Accurate tumor segmentation from brain tissues in Magnetic Resonance Imaging(MRI)imaging is crucial in the pre-surgical planning of brain tumor malignancy.MRI images’heterogeneous intensity and fuzzy boundaries make ...Accurate tumor segmentation from brain tissues in Magnetic Resonance Imaging(MRI)imaging is crucial in the pre-surgical planning of brain tumor malignancy.MRI images’heterogeneous intensity and fuzzy boundaries make brain tumor segmentation challenging.Furthermore,recent studies have yet to fully employ MRI sequences’considerable and supplementary information,which offers critical a priori knowledge.This paper proposes a clinical knowledge-based hybrid Swin Transformermultimodal brain tumor segmentation algorithmbased on how experts identify malignancies from MRI images.During the encoder phase,a dual backbone network with a Swin Transformer backbone to capture long dependencies from 3D MR images and a Convolutional Neural Network(CNN)-based backbone to represent local features have been constructed.Instead of directly connecting all the MRI sequences,the proposed method re-organizes them and splits them into two groups based on MRI principles and characteristics:T1 and T1ce,T2 and Flair.These aggregated images are received by the dual-stem Swin Transformer-based encoder branch,and the multimodal sequence-interacted cross-attention module(MScAM)captures the interactive information between two sets of linked modalities in each stage.In the CNN-based encoder branch,a triple down-sampling module(TDsM)has been proposed to balance the performance while downsampling.In the final stage of the encoder,the feature maps acquired from two branches are concatenated as input to the decoder,which is constrained by MScAM outputs.The proposed method has been evaluated on datasets from the MICCAI BraTS2021 Challenge.The results of the experiments demonstrate that the method algorithm can precisely segment brain tumors,especially the portions within tumors.展开更多
Background: The profile of primary brain tumors and treatment modalities employed in Tanzania remains largely unknown. The study aimed to describe the baseline clinical-pathological profile and treatment modalities fo...Background: The profile of primary brain tumors and treatment modalities employed in Tanzania remains largely unknown. The study aimed to describe the baseline clinical-pathological profile and treatment modalities for primary brain tumors in adults treated at the Ocean Road Cancer Institute (ORCI) from 2017 to 2020. Materials and Methods: This was a retrospective study conducted at ORCI by reviewing 61 medical records of patients with primary brain tumors over the age of 15 from January 2017 to December 2020. A structured questionnaire was used to retrieve information on sociodemographic, clinical-pathological characteristics, and treatment modalities. The 2007 WHO classification system and the International Classification of Cancer Diseases (ICD-0-3) were used for classification and diagnosis. The X<sup>2</sup> test and Fisher’s exact test were used to compare the proportions and an independent t-test was used to compare the means. A P-value less than 0.05 was deemed statistically significant. The Results: The mean age of the females was 41.8 years and the mean age of males was 42.9 years. Overall M: F ratio was 1:1.2. Meningioma was the only tumor that was more commonly found in women with M:F of 1:2.1. The most prevalent symptom was headache (57.4%). Glioblastoma (GBM) was the most common tumor among adults (38%), followed by astrocytomas (23%) and meningioma (18%). Approximately 91.8% of all tumors occurred in the supratentorial region. The Frontal lobe was the most common site (29.5%). Approximately 81.9% of patients received surgery. The gross tumor resection (GTR) rate was 26.2%, and the subtotal tumor resection (STR) rate was 55.7%. Roughly 18% of the tumors were inoperable. An estimated 80.3% of respondents received radiation therapy. The radiotherapy technique was 3DCRT in two-thirds of the patients and the rest received conventional 2D radiotherapy. The mean equivalent dose in the 2 Gy fractions (EQD2) was 43.9 Gy. Respondents with low-grade intracranial tumors were treated with a mean EQD2 of 47.3 Gy, while those with high-grade intracranial tumors were treated with a mean EQD2 of 44.3 Gy and the difference was statistically significant. Only half of the patients who received adjuvant radiotherapy received it concurrently with chemotherapy. Temozolomide was the most widely used cytotoxic medication. Conclusion: Mean age of the patients was 41 years old. Most tumors were in the supratentorial area and GBM was the most common tumor. Only meningioma was a bit more common amongst females. Overall, radiotherapy doses and the gross tumor resection rates were low. Concurrent chemotherapy with radiotherapy was given to a few patients.展开更多
Cancer stem-like cells(CSCs)with potential of self-renewal drive tumorigenesis.Brain tumor microenvironment(TME)has been identified as a critical regulator of malignancy progression.Many researchers are searching new ...Cancer stem-like cells(CSCs)with potential of self-renewal drive tumorigenesis.Brain tumor microenvironment(TME)has been identified as a critical regulator of malignancy progression.Many researchers are searching new ways to characterize tumors with the goal of predicting how they respond to treatment.Here,we describe the striking parallels between normal stem cells and CSCs.We review the microenvironmental aspects of brain tumors,in particular composition and vital roles of immune cells infiltrating glioma and medulloblastoma.By highlighting that CSCs cooperate with TME via various cellular communication approaches,we discuss the recent advances in therapeutic strategies targeting the components of TME.Identification of the complex and interconnected factors can facilitate the development of promising treatments for these deadly malignancies.展开更多
Nonresectable Low-Grade Astrocytomas (LGA) can compromise function and threaten life. For the majority of patients, the most appropriate strategy is initial chemotherapy followed by Radiation Therapy (RT). Since curat...Nonresectable Low-Grade Astrocytomas (LGA) can compromise function and threaten life. For the majority of patients, the most appropriate strategy is initial chemotherapy followed by Radiation Therapy (RT). Since curative treatment is not available for most of these patients, it is reasonable to conduct clinical studies to evaluate new agents. This Phase II study evaluates efficacy and safety of Antineoplastons A10 and AS2-1 (ANP) in LGA. Sixteen children diagnosed with LGA were treated. They included 12 males and 4 females, ages 1.6 - 17.4 years (median 10.6). Efficacy was evaluated in 16 patients. The majority of patients were previously treated, but 1 patient had stereotactic biopsy only. Out of the remaining 15 patients, 6 patients received chemotherapy, and 7 patients had surgery, and 2 patients received RT and chemotherapy after surgery. The patients received treatment with ANP administered daily every 4 hours (median dose of A10 was 7.71 g/kg/d and AS2-1 was 0.26 g/kg/d) until objective response or stable disease was documented and for 8 months thereafter. The duration of ANP IV ranged from 1.4 to 286 weeks with a median of 83 weeks. A complete response was documented in 25.0%, partial response in 12.5%, and stable disease in 37.5%. Overall survival was 67.7% at 5 years, and 54.2% at 10 and 15 years. Progression-free survival was 48.1%, 34.4% and 34.4% at 5, 10, and 15 years respectively. The treatment was associated with grade 3 or grade 4 Adverse Drug Experiences (ADE) in 6 patients. There were two hypernatremias of grade 4 (12%). Grade 3 ADE included urinary frequency (6%), fatigue (6%) and hypernatremia (6%). There were no chronic toxicities, and there was a high quality of survival. ANP shows efficacy with a very good toxicity profile in this cohort of children with low-grade astrocytoma.展开更多
The use of intelligent machines to work and react like humans is vital in emerging smart cities.Computer-aided analysis of complex and huge MRI(Mag-netic Resonance Imaging)scans is very important in healthcare applica...The use of intelligent machines to work and react like humans is vital in emerging smart cities.Computer-aided analysis of complex and huge MRI(Mag-netic Resonance Imaging)scans is very important in healthcare applications.Among AI(Artificial Intelligence)driven healthcare applications,tumor detection is one of the contemporary researchfields that have become attractive to research-ers.There are several modalities of imaging performed on the brain for the pur-pose of tumor detection.This paper offers a deep learning approach for detecting brain tumors from MR(Magnetic Resonance)images based on changes in the division of the training and testing data and the structure of the CNN(Convolu-tional Neural Network)layers.The proposed approach is carried out on a brain tumor dataset from the National Centre of Image-Guided Therapy,including about 4700 MRI images of ten brain tumor cases with both normal and abnormal states.The dataset is divided into test,and train subsets with a ratio of the training set to the validation set of 70:30.The main contribution of this paper is introdu-cing an optimum deep learning structure of CNN layers.The simulation results are obtained for 50 epochs in the training phase.The simulation results reveal that the optimum CNN architecture consists of four layers.展开更多
目的探析磁共振弥散联合波谱分析技术应用于脑肿瘤方面的诊断价值。方法选取2013年8月-2014年8月我院的40例经手术和病理检查证实为脑肿瘤的患者为研究对象,分别对患者给予常规磁共振检查与磁共振弥散联合波谱分析检查,分析对比两种检...目的探析磁共振弥散联合波谱分析技术应用于脑肿瘤方面的诊断价值。方法选取2013年8月-2014年8月我院的40例经手术和病理检查证实为脑肿瘤的患者为研究对象,分别对患者给予常规磁共振检查与磁共振弥散联合波谱分析检查,分析对比两种检查方式的检查结果、表观弥散系数以及波谱图,并分别计算出肿瘤增强区和对侧正常区的NAA/Cho、NAA/Cr和Cho/Cr比值等。结果脑转移瘤的平均ADC值为(12.08±2.92)×10^(-4)mm^2/s,脑膜瘤的平均ADC值为(13.17±2.98)×10^(-4)m m ~2/s,星形细胞瘤的平均A D C值为(13.76±2.99)×10^(-4)mm^2/s。三种脑肿瘤的ADC值均高于正常对侧脑组织,差异具有统计学意义(均P>0.05),且三种肿瘤任意选取两种比较,差异无统计学意义(均P>0.05)。三种肿瘤的NAA均较正常组织低,差异具有统计学意义(均P<0.05),转移瘤与脑膜瘤的NAA/Cho、NAA/Cr值明显低于星形细胞瘤(均P<0.05),三种肿瘤的Cr明显低于正常脑组织(均P<0.05)。星形细胞瘤有4例Lac峰,1例Lip峰;脑膜瘤有3例Lac峰,1例Lip峰,1例Ala峰;转移瘤有2例Lac峰,5例Lip峰。结论磁共振弥散及波谱两种技术均有其优势,若联合应用能更加敏感的发现疾病以及精准的辨别疾病,值得临床广泛推广使用。展开更多
基金supported in part by the National Natural Science Foundation of China under Grant No.U20A20197Liaoning Key Research and Development Project 2020JH2/10100040+1 种基金Natural Science Foundation of Liaoning Province 2021-KF-12-01the Foundation of National Key Laboratory OEIP-O-202005.
文摘Accurate tumor segmentation from brain tissues in Magnetic Resonance Imaging(MRI)imaging is crucial in the pre-surgical planning of brain tumor malignancy.MRI images’heterogeneous intensity and fuzzy boundaries make brain tumor segmentation challenging.Furthermore,recent studies have yet to fully employ MRI sequences’considerable and supplementary information,which offers critical a priori knowledge.This paper proposes a clinical knowledge-based hybrid Swin Transformermultimodal brain tumor segmentation algorithmbased on how experts identify malignancies from MRI images.During the encoder phase,a dual backbone network with a Swin Transformer backbone to capture long dependencies from 3D MR images and a Convolutional Neural Network(CNN)-based backbone to represent local features have been constructed.Instead of directly connecting all the MRI sequences,the proposed method re-organizes them and splits them into two groups based on MRI principles and characteristics:T1 and T1ce,T2 and Flair.These aggregated images are received by the dual-stem Swin Transformer-based encoder branch,and the multimodal sequence-interacted cross-attention module(MScAM)captures the interactive information between two sets of linked modalities in each stage.In the CNN-based encoder branch,a triple down-sampling module(TDsM)has been proposed to balance the performance while downsampling.In the final stage of the encoder,the feature maps acquired from two branches are concatenated as input to the decoder,which is constrained by MScAM outputs.The proposed method has been evaluated on datasets from the MICCAI BraTS2021 Challenge.The results of the experiments demonstrate that the method algorithm can precisely segment brain tumors,especially the portions within tumors.
文摘Background: The profile of primary brain tumors and treatment modalities employed in Tanzania remains largely unknown. The study aimed to describe the baseline clinical-pathological profile and treatment modalities for primary brain tumors in adults treated at the Ocean Road Cancer Institute (ORCI) from 2017 to 2020. Materials and Methods: This was a retrospective study conducted at ORCI by reviewing 61 medical records of patients with primary brain tumors over the age of 15 from January 2017 to December 2020. A structured questionnaire was used to retrieve information on sociodemographic, clinical-pathological characteristics, and treatment modalities. The 2007 WHO classification system and the International Classification of Cancer Diseases (ICD-0-3) were used for classification and diagnosis. The X<sup>2</sup> test and Fisher’s exact test were used to compare the proportions and an independent t-test was used to compare the means. A P-value less than 0.05 was deemed statistically significant. The Results: The mean age of the females was 41.8 years and the mean age of males was 42.9 years. Overall M: F ratio was 1:1.2. Meningioma was the only tumor that was more commonly found in women with M:F of 1:2.1. The most prevalent symptom was headache (57.4%). Glioblastoma (GBM) was the most common tumor among adults (38%), followed by astrocytomas (23%) and meningioma (18%). Approximately 91.8% of all tumors occurred in the supratentorial region. The Frontal lobe was the most common site (29.5%). Approximately 81.9% of patients received surgery. The gross tumor resection (GTR) rate was 26.2%, and the subtotal tumor resection (STR) rate was 55.7%. Roughly 18% of the tumors were inoperable. An estimated 80.3% of respondents received radiation therapy. The radiotherapy technique was 3DCRT in two-thirds of the patients and the rest received conventional 2D radiotherapy. The mean equivalent dose in the 2 Gy fractions (EQD2) was 43.9 Gy. Respondents with low-grade intracranial tumors were treated with a mean EQD2 of 47.3 Gy, while those with high-grade intracranial tumors were treated with a mean EQD2 of 44.3 Gy and the difference was statistically significant. Only half of the patients who received adjuvant radiotherapy received it concurrently with chemotherapy. Temozolomide was the most widely used cytotoxic medication. Conclusion: Mean age of the patients was 41 years old. Most tumors were in the supratentorial area and GBM was the most common tumor. Only meningioma was a bit more common amongst females. Overall, radiotherapy doses and the gross tumor resection rates were low. Concurrent chemotherapy with radiotherapy was given to a few patients.
基金Supported by The Medical Big Data Research Program of Chinese PLA General Hospital,No.2018MBD-20(to Feng SY)National Natural Science Foundation of China,No.81902975(to Liu HL)and the 65th China Postdoctoral Science Foundation,No.2019M653940(to Liu HL).
文摘Cancer stem-like cells(CSCs)with potential of self-renewal drive tumorigenesis.Brain tumor microenvironment(TME)has been identified as a critical regulator of malignancy progression.Many researchers are searching new ways to characterize tumors with the goal of predicting how they respond to treatment.Here,we describe the striking parallels between normal stem cells and CSCs.We review the microenvironmental aspects of brain tumors,in particular composition and vital roles of immune cells infiltrating glioma and medulloblastoma.By highlighting that CSCs cooperate with TME via various cellular communication approaches,we discuss the recent advances in therapeutic strategies targeting the components of TME.Identification of the complex and interconnected factors can facilitate the development of promising treatments for these deadly malignancies.
文摘Nonresectable Low-Grade Astrocytomas (LGA) can compromise function and threaten life. For the majority of patients, the most appropriate strategy is initial chemotherapy followed by Radiation Therapy (RT). Since curative treatment is not available for most of these patients, it is reasonable to conduct clinical studies to evaluate new agents. This Phase II study evaluates efficacy and safety of Antineoplastons A10 and AS2-1 (ANP) in LGA. Sixteen children diagnosed with LGA were treated. They included 12 males and 4 females, ages 1.6 - 17.4 years (median 10.6). Efficacy was evaluated in 16 patients. The majority of patients were previously treated, but 1 patient had stereotactic biopsy only. Out of the remaining 15 patients, 6 patients received chemotherapy, and 7 patients had surgery, and 2 patients received RT and chemotherapy after surgery. The patients received treatment with ANP administered daily every 4 hours (median dose of A10 was 7.71 g/kg/d and AS2-1 was 0.26 g/kg/d) until objective response or stable disease was documented and for 8 months thereafter. The duration of ANP IV ranged from 1.4 to 286 weeks with a median of 83 weeks. A complete response was documented in 25.0%, partial response in 12.5%, and stable disease in 37.5%. Overall survival was 67.7% at 5 years, and 54.2% at 10 and 15 years. Progression-free survival was 48.1%, 34.4% and 34.4% at 5, 10, and 15 years respectively. The treatment was associated with grade 3 or grade 4 Adverse Drug Experiences (ADE) in 6 patients. There were two hypernatremias of grade 4 (12%). Grade 3 ADE included urinary frequency (6%), fatigue (6%) and hypernatremia (6%). There were no chronic toxicities, and there was a high quality of survival. ANP shows efficacy with a very good toxicity profile in this cohort of children with low-grade astrocytoma.
基金funded and supported by the Taif University Researchers,Taif University,Taif,Saudi Arabia,under Project TURSP-2020/147.
文摘The use of intelligent machines to work and react like humans is vital in emerging smart cities.Computer-aided analysis of complex and huge MRI(Mag-netic Resonance Imaging)scans is very important in healthcare applications.Among AI(Artificial Intelligence)driven healthcare applications,tumor detection is one of the contemporary researchfields that have become attractive to research-ers.There are several modalities of imaging performed on the brain for the pur-pose of tumor detection.This paper offers a deep learning approach for detecting brain tumors from MR(Magnetic Resonance)images based on changes in the division of the training and testing data and the structure of the CNN(Convolu-tional Neural Network)layers.The proposed approach is carried out on a brain tumor dataset from the National Centre of Image-Guided Therapy,including about 4700 MRI images of ten brain tumor cases with both normal and abnormal states.The dataset is divided into test,and train subsets with a ratio of the training set to the validation set of 70:30.The main contribution of this paper is introdu-cing an optimum deep learning structure of CNN layers.The simulation results are obtained for 50 epochs in the training phase.The simulation results reveal that the optimum CNN architecture consists of four layers.
文摘目的探析磁共振弥散联合波谱分析技术应用于脑肿瘤方面的诊断价值。方法选取2013年8月-2014年8月我院的40例经手术和病理检查证实为脑肿瘤的患者为研究对象,分别对患者给予常规磁共振检查与磁共振弥散联合波谱分析检查,分析对比两种检查方式的检查结果、表观弥散系数以及波谱图,并分别计算出肿瘤增强区和对侧正常区的NAA/Cho、NAA/Cr和Cho/Cr比值等。结果脑转移瘤的平均ADC值为(12.08±2.92)×10^(-4)mm^2/s,脑膜瘤的平均ADC值为(13.17±2.98)×10^(-4)m m ~2/s,星形细胞瘤的平均A D C值为(13.76±2.99)×10^(-4)mm^2/s。三种脑肿瘤的ADC值均高于正常对侧脑组织,差异具有统计学意义(均P>0.05),且三种肿瘤任意选取两种比较,差异无统计学意义(均P>0.05)。三种肿瘤的NAA均较正常组织低,差异具有统计学意义(均P<0.05),转移瘤与脑膜瘤的NAA/Cho、NAA/Cr值明显低于星形细胞瘤(均P<0.05),三种肿瘤的Cr明显低于正常脑组织(均P<0.05)。星形细胞瘤有4例Lac峰,1例Lip峰;脑膜瘤有3例Lac峰,1例Lip峰,1例Ala峰;转移瘤有2例Lac峰,5例Lip峰。结论磁共振弥散及波谱两种技术均有其优势,若联合应用能更加敏感的发现疾病以及精准的辨别疾病,值得临床广泛推广使用。
