Zenas Igbinoba, KM Capaccione, B. Dsouza, Ashna Shetty, Mary M. Salvatore
Imaging of patients with COVID-19 has provided unique insights into the pathophysiology of the infection. Cysts are a rare manifestation of the disease in the lung. The aim of this research was to compare COVID-19-positive patients with cysts on CT to patients without cysts and propose a mechanism for cyst formation in this patient population based on radiographic observations.Our HIPAA-compliant IRB-approved research project involved a retrospective review of 219 chest CT scans identified in COVID-19-positive inpatients and emergency room patients at Columbia University Irving Medical Center from February 27, 2020 to July 17, 2020. A thoracic radiologist with over 20 years of experience reviewed the images on lung window settings and identified the presence of cysts, their distribution (central or pleural based), and if there was an accompanying pneumothorax. The extent of consolidation of the entire lung on a scale of 0–16 and the presence of fibrosis were also documented.Cysts were identified in 10 of the 219 patients. CT scans with cysts were obtained on average on day 57 of symptoms (range 16–115 days) compared to CT scans of those without cysts that were obtained on average on day 19 (range 0–89 days). The distribution of cysts was heterogeneous; six patients had multiple cysts while four were isolated. Seven cysts were peripheral in distribution while three were central. Two patients with cysts developed a subsequent pneumothorax. Fifty percent of those with cysts had been intubated.Patients with COVID-19 develop cystic lung lesions for at least two reasons; pleural-based lesions are more likely areas of infarction and central lesions with surrounding ground glass are more likely related to infection and/or mechanical ventilation.
{"title":"Radiographic analysis provides evidence for the etiology of pulmonary cysts in COVID-19","authors":"Zenas Igbinoba, KM Capaccione, B. Dsouza, Ashna Shetty, Mary M. Salvatore","doi":"10.1556/1647.2023.00159","DOIUrl":"https://doi.org/10.1556/1647.2023.00159","url":null,"abstract":"Imaging of patients with COVID-19 has provided unique insights into the pathophysiology of the infection. Cysts are a rare manifestation of the disease in the lung. The aim of this research was to compare COVID-19-positive patients with cysts on CT to patients without cysts and propose a mechanism for cyst formation in this patient population based on radiographic observations.Our HIPAA-compliant IRB-approved research project involved a retrospective review of 219 chest CT scans identified in COVID-19-positive inpatients and emergency room patients at Columbia University Irving Medical Center from February 27, 2020 to July 17, 2020. A thoracic radiologist with over 20 years of experience reviewed the images on lung window settings and identified the presence of cysts, their distribution (central or pleural based), and if there was an accompanying pneumothorax. The extent of consolidation of the entire lung on a scale of 0–16 and the presence of fibrosis were also documented.Cysts were identified in 10 of the 219 patients. CT scans with cysts were obtained on average on day 57 of symptoms (range 16–115 days) compared to CT scans of those without cysts that were obtained on average on day 19 (range 0–89 days). The distribution of cysts was heterogeneous; six patients had multiple cysts while four were isolated. Seven cysts were peripheral in distribution while three were central. Two patients with cysts developed a subsequent pneumothorax. Fifty percent of those with cysts had been intubated.Patients with COVID-19 develop cystic lung lesions for at least two reasons; pleural-based lesions are more likely areas of infarction and central lesions with surrounding ground glass are more likely related to infection and/or mechanical ventilation.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"19 1","pages":""},"PeriodicalIF":0.4,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139150268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
César Hayashi-Mercado, M. González-Urueta, A. Aguilar-West, María Dolores Montiel-Moreno
Dieulafoy's lesion is defined as a dilated submucosal artery that can cause spontaneous rupture and massive gastrointestinal bleeding. It is usually an incidental finding and is identified as a prominent linear or serpentine artery.We report the case of a 47-year-old patient who presented with a Dieulafoy's lesion located in the gastric fundus, which was repeatedly treated with clipping and endoscopic sclerosis, without resolving. She presented to the interventional radiology service for endovascular treatment, which after performing angiography confirmed active bleeding at the level of the left gastric artery and proceeded to embolize with 2 coils. This is a case where endovascular treatment proves to be an effective and decisive option for the treatment of bleeding in this type of injury.
{"title":"Dieulafoy's lesion, the endovascular approach as a therapeutic option when endoscopic treatment has failed: A case report and brief review","authors":"César Hayashi-Mercado, M. González-Urueta, A. Aguilar-West, María Dolores Montiel-Moreno","doi":"10.1556/1647.2023.00142","DOIUrl":"https://doi.org/10.1556/1647.2023.00142","url":null,"abstract":"Dieulafoy's lesion is defined as a dilated submucosal artery that can cause spontaneous rupture and massive gastrointestinal bleeding. It is usually an incidental finding and is identified as a prominent linear or serpentine artery.We report the case of a 47-year-old patient who presented with a Dieulafoy's lesion located in the gastric fundus, which was repeatedly treated with clipping and endoscopic sclerosis, without resolving. She presented to the interventional radiology service for endovascular treatment, which after performing angiography confirmed active bleeding at the level of the left gastric artery and proceeded to embolize with 2 coils. This is a case where endovascular treatment proves to be an effective and decisive option for the treatment of bleeding in this type of injury.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"115 4","pages":""},"PeriodicalIF":0.4,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138953842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cor Triatriatum Sinister (CTS) represents a rare congenital cardiac defect characterized by the presence of a fibro-muscular membrane separating the left atrium into two cavities. During adulthood CTS may be asymptomatic and incidentally found during imaging diagnostic workflow. Bidimensional (2D) transthoracic echocardiography (TTE) is considered the first-line imaging technique for the evaluation of CTS. Cardiac magnetic resonance (CMR) and transoesophageal echocardiography (TEE) are advanced diagnostic tools, usually required to obtain additional data. When these diagnostic techniques are contraindicated or not available, three-dimensional (3D) TTE may provide useful information which may help in the morphological assessment of CTS. Moreover, this widespread technique is safe and frequently available in the echocardiography laboratories, although the acoustic window and the training of the operator may be limiting factors. With this case report we sought to emphasize the usefulness of this technique as a valid alternative to CMR and TEE in selected settings.
{"title":"Three-dimensional (3D) transthoracic echocardiography in Cor Triatriatum Sinister: Make new friends but keep the old","authors":"P. Basile, Daniela Santoro, A. Guaricci","doi":"10.1556/1647.2023.00165","DOIUrl":"https://doi.org/10.1556/1647.2023.00165","url":null,"abstract":"Cor Triatriatum Sinister (CTS) represents a rare congenital cardiac defect characterized by the presence of a fibro-muscular membrane separating the left atrium into two cavities. During adulthood CTS may be asymptomatic and incidentally found during imaging diagnostic workflow. Bidimensional (2D) transthoracic echocardiography (TTE) is considered the first-line imaging technique for the evaluation of CTS. Cardiac magnetic resonance (CMR) and transoesophageal echocardiography (TEE) are advanced diagnostic tools, usually required to obtain additional data. When these diagnostic techniques are contraindicated or not available, three-dimensional (3D) TTE may provide useful information which may help in the morphological assessment of CTS. Moreover, this widespread technique is safe and frequently available in the echocardiography laboratories, although the acoustic window and the training of the operator may be limiting factors. With this case report we sought to emphasize the usefulness of this technique as a valid alternative to CMR and TEE in selected settings.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"8 6","pages":""},"PeriodicalIF":0.4,"publicationDate":"2023-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139001035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Basidiobolomycosis is a rare subcutaneous fungal infection caused by Basidiobolus ranarum. Gastrointestinal Basidiobolomycosis GIB has been increasingly reported in the literature.We present a case of a 50-year-old male patient who presented by abdominal pain and weight loss. Imaging showed a left colon mass with a small liver lesion. Provisional diagnosis of colon cancer with liver metastasis was made. Endoscopic stenting and biopsy were done, and the results of the biopsy were not conclusive. The condition was complicated by perforation, and emergency laparotomy was done. The diagnosis of colon Basidiobolomycosis was reached from surgical histopathology. Unfortunately, the patient's condition deteriorated post operatively and the patient passed away a few days after surgery.GIB is a rare fungal infection commonly presenting as a colonic neoplastic mass or inflammatory bowel disease. The endoscopy biopsy usually fails to provide definitive diagnosis. Post-operative histopathological examination with or without culture provides a definite diagnosis. Treatment of GIB includes surgical resection with appropriate antifungal therapy which revealed dramatic response in most of the cases. However, delayed diagnosis and treatment lead to dissemination of the disease which is life-threatening condition.
{"title":"Colonic basidiobolomycosis masquerading as colon cancer with liver metastasis: A case report and review of literature","authors":"Mohammad A. Wazzan, M. El-Diasty","doi":"10.1556/1647.2023.00183","DOIUrl":"https://doi.org/10.1556/1647.2023.00183","url":null,"abstract":"Basidiobolomycosis is a rare subcutaneous fungal infection caused by Basidiobolus ranarum. Gastrointestinal Basidiobolomycosis GIB has been increasingly reported in the literature.We present a case of a 50-year-old male patient who presented by abdominal pain and weight loss. Imaging showed a left colon mass with a small liver lesion. Provisional diagnosis of colon cancer with liver metastasis was made. Endoscopic stenting and biopsy were done, and the results of the biopsy were not conclusive. The condition was complicated by perforation, and emergency laparotomy was done. The diagnosis of colon Basidiobolomycosis was reached from surgical histopathology. Unfortunately, the patient's condition deteriorated post operatively and the patient passed away a few days after surgery.GIB is a rare fungal infection commonly presenting as a colonic neoplastic mass or inflammatory bowel disease. The endoscopy biopsy usually fails to provide definitive diagnosis. Post-operative histopathological examination with or without culture provides a definite diagnosis. Treatment of GIB includes surgical resection with appropriate antifungal therapy which revealed dramatic response in most of the cases. However, delayed diagnosis and treatment lead to dissemination of the disease which is life-threatening condition.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"48 1","pages":""},"PeriodicalIF":0.4,"publicationDate":"2023-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138976896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. Cirimele, Giulia D'Amone, C. Mallio, B. Zobel, E. Faiella
To provide a pictorial review of the main clinical applications of DECT with a focus on traumatic and non-traumatic emergencies.DECT is becoming increasingly common in clinical practice. The differences in attenuation between two different datasets allow to perform a qualitative and quantitative characterization of the materials contained in a single voxel. Virtual monoenergetic images, material decomposition images, electron density maps, and atomic number maps are created by post-processing algorithms and offer the radiologist useful diagnostic data.We present a series of cases illustrating the utility of DECT in the diagnosis and management of acute pathologies, with a special focus on musculoskeletal imaging and neuroimaging.DECT is a useful imaging technique that may allow radiologists to make quicker and more precise diagnoses in the emergency setting.
{"title":"Dual-energy CT in the emergency department: A pictorial essay from a single center experience","authors":"V. Cirimele, Giulia D'Amone, C. Mallio, B. Zobel, E. Faiella","doi":"10.1556/1647.2023.00152","DOIUrl":"https://doi.org/10.1556/1647.2023.00152","url":null,"abstract":"To provide a pictorial review of the main clinical applications of DECT with a focus on traumatic and non-traumatic emergencies.DECT is becoming increasingly common in clinical practice. The differences in attenuation between two different datasets allow to perform a qualitative and quantitative characterization of the materials contained in a single voxel. Virtual monoenergetic images, material decomposition images, electron density maps, and atomic number maps are created by post-processing algorithms and offer the radiologist useful diagnostic data.We present a series of cases illustrating the utility of DECT in the diagnosis and management of acute pathologies, with a special focus on musculoskeletal imaging and neuroimaging.DECT is a useful imaging technique that may allow radiologists to make quicker and more precise diagnoses in the emergency setting.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"30 2","pages":""},"PeriodicalIF":0.4,"publicationDate":"2023-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138979368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Primary hypertrophic osteoarthropathy (HOA) is a rare condition with no identifiable cause, accounting for 3%–5% of all HOA cases. It is challenging to identify incomplete primary HOA, which can be misdiagnosed as other hypertrophic periostitis diseases. At least two of the four criteria set by Borochowitz and Rimoin (1990) must be present to diagnose primary HOA. Diagnostic difficulties due to incomplete or atypical manifestations are common. We present a case of incomplete primary PHOA at Hanoi Medical University Hospital in Vietnam. A 37-year-old male presented with ankle joint pain for nearly four years. X-ray and magnetic resonance imaging showed periostitis in the tibias and fibulas, which could not exclude Camurati–Engelmann disease. Finally, gene sequencing on the Illumina MiSeq system identified a missense mutation (c.295C>T) in the solute carrier organic anion transporter family member 2A1 (SLCO2A1) gene on chromosome 3. Our case report and literature review aim to improve specialists' understanding of incomplete primary HOA and reduce the frequency of missed diagnoses.
{"title":"Atypical primary hypertrophic osteoarthropathy diagnosed with a novel SLCO2A1 gene mutation","authors":"Pham Hoai Thu, Do-Thi Huyen Trang, Luu Canh Linh, N. Duc","doi":"10.1556/1647.2023.00145","DOIUrl":"https://doi.org/10.1556/1647.2023.00145","url":null,"abstract":"Primary hypertrophic osteoarthropathy (HOA) is a rare condition with no identifiable cause, accounting for 3%–5% of all HOA cases. It is challenging to identify incomplete primary HOA, which can be misdiagnosed as other hypertrophic periostitis diseases. At least two of the four criteria set by Borochowitz and Rimoin (1990) must be present to diagnose primary HOA. Diagnostic difficulties due to incomplete or atypical manifestations are common. We present a case of incomplete primary PHOA at Hanoi Medical University Hospital in Vietnam. A 37-year-old male presented with ankle joint pain for nearly four years. X-ray and magnetic resonance imaging showed periostitis in the tibias and fibulas, which could not exclude Camurati–Engelmann disease. Finally, gene sequencing on the Illumina MiSeq system identified a missense mutation (c.295C>T) in the solute carrier organic anion transporter family member 2A1 (SLCO2A1) gene on chromosome 3. Our case report and literature review aim to improve specialists' understanding of incomplete primary HOA and reduce the frequency of missed diagnoses.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"47 21","pages":""},"PeriodicalIF":0.4,"publicationDate":"2023-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138588667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Elena Belloni, Federica Lucev, Davide Stoppa, Alberto Casazza
Pulmonary interstitial emphysema (PIE) is a rare condition most commonly encountered in mechanically ventilated patients, either infants or adults. This condition can also be diagnosed in blunt chest trauma or other conditions while performing Valsalva-like maneuvers and is often associated with pneumothorax and subcutaneous emphysema. We present the case of a patient with subtle PIE, subcutaneous emphysema and massive pneumomediastinum after protracted vomiting following a suicidal attempt by caustic ingestion. Radiologists should be aware of the potentially subtle Computed Tomography features of PIE in order to make the correct diagnosis and rule out other tracheobronchial and esophageal injuries.
肺间质气肿（PIE）是一种罕见疾病，最常见于接受机械通气的婴儿或成人患者。这种病症也可在钝性胸部创伤或其他情况下进行类似瓦尔萨尔瓦动作时被诊断出来，并且通常与气胸和皮下气肿有关。我们介绍了一例因企图摄入腐蚀性食物自杀而长期呕吐的患者，该患者伴有细微的 PIE、皮下气肿和巨大的气胸。放射科医生应了解 PIE 潜在的计算机断层扫描特征，以便做出正确诊断并排除其他气管支气管和食管损伤。
{"title":"Subtle pulmonary interstitial emphysema in attempted suicide by ingestion of a cleaning product: Computed Tomography features","authors":"Elena Belloni, Federica Lucev, Davide Stoppa, Alberto Casazza","doi":"10.1556/1647.2023.00166","DOIUrl":"https://doi.org/10.1556/1647.2023.00166","url":null,"abstract":"Pulmonary interstitial emphysema (PIE) is a rare condition most commonly encountered in mechanically ventilated patients, either infants or adults. This condition can also be diagnosed in blunt chest trauma or other conditions while performing Valsalva-like maneuvers and is often associated with pneumothorax and subcutaneous emphysema. We present the case of a patient with subtle PIE, subcutaneous emphysema and massive pneumomediastinum after protracted vomiting following a suicidal attempt by caustic ingestion. Radiologists should be aware of the potentially subtle Computed Tomography features of PIE in order to make the correct diagnosis and rule out other tracheobronchial and esophageal injuries.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"1 1","pages":""},"PeriodicalIF":0.4,"publicationDate":"2023-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139269543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Background and aim Calcium-suppressed imaging with dual-energy CT can visualize subtle cellular changes in the bone marrow. The purpose of this study was to investigate the application value of calcium-suppressed images in the evaluation of cancellous bone metastasis treated by stereotactic ablative radiotherapy (SABR). Patients and methods Dual-energy CT was performed before and after SABR in 10 patients with cancellous bone metastasis from breast cancer. Signal intensities of cancellous bone metastases to skeletal muscle were compared using calcium-suppressed images. Results The relative signal intensity of cancellous bone metastasis before SABR was 0.99 ± 0.02, while after SABR it was 0.95 ± 0.06 ( P < 0.05). Visual assessment of the signal intensity of cancellous bone metastases showed a decrease in signal intensity in all cases. Conclusions Calcium-suppressed imaging with dual-energy CT may be able to evaluate cancellous bone metastases treated by SABR.
{"title":"Dual-energy spectral CT for the evaluation of cancellous bone metastasis treated by stereotactic ablative radiotherapy","authors":"Yukihiro Hama, Etsuko Tate","doi":"10.1556/1647.2023.00127","DOIUrl":"https://doi.org/10.1556/1647.2023.00127","url":null,"abstract":"Abstract Background and aim Calcium-suppressed imaging with dual-energy CT can visualize subtle cellular changes in the bone marrow. The purpose of this study was to investigate the application value of calcium-suppressed images in the evaluation of cancellous bone metastasis treated by stereotactic ablative radiotherapy (SABR). Patients and methods Dual-energy CT was performed before and after SABR in 10 patients with cancellous bone metastasis from breast cancer. Signal intensities of cancellous bone metastases to skeletal muscle were compared using calcium-suppressed images. Results The relative signal intensity of cancellous bone metastasis before SABR was 0.99 ± 0.02, while after SABR it was 0.95 ± 0.06 ( P < 0.05). Visual assessment of the signal intensity of cancellous bone metastases showed a decrease in signal intensity in all cases. Conclusions Calcium-suppressed imaging with dual-energy CT may be able to evaluate cancellous bone metastases treated by SABR.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135646761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Due to the complexity of the images and dearth of anatomical models, it is highly difficult to accurately represent the various deformations in each component of the medical images. In recent years, a significant number of children and adults have affected from brain tumors, which is one of the most terrible types of disease affects the people around the world. Moreover, the Magnetic Resonance Imaging (MRI) based brain tumor detection is one of a significant study area in the field of medical imaging. Since, the use of computerized methods aids in the detection and treatment of disease by the medical professionals. The development of an automated method for the accurate detection and classification of tumors from brain MRIs. In this framework, a tanh normalization process is used to smooth out the input brain MRIs with less noise artefacts and improved quality. Then, a group feature extraction model is used to extract the relevant features from the normalized image, which includes both Speeded Up Robust Features (SURF) and Grey Level Co-occurrence Matrix (GLCM) features. The Water Chaotic Fruitfly Optimization (WChFO) method is used to identify the best features for increasing the speed of classifier training and testing processes with less time. Moreover, a Deep Recurrent Neural Network (DRNN) model is used to classify the type of brain tumor for accurate early diagnosis and treatment. The most well-known benchmarking datasets, like BRATS and Kaggle, employed for analysis in order to assess the effectiveness and results of the proposed brain tumor diagnosis system. By using the proposed WChFO-DRNN technique, the accuracy of the tumor detection system is increased to 99.2% with the sensitivity, specificity of 99% and time consumption of 0.2s.
{"title":"An automated detection and classification of brain tumor from MRIs using Water Chaotic Fruitfly Optimization (WChFO) based Deep Recurrent Neural Network (DRNN)","authors":"Rama Mohan Pasupuleti, Sarvade Pedda Venkata Subba Rao, Prema Kothandan, Samarthi Swapna Rani, Sathees Babu Shanmuganathan, Vijayaprabhu Arumugam","doi":"10.1556/1647.2023.00122","DOIUrl":"https://doi.org/10.1556/1647.2023.00122","url":null,"abstract":"Abstract Due to the complexity of the images and dearth of anatomical models, it is highly difficult to accurately represent the various deformations in each component of the medical images. In recent years, a significant number of children and adults have affected from brain tumors, which is one of the most terrible types of disease affects the people around the world. Moreover, the Magnetic Resonance Imaging (MRI) based brain tumor detection is one of a significant study area in the field of medical imaging. Since, the use of computerized methods aids in the detection and treatment of disease by the medical professionals. The development of an automated method for the accurate detection and classification of tumors from brain MRIs. In this framework, a tanh normalization process is used to smooth out the input brain MRIs with less noise artefacts and improved quality. Then, a group feature extraction model is used to extract the relevant features from the normalized image, which includes both Speeded Up Robust Features (SURF) and Grey Level Co-occurrence Matrix (GLCM) features. The Water Chaotic Fruitfly Optimization (WChFO) method is used to identify the best features for increasing the speed of classifier training and testing processes with less time. Moreover, a Deep Recurrent Neural Network (DRNN) model is used to classify the type of brain tumor for accurate early diagnosis and treatment. The most well-known benchmarking datasets, like BRATS and Kaggle, employed for analysis in order to assess the effectiveness and results of the proposed brain tumor diagnosis system. By using the proposed WChFO-DRNN technique, the accuracy of the tumor detection system is increased to 99.2% with the sensitivity, specificity of 99% and time consumption of 0.2s.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135981532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-09DOI: 10.1183/13993003.congress-2023.oa4848
Lucio Calandriello, John Mackintosh, Federico Felder, Aditya Agrawal, Omer Alamoudi, Laura Alberti, Giuseppe Aquaro, Juan Arenas-Jiménez, Iain Au-Yong, Sergey Avdeev, Maurizio Balbi, Bruno Baldi, Andrea Yu-Lin Ban, Ionela-Nicoleta Belaconi, Elisabeth Bendstrup, David Bennett, Hans-Christian Blum, Nicola Boscolo Bariga, Gracijela Bozovic, Marsel Broqi, John Bruzzi, Ivette Buendia-Roldan, Diana Calaras, Sérgio Campainha, Roberto G. Carbone, André Carvalho, Lorenzo Cereser, Gin Tsen Chai, Sachin Chaudhary, Nazia Chaudhuri, Patrick Alain Chui Wan Cheong, Wendy Cooper, Giuseppe Cutaia, Rosa D'Abronzo, Martijn D. De Kruif, Diemen Delgado-García, Sahajal Dhooria, Jesus J Diaz-Castanon, Glenn Eiger, Samantha Ellis, Rosa Estrada-Y-Martin, Yingying Fang
Methods: We evaluated a deep learning algorithm (DL), for classifying HRCT based on ATS/ERS/JRS/ALAT IPF guideline criteria (SOFIA), among an international group of radiologists and pulmonologists. Participants evaluated HRCTs from 203 suspected IPF patients, assigning a likelihood score for each of the guideline-based HRCT categories (each 0-100%, summing to 100%). SOFIA scores were then provided, and participants were given the opportunity to revise their scores. Agreement on (weighted kappa) and prognostic accuracy (Cox regression and C-index) of 1) UIP scores, 2) guideline-based diagnosis and 3) INBUILD categorisation (UIP/probable UIP vs indeterminate/alternative diagnosis – i.e., trial screening mode) were evaluated. Results: 116 participants completed the study, including 20 ILD trained radiologists. The majority opinion of ILD radiologists on each HRCT was used as a diagnostic reference standard. SOFIA improved agreement for UIP probability scores among all participants, excluding the ILD radiologists, (0.67 [IQR 0.57-0.73] vs 0.71 [IQR, 0.65-0.76], p=2.1x10-5) and guideline-based diagnoses (0.50 [IQR 0.43-0.54] vs 0.61 [IQR, 0.56-0.66], p=2.8x10-16) and INBUILD categorisation (0.42 [IQR 0.35-0.47] vs 0.56 [IQR, 0.49-0.62], p=7.1x10-19). Prognostic accuracy for UIP probability scores (mortality) were good for radiologist scoring (n=116, C-index=0.60 [IQR 0.58-0.62]), and these improved with the addition of SOFIA (C-index=0.63 [IQR 0.61-0.65], p=3.6x10-12). Conclusion: In pulmonary fibrosis, DL support may improve accuracy of HRCT diagnoses, provide prognostic information and faciliate screening in clinical trials.
{"title":"Late Breaking Abstract - Artificial intelligence-based decision support for HRCT stratification in fibrotic lung disease; an international study of 116 observers from 37 countries.","authors":"Lucio Calandriello, John Mackintosh, Federico Felder, Aditya Agrawal, Omer Alamoudi, Laura Alberti, Giuseppe Aquaro, Juan Arenas-Jiménez, Iain Au-Yong, Sergey Avdeev, Maurizio Balbi, Bruno Baldi, Andrea Yu-Lin Ban, Ionela-Nicoleta Belaconi, Elisabeth Bendstrup, David Bennett, Hans-Christian Blum, Nicola Boscolo Bariga, Gracijela Bozovic, Marsel Broqi, John Bruzzi, Ivette Buendia-Roldan, Diana Calaras, Sérgio Campainha, Roberto G. Carbone, André Carvalho, Lorenzo Cereser, Gin Tsen Chai, Sachin Chaudhary, Nazia Chaudhuri, Patrick Alain Chui Wan Cheong, Wendy Cooper, Giuseppe Cutaia, Rosa D'Abronzo, Martijn D. De Kruif, Diemen Delgado-García, Sahajal Dhooria, Jesus J Diaz-Castanon, Glenn Eiger, Samantha Ellis, Rosa Estrada-Y-Martin, Yingying Fang","doi":"10.1183/13993003.congress-2023.oa4848","DOIUrl":"https://doi.org/10.1183/13993003.congress-2023.oa4848","url":null,"abstract":"<b>Methods:</b> We evaluated a deep learning algorithm (DL), for classifying HRCT based on ATS/ERS/JRS/ALAT IPF guideline criteria (SOFIA), among an international group of radiologists and pulmonologists. Participants evaluated HRCTs from 203 suspected IPF patients, assigning a likelihood score for each of the guideline-based HRCT categories (each 0-100%, summing to 100%). SOFIA scores were then provided, and participants were given the opportunity to revise their scores. Agreement on (weighted kappa) and prognostic accuracy (Cox regression and C-index) of 1) UIP scores, 2) guideline-based diagnosis and 3) INBUILD categorisation (UIP/probable UIP vs indeterminate/alternative diagnosis – i.e., trial screening mode) were evaluated. <b>Results:</b> 116 participants completed the study, including 20 ILD trained radiologists. The majority opinion of ILD radiologists on each HRCT was used as a diagnostic reference standard. SOFIA improved agreement for UIP probability scores among all participants, excluding the ILD radiologists, (0.67 [IQR 0.57-0.73] vs 0.71 [IQR, 0.65-0.76], p=2.1x10-5) and guideline-based diagnoses (0.50 [IQR 0.43-0.54] vs 0.61 [IQR, 0.56-0.66], p=2.8x10-16) and INBUILD categorisation (0.42 [IQR 0.35-0.47] vs 0.56 [IQR, 0.49-0.62], p=7.1x10-19). Prognostic accuracy for UIP probability scores (mortality) were good for radiologist scoring (n=116, C-index=0.60 [IQR 0.58-0.62]), and these improved with the addition of SOFIA (C-index=0.63 [IQR 0.61-0.65], p=3.6x10-12). <b>Conclusion:</b> In pulmonary fibrosis, DL support may improve accuracy of HRCT diagnoses, provide prognostic information and faciliate screening in clinical trials.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136194526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：