RESUMO
OBJECTIVES: The interpretation of mammograms requires many years of training and experience. Currently, training in mammography, like the rest of diagnostic radiology, is through institutional libraries, books, and experience accumulated over time. We explore whether artificial Intelligence (AI)-generated images can help in simulation education and result in measurable improvement in performance of residents in training. METHODS: We developed a generative adversarial network (GAN) that was capable of generating mammography images with varying characteristics, such as size and density, and created a tool with which a user could control these characteristics. The tool allowed the user (a radiology resident) to realistically insert cancers within different regions of the mammogram. We then provided this tool to residents in training. Residents were randomized into a practice group and a non-practice group, and the difference in performance before and after practice with such a tool (in comparison to no intervention in the non-practice group) was assessed. RESULTS: Fifty residents participated in the study, 27 underwent simulation training, and 23 did not. There was a significant improvement in the sensitivity (7.43 percent, significant at p-value = 0.03), negative predictive value (5.05 percent, significant at p-value = 0.008) and accuracy (6.49 percent, significant at p-value = 0.01) among residents in the detection of cancer on mammograms after simulation training. CONCLUSION: Our study shows the value of simulation training in diagnostic radiology and explores the potential of generative AI to enable such simulation training. CLINICAL RELEVANCE STATEMENT: Using generative artificial intelligence, simulation training modules can be developed that can help residents in training by providing them with a visual impression of a variety of different cases. KEY POINTS: Generative networks can produce diagnostic imaging with specific characteristics, potentially useful for training residents. Training with generating images improved residents' mammographic diagnostic abilities. Development of a game-like interface that exploits these networks can result in improvement in performance over a short training period.
RESUMO
OBJECTIVES: To analyze the performance of deep learning in isodense/obscure masses in dense breasts. To build and validate a deep learning (DL) model using core radiology principles and analyze its performance in isodense/obscure masses. To show performance on screening mammography as well as diagnostic mammography distribution. METHODS: This was a retrospective, single-institution, multi-centre study with external validation. For model building, we took a 3-pronged approach. First, we explicitly taught the network to learn features other than density differences: such as spiculations and architectural distortion. Second, we used the opposite breast to enable the detection of asymmetries. Third, we systematically enhanced each image by piece-wise-linear transformation. We tested the network on a diagnostic mammography dataset (2569 images with 243 cancers, January to June 2018) and a screening mammography dataset (2146 images with 59 cancers, patient recruitment from January to April 2021) from a different centre (external validation). RESULTS: When trained with our proposed technique (and compared with baseline network), sensitivity for malignancy increased from 82.7 to 84.7% at 0.2 False positives per image (FPI) in the diagnostic mammography dataset, 67.9 to 73.8% in the subset of patients with dense breasts, 74.6 to 85.3 in the subset of patients with isodense/obscure cancers and 84.9 to 88.7 in an external validation test set with a screening mammography distribution. We showed that our sensitivity exceeded currently reported values (0.90 at 0.2 FPI) on a public benchmark dataset (INBreast). CONCLUSION: Modelling traditional mammographic teaching into a DL framework can help improve cancer detection accuracy in dense breasts. CLINICAL RELEVANCE STATEMENT: Incorporating medical knowledge into neural network design can help us overcome some limitations associated with specific modalities. In this paper, we show how one such deep neural network can help improve performance on mammographically dense breasts. KEY POINTS: ⢠Although state-of-the-art deep learning networks achieve good results in cancer detection in mammography in general, isodense, obscure masses and mammographically dense breasts posed a challenge to deep learning networks. ⢠Collaborative network design and incorporation of traditional radiology teaching into the deep learning approach helped mitigate the problem. ⢠The accuracy of deep learning networks may be translatable to different patient distributions. We showed the results of our network on screening as well as diagnostic mammography datasets.
Assuntos
Neoplasias da Mama , Aprendizado Profundo , Humanos , Feminino , Mamografia/métodos , Densidade da Mama , Estudos Retrospectivos , Neoplasias da Mama/diagnóstico por imagem , Detecção Precoce de CâncerRESUMO
A middle-aged woman presented with symptomatic complete heart block and underwent an uneventful dual chamber pacemaker implantation. Three weeks post procedure, she developed left arm pain and weakness, with neurological localization to the lower trunk of left brachial plexus. Possibilities of traumatic compression by the device/leads or postoperative idiopathic brachial plexopathy were considered. After ruling out traumatic causes, she was started on oral steroids, to which she responded remarkably. This case highlights the importance of recognizing this rare cause of brachial plexopathy following pacemaker implantation, because not only does an expedited diagnosis and medical treatment lead to prompt recovery with minimal neurological deficits, but it also circumvents an unnecessary surgical re-exploration.
Assuntos
Neuropatias do Plexo Braquial , Plexo Braquial , Marca-Passo Artificial , Neuropatias do Plexo Braquial/diagnóstico , Neuropatias do Plexo Braquial/etiologia , Feminino , Humanos , Pessoa de Meia-Idade , Marca-Passo Artificial/efeitos adversosRESUMO
Aims: The conventional Seldinger and trocar techniques of percutaneous nephrostomy (PCN) have inherent limitations in infants and younger children. We studied the role of a novel coaxial technique of PCN in children under the age of 5 years in comparison to the conventional techniques. Materials and Methods: This was a single-center feasibility trial based on 24 consecutive patients (n = 24 kidneys) under the age of 5 years, conducted over 12 months, substratified into Group I (n = 10): PCN with conventional Seldinger (n = 2) and trocar (n = 8) techniques and Group II (n = 14): PCN with proposed coaxial technique. In the proposed technique, catheter was inserted through the bore of a 14-G needle. The observation parameters included successful placement of PCN into the renal pelvis with free drainage of urine, number of needle punctures, duration of procedure, need for fluoroscopy, and procedural complications. Results: Proposed technique was successful in all cases with single-needle puncture, while conventional techniques were successful in 8/10 (80%) cases with multiple needle punctures required in 3/10 (33.3%) cases (P = 0.163 and 0.059, respectively). Proposed technique was associated with lower median procedure time (6 min vs. 10.5 min; P < 0.001) and lower incidence of fluoroscopy use (0/14, 0% vs. 5/10, 50%; P = 0.006) than the conventional techniques. No complications were seen with either technique. Conclusion: The proposed coaxial technique is a feasible alternative to the conventional techniques of PCN in young children. It reduces the procedure time and the need for fluoroscopy in these patients.
RESUMO
OBJECTIVES: To study whether a trained convolutional neural network (CNN) can be of assistance to radiologists in differentiating Coronavirus disease (COVID)-positive from COVID-negative patients using chest X-ray (CXR) through an ambispective clinical study. To identify subgroups of patients where artificial intelligence (AI) can be of particular value and analyse what imaging features may have contributed to the performance of AI by means of visualisation techniques. METHODS: CXR of 487 patients were classified into [4] categories-normal, classical COVID, indeterminate, and non-COVID by consensus opinion of 2 radiologists. CXR which were classified as "normal" and "indeterminate" were then subjected to analysis by AI, and final categorisation provided as guided by prediction of the network. Precision and recall of the radiologist alone and radiologist assisted by AI were calculated in comparison to reverse transcriptase-polymerase chain reaction (RT-PCR) as the gold standard. Attention maps of the CNN were analysed to understand regions in the CXR important to the AI algorithm in making a prediction. RESULTS: The precision of radiologists improved from 65.9 to 81.9% and recall improved from 17.5 to 71.75 when assistance with AI was provided. AI showed 92% accuracy in classifying "normal" CXR into COVID or non-COVID. Analysis of attention maps revealed attention on the cardiac shadow in these "normal" radiographs. CONCLUSION: This study shows how deployment of an AI algorithm can complement a human expert in the determination of COVID status. Analysis of the detected features suggests possible subtle cardiac changes, laying ground for further investigative studies into possible cardiac changes. KEY POINTS: ⢠Through an ambispective clinical study, we show how assistance with an AI algorithm can improve recall (sensitivity) and precision (positive predictive value) of radiologists in assessing CXR for possible COVID in comparison to RT-PCR. ⢠We show that AI achieves the best results in images classified as "normal" by radiologists. We conjecture that possible subtle cardiac in the CXR, imperceptible to the human eye, may have contributed to this prediction. ⢠The reported results may pave the way for a human computer collaboration whereby the expert with some help from the AI algorithm achieves higher accuracy in predicting COVID status on CXR than previously thought possible when considering either alone.
Assuntos
Inteligência Artificial , COVID-19 , Humanos , Radiografia Torácica , SARS-CoV-2 , Tomografia Computadorizada por Raios X , Raios XRESUMO
History A 44-year-old woman who was a resident of Bihar, which is a state in eastern India, presented to the surgical outpatient department of our hospital with a history of gradually increasing swelling of the right breast associated with redness, pain, and itching over the past month. She reported a general sense of malaise and experienced episodes of chills over the past 6 months; however, she had no documented fever. There was no history of breast trauma. No history suggestive of a possible hypercoagulable state could be elicited (she was a nonsmoker, had undergone uncomplicated normal vaginal delivery 15 years earlier, was not taking oral contraceptives, and had no history to suggest past deep venous thrombosis). General physical examination findings were unremarkable. On local examination, she was found to have diffuse enlargement of the right breast. The skin over the lateral part of the breast was erythematous and showed the presence of prominent superficial veins. On palpation, few ill-defined firm mobile masses were found in the upper outer quadrant with overlying skin induration. No skin ulceration or nipple discharge was present. Few firm and discrete lymph nodes were palpable in the right axilla. Laboratory investigations showed mild anemia (hemoglobin level, 10 g/dL; normal range, 12-15 g/dL), a total leukocyte count of 14 000 cells per microliter (14 cells × 109/L) (normal range, 4500-11 000 cells per microliter [4.5-11 cells × 109/L]), a normal differential leukocyte count (74% neutrophils [normal range, 40%-80%], 24% lymphocytes [normal range, 20%-40%], and 2% eosinophils [normal range, 1%-4%]), and an erythrocyte sedimentation rate of 31 mm per hour (normal range, 0-29 mm per hour). She underwent both mammography and US. Real-time US showed mobile structures on the series of US images obtained seconds apart. On the basis of the imaging findings, US-guided fine-needle aspiration cytology was performed to confirm the diagnosis, and appropriate treatment was instituted.
Assuntos
Doenças Mamárias/diagnóstico por imagem , Doenças Mamárias/parasitologia , Filariose/diagnóstico por imagem , Adulto , Biópsia por Agulha Fina , Feminino , Humanos , Mamografia , Ultrassonografia MamáriaRESUMO
History A 44-year-old woman who was a resident of Bihar, which is a state in eastern India, presented to the surgical outpatient department of our hospital with a history of gradually increasing swelling of the right breast associated with redness, pain, and itching over the past month (Fig 1). She reported a general sense of malaise and experienced episodes of chills over the past 6 months; however, she had no documented fever. There was no history of breast trauma. No history suggestive of a possible hypercoagulable state could be elicited (she was a nonsmoker, had undergone uncomplicated normal vaginal delivery 15 years earlier, was not taking oral contraceptives, and had no history to suggest past deep venous thrombosis). General physical examination findings were unremarkable. On local examination, she was found to have diffuse enlargement of the right breast. The skin over the lateral part of the breast was erythematous and showed the presence of prominent superficial veins. On palpation, few ill-defined firm mobile masses were found in the upper outer quadrant with overlying skin induration. No skin ulceration or nipple discharge was present. Few firm and discrete lymph nodes were palpable in the right axilla. Laboratory investigations showed mild anemia (hemoglobin level, 10 g/dL; normal range, 12-15 g/dL), a total leukocyte count of 14 000 cells per microliter (14 cells × 109/L) (normal range, 4500-11 000 cells per microliter [4.5-11 cells × 109/L]), a normal differential leukocyte count (74% neutrophils [normal range, 40%-80%], 24% lymphocytes [normal range, 20%-40%], and 2% eosinophils [normal range, 1%-4%]), and an erythrocyte sedimentation rate of 31 mm per hour (normal range, 0-29 mm per hour). She underwent both mammography (Fig 2) and US (Fig 3). Real-time US showed mobile structures on the series of US images obtained seconds apart (Fig 4). On the basis of the imaging findings, US-guided fine-needle aspiration cytology was performed to confirm the diagnosis, and appropriate treatment was instituted.
RESUMO
Background Although abundant literature is currently available on the use of deep learning for breast cancer detection in mammography, the quality of such literature is widely variable. Purpose To evaluate published literature on breast cancer detection in mammography for reproducibility and to ascertain best practices for model design. Methods The PubMed and Scopus databases were searched to identify records that described the use of deep learning to detect lesions or classify images into cancer or noncancer. A modification of Quality Assessment of Diagnostic Accuracy Studies (mQUADAS-2) tool was developed for this review and was applied to the included studies. Results of reported studies (area under curve [AUC] of receiver operator curve [ROC] curve, sensitivity, specificity) were recorded. Results A total of 12,123 records were screened, of which 107 fit the inclusion criteria. Training and test datasets, key idea behind model architecture, and results were recorded for these studies. Based on mQUADAS-2 assessment, 103 studies had high risk of bias due to nonrepresentative patient selection. Four studies were of adequate quality, of which three trained their own model, and one used a commercial network. Ensemble models were used in two of these. Common strategies used for model training included patch classifiers, image classification networks (ResNet in 67%), and object detection networks (RetinaNet in 67%). The highest reported AUC was 0.927 ± 0.008 on a screening dataset, while it reached 0.945 (0.919-0.968) on an enriched subset. Higher values of AUC (0.955) and specificity (98.5%) were reached when combined radiologist and Artificial Intelligence readings were used than either of them alone. None of the studies provided explainability beyond localization accuracy. None of the studies have studied interaction between AI and radiologist in a real world setting. Conclusion While deep learning holds much promise in mammography interpretation, evaluation in a reproducible clinical setting and explainable networks are the need of the hour.
RESUMO
PURPOSE: The proposed work aims to develop an algorithm to precisely segment the lung parenchyma in thoracic CT scans. To achieve this goal, the proposed technique utilized a combination of deep learning and traditional image processing algorithms. The initial step utilized a trained convolutional neural network (CNN) to generate preliminary lung masks, followed by the proposed post-processing algorithm for lung boundary correction. METHODS: First, the proposed method trained an improved 2D U-Net CNN model with Inception-ResNet-v2 as its backbone. The model was trained on 32 CT scans from two different sources: one from the VESSEL12 grand challenge and the other from AIIMS Delhi. Further, the model's performance was evaluated on a test dataset of 16 CT scans with juxta-pleural nodules obtained from AIIMS Delhi and the LUNA16 challenge. The model's performance was assessed using evaluation metrics such as average volumetric dice coefficient (DSCavg), average IoU score (IoUavg), and average F1 score (F1avg). Finally, the proposed post-processing algorithm was implemented to eliminate false positives from the model's prediction and to include juxta-pleural nodules in the final lung masks. RESULTS: The trained model reported a DSCavg of 0.9791 ± 0.008, IoUavg of 0.9624 ± 0.007, and F1avg of 0.9792 ± 0.004 on the test dataset. Applying the post-processing algorithm to the predicted lung masks obtained a DSCavg of 0.9713 ± 0.007, IoUavg of 0.9486 ± 0.007, and F1avg of 0.9701 ± 0.008. The post-processing algorithm successfully included juxta-pleural nodules in the final lung mask. CONCLUSIONS: Using a CNN model, the proposed method for lung parenchyma segmentation produced precise segmentation results. Furthermore, the post-processing algorithm addressed false positives and negatives in the model's predictions. Overall, the proposed approach demonstrated promising results for lung parenchyma segmentation. The method has the potential to be valuable in the advancement of computer-aided diagnosis (CAD) systems for automatic nodule detection.
Assuntos
Aprendizado Profundo , Humanos , Pulmão/diagnóstico por imagem , Tórax , Redes Neurais de Computação , Processamento de Imagem Assistida por Computador/métodos , Tomografia Computadorizada por Raios XRESUMO
PURPOSE: The current study explores the application of 3D U-Net architectures combined with Inception and ResNet modules for precise lung nodule detection through deep learning-based segmentation technique. This investigation is motivated by the objective of developing a Computer-Aided Diagnosis (CAD) system for effective diagnosis and prognostication of lung nodules in clinical settings. METHODS: The proposed method trained four different 3D U-Net models on the retrospective dataset obtained from AIIMS Delhi. To augment the training dataset, affine transformations and intensity transforms were utilized. Preprocessing steps included CT scan voxel resampling, intensity normalization, and lung parenchyma segmentation. Model optimization utilized a hybrid loss function that combined Dice Loss and Focal Loss. The model performance of all four 3D U-Nets was evaluated patient-wise using dice coefficient and Jaccard coefficient, then averaged to obtain the average volumetric dice coefficient (DSCavg) and average Jaccard coefficient (IoUavg) on a test dataset comprising 53 CT scans. Additionally, an ensemble approach (Model-V) was utilized featuring 3D U-Net (Model-I), ResNet (Model-II), and Inception (Model-III) 3D U-Net architectures, combined with two distinct patch sizes for further investigation. RESULTS: The ensemble of models obtained the highest DSCavg of 0.84 ± 0.05 and IoUavg of 0.74 ± 0.06 on the test dataset, compared against individual models. It mitigated false positives, overestimations, and underestimations observed in individual U-Net models. Moreover, the ensemble of models reduced average false positives per scan in the test dataset (1.57 nodules/scan) compared to individual models (2.69-3.39 nodules/scan). CONCLUSIONS: The suggested ensemble approach presents a strong and effective strategy for automatically detecting and delineating lung nodules, potentially aiding CAD systems in clinical settings. This approach could assist radiologists in laborious and meticulous lung nodule detection tasks in CT scans, improving lung cancer diagnosis and treatment planning.
RESUMO
With the rapid integration of artificial intelligence into medical practice, there has been an exponential increase in the number of scientific papers and industry players offering models designed for various tasks. Understanding these, however, is difficult for a radiologist in practice, given the core mathematical principles and complicated terminology involved. This review aims to elucidate the core mathematical concepts of both machine learning and deep learning models, explaining the various steps and common terminology in common layman language. Thus, by the end of this article, the reader should be able to understand the basics of how prediction models are built and trained, including challenges faced and how to avoid them. The reader would also be equipped to adequately evaluate various models, and take a decision on whether a model is likely to perform adequately in the real-world setting.
Assuntos
Algoritmos , Inteligência Artificial , Humanos , Aprendizado de Máquina , Radiologistas , Pessoal de SaúdeRESUMO
We encountered a giant dermatofibrosarcoma protuberans (DFSP) of the neck and chest wall which presented a challenge in terms of perioperative analgesia management. In recent years, erector spinae plane (ESP) block has emerged as an effective and safe analgesia technique for various surgical procedures as well as for chronic neuropathic pain without any untoward complications. A continuous lower cervical ESP block can be used successfully as an effective analgesic technique for extensive DFSP surgery involving the neck and chest wall area.
Assuntos
Dermatofibrossarcoma , Bloqueio Nervoso , Neoplasias Cutâneas , Parede Torácica , Humanos , Parede Torácica/cirurgia , Dor Pós-Operatória , Bloqueio Nervoso/métodos , Dermatofibrossarcoma/cirurgia , Dermatofibrossarcoma/complicações , Neoplasias Cutâneas/complicaçõesRESUMO
Data Privacy has increasingly become a matter of concern in the era of large public digital respositories of data. This is particularly true in healthcare where data can be misused if traced back to patients, and brings with itself a myriad of possibilities. Bring custodians of data, as well as being at the helm of disigning studies and products that can potentially benefit products, healthcare professionals often find themselves unsure about ethical and legal constraints that undelie data sharing. In this review we touch upon the concerns, leal frameworks as well as some common practices in these respects.
RESUMO
Management of central nervous system (CNS) metastases from epithelial ovarian cancer (EOC) is an unmet need. We analyzed data on 41 such patients to evaluate predictors of outcome. Between January, 2010 and December 2020, among 1028 patients with EOC treated at our institute 41 (3.98%) developed CNS metastasis. Median age of patients was 48 years, ranging from 22 to 75 years. Primary outcome measure was progression free survival (PFS). Overall survival (OS), and analysis of prognostic factors were secondary outcome measures. An intention to treat analysis was done. We also performed review the literature (n=2253) as regards to clinicopathological and radiological features, treatment received, survival outcomes and prognostic factors. Median time from diagnosis of EOC to CNS metastasis was 27 months (range: 0 to 101 months). 33(80.5%) patients had FIGO stage III-IV at baseline and serous carcinoma (75.6%) was common pathology subtype. Thirteen (31.7%) patients had isolated CNS metastasis and 28 (68.3%) had intra-abdominal disease in addition. Nineteen (46.3%) patients achieved complete response post treatment with surgery, radiation and chemotherapy. Median PFS and OS from the time of CNS metastasis is 12 (range:1 to 51) months and 33 (range: 1 to 71) months, respectively. Absence of extracranial disease and lower serum CA-125 at diagnosis of CNS metastasis were predictive of superior PFS and OS on multivariate analysis. CNS metastasis is a late event in EOC, post multiple lines of treatment. Patients with disease limited to brain and treated with surgical resection and chemoradiation have best outcome.
Assuntos
Neoplasias do Sistema Nervoso Central , Neoplasias Ovarianas , Humanos , Feminino , Pessoa de Meia-Idade , Carcinoma Epitelial do Ovário , Neoplasias Ovarianas/patologia , Prognóstico , Neoplasias do Sistema Nervoso Central/terapia , Estadiamento de Neoplasias , EncéfaloRESUMO
The presence of lung metastases in patients with primary malignancies is an important criterion for treatment management and prognostication. Computed tomography (CT) of the chest is the preferred method to detect lung metastasis. However, CT has limited efficacy in differentiating metastatic nodules from benign nodules (e.g., granulomas due to tuberculosis) especially at early stages (<5 mm). There is also a significant subjectivity associated in making this distinction, leading to frequent CT follow-ups and additional radiation exposure along with financial and emotional burden to the patients and family. Even 18F-fluoro-deoxyglucose positron emission technology-computed tomography (18F-FDG PET-CT) is not always confirmatory for this clinical problem. While pathological biopsy is the gold standard to demonstrate malignancy, invasive sampling of small lung nodules is often not clinically feasible. Currently, there is no non-invasive imaging technique that can reliably characterize lung metastases. The lung is one of the favored sites of metastasis in sarcomas. Hence, patients with sarcomas, especially from tuberculosis prevalent developing countries, can provide an ideal platform to develop a model to differentiate lung metastases from benign nodules. To overcome the lack of optimal specificity of CT scan in detecting pulmonary metastasis, a novel artificial intelligence (AI)-based protocol is proposed utilizing a combination of radiological and clinical biomarkers to identify lung nodules and characterize it as benign or metastasis. This protocol includes a retrospective cohort of nearly 2,000-2,250 sample nodules (from at least 450 patients) for training and testing and an ambispective cohort of nearly 500 nodules (from 100 patients; 50 patients each from the retrospective and prospective cohort) for validation. Ground-truth annotation of lung nodules will be performed using an in-house-built segmentation tool. Ground-truth labeling of lung nodules (metastatic/benign) will be performed based on histopathological results or baseline and/or follow-up radiological findings along with clinical outcome of the patient. Optimal methods for data handling and statistical analysis are included to develop a robust protocol for early detection and classification of pulmonary metastasis at baseline and at follow-up and identification of associated potential clinical and radiological markers.
RESUMO
BACKGROUND: Performing ultrasound during the current pandemic time is quite challenging. To reduce the chances of cross-infection and keep healthcare workers safe, a robotic ultrasound system was developed, which can be controlled remotely. It will also pave way for broadening the reach of ultrasound in remote distant rural areas as well. AIM: To assess the feasibility of a robotic system in performing abdominal ultrasound and compare it with the conventional ultrasound system. METHODS: A total of 21 healthy volunteers were recruited. Ultrasound was performed in two settings, using the robotic arm and conventional hand-held procedure. Images acquired were analyzed by separate radiologists. RESULTS: Our study showed that the robotic arm model was feasible, and the results varied based on the organ imaged. The liver images showed no significant difference. For other organs, the need for repeat imaging was higher in the robotic arm, which could be attributed to the radiologist's learning curve and ability to control the haptic device. The doctor and volunteer surveys also showed significant comfort with acceptance of the technology and they expressed their desire to use it in the future. CONCLUSION: This study shows that robotic ultrasound is feasible and is the need of the hour during the pandemic.
RESUMO
While detection of malignancies on mammography has received a boost with the use of Convolutional Neural Networks (CNN), detection of cancers of very small size remains challenging. This is however clinically significant as the purpose of mammography is early detection of cancer, making it imperative to pick them up when they are still very small. Mammography has the highest spatial resolution (image sizes as high as 3328 × 4096 pixels) out of all imaging modalities, a requirement that stems from the need to detect fine features of the smallest cancers on screening. However due to computational constraints, most state of the art CNNs work on reduced resolution images. Those that work on higher resolutions, compromise on global context and work at single scale. In this work, we show that resolution, scale and image-context are all important independent factors in detection of small masses. We thereby use a fully convolutional network, with the ability to take any input size. In addition, we incorporate a systematic multi-scale, multi-resolution approach, and encode image context, which we show are critical factors to detection of small masses. We show that this approach improves the detection of cancer, particularly for small masses in comparison to the baseline model. We perform a single institution multicentre study, and show the performance of the model on a diagnostic mammography dataset, a screening mammography dataset, as well as a curated dataset of small cancers < 1 cm in size. We show that our approach improves the sensitivity from 61.53 to 87.18% at 0.3 False Positives per Image (FPI) on this small cancer dataset. Model and code are available from https://github.com/amangupt01/Small_Cancer_Detection.
Assuntos
Neoplasias da Mama , Mamografia , Neoplasias da Mama/diagnóstico por imagem , Detecção Precoce de Câncer , Feminino , Humanos , Mamografia/métodos , Programas de Rastreamento , Redes Neurais de ComputaçãoRESUMO
Introduction The COVID-19 pandemic has been a major public health threat for the past three years. The RNA virus has been constantly evolving, changing the manifestations and progression of the disease. Some factors which impact the progression to severe COVID-19 or mortality include comorbidities such as diabetes mellitus, hypertension, and obesity. In this study, we followed a cohort of patients to evaluate the risk factors leading to severe manifestations and mortality from COVID-19. Methodology We conducted a prospective observational study of 589 COVID-19 patients to assess the risk factors associated with the severity and mortality of the disease. Results In our cohort, 83.5% were male, with a median age (p25, p75) of 39.71 (30-48) years. The most common comorbidities included diabetes mellitus (7.8%) and hypertension (7.9%). About 41.7% had an asymptomatic disease, and of the symptomatic, 45% were mild, 6% moderate, and 7% severe. The mortality rate was 4.1%. Risk factors for severity included breathlessness (p=0.02), leukocytosis (p=0.02), and deranged renal function (p=0.04). Risk factors for mortality included older age (p=0.04), anemia (p=0.02), and leukocytosis (p=0.02). Conclusions COVID-19 commonly leads to asymptomatic or mild illness. The major factors we found that were associated with severity include breathlessness at presentation, leukocytosis, and deranged renal functions. The factors associated with mortality include older age, anemia, and leukocytosis.
RESUMO
Objectives Accurate delineation of anatomy in children with ambiguous genitalia early in life is important. This commonly involves conventional fluoroscopic genitogram (traumatic to the child) and magnetic resonance imaging (MRI) examination (involves sedation). In this study, our objectives were twofold: (1) to describe the findings on transperineal ultrasound (TPUS) in normal children and (2) to describe the findings on TPUS in children with ambiguous genitalia and correlate them with conventional genitogram. Materials and Methods TPUS was prospectively performed in 10 children without genital ambiguity (5 girls and 5 boys). Subsequently, 15 consecutive children having disorders of sex differentiation (DSDs) with genital ambiguity underwent TPUS. The presence or absence of müllerian structures was documented. Of these patients, 14 also underwent conventional genitogram as a part of routine evaluation. The gold standard was established either by comparison with surgical findings (in patients who underwent surgery) or by comparison with a combination of findings on genitogram and transabdominal ultrasound in patients who did not undergo surgery. Results In all normal children, lower urogenital tracts could be clearly delineated on TPUS. Out of the 15 children with ambiguous genitalia, TPUS could establish the presence/absence of müllerian structures in 14. This was concordant with findings on conventional genitogram/surgery. In one patient, müllerian structure was missed on TPUS but demonstrated on genitogram. In two children, TPUS showed the müllerian structure, which was not seen on genitogram. When both the controls and the cases were combined, TPUS had an accuracy of 95% and specificity of 100% in the detection of müllerian structures. Conclusion TPUS is feasible and accurate in demonstration of lower urogenital tract anatomy in children with DSDs having ambiguous genitalia. It can be performed without sedation, and is suitable for use as a screening modality in children with ambiguous genitalia.