Search

Objective: The incidence of congenital hypothyroidism (CHT) has progressively increased in several regions around the world but has yet to be evaluated in Northern Ireland (NI). CHT screening programme was introduced in NI in 1980 and has had a relatively unchanged protocol since its inception. The purpose of the study was to evaluate the incidence of CHT in NI from 1981 to 2020 and to explore possible contributing factors to any changes seen over the 40‐year period. Design: This was a retrospective database review of children diagnosed with CHT in NI between 1981 and 2020. Data was collected from the patients' medical (paper and electronic) records, including epidemiological, clinical, laboratory, and radiological features as well as outcomes at 3 years. Results: Of 800,404 new‐borns who were screened for CHT in NI between January 1981 and March 2020, 471 were diagnosed with CHT. There was a steady and significant increase in incidence of CHT over time with an incidence of 26 cases per 100,000 livebirths in 1981 versus 71 cases per 100,000 in 2019 (p <.001). Of these 471, 77 new‐borns (16%) were born preterm. The incidence of CHT was observed twice as much in female compared to male new‐borns. Diagnostic imaging including radioisotope uptake and thyroid ultrasound scans were performed in 143 cases (30%). Of these, 101 (70%) cases had thyroid dysgenesis and 42 (30%) cases had thyroid dyshormonogenesis. There were 293 (62%) of 471 patients had confirmed permanent CHT, and 90 patients (19%) had transient CHT. Over that period at least 95% of the population were recorded as having United Kingdom/Ireland as country of birth. Conclusion: Our findings demonstrate a nearly tripling of the CHT incidence observed over the last 40 years. This is against a background of a relatively stable population demographics. Future research should focus on the underlying cause(s) of this condition which may include changing environmental exposures in utero. [ABSTRACT FROM AUTHOR]

We propose an IGZO thin‐film transistor (TFT) with a multi‐layered gate dielectric for X‐ray flat‐panel detectors (FPDs). By minimizing X‐ray effects on the gate insulator and threshold‐voltage shift in the IGZO layer, we achieve high radiation hardness. These TFTs in FPD are ideal for medical imaging and nondestructive inspection. [ABSTRACT FROM AUTHOR]

Optimal visualization of needles in clinical ultrasound imaging is important and challenging, especially at steep angles. Improvement of visualization has been attempted with various techniques, for example, coatings and dimples. This systematic review summarizes enhancement techniques and identifies superior echogenic surface enhancements. Twenty‐four papers were identified providing visibility measures for 33 different echogenic needles. These were grouped according to surface characteristics and ranked. Echogenic needles ranked higher than standard needles especially at steeper angles. Among the echogenic needles, coated needles were seemingly better visualized "in vivo" than noncoated needles, despite heterogeneity in study conditions. No unambiguous comparison revealed which needle was best visualized. [ABSTRACT FROM AUTHOR]

Hyperpolarized (HP) 129Xe MRI uniquely images pulmonary ventilation, gas exchange, and terminal airway morphology rapidly and safely, providing novel information not possible using conventional imaging modalities or pulmonary function tests. As such, there is mounting interest in expanding the use of biomarkers derived from HP 129Xe MRI as outcome measures in multi‐site clinical trials across a range of pulmonary disorders. Until recently, HP 129Xe MRI techniques have been developed largely independently at a limited number of academic centers, without harmonizing acquisition strategies. To promote uniformity and adoption of HP 129Xe MRI more widely in translational research, multi‐site trials, and ultimately clinical practice, this position paper from the 129Xe MRI Clinical Trials Consortium (https://cpir.cchmc.org/XeMRICTC) recommends standard protocols to harmonize methods for image acquisition in HP 129Xe MRI. Recommendations are described for the most common HP gas MRI techniques—calibration, ventilation, alveolar‐airspace size, and gas exchange—across MRI scanner manufacturers most used for this application. Moreover, recommendations are described for 129Xe dose volumes and breath‐hold standardization to further foster consistency of imaging studies. The intention is that sites with HP 129Xe MRI capabilities can readily implement these methods to obtain consistent high‐quality images that provide regional insight into lung structure and function. While this document represents consensus at a snapshot in time, a roadmap for technical developments is provided that will further increase image quality and efficiency. These standardized dosing and imaging protocols will facilitate the wider adoption of HP 129Xe MRI for multi‐site pulmonary research. [ABSTRACT FROM AUTHOR]

ABSTRACT The ability to perform bedside thoracic ultrasound is increasingly recognized as an essential skill for thoracic clinicians, extending the clinical examination and aiding diagnostic and therapeutic procedures. Thoracic ultrasound reduces complications and increases success rates when used prior to thoracentesis or intercostal chest tube insertion. It is increasingly difficult to defend performing these procedures without real or near-real time image guidance. To assist thoracic physicians and others achieve and demonstrate thoracic ultrasound competence, the Interventional Pulmonology Special Interest Group ( IP-SIG) of the Thoracic Society of Australia and New Zealand ( TSANZ) has developed a new pathway with four components: (i) completion of an approved thoracic ultrasound theory and hands-on teaching course. (ii) A log of at least 40 relevant scans. (iii) Two formative assessments (following 5-10 scans and again after 20 scans) using the Ultrasound-Guided Thoracentesis Skills and Tasks Assessment Tool ( UG-STAT). (iv) A barrier assessment ( UG-STAT, pass score of 90%) by an accredited assessor not directly involved in the candidate's training. Upon completion of these requirements a candidate may apply to the TSANZ for recognition of competence. This pathway is intended to provide a regional standard for thoracic ultrasound training. [ABSTRACT FROM AUTHOR]

The article presents information on several research papers related to neurointensive care. In one of the paper cerebral perfusion pressure (CPP) is analyzed. CPP is an important parameter in neurointensive care patients. CPP equals mean arterial pressure minus intracranial pressure. Since active treatment is often used to reach the target CPP recommended in the literature, it is important that CPP is measured in a reproducible way. In another research paper, the importance of magnetic resonance imaging in acute cerebellitis is found out. The article also presents information about other research papers.

Solution‐processed organic photodetectors (OPDs) have witnessed great progress in the past few years. With silicon‐like performance achieved, OPDs enable new medical imaging applications by offering cost‐effective light detection over large area. Herein, we illustrate the compelling advantages of high spatial and temporal resolution OPD arrays for medical X‐ray detectors and wearable pulse oximeters. [ABSTRACT FROM AUTHOR]

The fifth Bioengineering and Image Research Opportunities Workshop (BIROW V) was held on January 18–19, 2008. As with previous BIROW meetings, the purpose of BIROW V was to identify and characterize research and engineering opportunities in biomedical engineering and imaging. The topic of this BIROW meeting was Imaging and Characterizing Structure and Function in Native and Engineered Tissues. Under this topic, four areas were explored in depth: (1) Heterogeneous single-cell measurements and their integration into tissue and organism models; (2) Functional, molecular and structural imaging of engineered tissue in vitro and in vivo; (3) New technologies for characterizing cells and tissues in situ; (4) Imaging for targeted cell, gene and drug delivery. [ABSTRACT FROM AUTHOR]

The article presents a study on conductive polyaniline-coated electroactive paper actuators. It discusses details of the experimentation to design electroactive paper actuators (EAPap) with conductive polymers, including their synthesis, characterization and actuation behaviors. It explores the significance of the research on applications in medical imaging, artificial muscles and organs and smart materials for vibration and noise control.

Optic disc (OD) and optic cup (OC) segmentation is an important task in ophthalmic medicine and is crucial for aiding glaucoma screening. With the development of smart healthcare and the increase of large datasets, there is an increasing number of research efforts targeting OD and OC segmentation, making it particularly important to provide a systematic review of the latest advances in the field. This paper presents a systematic review of commonly used datasets, evaluation metrics, and related research results in the field of OD and OC segmentation. The advantages and disadvantages of segmentation techniques based on traditional and deep learning methods are comparatively analysed. In addition, this study emphasizes the importance of OD and OC segmentation efforts in smart healthcare. Despite the technological advances, the lack of generalization capability is still a major obstacle limiting its clinical application. To address this issue, this study explores unsupervised domain adaptation methods to enhance the generalization performance of segmentation techniques and provide new strategies for clinical diagnosis. Finally, this paper discusses the challenges and future research directions faced by OD and OC segmentation when applied in the medical field to help readers comprehensively grasp the research dynamics in this area. [ABSTRACT FROM AUTHOR]

The Internet of Multimedia Things (IoMT) refers to a network of interconnected multimedia devices that communicate with each other over the Internet. Recently, smart healthcare has emerged as a significant application of the IoMT, particularly in the context of knowledge‐based learning systems. Smart healthcare systems leverage knowledge‐based learning to become more context‐aware, adaptable, and auditable while maintaining the ability to learn from historical data. In smart healthcare systems, devices capture images, such as X‐rays, Magnetic Resonance Imaging. The security and integrity of these images are crucial for the databases used in knowledge‐based learning systems to foster structured decision‐making and enhance the learning abilities of AI. Moreover, in knowledge‐driven systems, the storage and transmission of HD medical images exert a burden on the limited bandwidth of the communication channel, leading to data transmission delays. To address the security and latency concerns, this paper presents a lightweight medical image encryption scheme utilising bit‐plane decomposition and chaos theory. The results of the experiment yield entropy, energy, and correlation values of 7.999, 0.0156, and 0.0001, respectively. This validates the effectiveness of the encryption system proposed in this paper, which offers high‐quality encryption, a large key space, key sensitivity, and resistance to statistical attacks. [ABSTRACT FROM AUTHOR]

Focuses on the use of computed tomography (CT) in geriatric psychiatry. Application of CT to discriminate patients with dementia from normal elderly controls; Evolution of medical diagnostic imaging systems; Significance of CT to dementia management.

A low‐cost and easy‐to‐fabricate microchip remains a key challenge for the development of true point‐of‐care (POC) diagnostics. Cellulose paper and plastic are thin, light, flexible, and abundant raw materials, which make them excellent substrates for mass production of POC devices. Herein, a hybrid paper–plastic microchip (PPMC) is developed, which can be used for both single and multiplexed detection of different targets, providing flexibility in the design and fabrication of the microchip. The developed PPMC with printed electronics is evaluated for sensitive and reliable detection of a broad range of targets, such as liver and colon cancer protein biomarkers, intact Zika virus, and human papillomavirus nucleic acid amplicons. The presented approach allows a highly specific detection of the tested targets with detection limits as low as 102 ng mL−1 for protein biomarkers, 103 particle per milliliter for virus particles, and 102 copies per microliter for a target nucleic acid. This approach can potentially be considered for the development of inexpensive and stable POC microchip diagnostics and is suitable for the detection of a wide range of microbial infections and cancer biomarkers. Cellulose paper and plastic are thin, light, flexible, and abundant raw materials, and represent excellent substrates for mass production of point‐of‐care diagnostics. This work describes a new category of hybrid flexible electronic systems that integrates cellulose paper and plastic substrates for the detection of nucleic acid, intact virus particles, and cancer protein biomarkers. [ABSTRACT FROM AUTHOR]

Tc-99m ECD SISCOM for Focus Detection in Patients with Complex Partial Seizures of Frontal Lobe Origin.Purpose:We investigated the clinical usefulness of the subtraction of interictal from ictal single-photon emission computed tomography (SPECT) coregistered to magnetic resonance imaging (MRI) (SISCOM), in detection of a seizure focus in patients with intractable frontal lobe complex partial seizures (CPSs). As a radiopharmaceutical, we used technetium-99m-ethyl cysteinate diethylester (99mTc-ECD), because it is more stable than technetium-99m-hexamethylpropylene amine oxime (99mTc-HMPAO) and, therefore, more convenient for observing ictal or periictal events.Subjects and Methods:Three patients who had typical frontal CPSs and achieved significant improvement after focus resection were subjects of this study. After presurgical examinations, including repeated EEGs, video-EEG monitoring, MRI, neuropsychological testing,[11C]flumazenil (FMZ) positron emission tomography (PET), and[18F]fluorodeoxyglucose (FDG) PET, two patients underwent invasive monitoring for focus detection. The remaining patient underwent focus resection without invasive monitoring, because MRI revealed cortical dysplasia in the right orbitofrontal (OF) gyrus, and EEG demonstrated an ictal onset in the region of the corresponding lesion. Ictal SPECT images were obtained by recognizing ictal onset with video monitoring. The time lag between seizure onset and injection of the radiopharmaceutical was recorded. The SISCOM images were reconstructed by using the image-analysis software Dr. View (Asahi Kasei Joho, Tokyo, Japan) running on a personal computer.Results:The SISCOM images demonstrated increased ECD uptake in the left anterior cingulate and OF gyrus in patient 1, in the right anterior cingulate gyrus in patient 2, and in the right OF gyrus in patient 3. The time lag between seizure onset and the isotope injection was 59 s in patient 1, 37 s in patient 2, and 53 s in patient 3. In each patient, laterality of the seizure onset in the frontal limbic systems showed good agreement with the area showing increased ECD uptake. We then analyzed the diagnostic value for focus detection of interictal FMZ-PET and FDG-PET in the same patients. In the focus area determined by electrocorticography or EEG, FMZ-PET detected decreased binding only in patient 3, but not in patients 1 and 2, whereas FDG-PET detected hypometabolism in patients 1 and 3, but not in patient 2. As for the focus detection of patients with frontal CPS, SISCOM seemed to have a superior diagnostic value over interictal FMZ-PET and FDG-PET. We also found that SISCOM might be a suitable indicator to determine the position of intracranial electrodes placement.Conclusions:We demonstrated that SISCOM is an important presurgical examination for focus detection in patients with intractable frontal lobe CPSs. Clinical Usefulness of a Three-Dimensional Stereotaxic Region of Interest Template (3D-SRT) in Temporal Lobe Epilepsy.Purpose:Single-photon emission computed tomography (SPECT) is a noninvasive functional neuroimaging study used as part of presurgical evaluation when attempting to localize an epileptogenic region. It is well recognized that the interictal SPECT in patients with mesial temporal lobe epilepsy demonstrates hypoperfusion areas in the temporal lobe ipsilateral to the epileptic focus. We evaluated the pattern of regional cerebral blood flow (rCBF) by visual inspection of SPECT images in epilepsy patients, but it is difficult to evaluate rCBF quantitatively in the current clinical SPECT systems.Subjects and Methods:In this study, we analyzed changes of the rCBF in temporal lobe epilepsy by using a fully automated rCBF quantification program; the three-dimensional stereotaxic region of interest (ROI) template (3D-SRT). 3D-SRT has been reported to measure automatically the area-weighted mean value of the rCBF for each of 24 segments arbitrarily defined as the anatomic area supplied from major arteries from values of 536 ROIs of the whole brain. The 12 paired segments are as follows: anterior, precentral, central, parietal, angular, temporal, occipital, pericallosal, lenticular nucleus, thalamus, hippocampus, and cerebellum segments. Twenty-one patients with unilateral mesial temporal lobe epilepsies who received anterior temporal lobectomy with amygdalohippocampectomy were included in this study. The ages of patients ranged from 14 to 49 years (mean, 27 years), and the duration of seizures, from 1 to 31 years (mean, 13.4 years). Histopathologic diagnoses were as follows: hippocampal sclerosis (n= 15), cortical dysplasia (n= 3), dysembryoplastic neuroepithelial tumor (DNT) (n= 1), ganglioglioma (n= 1), and arteriovenous malformation (AVM) (n= 1).99mTc-ECD SPECT was obtained during an interictal period in all patients, and rCBF was calculated by using 3D-SRT. To compare the values of rCBF between 21 patients, we determined the laterality indices (LIs) in all 12 segments of each patient (LI= |(left– right)|/|(left+ right)|× 100). The mean LIs were as follows: 1.17 in anterior, 2.91 in precentral, 2.64 in central, 3.19 in parietal, 3.47 in angular, 4.92 in temporal, 2.19 in occipital, 1.57 in pericallosal, 2.23 in lenticular nucleus, 4.99 in thalamus, 4.82 in hippocampus, and 1.74 in cerebellum. The LIs of thalamus, temporal, hippocampus, and angular were significantly higher (p<0.01) compared with that of the anterior. These results demonstrated that the laterality of rCBF is obvious in the temporal lobe and hippocampus as well as the thalamus in patients with mesial temporal epilepsy. The outcome after surgery at the time of follow-up according to Engel's classification was class I and II in 18 patients (85.7%) and class III in three (14.3%). No correlation was found between the mean LIs of class I/II and those of class III in all segments except thalamus. In the thalamus, LI is significantly higher (p<0.01) in class I/II (5.58± 1.12) than in class III (1.45± 0. 17), suggesting that patients showing laterality of rCBF in thalamus are expected to achieve good surgical outcome from temporal lobectomy. The 3D-SRT is a useful modality to quantify the rCBF in the evaluation of an epileptogenic area. Usefulness of Brain MRI-FLAIR in Predicting Prognosis of Convulsive Status.Background:Early delineation of the pathologic changes in the acute stage of convulsive status in infants is important to predict prognosis. We report five cases during the acute stage after convulsive status to demonstrate that important findings readily are detected with T2-weighted imaging, by using a fluid-attenuated inversion recovery (FLAIR) pulse sequence.Methods:Five infants[one with severe myoclonic epilepsy in infancy (SMEI), one with complex partial seizure (CPS), and three with influenza encephalopathy (IE)] who manifested Todd's palsy after unilateral convulsive status were studied. Informed consent to releases the research results was obtained from all parents.Results:The SMEI case (female) was admitted because of convulsions at age 6 months. The first brain MRI performed 2 weeks afterward showed no abnormality on standard T1-weighted images (T1WI), T2-weighted images (T2WI) and T2-weighted imaging using FLAIR sequence[repetition time (TR) 7,280 ms, inversion time (TI) 1,700 ms, echo time (TE) 110 ms]. Subsequently, she frequently manifested convulsive status with right or left seizures triggered by high fever or photic and pattern stimulation. At age 23 months, after an episode of convulsive status with high fever, she had a right body unilateral seizure. T2-weighted images using FLAIR pulse sequence (TR/TI/TE 7280/1700/132) clearly depicted diffuse and multiple high-intensity areas in the left hemispheric white matter and right hippocampus. However, these finding were not detected by standard T1WI and T2WI. The CPS case was a 4-year-old female infant with developmental delay who had CPSs and left Todd's palsy that continued for∼2 h. After 1 week, brain MRI was performed. Lesions in the white matter of the right frontal lobe were more clearly detected on high-contrast images provided by T2-weighted images, using a FLAIR pulse sequence (TR/TI/TE 9000/2200/138) than by T2WI and T1WI. However, these findings disappeared after 3 months. Among three cases of unilateral convulsion and Todd's palsy caused by influenza encephalopathy, only one case showed hyperintense areas of frontotemporal cortical lesions on T2-weighted images with FLAIR pulse sequence (TR/TI/TE 9000/2300/137) and diffusion-weighted imaging (TR/TE 270/137). This case had no after effects and the findings on the diffusion-weighted imaging disappeared at follow-up MRI. However, the hyperintense lesions in the left hippocampus and white matter of the left frontal cortex were still depicted by T2-weighted images, with a FLAIR pulse sequence (TR/TI/TE 9000/2300/137).Conclusions:In cases of convulsive status epilepticus during infancy, subsequent development of brain lesions, including hippocampal sclerosis, is a potential concern. Heavily T2-weighted images, using a FLAIR pulse sequ strong MR contrast of pathologic tissues. The results that we obtained suggest the usefulness of the MRI-FLAIR for estimating prognosis of patients with convulsive status. Usefulness of[ 123I]Iomazenil SPECT in the Localization of Epileptic Foci in Refractory Epilepsy Patients without Obvious MRI Abnormality.Purpose:Changes in the central-type benzodiazepine receptors (BZRs) can be detected by positron emission tomography (PET) with flumazenil, an antagonist of BZR, or by single-photon emission computed tomography (SPECT) with iomazenil (IMZ), a partial inverse agonist of BZR. A decrease of the BZR density in an epileptic focus has been demonstrated, and BZR imaging is expected to depict the focus as a decreased uptake area. This study investigated the usefulness of IMZ-SPECT for the detection of epileptic foci in patients with refractory epilepsy showing no obvious MRI abnormality.Subjects and Methods:Twenty-three patients who underwent surgery for medically intractable partial seizures without definite abnormality on MRI were studied. The mean age at seizure onset was 12.7 (4–27) years, and the mean age at operation was 28 (20–42) years. All patients underwent interictal IMZ-SPECT and[123I]iodeamphetamine (IMP) SPECT for cerebral blood flow before operation. IMZ-SPECT was performed 3 h after intravenous injection of IMZ (167 MBq), and IMP-SPECT was performed immediately after intravenous injection of IMP (111–222 MBq). Nineteen patients underwent prolonged intracranial EEG recording before surgery. Frontal resection was performed in 12 patients, anterior temporal lobectomy in eight, amygdalohippocampectomy in two, and frontoparietal resection in one. The pathological diagnosis was focal cortical dysplasia (FCD) in eight patients, mesial temporal sclerosis (MTS) in nine, others in two, and no abnormality in four. The abilities of IMZ- and IMP-SPECT to detect abnormalities and epileptic foci were compared. Sensitivity was assessed in all patients, and specificity was assessed in 14 patients who were seizure free for>1 year after operation. Moreover, to investigate the difference in detectability according to pathological background, the detection rates of MTS and FCD by both methods were compared.Results:In all patients, the sensitivity was 61% (14 patients) for IMZ-SPECT and 28% (eight patients) for IMP-SPECT. Neither IMZ- nor IMP-SPECT could detect epileptic foci in seven (30%) patients. In fourteen patients who were seizure free for>1 year after operation, the specificity was 86% (12 patients) for IMZ-SPECT and 36% (five patients) for Iological findings, the detection rates of FCD and MTS were, respectively, 75% (six patients) and 56% (five patients) for IMZ-SPECT, and 28% (one patient) and 56% (five patients) for IMP-SPECT. Despite the absence of definite abnormal pathology in four patients, IMZ- and IMP-SPECT detected an epileptic focus in one patient each.Conclusions:These results show that, compared with IMP-SPECT, IMZ-SPECT is more useful for the detection of epileptic foci in refractory partial epilepsy showing no obvious MRI abnormality. IMZ-SPECT especially is effective to detect FCD. These findings indicate that IMZ-SPECT can play an important role in presurgical evaluation as a noninvasive interictal imaging technique. α-[ 11C]-Methyl-l-Tryptophan Uptake in the Cortex of Patients with Periventricular Nodular Heterotopia and Epilepsy.Background:Periventricular nodular heterotopia (PVNH) is a commonly identified malformation of cortical development. Although the association between PVNH and epilepsy is well known, controversy exists concerning the location of the epileptogenic area. Some evidence suggests an involvement of the neocortex. We recently demonstrated that(α-[11C]methyl-l-tryptophan (α-MTrp) positron emission tomography (PET) is a useful tool in the localization of the epileptogenic area in partial epilepsy, especially in patients with tuberous sclerosis or cortical dysplasia.Purpose:To determine whetherα-MTrp PET can detect neocortical changes in PVNH secondary to abnormal serotoninergic or kynurenine pathway metabolism.Methods:We studied four patients (mean age, 28 years; range, 23–36 years) with PVNH and intractable seizures by usingα-MTrp PET. Three had bilateral PVNH, and one had unilateral PVNH. The netα-MTrp uptake constant K* was calculated from the time–activity curve, and the input function estimated from the venous sinus radioactivity and blood samples. We compared the K* image of each patient with those of 21 normal control subjects (mean age, 35± 14 years) by using the statistical parametric mapping (SPM) program. We compared the location of increased uptake ofα-MTrp with the location of epileptic EEG abnormalities. We defined a significant cluster as a cluster with a height of p<0.005 and an extent threshold of 100. When no clusters met this definition, we examined again with a height of p<0.05.Results:In patient 1, EEG localized seizure onset in the right posterior temporal neocortex overlying the PVNH. PET revealed increasedα-MTrp uptake in the same area, as well as in the right frontotemporal and the left frontopolar areas. In patients 2 and 3,α-MTrp PET showed increased uptake in the areas of the additional seizure foci, but not the areas of seizure generation depicted on EEG. In patient 4 with unilateral PVNH, multifocal increases ofα-MTrp uptake were observed.α-MTrp PET did not show increased uptake in the PVNH itself in all the patients studied.Conclusions:In PVNH,α-MTrp PET detected abnormal metabolism of tryptophan in the neocortex. In some patients, the increase was seen in several neocortical areas but never included the heterotopic nodules. Based on our previous observations, this finding suggests epileptogenicity in the neocortex overlying PVNH. The pathologic mechanism of the abnormality underlying the widespread alteration of cortical tryptophan metabolism extending beyond the MRI-visible lesion remains unclear. Neocortical areas overlying PVNH display abnormal tryptophan metabolism. This abnormality is suggestive of a widespread epileptogenic lesion extending beyond the MRI-visible lesion. Proton Magnetic Resonance Spectroscopy of the Cerebrum in West Syndrome.Purpose:To evaluate cerebral dysfunction in West syndrome by using proton magnetic resonance spectroscopy (1H-MRS).Subjects and Methods:1H-MRS was performed in 17 patients with West syndrome (cryptogenic, seven patients; symptomatic, 10 patients). Informed consent for participation in this study was obtained from the families of all the patients. Magnetic resonance spectra of the parietal region were acquired by using a STEAM sequence (TR= 5,000 ms; TE= 18 ms). Evolutional changes of1H-MRS were observed for>2 years from the onset of West syndrome.Results:The ratios ofN-acetylaspartate (NAA) to creatine/phosphocreatine (Cr) increased with age in patients who showed cessation of spasms. Conversely, the ratios of NAA to Cr remained low or decreased with age in patients whose spasms were not controlled and in all the patients who showed severe developmental delay.Conclusions:From these findings, we speculate that West syndrome causes progressive neuronal damage.1H-MRS is a valuable tool to evaluate neuronal damage and to predict mental prognosis in West syndrome. [ABSTRACT FROM AUTHOR]

Tumour medical image segmentation plays a crucial role in clinical imaging diagnosis. Existing research has achieved good results, enabling the segmentation of three tumour regions in MRI brain tumour images. Existing models have limited focus on the brain tumour areas, and the long‐term dependency of features is weakened as the network depth increases, resulting in blurred edge segmentation of the targets. Additionally, considering the excellent segmentation performance of the Swin Transformer(Swin‐T) network, its network structure and parameters are relatively large. To address these limitations, this paper proposes a brain tumour segmentation framework with deep nuanced reasoning and Swin‐T. It is mainly composed of the backbone hybrid network (BHN) and the deep micro texture extraction module (DMTE). The BHN combines the Swin‐T stage with a new downsampling transition module called dual path feature reasoning (DPFR). The entire network framework is designed to extract global and local features from multi‐modal data, enabling it to capture and analyze deep texture features in multi‐modal images. It provides significant optimization over the Swin‐T network structure. Experimental results on the BraTS dataset demonstrate that the proposed method outperforms other state‐of‐the‐art models in terms of segmentation performance. The corresponding source codes are available at https://github.com/CurbUni/Brain‐Tumor‐Segmentation‐Framework‐with‐Deep‐Nuanced‐Reasoning‐and‐Swin‐T. [ABSTRACT FROM AUTHOR]

Automatic segmentation of renal tumours during renal cell carcinoma surgery can help doctors accurately locate the tumour region, protect the tissues and organs around the kidneys, enhance surgical efficiency, and reduce the possibility of leakage and misdiagnosis. However, since general polyp endoscopic image segmentation models have many problems when facing the task of renal tumour segmentation, there needs to be more research on the segmentation of endoscopic images of renal tumours. This paper proposes a multi‐scale dynamic segmentation kernel network for endoscopic image segmentation of kidney tumours. First, a spatial receptive field module is proposed to augment the feature information and improve the performance of the whole network. Second, an enhanced cross‐attention module is offered to attenuate the effect of a high‐similarity segmentation background. Finally, a multi‐scale dynamic segmentation kernel module is introduced to gradually refine the segmentation results from small to large sizes to obtain more accurate tumour boundaries. Extensive experiments on the established kidney tumour endoscopic dataset and publicly available endoscopic datasets show that this method exhibits enhanced performance and generalization capabilities compared to existing techniques. On this renal tumour dataset, MDSK‐Net achieved excellent results of 94.1% and 90.1% on mDice and mIoU. [ABSTRACT FROM AUTHOR]

Nail fold capillaroscopy is an important means of monitoring human health. Panoramic nail fold images improve the efficiency and accuracy of examinations. However, the acquisition of panoramic nail fold images is seldom studied and the problem manifests of few matching feature points when image stitching is used for such images. Therefore, this paper presents a method for panoramic nail fold image stitching based on vascular contour enhancement, which first solves the problem of few matching feature points by pre‐processing the image with contrast‐constrained adaptive histogram equalization (CLAHE), bilateral filtering (BF), and sharpening algorithms. The panoramic images of the nail fold blood vessels are then successfully stitched using the fast robust feature (SURF), fast library of approximate nearest neighbors (FLANN) and random sample agreement (RANSAC) algorithms. The experimental results show that the panoramic image stitched by this paper's algorithm has a field of view width of 7.43 mm, which improves the efficiency and accuracy of diagnosis. [ABSTRACT FROM AUTHOR]

Rapid changes in artificial intelligence (AI) have already impacted the medical field. While the use of AI to assist medical diagnosis has been documented, AI is continually expanding within medical applications. AI applications in sonography and their effect on ultrasound examinations and sonographers are still indeterminate. Six papers were reviewed to investigate AI applications and effects within the sonography field. These papers provided results on a range of ultrasound applications including breast, obstetric, skin lesions, carotid, blood flow and cardiac ultrasound imaging when combined with AI. In this narrative review, the application of AI demonstrated that accuracy and speed of clinical diagnosis can be improved. These six aspects of ultrasound imaging combined with AI demonstrated the potential to assist the operator and clinicians with a diagnosis in various applications and settings. Additionally, AI can be beneficial to telehealth applications for rural and remote areas where healthcare access can be limited. These changes are opportunities to assist with medical care to provide benefits to patients, sonographers and clinicians as AI transitions to a positive integration within many aspects of clinical care. [ABSTRACT FROM AUTHOR]

Medical image colouring techniques enable to colourize grey‐scale medical images for assisting doctors in diagnosis. Benefiting from the non‐linear fitting ability of deep neural network, deep medical image colouring techniques have achieved remarkable results. However, existing methods are still facing content and structure feature leakage, unrealistic colouring and poor scale invariability. Thus, this paper, proposes a Transformer‐based medical image colouring algorithm with long‐term dependency to avoid feature leakage of coloured images. To be specific, this method employs two different Transformer encoders to generate and encode feature sequences for grey‐scale medical images and real human colour slice images, respectively. Then, a novel multi‐layer Transformer decoder is used to stylize grey‐scale map image features based on the real physical colour feature sequences. For colouring images at different scales, we implement content‐ aware positional encoding with scale invariance and propose style‐aware positional encoding strategy to take realistic and physical colour prior into account. Extensive experimental results indicate our method has achieved better colourization effects than recent state‐of‐the‐art medical image colourization methods. [ABSTRACT FROM AUTHOR]

Lung segmentation is an essential step in a computer‐aided diagnosis system for chest radiographs. The lung parenchyma is first segmented in pulmonary computer‐aided diagnosis systems to remove the interference of non‐lung regions while increasing the effectiveness of the subsequent work. Nevertheless, most medical image segmentation methods nowadays use U‐Net and its variants. These variant networks perform poorly in segmentation to detect smaller structures and cannot accurately segment boundary regions. A multi‐interaction feature fusion network model based on Kiu‐Net is presented in this paper to address this problem. Specifically, U‐Net and Ki‐Net are first utilized to extract high‐level and detailed features of chest images, respectively. Then, cross‐residual fusion modules are employed in the network encoding stage to obtain complementary features from these two networks. Second, the global information module is introduced to guarantee the segmented region's integrity. Finally, in the network decoding stage, the multi‐interaction module is presented, which allows to interact with multiple kinds of information, such as global contextual information, branching features, and fused features, to obtain more practical information. The performance of the proposed model was assessed on both the Montgomery County (MC) and Shenzhen datasets, demonstrating its superiority over existing methods according to the experimental results. [ABSTRACT FROM AUTHOR]

Background Malignant melanoma and non-melanoma skin cancers are among the fastest increasing malignancies in many countries. With the help of new tools, such as teledermoscopy referrals between primary health care and dermatology clinics, the management of these patients could be made more efficient. Objective To evaluate the diagnostic agreement and interobserver concordance achieved when assessing referrals sent through a mobile teledermoscopic referral system as compared to referrals sent via the current paper-based system without images. Methods The referral information from 80 teledermoscopy referrals and 77 paper referrals were evaluated by six Swedish dermatologists. They were asked to answer questions about the probable diagnosis, the priority, and a management decision. Results Teledermoscopy generally resulted in higher diagnostic agreement, better triaging and more malignant tumours being booked directly to surgery. The largest difference between the referral methods was seen for invasive melanomas. Referrals for benign lesions were significantly more often correctly resent to primary health care with teledermoscopy. However, referrals for cases of melanoma in situ were also incorrectly resent five times. The interobserver concordance was moderate with both methods. Conclusion By adding clinical and dermoscopic images to referrals, the triage process for both benign and dangerous skin tumours can be improved. With teledermoscopy, patients with melanoma especially can receive treatment more swiftly. [ABSTRACT FROM AUTHOR]

Purpose: The discoid meniscus (DM) is distinguished by its thickened, disc‐shaped formation, which extends over the tibial plateau. The likelihood of developing osteoarthritis escalates if a DM tear remains undiagnosed and untreated. While DM tears can be diagnosed through arthroscopy, the high cost, invasive nature and limited availability of this procedure highlight the need for a better diagnostic modality. This study aims to determine the accuracy of magnetic resonance imaging (MRI) in diagnosing DM tears. Methods: A systematic review was conducted to gather articles with at least 10 cases on the comparison of MRI and arthroscopy as the gold standard for DM tear diagnosis. Stata and MetaDisc were used to conduct the statistical analysis. The quality of the included studies was evaluated using the Quality Assessment of Diagnostic Accuracy Studies‐2 tool. Results: Five diagnostic performance studies, derived from four original research papers involving 305 patients, were evaluated. Based on the pooled data, the sensitivity, specificity, diagnostic odds ratio, positive limit of detection and negative limit of detection were found to be 0.87 (95% confidence interval [CI], 0.82–0.91) and 0.84 (95% CI, 0.75–0.90), 32.88 (95% CI, 5.81–186.02), 5.22 (95% CI, 1.71–15.92) and 0.18 (95% CI, 0.09–0.38), respectively. A hierarchical summary receiver operating characteristic curve with an area under the curve of 0.92 was generated. Conclusion: This meta‐analysis demonstrates that MRI has excellent sensitivity and specificity for diagnosing DM tears. Despite its lower accuracy compared to arthroscopy, MRI can be used in symptomatic patients as a viable alternative to arthroscopy due to its inherent advantages. Level of Evidence: Level IV. [ABSTRACT FROM AUTHOR]

Lesion segmentation is a fundamental task in medical image processing, often facing the challenge of subtle lesions. It is important to detect these lesions, even though they can be difficult to identify. Convolutional neural networks, an effective method in medical image processing, often ignore the relationship between lesions, leading to topological errors during training. To tackle topological errors, move is made from pixel‐level to hypergraph representations. Hypergraphs can model lesions as vertices connected by hyperedges, capturing the topology between lesions. This paper introduces a novel dynamic hypergraph learning strategy called DHLS. DHLS allows for the dynamic construction of hypergraphs contingent upon input vertex variations. A hypergraph global‐aware segmentation network, termed HGSNet, is further proposed. HGSNet can capture the key high‐order structure information, which is able to enhance global topology expression. Additionally, a composite loss function is introduced. The function emphasizes the global aspect and the boundary of segmentation regions. The experimental setup compared HGSNet with other advanced models on medical image datasets from various organs. The results demonstrate that HGSNet outperforms other models and achieves state‐of‐the‐art performance on three public datasets. [ABSTRACT FROM AUTHOR]

Purpose: The aim of this study is to develop a deep learning model capable of discriminating between pancreatic plasma cystic neoplasms (SCN) and mucinous cystic neoplasms (MCN) by leveraging patient‐specific clinical features and imaging outcomes. The intent is to offer valuable diagnostic support to clinicians in their clinical decision‐making processes. Methods: The construction of the deep learning model involved utilizing a dataset comprising abdominal magnetic resonance T2‐weighted images obtained from patients diagnosed with pancreatic cystic tumors at Changhai Hospital. The dataset comprised 207 patients with SCN and 93 patients with MCN, encompassing a total of 1761 images. The foundational architecture employed was DenseNet‐161, augmented with a hybrid attention mechanism module. This integration aimed to enhance the network's attentiveness toward channel and spatial features, thereby amplifying its performance. Additionally, clinical features were incorporated prior to the fully connected layer of the network to actively contribute to subsequent decision‐making processes, thereby significantly augmenting the model's classification accuracy. The final patient classification outcomes were derived using a joint voting methodology, and the model underwent comprehensive evaluation. Results: Using the five‐fold cross validation, the accuracy of the classification model in this paper was 92.44%, with an AUC value of 0.971, a precision rate of 0.956, a recall rate of 0.919, a specificity of 0.933, and an F1‐score of 0.936. Conclusion: This study demonstrates that the DenseNet model, which incorporates hybrid attention mechanisms and clinical features, is effective for distinguishing between SCN and MCN, and has potential application for the diagnosis of pancreatic cystic tumors in clinical practice. [ABSTRACT FROM AUTHOR]

Introduction: While there are many papers on maternal and foetal radiation doses from computed tomography pulmonary angiography (CTPA) and ventilation/perfusion (V/Q) lung scanning examinations for diagnosing pulmonary embolism in pregnant patients, few have used clinical data to examine the patient lifetime attributable risk (LAR) of different cancer types. This paper aims to estimate the cancer risk from maternal radiation doses from CTPA and V/Q examinations and associated foetal doses. Methods: Dosimetric data were determined for 267 pregnant patients who received CTPA and/or V/Q examinations over 8 years. Organ and foetal doses were determined using software allowing patient size variations for CTPA and using two different activity‐to‐organ dose conversion methods for V/Q scans. The LAR of cancer incidence was estimated using International Commission on Radiological Protection (ICRP) modelling including estimates of detriment. Results: Estimated total cancer incidence was 23 and 22 cases per 100,000 for CTPA and V/Q examinations, respectively, with detriment estimates of 18 and 20 cases. Cancer incidence was evenly divided between lung and breast cancer for CTPA with lung cancer being 80% of all cancer for V/Q. The median foetal doses were 0.03 mSv for CTPA and 0.29 mSv for V/Q. Significant differences in estimated foetal dose for V/Q scans were obtained by the two different methods used. The differences in dose between the modes of CTPA scan acquisition highlight the importance of optimisation. Conclusion: Maternal cancer incidence and detriment were remarkably similar for each examination. Optimisation of examinations is critical for low‐dose outcomes, particularly for CTPA examination. [ABSTRACT FROM AUTHOR]

The article presents abstracts on medical topics which includes innovation of endoscopic medicine and medical care, magnifying endoscopy with narrow band imaging, and a case of russell body gastritis.

Editorial. Discusses the European Federation of Neurological Societies (EFNS) guideline papers on neurological rehabilitation, acute neurological stroke units and neuroimaging in Europe. Task forces that produce the consensus guidelines of the EFNS; Recruitment of support for the publication of many guideline papers in a supplementary issue of the "European Journal of Neurology"; Translation of the guideline papers into the various languages of Europe.

Medical image segmentation is a key step in medical image analysis. The small differences in the background and foreground of medical images and the small size of most medical data sets make medical segmentation difficult. This paper uses a global‐local training strategy to train the network. In the global structure, ResNest is used as the backbone of the network, and parallel decoders are added to aggregate features, as well as gated axial attention to adapt to small datasets. In the local structure, the extraction of image details is accomplished by dividing the images into equal patches of the same size. To evaluate the performance of the model, qualitative and quantitative comparisons were performed on five datasets, Kvasir‐SEG, CVC‐ColonDB, CVC‐ClinicDB, CVC‐300, and ETIS‐LaribPolypDB, and the segmentation results were significantly better than the current mainstream polyp segmentation methods. The results show that the model has better segmentation performance and generalization ability. [ABSTRACT FROM AUTHOR]

Background: Dynamic magnetic resonance imaging (DMRI) is an essential medical imaging technique, but the slow data acquisition process limits its further development. Purpose: By exploiting the inherent spatio‐temporal correlation of MR images, low‐rank tensor based methods have been developed to accelerate imaging. However, the tensor rank used by these methods is defined by an unbalanced matricization scheme, which cannot capture the global correlation of DMR data efficiently during the reconstruction process. Methods: In this paper, an effective reconstruction model is proposed to achieve accurate reconstruction by using the tensor train (TT) rank defined by a well‐balanced matricization scheme to exploit the hidden correlation of DMR data and combining sparsity. Meanwhile, the ket augmentation (KA) technology is introduced to preprocess the DMR data into a higher‐order tensor through block structure addressing, which further improves the ability of TT rank to explore the local information of the image. In order to solve the proposed model, the alternating direction method of multipliers (ADMM) is used to decompose the optimization problem into several unconstrained subproblems. Results: The performance of the proposed method was validated on the 3D DMR image dataset by using different sampling trajectories and sampling rates. Extensive numerical experiments demonstrate that the reconstruction quality of the proposed method is superior to several state‐of‐the‐art reconstruction methods. Conclusions: The proposed method successfully utilizes the TT rank to explore the global correlation of DMR images, enabling more detailed information of the image to be captured. Besides, with the sparse priors, the proposed method can further improve the overall reconstruction quality for highly undersampled MR images. [ABSTRACT FROM AUTHOR]

In this paper, a method of stroke‐based rendering is proposed for image representation and reconstruction. The proposed method involves compositing a set of ellipses that greatly vary in location, size, rotation angle, color, and opacity. This study proves that alpha compositing is differentiable if a two‐dimensional Gaussian function is used to draw a solid ellipse. The gradient method can then be employed for automatically identifying the parameters of each ellipse such that the difference between the input image and the composited image is minimized. Experimental results indicate that the proposed method can represent various types of images including portraits, landscapes, buildings, street scenes, artificial objects, medical images etc. The proposed method can particularly render the most details and significant features of an input image with fewer strokes compared to other stroke‐based rendering algorithms. This study also demonstrates that the proposed method can be applied in painting style simulation and sparse‐view computed tomography imaging. [ABSTRACT FROM AUTHOR]

Deep learning image segmentation has become an important field of interest in recent years, especially when it comes to medical images. Segmentation of medical image modalities such as magnetic resonance imaging (MRI) and computed tomography (CT) can benefit diagnosis accuracy, speed up diagnosis process, and decrease workload. The most famously used deep learning models in the medical image segmentation are the UNET‐based models, which have been repeatedly proven to provide a high percentage of accuracy in medical image segmentation. But, most of the available datasets contain a single modality and thus are not big enough to train complex architectures. Lately, it has been shown that using multiple modalities with multiple streams architectures can provide higher accuracy more than single modality with a single stream architecture. In this paper, the benefits of dual‐stream and triple‐stream architectures are demonstrated when processing multiple modalities. This work shows that dual stream can achieve dice of 0.97 on CT images and 0.89 on MRI images, while in triple stream architectures can achieve dice of 0.97 on CT images and 0.96 on MRI images. To the best of our knowledge, these are the best results to date. [ABSTRACT FROM AUTHOR]

Background: The diagnosis of basal cell carcinoma (BCC) is based on clinical and dermoscopical features. In uncertain cases, innovative imaging techniques, such as reflectance confocal microscopy (RCM) and optical coherence tomography (OCT), have been used. The main limitation of these techniques is the inability to study deep margins. HFUS (high‐frequency ultrasound) and the most recent UHFUS (ultra‐high‐frequency ultrasound) have been used in various applications in dermatology, but they are not yet routinely used in the diagnosis of BCC. A key point in clinical practice is to find an imaging technique that can help to reduce post‐surgical recurrences with a careful presurgical assessment of the lesional margins. This technique should show high sensitivity, specificity, reproducibility and simplicity of execution. This concept is very important for the optimal management of patients who are often elderly and have many comorbidities. The aim of the paper is to analyse the characteristics of current imaging techniques and the studies in the literature on this topic. Materials and methods: The authors independently searched the MEDLINE, PubMed, Embase, Scopus, ScienceDirect and Cochrane Library databases for studies looking for non‐invasive imaging techniques for the presurgical margin assessment of BCC. Results: Preoperative study of the BCC subtype can help to obtain a complete excision with free margins. Different non‐invasive imaging techniques have been studied for in vivo evaluation of tumour margins, comparing the histologic evaluation with a radical surgery. The possibility to study the lateral and deep margins would allow a reduction of recurrences and sparing of healthy tissue. Conclusion: HFUS and UHFUS represent the most promising, non‐invasive techniques for the pre‐operative study of BCC facilitating the characterization of vascularization, deep lateral margins and high‐risk subtypes, although they are limited by insufficient literature unlike RCM and OCT. [ABSTRACT FROM AUTHOR]

Motivation: Medical image analysis involves a series of tasks used to assist physicians in qualitative and quantitative analyses of lesions or anatomical structures which can significantly improve the accuracy and reliability of medical diagnoses and prognoses. Traditionally, these tedious tasks were finished by experienced physicians or medical physicists and were marred with two major problems, low efficiency and bias. In the past decade, many machine learning methods have been applied to accelerate and automate the image analysis process. Compared to the enormous deployments of supervised and unsupervised learning models, attempts to use reinforcement learning in medical image analysis are still scarce. We hope that this review article could serve as the stepping stone for related research in the future. Significance: We found that although reinforcement learning has gradually gained momentum in recent years, many researchers in the medical analysis field still find it hard to understand and deploy in clinical settings. One possible cause is a lack of well‐organized review articles intended for readers without professional computer science backgrounds. Rather than to provide a comprehensive list of all reinforcement learning models applied in medical image analysis, the aim of this review is to help the readers formulate and solve their medical image analysis research through the lens of reinforcement learning. Approach & Results: We selected published articles from Google Scholar and PubMed. Considering the scarcity of related articles, we also included some outstanding newest preprints. The papers were carefully reviewed and categorized according to the type of image analysis task. In this article, we first reviewed the basic concepts and popular models of reinforcement learning. Then, we explored the applications of reinforcement learning models in medical image analysis. Finally, we concluded the article by discussing the reviewed reinforcement learning approaches' limitations and possible future improvements. [ABSTRACT FROM AUTHOR]

The article focuses on the study conducted by Ceri Sherlock and colleagues concerning the use of magnetic resonance imaging (MRI) to evaluate foot pain in standing horses. MRI revealed lesions in lame horses which included fluid distention of the distal interphalangeal joint, changes to the navicular bone and deep digital flexor tendonitis.

This paper proposes a robust watermarking method against high‐density salt and pepper noise attacks. Automatic region of interest (ROI) detection, embedding encoded data, removing different densities of noise, data extraction by omitting, and labeling the noisy pixels of Region of Non‐Interest (RONI), and decoding the extracted data using ROI pixel information as a key, are various steps of the presented scheme. The automatic ROI detection method separates the RONI from ROI with four vertices of the smallest rectangle, for the embedding process. The encoded watermark data is embedded into the least significant bits of RONI in four neighbour pixels. Adaptive Removal of high‐density Salt and pepper Noise method can enhance image quality and reduce the effect of salt and pepper noise attacks. The embedded information is preserved from destruction if the host image is impaired through the power of robustness. The best results are obtained through the action of extracting the watermark from RONI pixels, utilizing the same ROI detection method. Omitting and labeling the noisy pixels of the RONI will ensure healthy extracted watermark data, leading to decreased Bit Error Rate (BER) values. Finally, these data are interpreted using the key of ROI pixels, and the watermark data is decoded and retrieved. Due to salt and pepper noise obliterating pixel bits and their corresponding transform coefficients in the transform domain, the spatial domain is employed to enhance robustness against such attacks. The results show the high performance of the presented scheme. The average BER value for five MRI databases in a 97% salt and pepper noise attack is 38.6. [ABSTRACT FROM AUTHOR]

Objective: Late‐onset GM2 gangliosidosis (LOGG) subtypes late‐onset Tay‐Sachs (LOTS) and Sandhoff disease (LOSD) are ultra‐rare neurodegenerative lysosomal storage disorders presenting with weakness, ataxia, and neuropsychiatric symptoms. Previous studies considered LOTS and LOSD clinically indistinguishable; recent studies have challenged this. We performed a scoping review to ascertain whether imaging and clinical features may differentiate these diseases. Methods: We examined MEDLINE/non‐MEDLINE databases up to May 2022. Articles reporting brain imaging findings in genetically/enzymatically confirmed LOGG, symptom onset at age ≥ 10 years (or evaluated at least once ≥18 years) were included, yielding 170 LOGG patients (LOTS = 127, LOSD = 43) across 68 papers. We compared LOTS versus LOSD and performed regression analyses. Results were corrected for multiple comparisons. Results: Age of onset was lower in LOTS versus LOSD (17.9 ± 8.2 vs. 23.9 ± 14.4 years, p = 0.017), although disease duration was similar (p = 0.34). LOTS more commonly had psychosis/bipolar symptoms (35.0% vs. 9.30%, p = 0.011) but less frequent swallowing problems (4.10% vs. 18.60%, p = 0.041). Cerebellar atrophy was more common in LOTS (89.0%) versus LOSD (60.5%), p < 0.0001, with more severe atrophy in LOTS (p = 0.0005). Brainstem atrophy was documented only in LOTS (14.2%). Independent predictors of LOTS versus LOSD (odds ratio [95% confidence interval]) included the presence of psychosis/bipolar symptoms (4.95 [1.59–19.52], p = 0.011), no swallowing symptoms (0.16 [0.036–0.64], p = 0.011), and cerebellar atrophy (5.81 [2.10–17.08], p = 0.0009). Lower age of onset (0.96 [0.93–1.00], p = 0.075) and tremor (2.50 [0.94–7.43], p = 0.078) were marginally statistically significant but felt relevant to include in the model. Interpretation: These data suggest significant differences in symptomatology, disease course, and imaging findings between LOTS and LOSD. [ABSTRACT FROM AUTHOR]

Currently, the clinical diagnosis of burn depth primarily relies on physicians' judgements based on patients' symptoms and physical signs, particularly the morphological characteristics of the wound. This method highly depends on individual doctors' clinical experience, proving challenging for less experienced or primary care physicians, with results often varying from one practitioner to another. Therefore, scholars have been exploring an objective and quantitative auxiliary examination technique to enhance the accuracy and consistency of burn depth diagnosis. Non‐invasive medical imaging technology, with its significant advantages in examining tissue surface morphology, blood flow in deep and changes in structure and composition, has become a hot topic in burn diagnostic technology research in recent years. This paper reviews various non‐invasive medical imaging technologies that have shown potential in burn depth diagnosis. These technologies are summarized and synthesized in terms of imaging principles, current research status, advantages and limitations, aiming to provide a reference for clinical application or research for burn specialists. [ABSTRACT FROM AUTHOR]

In recent years, convolutional neural networks (CNN)‐based automatic segmentation of medical images has become one of the hot topics in clinical disease diagnosis. It is still a challenging task to improve the segmentation accuracy of the network model with the large variation of pathological regions in different patients and the fuzzy boundary of pathological regions. A Dual‐path Multi‐scale Attention Guided network (DMAGNet) for medical image segmentation is proposed in this paper. First, the Dual‐path Multi‐scale Attention Fusion Module (DMAF) is proposed as a novel skip connection strategy, which is applied to encode semantic dependencies between high‐level and low‐level channels. Second, the Multi‐scale Normalized Channel Attention Module (MNCA) based on the atrous convolution, normalization channel attention mechanism, and the Depthwise Separable Convolutions (DSConv) is developed to strengthen dependencies between channels. Finally, the encoder–decoder backbone employs the DSConv, as well as the pretrained Resnet34 block is combined in the encoder part to further improve the backbone network performance. Comprehensive experiments on brain, lung, and liver segmentation tasks show that the proposed DMAGNet outperforms the original U‐Net method and other advanced methods. First, the Dual‐path Multi‐scale Attention Fusion Module (DMAF) is proposed as a novel skip connection strategy, which is applied to encode semantic dependencies between high‐level and low‐level channels. Second, the Multi‐scale Normalized Channel Attention Module (MNCA) based on the atrous convolution, normalization channel attention mechanism, and the Depthwise Separable Convolutions (DSConv) is developed to strengthen dependencies between channels. Finally, the encoder–decoder backbone employs the DSConv, as well as the pretrained Resnet34 block is combined in the encoder part to further improve the backbone network performance. Comprehensive experiments on brain, lung, and liver segmentation tasks show that the proposed DMAGNet outperforms the original U‐Net method and other advanced methods. [ABSTRACT FROM AUTHOR]

This paper aggregates and summarizes studies that use paleoradiology techniques in the analysis of pediatric remains. Building on these findings, we offer evidence‐based, best‐practice protocols for the use of radiographic techniques in the assessment of pediatric remains from archaeological contexts. We also provide a recommended reporting worksheet for recording findings in a standardized way. After reviewing studies of pediatric remains that used radiographic techniques, with a focus on three major bioarchaeological journals, PubMed, and the Yearbook of Mummy Studies, we identified areas for improvement in the acquisition and reporting of paleoradiographic findings in pediatric remains. Although radiological techniques are used with increasing frequency in the assessment of pediatric remains, no standardized pediatric imaging protocols presently exist. We combine insights gained from existing literature with current clinical imaging protocols in order to provide best‐practice protocols for the acquisition and reporting of radiographic findings from archeological contexts, specific to pediatric remains. This is, as far as we know, the first proposal of imaging protocols specifically tailored for the assessment of pediatric remains from bioarchaeological contexts. Recognizing the limitations faced by archaeologists around the use of imaging technologies in their fieldwork (including lack of funding, equipment access, and permit acquisition, among others), this review is offered not to criticize previous work, but in the hope that the need for appropriate radiographic study can be incorporated into research plans and funding applications from the beginning, and that granting agencies will encourage and support these types of analyses in skeletal studies. It holds implications for how paleoradiology techniques might be systematically used and applied to pediatric remains from multiple time periods, across the world. Our proposed imaging acquisition and reporting protocols are primarily based on English‐language sources. Further assessment of the proposed protocols, following systematic application in multiple contexts, is recommended. [ABSTRACT FROM AUTHOR]

Based on literature, intensity‐modulated radiation therapy (IMRT) provides less related toxicity compared with conventional 2D/3D‐RT with no impact on oncological outcomes for oropharyngeal cancer. The aim of this systematic review and meta‐analysis is to assess whether IMRT might provide similar clinical outcomes with reduced related toxicity in comparison with conventional 2D/3D RT in patients treated for clinically advanced oropharyngeal cancer (OPC). Inclusion criteria for paper selection included: squamous OPC patients, treatment performed by concomitant CRT or RT alone, four treatment performed for curative intent, and presence of clinical outcome of interest, namely, overall survival (OS) and disease‐free survival (DFS) and full paper available in English. Acute and late toxicities were retrieved together with OS and DFS. Crude relative risk estimates of relapse and death comparing 2D/3D‐RT versus IMRT were calculated from tabular data, extracting events at 2–3 years of follow‐up. Eight studies were selected. Six of them were included in the meta‐analysis considering summary relative risk. Considering both acute and late toxicities, the considered studies evidenced advantages for IMRT populations, with the 2D/3D‐RT population showing higher frequencies than the IMRT one. No statistical difference between IMRT and 2D/3D‐RT in terms of death (SRR = 0.93, 95% CI: 0.83–1.04 with no heterogeneity I2 = 0%) and relapse (SRR = 0.92, 95% CI: 0.83–1.03, with no heterogeneity I2 = 0%) was found. Results of our study suggest the improvement in the therapeutic index with IMRT with evidenced reduced toxicity without any worsening in clinical outcome when compared to 2D/3DCRT. [ABSTRACT FROM AUTHOR]

Background: Line‐field confocal optical coherence tomography (LC‐OCT) is an emerging diagnostic tool with imaging depth reaching ~400 μm and a novel three‐dimensional (3D) cube providing cellular resolution. As far as we are aware, there are only a limited number of papers that have reported diagnostic criteria for melanocytic lesions using this technique, and none of them have been multicentric. Objectives: Our aim was to establish the diagnostic criteria for melanocytic lesions using LC‐OCT and identify the most significant architectural and cytologic features associated with malignancy. Methods: A retrospective evaluation of 80 consecutive melanocytic lesions from a prospective multicentric data set spanning three European centres was conducted. We excluded facial, acral and mucosal lesions from the study. Dermoscopic and LC‐OCT images were evaluated by a consensus of four observers. Multivariate logistic regression with backward elimination was employed. Results: The main melanoma diagnostic criteria include detecting >10 pagetoid cells in 3D acquisition, irregular 3D epidermal architecture, disrupted dermoepidermal junction (DEJ) and clefting. Significant risk factors were irregular 3D epidermal architecture, >10 pagetoid cells, dendritic cells at DEJ without underlying inflammation. Novel malignancy criteria in vertical view were DEJ disruption and clefting around atypical melanocyte nests. Exclusive melanoma features were epidermal nests, epidermal consumption, dense dermal nests with atypia. Protective features in the absence of any malignancy indicators were DEJ ring pattern, cobblestone, elongated rete ridges (vertical), well‐defined DEJ and wave pattern (vertical). Conclusions: A series of diagnostic criteria for the identification of melanocytic lesions with LC‐OCT have been established. Validation of these criteria in clinical practice through future studies is essential to further establish their utility. [ABSTRACT FROM AUTHOR]

Accurate segmentation of brain tumors from magnetic resonance imaging (MRI) is crucial for diagnosis, treatment planning, and monitoring of patients with neurological disorders. This paper proposes an approach for brain tumor segmentation employing a cascaded architecture integrating L‐Net and W‐Net deep learning models. The proposed cascaded model leverages the strengths of U‐Net as a baseline model to enhance the precision and robustness of the segmentation process. In the proposed framework, the L‐Net excels in capturing the mask, while the W‐Net focuses on fine‐grained features and spatial information to discern complex tumor boundaries. The cascaded configuration allows for a seamless integration of these complementary models, enhancing the overall segmentation performance. To evaluate the proposed approach, extensive experiments were conducted on the datasets of BraTs and SMS Medical College comprising multi‐modal MRI images. The experimental results demonstrate that the cascaded L‐Net and W‐Net model consistently outperforms individual models and other state‐of‐the‐art segmentation methods. The performance metrics such as the Dice Similarity Coefficient value achieved indicate high segmentation accuracy, while Sensitivity and Specificity metrics showcase the model's ability to correctly identify tumor regions and exclude healthy tissues. Moreover, the low Hausdorff Distance values confirm the model's capability to accurately delineate tumor boundaries. In comparison with the existing methods, the proposed cascaded scheme leverages the strengths of each network, leading to superior performance compared to existing works of literature. [ABSTRACT FROM AUTHOR]

The detection of polyps plays a significant role in colonoscopy examinations, cancer diagnosis, and early patient treatment. However, due to the diversity in the size, color, and shape of polyps, as well as the presence of low image contrast with the surrounding mucosa and fuzzy boundaries, precise polyp segmentation remains a challenging task. Furthermore, this task requires excellent real‐time performance to promptly and efficiently present predictive results to doctors during colonoscopy examinations. To address these challenges, a novel neural network, called CafeNet, is proposed in this paper for rapid and accurate polyp segmentation. CafeNet utilizes newly designed multi‐scale context aggregation (MCA) modules to adapt to the extensive variations in polyp morphology, covering small to large polyps by fusing simplified global contextual information and local information at different scales. Additionally, the proposed network utilizes newly designed multi‐level foreground enhancement (MFE) modules to compute and extract differential features between adjacent layers and uses the prediction output from the adjacent lower‐layer decoder as a guidance map to enhance the polyp information extracted by the upper‐layer encoder, thereby improving the contrast between polyps and the background. The polyp segmentation performance of the proposed CafeNet network is evaluated on five benchmark public datasets using six evaluation metrics. Experimental results indicate that CafeNet outperforms the state‐of‐the‐art networks, while also exhibiting the least parameter count along with excellent real‐time operational speed. [ABSTRACT FROM AUTHOR]

Accurately and rapidly segmenting the prostate in transrectal ultrasound (TRUS) images remains challenging due to the complex semantic information in ultrasound images. The paper discusses a cross‐layer connection with SegFormer attention U‐Net for efficient TRUS image segmentation. The SegFormer framework is enhanced by reducing model parameters and complexity without sacrificing accuracy. We introduce layer‐skipping connections for precise positioning and combine local context with global dependency for superior feature recognition. The decoder is improved with Multi‐layer Perceptual Convolutional Block Attention Module (MCBAM) for better upsampling and reduced information loss, leading to increased accuracy. The experimental results show that compared with classic or popular deep learning methods, this method has better segmentation performance, with the dice similarity coefficient (DSC) of 97.55% and the intersection over union (IoU) of 95.23%. This approach balances encoder efficiency, multi‐layer information flow, and parameter reduction. [ABSTRACT FROM AUTHOR]

This paper studies a tensor factor model that augments samples from multiple classes. The nuisance common patterns shared across classes are characterised by pervasive noises, and the patterns that distinguish different classes are represented by class‐specific components. Additionally, the pervasive component is modelled by the production of a low‐rank tensor latent factor and several factor loading matrices. This augmented tensor factor model can be expanded to a series of matrix variate tensor factor models and estimated using principal component analysis. The ranks of latent factors are estimated using a modified eigen‐ratio method. The proposed estimators have fast convergence rates and enjoy the blessing of dimensionality. The proposed factor model is applied to address the challenge of overlapping issues in image classification through a factor adjustment procedure. The procedure is shown to be powerful through synthetic experiments and an application to COVID‐19 pneumonia diagnosis from frontal chest X‐ray images. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) is a ubiquitous medical imaging technology with applications in disease diagnostics, intervention, and treatment planning. Accurate MRI segmentation is critical for diagnosing abnormalities, monitoring diseases, and deciding on a course of treatment. With the advent of advanced deep learning frameworks, fully automated and accurate MRI segmentation is advancing. Traditional supervised deep learning techniques have advanced tremendously, reaching clinical‐level accuracy in the field of segmentation. However, these algorithms still require a large amount of annotated data, which is oftentimes unavailable or impractical. One way to circumvent this issue is to utilize algorithms that exploit a limited amount of labeled data. This paper aims to review such state‐of‐the‐art algorithms that use a limited number of annotated samples. We explain the fundamental principles of self‐supervised learning, generative models, few‐shot learning, and semi‐supervised learning and summarize their applications in cardiac, abdomen, and brain MRI segmentation. Throughout this review, we highlight algorithms that can be employed based on the quantity of annotated data available. We also present a comprehensive list of notable publicly available MRI segmentation datasets. To conclude, we discuss possible future directions of the field—including emerging algorithms, such as contrastive language‐image pretraining, and potential combinations across the methods discussed—that can further increase the efficacy of image segmentation with limited labels. [ABSTRACT FROM AUTHOR]

Medical imaging is widely used in the diagnosis and treatment of cancer, and artificial intelligence (AI) has achieved tremendous success in medical image analysis. This paper reviews AI‐based tumor subregion analysis in medical imaging. We summarize the latest AI‐based methods for tumor subregion analysis and their applications. Specifically, we categorize the AI‐based methods by training strategy: supervised and unsupervised. A detailed review of each category is presented, highlighting important contributions and achievements. Specific challenges and potential applications of AI in tumor subregion analysis are discussed. [ABSTRACT FROM AUTHOR]

A computer‐aided detection (CADe) scheme, relying on a large number of high‐quality images with annotations, could help radiologists effectively detect lung nodules. However, such medical data are generally difficult to obtain. To address this issue, this paper proposes a novel method based on a conditional generative adversarial network (CGAN) to generate new samples for data augmentation (DA). This method employs a 3D CGAN based on a squeeze‐and‐excitation mechanism and residual learning to synthesize realistic and diverse lung nodules in chest computed tomography (CT) images to improve the performance of the CADe system. To evaluate the proposed method, this paper uses synthetic samples for DA to train the lung nodule detection network. The results indicate that these synthetic samples, which cover a part of the data distribution unfilled by the original data, can boost the overall performance of the nodule detection network at fixed false positive (FP) rates. [ABSTRACT FROM AUTHOR]