity, it had a slightly lower proportion of overdiagnosis. EUS had sensitivity and specificity similar to those of non-ME and ME, but EUS had a higher proportion of overdiagnosis. Non-ME and ME are useful for the diagnosis of cancer invasion depth. EUS may increase overdiagnosis, and caution is required in determining its indications.

Comparison of Magnetic Resonance Imaging and Ultrasonography in Tumor Size: Evaluation of Equality in Advanced Cervical Cancer Patients.

Background: Cervical cancer is the fourth most common cancer among women worldwide. In Indonesia, cervical cancer is the second most frequent disease related to cancer. Based on staging system criteria, clinical findings are the main criteria to determine cervical cancer stage. In the revised version of the Federation of Gynecology and Obstetrics staging system criteria for cervical cancer, radiological examination for pretreatment evaluation in gynecological malignancies has been used in routine modalities. Magnetic resonance imaging (MRI) and ultrasonography (USG) are commonly used in the presurgery determination of tumor size and the follow-up of cervical cancer patients. Tumor size determines cancer stage which influences the treatment and the survival. The equality of diagnostic accuracy was compared for MRI and ultrasound in this study for tumor size evaluation of cervical cancer patients. Methods: This was a prospective study including 195 patients with cervical cancer Stage IIIB in Dr. Cipto Mangunkusumo Hospital from 2016 to 2018. The tumor sizes and stages of cervical cancer were assessed on MRI and ultrasound. This study evaluated diagnostic accuracy between MRI and US. The sensitivity and specificity were compared by using McNemar test. Results: The result of the study showed that from 195 patients, 76 patients fulfilled the study inclusion criteria. There is a significant difference in assessing tumor size in cervical cancer patients between ultrasound and MRI (mean, 1.72 cm; P < 0.0001). US had 82% sensitivity, 88% specificity, and 82% diagnostic accuracy (P = 0.003, McNemar test). Conclusion: Ultrasound examination showed a comparable accuracy to MRI for assessing tumor size in cervical cancer. US is an affordable and feasible diagnostic staging tool with accuracy comparable to MRI.

Transfer Deep Learning for Dental and Maxillofacial Imaging Modality Classification: A Preliminary Study.

OBJECTIVE: To apply the technique of transfer deep learning on a small data set for automatic classification of X-ray modalities in dentistry. STUDY DESIGN: For solving the problem of classification, the convolution neural networks based on VGG16, NASNetLarge and Xception architectures were used, which received pre-training on ImageNet subset. In this research, we used an in-house dataset created within the School of Dental Medicine, Tel Aviv University. The training dataset contained anonymized 496 digital Panoramic and Cephalometric X-ray images for orthodontic examinations from CS 8100 Digital Panoramic System (Carestream Dental LLC, Atlanta, USA). The models were trained using NVIDIA GeForce GTX 1080 Ti GPU. The study was approved by the ethical committee of Tel Aviv University. RESULTS: The test dataset contained 124 X-ray images from 2 different devices: CS 8100 Digital Panoramic System and Planmeca ProMax 2D (Planmeca, Helsinki, Finland). X-ray images in the test database were not pre-processed. The accuracy of all neural network architectures was 100%. Following a result of almost absolute accuracy, the other statistical metrics were not relevant. CONCLUSIONS: In this study, good results have been obtained for the automatic classification of different modalities of X-ray images used in dentistry. The most promising direction for the development of this kind of application is the transfer deep learning. Further studies on automatic classification of modalities, as well as sub-modalities, can maximally reduce occasional difficulties arising in this field in the daily practice of the dentist and, eventually, improve the quality of diagnosis and treatment.

The role of OCT-A in retinal disease management.

Optical coherence tomography angiography (OCT-A) is a non-invasive, non-dye-based imaging modality that has the potential to enhance our understanding of retinal diseases. While this rapidly advancing imaging modality offers great potential, there is a need for community-wide understanding of the range of technologies and methods for interpreting the images, as well as a need to enhance understanding of images from disease-free eyes for reference when screening for retinal diseases. Importantly, clinical trials have been designed without OCT-A-based endpoints; therefore, caution is required when making treatment decisions based on OCT-A imaging alone. With this in mind, a full understanding of the advantages and limitations of OCT-A will be vital for effective development of the technique within the field of ophthalmology. On behalf of the Vision Academy Steering Committee (sponsored by Bayer), this publication summarizes the views of the authors on the current use of OCT-A imaging and explores its potential for future applications in research and clinical practice.

Preoperative imaging evaluation of pancreatic pathologies for the objective prediction of pancreatic fistula after pancreaticoduodenectomy.

In performing pancreaticoduodenectomy (PD) or when conducting clinical trials involving PD procedure, a universal platform for predicting the risk of postoperative pancreatic fistula (POPF) is indispensable. In this article, the most significant imaging studies that focused on the objective preoperative assessment of pancreatic pathologies in association with the occurrence of POPF after PD were reviewed. Several recently developed imaging modalities can objectively predict the occurrence of POPF after PD by assessing the elasticity, fibrosis, and fatty infiltration of the pancreas. These valuable imaging modalities include: (1) acoustic radiation force impulse ultrasound (US) electrography which provides information about the elastic properties of the pancreas; (2) contrast-enhanced computed tomography (CT) and magnetic resonance imaging (MRI) with/without contrast-enhancement which reflect the histological degree of pancreatic fibrosis; and (3) multi-detector row CT and/or MRI which reflects the microscopic fatty infiltration of the pancreas. The precise and objective preoperative risk assessment of POPF enables surgeons to customize appropriate management strategies for individual patients undergoing PD. This would be also beneficial for stratifying patients for enrolment in relevant studies that involve pancreatic head resection, as objective criteria could be set for the definitive evaluation of collected data related to surgical outcomes across different institutions and surgeons.

Preoperative prediction of the size of pure ductal carcinoma in situ using three imaging modalities as compared to histopathological size: does magnetic resonance imaging add value?

PURPOSE: The purpose of this study was to evaluate whether magnetic resonance imaging (MRI) and ultrasonography add value to traditional mammography in an Asian population with ductal carcinoma in situ (DCIS). METHODS: Data of 244 patients with pure DCIS treated at Severance Hospital between 2013 and 2015 were analyzed retrospectively. Data extracted included age, preoperative diagnosis, tumor size on preoperative imaging studies, and final histopathological tumor type and size, including hormone receptor status. The extent of correlation between imaging and histopathological tumor sizes was evaluated using a variety of methods, including Bland-Altman analysis. RESULTS: The mean patient age was 52.39 years (SD = 10.31). The mean measurements of the tumor on preoperative ultrasonography, mammography, MRI, and histopathology were 1.80 (SD = 1.23) cm, 2.97 (SD = 1.92) cm, 2.53(SD = 1.84) cm, and 1.88 (SD = 1.36) cm, respectively. The mean differences in tumor size between ultrasonography, mammography, and MRI compared with histopathology were -0.09 (SD = 1.39), 1.09 (SD = 1.89), and 0.65 (SD = 1.78), respectively. The correlation between the sizes was significant with r values for ultrasonography, mammography, and MRI of 0.447 (SE = 0.061), 0.375 (SE = 0.042), and 0.409 (SE = 0.043), respectively. Mammography and MRI estimated tumor size significantly better for patients older than 50 years (p = 0.045 and <0.001, respectively). Mammography also provided good estimation for patients with a body mass index under 25 (p = 0.041). CONCLUSION: MRI is better at estimation of histopathological DCIS size compared with mammography. However, ultrasonography had better estimation compared with MRI and mammography, probably owing to the high breast density in this population.

Resisting Sleep Pressure: Impact on Resting State Functional Network Connectivity.

In today's 24/7 society, sleep restriction is a common phenomenon which leads to increased levels of sleep pressure in daily life. However, the magnitude and extent of impairment of brain functioning due to increased sleep pressure is still not completely understood. Resting state network (RSN) analyses have become increasingly popular because they allow us to investigate brain activity patterns in the absence of a specific task and to identify changes under different levels of vigilance (e.g. due to increased sleep pressure). RSNs are commonly derived from BOLD fMRI signals but studies progressively also employ cerebral blood flow (CBF) signals. To investigate the impact of sleep pressure on RSNs, we examined RSNs of participants under high (19 h awake) and normal (10 h awake) sleep pressure with three imaging modalities (arterial spin labeling, BOLD, pseudo BOLD) while providing confirmation of vigilance states in most conditions. We demonstrated that CBF and pseudo BOLD signals (measured with arterial spin labeling) are suited to derive independent component analysis based RSNs. The spatial map differences of these RSNs were rather small, suggesting a strong biological substrate underlying these networks. Interestingly, increased sleep pressure, namely longer time awake, specifically changed the functional network connectivity (FNC) between RSNs. In summary, all FNCs of the default mode network with any other network or component showed increasing effects as a function of increased 'time awake'. All other FNCs became more anti-correlated with increased 'time awake'. The sensorimotor networks were the only ones who showed a within network change of FNC, namely decreased connectivity as function of 'time awake'. These specific changes of FNC could reflect both compensatory mechanisms aiming to fight sleep as well as a first reduction of consciousness while becoming drowsy. We think that the specific changes observed in functional network connectivity could imply an impairment of information transfer between the affected RSNs.

Magnetic Resonance Imaging Compared with Rectal Endoscopic Sonography for the Prediction of Infiltration Depth in Colorectal Endometriosis.

STUDY OBJECTIVE: To compare the accuracies of magnetic resonance imaging (MRI) and rectal endoscopic sonography (RES) in the prediction of the infiltration depth of colorectal endometriosis. DESIGN: A retrospective cohort study (Canadian Task Force classification II-2). SETTING: A university teaching hospital. PATIENTS: Forty patients with symptomatic deep infiltrating endometriosis (DIE) of the rectum who underwent colorectal resection were included. INTERVENTIONS: All patients underwent abdominopelvic MRI and RES preoperatively to assess the infiltration depth of colorectal endometriosis, and segmental resection of the rectosigmoid by laparoscopy was performed if RES showed bowel invasion. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), positive and negative likelihood ratios (LRs), and intermethod agreement were calculated for DIE muscularis and submucosal/mucosal infiltration confirmed by histopathological analysis. MEASUREMENTS AND MAIN RESULTS: For MRI detection of DIE muscularis infiltration, the sensitivity, specificity, PPV, NPV, and negative LR were 68%, 100%, 100%, 20%, and 0.32, respectively. For the MRI detection of DIE submucosal/mucosal involvement, the sensitivity, specificity, PPV, NPV, and positive and negative LRs were 47%, 81%, 69%, 63%, 2.49, and 0.65, respectively. The PPV of RES detection of DIE muscularis infiltration was 93%. For the RES detection of DIE submucosal/mucosal layers, the sensitivity, specificity, PPV, NPV, and positive and negative LRs were 79%, 48%, 58%, 71%, 1.51, and 0.44, respectively. CONCLUSION: In the current study, MRI is valuable for detecting endometriosis of the rectum but is less accurate in detecting submucosal/mucosal involvement than RES. Magnetic resonance imaging was not successful for preoperative determination of segmental resection versus a more conservative approach. When bowel involvement is detected by MRI, RES is not essential. When symptoms suggest DIE in patients without intestinal lesions detected by MRI, RES is necessary to exclude bowel invasion.

Safety and Clinical Effectiveness of Percutaneous Vertebroplasty in the Elderly (≥80 years).

PURPOSE: To evaluate the safety and clinical effectiveness of percutaneous vertebroplasty (PVP) in patients aged 80 and over. METHODS: One hundred and seventy-three patients (127 women, 46 men; mean age = 84.2y) underwent 201 PVP procedures (391 vertebrae) in our institution from June 2008 to March 2012. One hundred and twenty-six patients (73 %) had osteoporotic vertebral compression fractures (VCF), 36 (20.5 %) were treated for tumour lesions, and the remaining 11 (6.5 %) for lesions from another cause. Comorbidities and American Society of Anesthesiologists (ASA) scores were assessed before treatment. Periprocedural and delayed complications were systematically recorded. A qualitative scale was used to evaluate pain relief at 1-month follow-up, ranging from significant pain worsening to marked improvement or disappearance. New fracture occurrence was assessed on follow-up imaging. RESULTS: Forty-five percent of patients had pretreatment ASA class scores ≥3. No major complication occurred. Pain was unchanged in 16.9 % of cases, mildly improved in 31.5 %, and disappeared in 47.8 %. We identified 27 (11 %) symptomatic new VCFs in patients with osteoporosis on follow-up imaging. The mean delay in diagnosis of new fractures was 5 ± 8.7 months. CONCLUSIONS: Even in the elderly, PVP remains a safe and effective technique for pain relief, independently of the underlying disease. KEY POINTS: • Post-PVP pain improvement was observed in 79.3 % of elderly patients. • PVP remains a safe technique in elderly patients. • No decompensation of comorbidity was observed in our series.

Vasa vasorum in atherosclerosis and clinical significance.

Atherosclerosis is a chronic inflammatory disease that leads to several acute cardiovascular complications with poor prognosis. For decades, the role of the adventitial vasa vasorum (VV) in the initiation and progression of atherosclerosis has received broad attention. The presence of VV neovascularization precedes the apparent symptoms of clinical atherosclerosis. VV also mediates inflammatory cell infiltration, intimal thickening, intraplaque hemorrhage, and subsequent atherothrombosis that results in stroke or myocardial infarction. Intraplaque neovessels originating from VV can be immature and hence susceptible to leakage, and are thus regarded as the leading cause of intraplaque hemorrhage. Evidence supports VV as a new surrogate target of atherosclerosis evaluation and treatment. This review provides an overview into the relationship between VV and atherosclerosis, including the anatomy and function of VV, the stimuli of VV neovascularization, and the available underlying mechanisms that lead to poor prognosis. We also summarize translational researches on VV imaging modalities and potential therapies that target VV neovascularization or its stimuli.

Clinical characteristics and prognosis of patients with isolated cardiac sarcoidosis: Insights from the ILLUMINATE-CS study.

AIM: Data on the clinical features and prognosis of patients with isolated cardiac sarcoidosis (iCS) are limited. This study evaluated the clinical characteristics and prognostic impact of iCS. METHODS AND RESULTS: This was a secondary analysis of the ILLUMINATE-CS study, a multicentre, retrospective registry investigating the clinical characteristics and prognosis of cardiac sarcoidosis. iCS was diagnosed according to the 2016 Japanese Circulation Society (JCS) guidelines. Clinical characteristics and prognosis were compared between patients with iCS and systemic cardiac sarcoidosis (sCS). The primary outcome was a combined endpoint of all-cause death, hospitalization for heart failure, or fatal ventricular arrhythmia events. Among 475 patients with CS (mean age, 62.0 ± 10.9 years; female ratio, 59%) diagnosed by the JCS guidelines, 119 (25.1%) were diagnosed with iCS. Patients with iCS had a higher prevalence of a history of atrial fibrillation or hospitalization for heart failure, or lower left ventricular ejection fraction than those with sCS. During a median follow-up of 42.3 (interquartile range, 22.8-72.5) months, 141 primary outcomes (29.7%) occurred. Cox proportional hazard analysis revealed that iCS was a significant risk factor for the primary outcome in the unadjusted model (hazard ratio [HR] 1.62; 95% confidence interval [CI] 1.12-2.34; p = 0.011). However, this association was not retained after adjustment for other covariates (adjusted HR 1.27; 95% CI 0.86-1.88; p = 0.226). CONCLUSIONS: Patients with iCS had more impaired cardiovascular function at the time of diagnosis than those with sCS. However, iCS was not independently associated with poor prognosis after adjustment for prognostic factors.

The reliability of clinical tools with and without ultrasound guidance to measure leg-length inequality.

Purpose: To determine and compare the reliability and efficiency of various methods of leg-length measurement. Methods: A total of 88 leg-lengths were measured among 50 subjects (79%-84% female, mean age = 30-33 years). Leg-lengths were measured in both supine and standing positions using multiple devices, including a tape measure, a LASER distance meter, and diagnostic ultrasound. Results: All methods of leg-length measurement using the middle of the femoral head as a reference point, identified via ultrasound, demonstrated excellent reliability (intraclass correlation coefficient = 0.95-1.00). Measurements performed in supine, using the anterior superior iliac spine as a reference point, with a tape measure, demonstrated good-to-excellent reliability (intraclass correlation coefficient = 0.86-0.95, standard error of the measurement = 16.1-19.9 cm). Standing measurements using the anterior superior iliac spine as a reference point, using a tape measure, demonstrated fair-to-excellent reliability (intraclass correlation coefficient = 0.71-0.95). Conclusion: Ultrasound-guided landmark identification appear to be a more reliable method compared to palpation of the anterior superior iliac spine for measurement of leg-length using clinical tools. When coupled with ultrasound guidance, a hand-held LASER distance meter/pitch locator apparatus or a retractable tape measure appears to be acceptable alternatives to a fixed LASER distance meter on a linear actuator for leg-length measurement.

Renal mass imaging modalities: does body mass index (BMI) matter?

PURPOSE: Accurate measurement of renal mass size is crucial in the management of renal cancer. With the burdensome cost of imaging yet its need for management, a better understanding of the variability among patients when determining mass size remains of urgent importance. Current guidelines on optimal imaging are limited, especially with respect to body mass index (BMI). The aim of this study is to discern which modalities accurately measure renal mass size and whether BMI influences such accuracy. METHODS: A multi-institutional chart review was performed for adult patients undergoing partial or radical nephrectomy between 2018 and 2021, with 236 patients ultimately included. Patients were categorized by BMI (BMI 1: 18.5-24.9, BMI 2: 25-29.9, BMI 3: 30-34.9, and BMI 4: ≥ 35). The greatest mass lengths were compared between the pathology report and the following: computerized tomography (CT), renal ultrasound, and magnetic resonance imaging (MRI). RESULTS: The difference between greatest length on CT with contrast and MRI were significantly different when compared to pathologic measurement. BMI groups 3 and 4 were found to have a significant difference in size estimates compared to BMI 2 for CT with contrast. No difference was found between size estimates by BMI group for any other imaging modality. CONCLUSION: CT with contrast becomes less accurate at estimating mass size for patients with BMI > 30. While contrast-enhanced CT remains a vital imaging modality for tissue enhancement in the context of unknown renal masses, caution must be used for mass size estimation in the obese population.

Automated Prediction of Diabetes Mellitus using Infrared Thermal Foot Images: Recurrent Neural Network Approach.

Millions of people worldwide are affected by Diabetes Mellitus (DM), which is a chronic disease. Evaluation of the DM indicator, namely blood glucose level, requires invasive methods such as glucometer or blood tests, which cause discomfort to the patient. Automated noninvasive monitoring methods are urgently needed to ensure consistency and better treatment. The regular monitoring of DM can prevent or delay the onset of complications. Thermal foot images have been proposed as noninvasive methods for the prediction of DM. Thermograms were acquired at Mittal Eye Hospital, Sangrur, India, from 50 participants in the diabetic (without neuropathic conditions) and non-diabetic groups using a thermal camera (FLIR E-60). This study proposes an automated prediction system for DM using thermal foot images and Recurrent Neural Network (RNN) approach. The proposed system processes the thermal images and extracts relevant features using a CNN (Convolutional Neural Network). The extracted features were then fed to the RNN to predict the presence or absence of the DM. The experimental results demonstrate that the proposed framework attains an accuracy of (97.14 ± 1.5) %, surpassing the predictive capabilities of light-weight convolutional neural network (Lw-CNN), which only achieves an accuracy of (82.9 ± 3) % in predicting DM. This performance outperformed other state-of-the-art methods in the field. Our approach has the potential to be used as prediction tool for DM. Therefore, the proposed system has the potential for prediction of DM and improve patient outcomes by enabling timely intervention. Future work should focus on evaluating the proposed system on a larger dataset and integrating it with clinical decision support systems for personalized care. This study holds the promise of transforming DM screening and diagnosis, leading to enhanced patient outcomes.

An extensive analysis of artificial intelligence and segmentation methods transforming cancer recognition in medical imaging.

Recent advancements in computational intelligence, deep learning, and computer-aided detection have had a significant impact on the field of medical imaging. The task of image segmentation, which involves accurately interpreting and identifying the content of an image, has garnered much attention. The main objective of this task is to separate objects from the background, thereby simplifying and enhancing the significance of the image. However, existing methods for image segmentation have their limitations when applied to certain types of images. This survey paper aims to highlight the importance of image segmentation techniques by providing a thorough examination of their advantages and disadvantages. The accurate detection of cancer regions in medical images is crucial for ensuring effective treatment. In this study, we have also extensive analysis of Computer-Aided Diagnosis (CAD) systems for cancer identification, with a focus on recent research advancements. The paper critically assesses various techniques for cancer detection and compares their effectiveness. Convolutional neural networks (CNNs) have attracted particular interest due to their ability to segment and classify medical images in large datasets, thanks to their capacity for self- learning and decision-making.