Classification of Mouse Lung Metastatic Tumor with Deep Learning
4
Citation
23
Reference
10
Related Paper
Citation Trend
Abstract:
Traditionally, pathologists microscopically examine tissue sections to detect pathological lesions; the many slides that must be evaluated impose severe work burdens. Also, diagnostic accuracy varies by pathologist training and experience; better diagnostic tools are required. Given the rapid development of computer vision, automated deep learning is now used to classify microscopic images, including medical images. Here, we used a Inception-v3 deep learning model to detect mouse lung metastatic tumors via whole slide imaging (WSI); we cropped the images to 151 by 151 pixels. The images were divided into training (53.8%) and test (46.2%) sets (21,017 and 18,016 images, respectively). When images from lung tissue containing tumor tissues were evaluated, the model accuracy was 98.76%. When images from normal lung tissue were evaluated, the model accuracy ("no tumor") was 99.87%. Thus, the deep learning model distinguished metastatic lesions from normal lung tissue. Our approach will allow the rapid and accurate analysis of various tissues.Keywords:
Lung tumor
Lung cancer is still a leading cause of cancer mortality in the world. The incidence of lung cancer in developed countries started to decrease mainly due to global anti-smoking campaigns. However, the incidence of lung cancer in women has been increasing in recent decades for various reasons. Furthermore, since the screening of lung cancer is not as yet very effective, clinically applicable molecular markers for early diagnosis are much required. Lung cancer in women appears to have differences compared with that in men, in terms of histologic types and susceptibility to environmental risk factors. This suggests that female lung cancer can be derived by carcinogenic mechanisms different from those involved in male lung cancer. Among female lung cancer patients, many are non-smokers, which could be studied to identify alternative carcinogenic mechanisms independent from smoking-related ones. In this paper, we reviewed molecular susceptibility markers and genetic changes in lung cancer tissues observed in female lung cancer patients, which have been validated by various studies and will be helpful to understand the tumorigenesis of lung cancer.
Genetic predisposition
Epidemiology of cancer
Cite
Citations (9)
Introduction: People with tuberculosis (TB) have an increased risk of pulmonary cancer. They are also disproportionately affected by risk factors like immune suppression, smoking, and alcohol misuse. A lung tumor is reported to have occurred after an episode of TB, but we reported a patient with a lung tumor with co-infection TB and lung abscess at the same time. Case: A 73-year-old man was hospitalized at Arifin Achmad General Hospital, Pekanbaru, with a 3-day history of bloody cough 2-3 times a day, 1-2 tablespoons estimated by the patient for blood from the cough. The patient had a cough with white phlegm in the last 4 months before the bloody cough. The patient also had a fever, night sweats, a limp body, decreased appetite for 6 months, and decreased body weight by 15 kg in the last year. Heterogenic consolidation on the superior lobe of the lung with prominence compression and irregular boundaries in the apex was found. We found an air bronchogram and multiple cavities with air-fluid levels inside the lesion. We also found a satellite nodule in the inferior lung and a mass connected with the chest wall. GeneXpert showed low detection for Mycobacterium tuberculosis. The patient was diagnosed with a left lung abscess, pulmonary TB, left lung tumor T4N2M1a, unspecified type of tumor stage IVA PS2, and osteoporosis. Conclusion: Lung tumors could also be diagnosed with co-infection TB. Proper diagnosis to make sure cancer and TB are co-infected is necessary. Therefore, it will not be just a single disease that is treated.
Bloody
Lung abscess
Productive Cough
Phlegm
Cite
Citations (0)
The Intel Collaborative Research Institute for Computational Intelligence (ICRI-CI) has been heavily supporting Machine Learning and Deep Learning research from its foundation in 2012. We have asked six leading ICRI-CI Deep Learning researchers to address the challenge of Why & When Deep Learning works, with the goal of looking inside Deep Learning, providing insights on how deep networks function, and uncovering key observations on their expressiveness, limitations, and potential. The output of this challenge resulted in five papers that address different facets of deep learning. These different facets include a high-level understating of why and when deep networks work (and do not work), the impact of geometry on the expressiveness of deep networks, and making deep networks interpretable.
Foundation (evidence)
Deep time
Cite
Citations (1)
Feature (linguistics)
Cite
Citations (881)
Lung tumor
Cite
Citations (2)
Objective To discuss clinical diagnostic value of combined detection multiple tumor marker contents in the lung cancer.Methods Selected 35 cases of lung cancer and another 35 cases of benign lung diseases as a control group admitted in our hospital from February 2007 to December 2010.Detected the levels of CEA、serum CA19-9、NSE and CYFRA21-1.Results The levels of single tumor markers in lung cancer group showed no significant difference from benign lung diseases group(P0.05),various levels of tumor markers for diagnosis of lung cancer had a sensitivity of 50.04%,specificity of 93.42%,accuracy of 72.94%.Conclusion Combined detection of 4 tumor markers for the diagnosis of lung cancer is great significance,is better than individual testing,provides more powerful evidence for diagnosis and differential diagnosis of lung cancer.
Tumor M2-PK
Lung tumor
Cite
Citations (0)
The various hurdles in machine learning are beaten by deep learning techniques and then the deep learning has gradually become preeminent in artificial intelligence. Deep learning uses neural networks to kindle decisions like humans. Deep learning flourished as an energetic approach and clarity marked its success in various domains. The study includes some dominant deep learning algorithms such as convolution neural network, fully convolutional network, autoencoder, and deep belief network to analyze the medical image and to detect and diagnose of cancer at an early stage. As early as the detection of cancer than to treat the disease is uncomplicated. Early diagnosis was particularly relevant for some cancers such as breast, skin, colon, and rectum, which prohibit the chance to grow and spread. Deep learning contributes to enhanced performance and better prediction in detection of cancer with medical images. The paper presents the study of a few deep learning software frameworks such as tensor flow, theano, caffe, torch, and keras. Tensor Flow provides excellent functionality for deep learning. Keras is a high-level neural network API that operates above on tensor flow or theano. The survey winds up by presenting several future avenues and open challenges that should be addressed by the researcher in the future.
Autoencoder
Cite
Citations (4)
[Abstract] Objective To study on the morbidity,morphology,histological type and biological characteristics of spontaneous lung tumor in Kunming mice. Methods A total of 1000 Kunming mice propagated in Changchun Institute of Biological Products were dissected, and the routine patholoical sections were prepared from the lobes of lung, trachea, pulmongical hilar lymph nodes, hearts, livers, spleens and brains of them and used for histopathological examination. Results Fifty - six cases of lung lump were observed during dissection. Thirty - five cases were diagnosed as lung tumor, and the rest 21 cases as nontumorous pathological change or metastatic tumor.The morbidity rate of spontaneous primary lung tumor was 3.5% . Most of the tumors were round and nodular,and a small proportion of them were oval,fungoid,platode,large biock or slightly square. Of the 35 cases of lung tumor, 32 were adenocarcinoma of lung, and the rest 3 were benign papillary adenoma. The 32 cases consisted of 20 cases of papillary, 5 cases of acinar, 6 cases of mixed type and 1 case of mucous papillary adenocarcinoma. Of the 35 mice with lung tumor,20 were male,and the rest 15 were female.The sex ratio of them was 4:3. The morbidity of lung tumor in the mice aged 10 - 14 months and those at the 8th to 12th litters increased significantly. Conclusion The morbidity of spontaneous lung showed no signifcant difference in the mice of different sexes. However, it increased as the increasing ages of the mice. A mouse should not give birth to more than 7 litters.
Lung tumor
Rest (music)
Histopathological examination
Papillary adenocarcinoma
Cite
Citations (0)
Abstract: Deep fake is a rapidly growing concern in society, and it has become a significant challenge to detect such manipulated media. Deep fake detection involves identifying whether a media file is authentic or generated using deep learning algorithms. In this project, we propose a deep learning-based approach for detecting deep fakes in videos. We use the Deep fake Detection Challenge dataset, which consists of real and Deep fake videos, to train and evaluate our deep learning model. We employ a Convolutional Neural Network (CNN) architecture for our implementation, which has shown great potential in previous studies. We pre-process the dataset using several techniques such as resizing, normalization, and data augmentation to enhance the quality of the input data. Our proposed model achieves high detection accuracy of 97.5% on the Deep fake Detection Challenge dataset, demonstrating the effectiveness of the proposed approach for deep fake detection. Our approach has the potential to be used in real-world scenarios to detect deep fakes, helping to mitigate the risks posed by deep fakes to individuals and society. The proposed methodology can also be extended to detect in other types of media, such as images and audio, providing a comprehensive solution for deep fake detection.
Deep Neural Networks
Normalization
Cite
Citations (2)
Objective To evaluate the clinical value of measuring the four tumor makers(CEA、CA_(125)、CA_(153)、SF)for diagnosis of lung cancer. Methods These tumor markers in serum were measured with electro-dhemiluminescence immunoassay,ECLIA) in 53 patients with lung cancers 62 benign lung disease and 20 healthy subjects. Results The levels of the markers in lung cancer group were all higher than those of benign lung diseases and healthy subjects(P0.01).The sensitivity of single tumor marker(CEA、CA_(125)、CA_(153)、SF)was58.49%,52.83%,47.17%,62.26% respectively.The sensitivity of combined measurement was 88.68 %. Conclusion Combined measurement of various serum tumor markers can significantly increase the diagnostic sensitivity for lung cancer,and provide useful information for early diagnosis of disease in patients with lung cancer.
Lung tumor
CA 15-3
Cite
Citations (0)