Cancer Detection Using Convolutional Neural Networks - Revision history

User at 03:45, 22 October 2022

2022-10-22T03:45:07Z

User at 03:45, 22 October 2022

2022-10-22T03:45:03Z

User at 03:45, 22 October 2022

2022-10-22T03:45:02Z

User at 03:44, 22 October 2022

2022-10-22T03:44:59Z

User at 03:44, 22 October 2022

2022-10-22T03:44:49Z

User at 03:44, 22 October 2022

2022-10-22T03:44:09Z

User at 03:44, 22 October 2022

2022-10-22T03:44:08Z

User at 03:43, 22 October 2022

2022-10-22T03:43:55Z

User at 03:43, 22 October 2022

2022-10-22T03:43:55Z

User: /* Convolutional Neural Networks */

2022-10-22T03:43:55Z

‎Convolutional Neural Networks

@@ Line 31: / Line 31: @@
 A CNN designed with 12 layers and over 4,000 filters analyzed lung CT scans to classify lung tumors as not present, benign, or malignant. This network saw a 93.55% accuracy rate, with a 95% rate for both sensitivity and selectivity[https://doi.org/10.1088/1757-899X/928/2/022035]. Another network was designed with a RetinaNet architecture to interpret both X-ray and CT scans. Originally created by Facebook, the RetinaNet architecture organizes features into a feature pyramid rather than a feature map, which layers different precisions of features for a more accurate representation of the image. It also uses focal loss learning algorithm, which adjusts the amount that a filter value is changed based on how influential that value was to the misclassification[https://towardsmachinelearning.org/retinanet-model-for-object-detection-explanation/]. This network mirrored expert human performance classifying lung tumors from CTs and X-rays, with 43 true positive classifications, 26 false positives, and 22 false negatives, with only 2 false positives resulting from other foreign bodies, the best result obtained by a CNN for this task[https://doi.org/10.1038/s41598-020-69789-z].
 == Gallery ==
@@ Line 104: / Line 110: @@
 Schultheiss, M., Schober, S. A., Lodde, M., Bodden, J., Aichele, J., Müller-Leisse, C., Renger, B., Pfeiffer, F., & Pfeiffer, D. (2020). A robust convolutional neural network for lung nodule detection in the presence of foreign bodies. Scientific Reports, 10(1), Article 1. [https://doi.org/10.1038/s41598-020-69789-z]

← Older revision		Revision as of 03:45, 22 October 2022
Line 57:		Line 57:

	Figure 6. The fully connected layer performing classifications for each pooled value		Figure 6. The fully connected layer performing classifications for each pooled value
		+
		+	[[File:TypesOfTumorsMRI.jpg]]
		+
		+	Figure 7. MRI images of a meningioma tumor(left), glioma tumor(middle), and pituitary tumor(right)
		+
		+	[[File:UsBreastLesion.jpg]]
		+
		+	Figure 8. An example of normal breast tissue and a breast lesion in an Ultrasound image
		+
		+	[[File:LungCT.jpg]]
		+
		+	Figure 9. CT images of lungs with and without Tumors

	== References ==		== References ==

@@ Line 25: / Line 25: @@
 '''Breast Cancer'''
-CNNs are currently capable of distinguishing between normal breast tissue, cystic masses, tumors, and other breast lesions visible in ultrasound images at 87.1% accuracy, which is an improvement over expert human readers who logged a 79.2% accuracy on the same dataset[https://doi.org/10.1007/s00330-019-06118-7]. Several networks have also been constructed for mammogram analysis, which can classify masses or tumors, breast density, breast asymmetry, and calcifications. Most all of the networks perform as well as humans, if not better[https://doi.org/10.1016/j.compbiomed.2021.104248].
+CNNs are currently capable of distinguishing between normal breast tissue, cystic masses, tumors, and other breast lesions visible in ultrasound images at 87.1% accuracy, which is an improvement over expert human readers who logged a 79.2% accuracy on the same dataset[https://doi.org/10.1007/s00330-019-06118-7]. Several networks have also been constructed for mammogram analysis, which can classify masses or tumors, breast density, breast asymmetry, and calcifications. Most all of the networks perform as well as humans, if not better. The dataset used tumors at early enough stages such that their successful detection would increase the patient's chances of survival by about 40% [https://doi.org/10.1016/j.compbiomed.2021.104248].
 '''Lung Cancer'''
@@ Line 85: / Line 86: @@
 Abdelrahman, L., Al Ghamdi, M., Collado-Mesa, F., & Abdel-Mottaleb, M. (2021). Convolutional neural networks for breast cancer detection in mammography: A survey. Computers in Biology and Medicine, 131, 104248. [https://doi.org/10.1016/j.compbiomed.2021.104248]

@@ Line 20: / Line 20: @@
 '''Brain Cancer'''
 CNNs have shown to be very effective at diagnosing brain cancers. In one study, researchers created three separate 16-layer CNNs: Network 1 determines whether a tumor is present, Network 2 determines the type of tumor present, and Network 3 determines the severity grade of the tumor. On a sample size of several thousand images each, Network 1 successfully categorized 99.33% of them, Network 2 had a 92.66% accuracy rate, and Network 3 had a 98.14% accuracy rate[https://doi.org/10.1007/s40998-021-00426-9]. Other networks have been created to try and improve the success rate of network 2. The highest classification accuracy rate achieved was 97.3%. This was done using a multiscale model, consisting of three parallel processing pathways that each use different spatial scales. This modification better extracted textures of each type of tumor[https://doi.org/10.3390/healthcare9020153].
@@ Line 71: / Line 79: @@
 Díaz-Pernas, F. J., Martínez-Zarzuela, M., Antón-Rodríguez, M., & González-Ortega, D. (2021). A Deep Learning Approach for Brain Tumor Classification and Segmentation Using a Multiscale Convolutional Neural Network. Healthcare, 9(2), 153. [https://doi.org/10.3390/healthcare9020153]

@@ Line 3: / Line 3: @@
 Cancer is a massive global health problem. It is the second leading cause of death worldwide each year[https://ourworldindata.org/cancer] and is one of the largest medical expenses for both individuals diagnosed and researchers looking for a cure[https://www.npr.org/sections/health-shots/2022/07/09/1110370391/cost-cancer-treatment-medical-debt]. Diagnosis is the first and arguably most important step in treating this issue. That’s because early diagnosis of cancer drastically improves mortality rates and lowers the cost of treatment[https://www.who.int/news/item/03-02-2017-early-cancer-diagnosis-saves-lives-cuts-treatment-costs].
-Medical imaging techniques[https://en.wikipedia.org/wiki/Medical_imaging] are some of the most common ways of diagnosing cancer. Images that are produced by a machine (specific to the test) are analyzed by physicians and other experts to determine if there is a tumor present, and if so then what type it is[https://www.cancer.gov/about-cancer/diagnosis-staging/diagnosis]. Some limitations to this method are human error in analysis, time costs of having people look at the images, and the fact that there isn’t always someone immediately available to make the diagnosis, especially given the shortage of physicians across the U.S. and worldwide. Neural networks, specifically Convolutional Neural Networks (CNNs) offer a potential solution for each of these limitations by automating the diagnostic analysis.
+Medical imaging techniques[https://en.wikipedia.org/wiki/Medical_imaging] are some of the most common ways of diagnosing cancer. Images that are produced by a machine (specific to the test) are analyzed by physicians and other experts to determine if there is a tumor present, and if so then what type it is[https://www.cancer.gov/about-cancer/diagnosis-staging/diagnosis]. Some limitations to this method are human error in analysis, time costs of having people look at the images, and the fact that there isn’t always someone immediately available to make the diagnosis, especially given the shortage of physicians across the U.S. and worldwide[https://www.ama-assn.org/practice-management/sustainability/doctor-shortages-are-here-and-they-ll-get-worse-if-we-don-t-act]. Neural networks, specifically Convolutional Neural Networks (CNNs) offer a potential solution for each of these limitations by automating the diagnostic analysis[https://www.altexsoft.com/blog/deep-learning-medical-diagnosis/].
@@ Line 14: / Line 14: @@
 The pooled data is then sent to the third and final hidden layer, which is the fully connected layer. This layer is identical to a perceptron in that it has a matrix of weight values that are combined with the pooled data points in a dense architecture, which identifies how each data point contributes to a certain category. It is as if each of the data points is casting a vote as to which category it believes the image should be a part of. These values are then sent to the output layer, which assigns a category to the input image[https://e2eml.school/how_convolutional_neural_networks_work.html].
@@ Line 46: / Line 53: @@
 Levey, N. (2022, July 9). She was already battling cancer. Then she had to fight the bill collectors. NPR. [https://www.npr.org/sections/health-shots/2022/07/09/1110370391/cost-cancer-treatment-medical-debt]
 Early cancer diagnosis saves lives, cuts treatment costs. (2017, February 3). World Health Organization. [https://www.who.int/news/item/03-02-2017-early-cancer-diagnosis-saves-lives-cuts-treatment-costs]
 How Cancer Is Diagnosed. (2019, July 17). National Cancer Institute. [https://www.cancer.gov/about-cancer/diagnosis-staging/diagnosis]
 Mishra, M. (2020, September 2). Convolutional Neural Networks, Explained. Medium. [https://towardsdatascience.com/convolutional-neural-networks-explained-9cc5188c4939]
@@ Line 56: / Line 67: @@
 Rohrer, B. (2016, August 18). How do Convolutional Neural Networks work? [https://e2eml.school/how_convolutional_neural_networks_work.html]

@@ Line 1: / Line 1: @@
 '''By Zachary Somma'''
@@ Line 15: / Line 19: @@
 [[File:CNN 2d architecture.png]]
 Figure 1. The layers of a standard CNN
 [[File:CNN 3d architecture.png]]
 Figure 2. Complete architecture of a standard CNN, showing length, width, and depth dimensionality
 == References ==
 Roser, M., & Ritchie, H. (2015). Cancer. Our World in Data. [https://ourworldindata.org/cancer]
 Mishra, M. (2020, September 2). Convolutional Neural Networks, Explained. Medium. [https://towardsdatascience.com/convolutional-neural-networks-explained-9cc5188c4939]

@@ Line 3: / Line 3: @@
 == Convolutional Neural Networks ==
-Convolutional Neural Networks are a special type of artificial neural network that are particularly good at categorizing images or grid-like datasets. Their architecture is sparse, topographic, feed-forward, multilayer, supervised, and both linear and non-linear on different layers[[2]].
+Convolutional Neural Networks are a special type of artificial neural network that are particularly good at categorizing images or grid-like datasets. Their architecture is sparse, topographic, feed-forward, multilayer, supervised, and both linear and non-linear on different layers[https://towardsdatascience.com/convolutional-neural-networks-explained-9cc5188c4939].
-Images in this network first pass through the input layer, where each pixel of an image is given a value based on the darkness of it. These values then are passed onto the first hidden layer, called the convolutional layer. This layer has a filter that uses a matrix of pre-determined dimensions and trained weight values. The dot products are calculated between the filter and all segments of the image with the same dimensionality as the filter. The values on the filter can be trained to identify specific characteristics about a particular image. Then as the filter scans over each segment of the image, the dot product essentially tells us whether or not that section of the image contained the desired feature. This layer of calculations can be repeated for however many characteristics are being filtered for[[2]].
+Images in this network first pass through the input layer, where each pixel of an image is given a value based on the darkness of it. These values then are passed onto the first hidden layer, called the convolutional layer. This layer has a filter that uses a matrix of pre-determined dimensions and trained weight values. The dot products are calculated between the filter and all segments of the image with the same dimensionality as the filter. The values on the filter can be trained to identify specific characteristics about a particular image. Then as the filter scans over each segment of the image, the dot product essentially tells us whether or not that section of the image contained the desired feature. This layer of calculations can be repeated for however many characteristics are being filtered for[https://towardsdatascience.com/convolutional-neural-networks-explained-9cc5188c4939].
-All of the dot product values are then output onto a feature map (sometimes called an activation map), which holds these dot products in the same topography as the original image. The feature map is sent to the next layer, called the pooling layer. Another filter of some specific size is used here, but instead of a dot product calculation, it simply carries over the largest value of each section looked at. The main function of this layer is to reduce the dimensionality of the feature map so that the most important data points are the ones being subject to the later classification[[3]].
+All of the dot product values are then output onto a feature map (sometimes called an activation map), which holds these dot products in the same topography as the original image. The feature map is sent to the next layer, called the pooling layer. Another filter of some specific size is used here, but instead of a dot product calculation, it simply carries over the largest value of each section looked at. The main function of this layer is to reduce the dimensionality of the feature map so that the most important data points are the ones being subject to the later classification[https://towardsdatascience.com/simple-introduction-to-convolutional-neural-networks-cdf8d3077bac].
-The pooled data is then sent to the third and final hidden layer, which is the fully connected layer. This layer is identical to a perceptron in that it has a matrix of weight values that are combined with the pooled data points in a dense architecture, which identifies how each data point contributes to a certain category. It is as if each of the data points is casting a vote as to which category it believes the image should be a part of. These values are then sent to the output layer, which assigns a category to the input image[[4]].
+The pooled data is then sent to the third and final hidden layer, which is the fully connected layer. This layer is identical to a perceptron in that it has a matrix of weight values that are combined with the pooled data points in a dense architecture, which identifies how each data point contributes to a certain category. It is as if each of the data points is casting a vote as to which category it believes the image should be a part of. These values are then sent to the output layer, which assigns a category to the input image[https://e2eml.school/how_convolutional_neural_networks_work.html].
@@ Line 20: / Line 20: @@
 == References ==
-[[1]]Roser, M., & Ritchie, H. (2015). Cancer. Our World in Data. [https://ourworldindata.org/cancer]
+Roser, M., & Ritchie, H. (2015). Cancer. Our World in Data. [https://ourworldindata.org/cancer]
-[[2]]Mishra, M. (2020, September 2). Convolutional Neural Networks, Explained. Medium. [https://towardsdatascience.com/convolutional-neural-networks-explained-9cc5188c4939]
+Mishra, M. (2020, September 2). Convolutional Neural Networks, Explained. Medium. [https://towardsdatascience.com/convolutional-neural-networks-explained-9cc5188c4939]
-[[3]]Stewart, M. (2020, July 29). Simple Introduction to Convolutional Neural Networks. Medium. [https://towardsdatascience.com/simple-introduction-to-convolutional-neural-networks-cdf8d3077bac]
+Stewart, M. (2020, July 29). Simple Introduction to Convolutional Neural Networks. Medium. [https://towardsdatascience.com/simple-introduction-to-convolutional-neural-networks-cdf8d3077bac]
-[[4]]Rohrer, B. (2016, August 18). How do Convolutional Neural Networks work? [https://e2eml.school/how_convolutional_neural_networks_work.html]
+Rohrer, B. (2016, August 18). How do Convolutional Neural Networks work? [https://e2eml.school/how_convolutional_neural_networks_work.html]

@@ Line 3: / Line 3: @@
 == Convolutional Neural Networks ==
-Convolutional Neural Networks are a special type of artificial neural network that are particularly good at categorizing images or grid-like datasets. Their architecture is sparse, topographic, feed-forward, multilayer, supervised, and both linear and non-linear on different layers.
+Convolutional Neural Networks are a special type of artificial neural network that are particularly good at categorizing images or grid-like datasets. Their architecture is sparse, topographic, feed-forward, multilayer, supervised, and both linear and non-linear on different layers[[1]].
 Images in this network first pass through the input layer, where each pixel of an image is given a value based on the darkness of it. These values then are passed onto the first hidden layer, called the convolutional layer. This layer has a filter that uses a matrix of pre-determined dimensions and trained weight values. The dot products are calculated between the filter and all segments of the image with the same dimensionality as the filter. The values on the filter can be trained to identify specific characteristics about a particular image. Then as the filter scans over each segment of the image, the dot product essentially tells us whether or not that section of the image contained the desired feature. This layer of calculations can be repeated for however many characteristics are being filtered for.
@@ Line 10: / Line 10: @@
 The pooled data is then sent to the third and final hidden layer, which is the fully connected layer. This layer is identical to a perceptron in that it has a matrix of weight values that are combined with the pooled data points in a dense architecture, which identifies how each data point contributes to a certain category. It is as if each of the data points is casting a vote as to which category it believes the image should be a part of. These values are then sent to the output layer, which assigns a category to the input image.
 [[File:CNN 2d architecture.png]]
 == References ==