A deep learning fusion model for accurate classification of brain tumours in Magnetic Resonance images

Detecting brain tumours is complex due to the natural variation in their location, shape, and intensity in images. While having accurate detection and segmentation of brain tumours would be beneficial, current methods still need to solve this problem despite the numerous available approaches. Precise analysis of Magnetic Resonance Imaging (MRI) is crucial for detecting, segmenting, and classifying brain tumours in medical diagnostics. Magnetic Resonance Imaging is a vital component in medical diagnosis, and it requires precise, efficient, careful, efficient, and reliable image analysis techniques. The authors developed a Deep Learning (DL) fusion model to classify brain tumours reliably. Deep Learning models require large amounts of training data to achieve good results, so the researchers utilised data augmentation techniques to increase the dataset size for training models. VGG16, ResNet50, and convolutional deep belief networks networks extracted deep features from MRI images. Softmax was used as the classifier, and the training set was supplemented with intentionally created MRI images of brain tumours in addition to the genuine ones. The features of two DL models were combined in the proposed model to generate a fusion model, which significantly increased classification accuracy. An openly accessible dataset from the internet was used to test the model's performance, and the experimental results showed that the proposed fusion model achieved a classification accuracy of 98.98%. Finally, the results were compared with existing methods, and the proposed model outperformed them significantly.

Quantification of spatial expansion of cervical tumours using Magnetic Resonance Imaging

Objective This research study aims to analyze existing principles regarding the processing and analysis of imaging data and apply these concepts to the setting of the magnetic resonance imaging arena with a main focus on its use in cervical tumours. Any possible models will then be formulated,with the possibility of testing these theories in an experimental study that would involve actual patient data collected from a collaborating healthcare institution. The applicability of quantification of spatial expansion will also be applied to specific cancers and medical conditions that commonly make use of the noninvasive feature of magnetic resonance imaging. Conclusion Diffusionweighted magnetic resonance imaging can be employed in examining the cellular dynamics of tumours as it assists in the localization,as well as displacement of particular cellular structures within a particular volume.

Preoperative and Postoperative Diffusion Tensor Imaging in Patients with Extra-Axial Lesions at the Frontal or Temporal Regions of the Brain and Their Correlations with Neuropsychological Outcomes

The underlying changes in the neuronal connectivity adjacent to brain tumours cannot always be depicted by conventional MR imaging. The hypothesis of this study was that preoperative neuropsychological deficits were associated with impairment of diffusivity in association fibre bundles. Hence, we investigated the potential of combined diffusion tensor imaging (DTI) fibre tracking and fractional anisotropy (FA) values of the fibres to determine changes in association fibres and their correlation to neuropsychological scores. Our study consisted of eighteen patients with extra-axial brain tumours in areas adjacent to the frontal and temporal lobes. They were assessed pre- and postoperatively with DTI and neuropsychological assessments. MR examinations were performed on a 3T-scanner. FA values were calculated for the uncinate fasciculus, arcuate fasciculus, superior fronto-occipital fasciculus, inferior fronto-occipital fasciculus and corticospinal tracts ipsilateral and contralateral to the tumor. These values were compared with neuropsychological scores for language, memory and attention. The analysis revealed marked differences in pre- and post-excision of the tumor in both FA values and neuropsychological scores. Quantitative DTI was able to show significant differences in diffusivity of the association fibres before and after the surgery (P < 0.05). The additional use of DTI-fibre integrity and neuropsychological tests may aid in prognostication and decision making prior to surgery.

Multimodal Imaging with 3D-Holograms for Preoperative Planning in Pediatric Cardiac Surgery:A Unique Case Report

Multimodal imaging,including augmented or mixed reality,transforms the physicians’interaction with clinical imaging,allowing more accurate data interpretation,better spatial resolution,and depth perception of the patient’s anatomy.We successfully overlay 3D holographic visualization to magnetic resonance imaging images for preoperative decision making of a complex case of cardiac tumour in a 7-year-old girl.

Imaged guided surgery during arteriovenous malformation of gastrointestinal stromal tumor using hyperspectral and indocyanine green visualization techniques:A case report

BACKGROUND This case report demonstrates the simultaneous development of a gastrointestinal stromal tumour(GIST)with arteriovenous malformations(AVMs)within the jejunal mesentery.A 74-year-old male presented to the department of surgery at our institution with a one-month history of abdominal pain.Contrast-enhanced computed tomography revealed an AVM.During exploratory laparotomy,hyperspectral imaging(HSI)and indocyanine green(ICG)fluorescence were used to evaluate the extent of the tumour and determine the resection margins.Intraoperative imaging confirmed AVM,while histopathological evaluation showed an epithelioid,partially spindle cell GIST.CASE SUMMARY This is the first case reporting the use of HSI and ICG to image GIST intermingled with an AVM.The resection margins were planned using intraoperative analysis of additional optical data.Image-guided surgery enhances the clinician’s knowledge of tissue composition and facilitates tissue differentiation.CONCLUSION Since image-guided surgery is safe,this procedure should increase in popularity among the next generation of surgeons as it is associated with better postoperative outcomes.

不同手术径路治疗咽旁间隙肿瘤的回顾性分析

目的总结并分析咽旁间隙肿瘤的临床特征、手术径路及预后,探讨不同手术径路治疗咽旁间隙肿瘤的优缺点。方法回顾性分析2018年9月~2022年10月安徽医科大学第一附属医院收住的44例咽旁间隙肿瘤患者的临床资料,所有患者术前都行CT和(或)MRI检查,所采用的手术径路如下:下颌骨劈开入路1例,经颈侧入路19例,经颈-腮腺入路7例,内镜辅助颈外入路1例,经口-颈侧联合入路2例,内镜下经口入路12例,经鼻内镜入路2例。结果术后组织病理类型丰富,其中良性肿瘤41例(93.2%),恶性肿瘤3例(6.8%),术后发生并发症13例,最常见的并发症为神经受损引起的症状;良性肿瘤随访8~56个月,其中1例神经鞘瘤术后复发两次,三次手术后治愈;恶性肿瘤随访18~54个月,2例术后行辅助放化疗,其中1例死亡;1例规律随访,未见复发。结论咽旁间隙是一个复杂的解剖区域,原发性咽旁间隙肿瘤绝大部分为良性肿瘤,早期多无特异性症状,病理类型多样。治疗上首选手术切除,术前的影像学检查对诊断是必需的,可以根据肿瘤的大小、形态、解剖位置以及与血管的关系选择等合适的手术径路完整切除肿瘤,总体预后较好。

基于深度学习的乳腺肿瘤良恶性自动诊断

超声是目前诊断乳腺肿瘤的常用手段之一。针对超声中良恶性肿瘤纹理相似,区分度小等问题,论文提出了一个基于深度学习的乳腺超声良恶性自动诊断模型以辅助医生诊断。论文采用Densenet加强细节特征提取,注意力机制模拟临床诊断,迁移学习缓解数据依赖。实验结果表明,该模型可为年轻医生提供良好的辅助诊断,具有较好的可靠性和临床实用性。

右肩部软组织血管纤维瘤一例

软组织血管纤维瘤是较为罕见的软组织来源的肿瘤,女性相对好发,临床表现及影像学表现无明显特异性,我们报道此病例,旨在提高对该病例的认识。

Evaluation of Clinical and Radiological Tumour Response during Neo-Adjuvant Breast Cancer Chemotherapy at Yalgado Ouedraogo University Hospital

Background: Neoadjuvant chemotherapy (NAC) is one of the treatment options for breast cancer. Its aim is to significantly reduce the size of the tumour in preparation for surgery. The aim of this work is to analyze the conditions of clinical and radiological evaluation of NAC at the Yalgado Ouédraogo University Hospital (CHUYO). Patients and Methods: This was a descriptive cross-sectional study based on the medical records of patients followed up in the cancer department of the CHUYO from 1 January 2013 to 31 December 2021. All patients followed for histologically proven, non-metastatic breast cancer and having received at least one course of NAC were included in this study. The variables were related to the socio-demographic characteristics of the patients, the indications, the protocols of NAC and the sequences of evaluation of the tumour response (clinical, radiological and anatomopathological). Results: We collected 105 cases. The average age of the patients concerned was 44 years. The most frequent histological type was non-specific invasive carcinoma in 97.1% of cases. Immunohistochemically, triple-negative patients accounted for 51.4%. At the initial stage, all patients underwent clinical exploration. Clinical measurement of the tumour was performed in 70.5% of cases. The radiological size of the tumour was determined by ultrasound in 59.1% of cases. One patient had a breast MRI. Thirty-one patients were lost to follow-up after the initial evaluation. At mid-term and at the end of treatment, clinical tumour size was performed in 38.6% and 45.6% of cases respectively. There was no breast imaging performed at mid- and end-of-treatment. CT scans were performed in all cases at baseline, mid-term and end of treatment for extension assessment but did not mention the breast tumour. The tumour response rate was not recorded. Conclusion: Clinical assessment of tumour response is almost always empirical and not quantified. Medical imaging examinations are prescribed sparingly so as not to compromise the regularity of treatment and patient assessment.

Endometriosis Misdiagnosed as a Metastatic Ovarian Tumour

Endometriosis is a debilitating problem with pain in the short term and high risk of infertility later. It is an oestrogen-dependent condition found in about 10% of women of reproductive age, about 1/3 of infertile women and as high as 80% of women with chronic pelvic pain. The condition is not well understood and thus associated with misdiagnosis and delayed diagnosis. Higher rates of misdiagnosis occur in blacks and this is especially for pelvic tumors-fibroids and ovarian tumors. We present here the case of a 30-year-old nullipara, who had an umbilical nodule (Sister Mary Joseph’s) and was found on imaging to have a pelvic tumor which was suspected to be an ovarian cancer. Diagnostic laparoscopy during the menstrual phase however revealed endometriosis in early stage. Misdiagnosis of endometriosis has potential to distort the course of the disease and endanger fertility prospects;early laparoscopic evaluation of patients with unclear pelvic pathologies would help to prevent this occurrence.

椎管内髓外硬膜下肿瘤的显微手术治疗

目的探讨椎管内髓外硬膜下肿瘤影像学特征、临床特征、显微手术疗效。方法回顾性分析2014年4月至2019年12月手术治疗的34例椎管内髓外硬膜下肿瘤的临床资料。结果34例中,脊膜瘤19例,神经鞘瘤15例;脊膜瘤以女性多见,疼痛少见,多出现囊变,T2WI多为等信号;而神经鞘瘤以男性多见,多有疼痛表现,囊变较少,T2WI多为高信号。34例肿瘤均全切除;全椎板切除28例,半椎板切除6例。术后未出现感染、脑脊液漏和脊髓缺血病变。术后随访12个月,McCormick脊髓功能分级Ⅰ级28例,Ⅱ级5例,Ⅲ级1例。结论椎管内髓外硬膜下肿瘤以脊膜瘤和神经鞘瘤最为常见,T2WI具有鉴别诊断价值;全椎板或半椎板入路手术治疗,肿瘤全切率高,复发率低,术后并发症少,能有效改善病人预后。

动态对比增强磁共振结合表观弥散系数鉴别恶性子宫间叶性肿瘤与弥散受限的子宫肌瘤

目的:评估动态对比增强磁共振成像(dynamic-contrast enhanced magnetic resonance imaging,DCE-MRI)和表观弥散系数(apparent diffusion coefficient,ADC)在鉴别恶性潜能未定的平滑肌肿瘤(smooth muscle tumours of uncertain malignant potential,STUMP)/恶性子宫间叶性肿瘤与在弥散加权成像(diffusion-weighted imaging,DWI)上表现为弥散受限的平滑肌瘤中的诊断效能。方法:连续收集2016年1月—2021年9月病理证实为子宫间叶性肿瘤患者68例,包括23例STUMP/恶性子宫间叶性肿瘤与45例弥散受限的平滑肌瘤,这些病灶在DWI(b=800 s/mm^(2))上均显示为弥散受限。对病灶进行常规MR特征评估以及ADC和DCE-MRI参数的直方图分析,受试者工作特征(receiver operating characteristic,ROC)曲线用于评估诊断性能。结果:STUMP/恶性子宫间叶性肿瘤囊变坏死的发生率高于非恶性组(34.8%vs.8.9%,P=0.016)。STUMP/恶性组的ADC中位数和Ve中位数显著低于非恶性组(P<0.001,P=0.012),鉴别STUMP/恶性子宫间叶性肿瘤的ROC曲线下面积(area under the curve,AUC)分别为0.795和0.713,ADC_(中位数)+Ve_(中位数)联合可将AUC提高到0.850,ADC_(中位数)+Ve_(中位数)+有无囊变坏死联合得到更高AUC(0.883)。结论:ADC、DCE-MRI参数与常规MR特征联合可作为鉴别STUMP/恶性子宫间叶性肿瘤与弥散受限的平滑肌瘤的敏感指标。

深度学习重建算法在磁共振颅脑增强中减少钆喷酸葡胺使用剂量的有效性研究

目的探讨通过应用深度学习重建(deep learning reconstruction,DL-Recon)算法提高颅脑MRI图像质量,实现在MRI临床实践中减少对比剂——钆喷酸葡胺(Gd-diethylenetriamine pentametric acid,Gd-DTPA)使用剂量的可行性。材料与方法收集2022年8月1日至2022年9月30日于我院放射科进行头部MRI增强扫描的60例患者。采用随机对照法,按照是否降低Gd-DTPA注射量平均分为正常药量组和降低药量组,并对两组患者分别使用常规重建方法和基于DL-Recon技术获取相应的T1WI图像。由两名医师在双盲条件下圈定感兴趣区进行信噪比(signal-to-noise ratio,SNR)及对比噪声比(contrast-to-noise ratio,CNR)分析,并对图像质量、伪影、均匀度及增强效果进行主观和客观评价,主观评价应用LIKERT五分制法,客观评价中通过分别计算图像背景以及额上回(superior frontal gyrus,SFG)、蛛网膜下腔(subarachnoid space,SAS)和红核(red nucleus,RN)的SNR对图像对比度进行评价。结果Gd-DTPA正常药量组中,相较于采用常规重建方法获得的图像,应用DL-Recon方法获取的图像在图像质量上显著升高(SNRSFG升高48.9%,CNRSFG提高91.5%);DL-Recon获取的图像伪影和图像整体质量得分均显著高于常规重建的图像(P<0.05)。降低药量组中,通过DL-Recon获取的图像与正常药量组的常规重建图像增强效果差异无统计学意义(P>0.05)。结论基于DL-Recon算法的MRI具备在保证图像质量的前提下降低Gd-DTPA注射量的应用能力。

结直肠癌肝转移预测及预后的影像组学综述

结直肠癌在国内外都是高发病率和高死亡率的肿瘤疾病,肝脏是结直肠癌血行转移最主要的靶器官,尽早准确地预测结直肠癌肝转移的发生以及监测患者治疗的预后反应,对患者的诊断和治疗尤为关键。新兴的影像组学为精准预测结直肠癌肝转移以及评估预后提供新的可能。对现有的结直肠癌肝转移影像组学研究进行综述,首先介绍结直肠癌肝转移研究的临床意义以及现有研究存在的缺陷,然后阐述结直肠癌肝转移影像组学的分析流程,接着对结直肠癌肝转移影像组学的4个研究方向展开综述,包括肝转移病理生长模式预测、隐匿性肝转移预测、肝转移疗效预后评估、肝转移患者生存期预后评估;阐明各个方向的最新研究进展及存在的缺陷性;最后对结直肠癌肝转移影像组学的未来发展趋势进行展望。

阔韧带血管平滑肌瘤一例及MRI分析

本文为回顾性研究,经过滨州医学院附属医院伦理委员会批准,免除受试者知情同意,批准文号:[2021](KT-050)。患者女,50岁,患者1天前因“取环”行彩超检查提示盆腔内实性低回声包块,于2022年2月19日因“查体发现盆腔肿物1天”入我院,患者一般情况可。月经规律,无痛经,无下腹痛,腹胀.

Deep Learning Framework for the Prediction of Childhood Medulloblastoma

This research work develops new and better prognostic markers for predicting Childhood MedulloBlastoma(CMB)using a well-defined deep learning architecture.A deep learning architecture could be designed using ideas from image processing and neural networks to predict CMB using histopathological images.First,a convolution process transforms the histopathological image into deep features that uniquely describe it using different two-dimensional filters of various sizes.A 10-layer deep learning architecture is designed to extract deep features.The introduction of pooling layers in the architecture reduces the feature dimension.The extracted and dimension-reduced deep features from the arrangement of convolution layers and pooling layers are used to classify histopathological images using a neural network classifier.The performance of the CMB classification system is evaluated using 1414(10×magnification)and 1071(100×magnification)augmented histopathological images with five classes of CMB such as desmoplastic,nodular,large cell,classic,and normal.Experimental results show that the average classification accuracy of 99.38%(10×)and 99.07%(100×)is attained by the proposed CNB classification system.

Novel lysosome-targeted anticancer fluorescent agents used in zebrafish and nude mouse tumour imaging

The design of three novel fatty nitrogen mustard-based anticancer agents with fluorophores incorporated into the alkene structure(CXL 118,CXL121,and CXL122)is described in this report.The results indicated that these compounds are selectively located in lysosomes and exhibit effective antitumour activity.Notably,these compounds can directly serve as both reporting and imaging agents in vitro and in vivo without the need to add other fluorescent tagging agents.

Brain Tumor Segmentation in Multimodal MRI Using U-Net Layered Structure

The brain tumour is the mass where some tissues become old or damaged,but they do not die or not leave their space.Mainly brain tumour masses occur due to malignant masses.These tissues must die so that new tissues are allowed to be born and take their place.Tumour segmentation is a complex and time-taking problem due to the tumour’s size,shape,and appearance variation.Manually finding such masses in the brain by analyzing Magnetic Resonance Images(MRI)is a crucial task for experts and radiologists.Radiologists could not work for large volume images simultaneously,and many errors occurred due to overwhelming image analysis.The main objective of this research study is the segmentation of tumors in brain MRI images with the help of digital image processing and deep learning approaches.This research study proposed an automatic model for tumor segmentation in MRI images.The proposed model has a few significant steps,which first apply the pre-processing method for the whole dataset to convert Neuroimaging Informatics Technology Initiative(NIFTI)volumes into the 3D NumPy array.In the second step,the proposed model adopts U-Net deep learning segmentation algorithm with an improved layered structure and sets the updated parameters.In the third step,the proposed model uses state-of-the-art Medical Image Computing and Computer-Assisted Intervention(MICCAI)BRATS 2018 dataset withMRI modalities such as T1,T1Gd,T2,and Fluidattenuated inversion recovery(FLAIR).Tumour types in MRI images are classified according to the tumour masses.Labelling of these masses carried by state-of-the-art approaches such that the first is enhancing tumour(label 4),edema(label 2),necrotic and non-enhancing tumour core(label 1),and the remaining region is label 0 such that edema(whole tumour),necrosis and active.The proposed model is evaluated and gets the Dice Coefficient(DSC)value for High-grade glioma(HGG)volumes for their test set-a,test set-b,and test set-c 0.9795, 0.9855 and 0.9793, respectively. DSC value for the Low-gradeglioma (LGG) volumes for the test set is 0.9950, which shows the proposedmodel has achieved significant results in segmenting the tumour in MRI usingdeep learning approaches. The proposed model is fully automatic that canimplement in clinics where human experts consumemaximumtime to identifythe tumorous region of the brain MRI. The proposed model can help in a wayit can proceed rapidly by treating the tumor segmentation in MRI.

Malignant proliferative ependymoma of the neck with lymph node metastasis:A case report

BACKGROUND Malignant proliferating trichilemmal tumor(MPTT)is an infrequent malignant neoplasm originating from cutaneous appendages,with only a handful of documented cases.This report delineates a unique instance of MPTT situated in the neck,accompanied by lymph node metastasis.A comprehensive exposition of its clinical trajectory and imaging manifestation is presented,aiming to enhance comprehension and management of this atypical ailment.CASE SUMMARY Patient concerns:A 79-year-old male presented with a longstanding right neck mass persisting for over six decades,exhibiting recent enlargement over the past year.Diagnoses:Enhanced magnetic resonance imaging of the neck unveiled an elliptical mass on the right neck side,characterized by an ill-defined border and a heterogeneous signal pattern.The mass exhibited subdued signal intensity on T1-weighted imaging(T1WI)and a heterogeneous high signal on T2-weighted imaging(T2WI),interspersed with a lengthy T1 and T2 cystic signal motif.Close anatomical association with the submandibular gland joint was noted,and intravenous gadolinium diethylene triamine pentaacetic acid administration facilitated conspicuous enhancement.Substantial enhancement of the solid segment prompted an initial preoperative diagnosis of malignant nerve sheath tumor.However,post-surgery histopathological and immunohistochemical analysis conclusively confirmed the diagnosis as malignant hyperplastic external hair root sheath tumor.Intervention:Complete excision of the tumor was successfully executed.Outcomes:The patient experienced a favorable postoperative recovery.CONCLUSION Malignant proliferative trichilemmal tumor external hair root sheath tumor is a cystic-solid lesion,appearing as low signal on T1WI images or high signal on T2WI with enhancement of the solid component.Suspicions of malignancy are heightened when the tumor border is indistinct,tissue planes are breached,or when linear or patchy high signals are observed in the subcutaneous tissue on T1 liver acquisition with volume acceleration enhanced images along with intermediate signal on T2WI and restricted diffusion on diffusion-weighted imaging images.Strong consideration for malignancy should arise if there are signs of compromised adjacent tissue relationships or direct invasion evident on imaging.We have incorporated the above-mentioned content into the entire manuscript.

Fabrication of doxorubicin and chlorotoxin-linked Eu-Gd2O3 nanorods with dual-model imaging and targeted therapy of brain tumor

It is urgent to find a technology accurately to better diagnose and treat to brain tumor.Eu-doped Gd2 O3 nanorods(Eu-Gd2 O3 NRs)with paramagnetic and fluorescent properties were conjugated with doxorubicin(Dox)and chlorotoxin(CTX)via PEGylation,hydrazone bond and sulfur bond(named as CTXNRs-Dox),and these NRs could release more Dox in lower pH environment.The results of cell experiments indicated that CTX-NRs-Dox had obvious targeting and toxic effects on U251 cells,as well as good fluorescence imaging behavior.The orthotopic glioma-transplanted mice models were constructed via the intracranial injection of glioma cells(U87 MG).The result of experiments after the tail-vein injection of the prepared NRs suggested that CTX-NRs-Dox could target to brain tumors via the long-time blood circulation,leading to their obvious contrast enhancement of MR imaging of the intracranial tumor and their significant inhibitory effect on the growth and metastasis of brain tumors.A mechanism of synergistic effect of CTX-NRs-Dox on targeting and inhabiting the brain tumor was proposed.Our research suggested that CTX-NRs-Dox had potential application prospect in the detection and treatment of glioma.