| Characteristics | \nPneumonia | \n
| History | \nUnderlying lung disease, contact with individuals having upper or lower respiratory infection, contact with birds/animals. | \n
| Causes | \nBacteria, virus, fungi; aspiration. | \n
| Body systems | \nRespiratory system—lungs. | \n
| Clinical symptoms | \nHigh fever (sometimes with chills and rigors), cough, wheezing, breathing difficulty, chest pain. | \n
| Investigations | \nBlood investigations—complete blood count, ESR, sputum examination and culture, chest X-ray, CT scan, bronchoscopy, thoracocentesis, pleural fluid aspiration and culture. | \n
| Treatments | \nAppropriate antimicrobial therapy, expectorant, antipyretics and analgesics, oxygen therapy (if required), fluids. | \n
stage_2_train_images.zip and stage_2_test_images.zip¶stage_2_train_labels.csv and Stage 2 Sample Submission stage_2_sample_submission.csv¶stage_2_detailed_class_info.csv¶patientIds and bounding box / target information.patientIds for the test set. Note that the sample submission contains one box per image, but there is no limit to the number of bounding boxes that can be assigned to a given image.patientId. Each patientId corresponds to a unique image.x coordinate of the bounding box.y coordinate of the bounding box.width of the bounding box.height of the bounding box.Target, indicating whether this sample has evidence of pneumonia.![](\"https://cdn.analyticsvidhya.com/wp-content/uploads/2019/07/Screenshot-from-2019-07-18-15-52-17.png\")
\n\nFaster RCNN will return the above output.\n\nThe Mask R-CNN framework is built on top of Faster R-CNN. So, for a given image, Mask R-CNN, in addition to the class label and bounding box coordinates for each object, will also return the object mask.\n\nLet’s first quickly understand how Faster R-CNN works. This will help us grasp the intuition behind Mask R-CNN as well.\n\n1) Faster R-CNN first uses a ConvNet to extract feature maps from the images![](\"https://viso.ai/wp-content/uploads/2021/03/mask-r-cnn-framework-for-instance-segmentation-1.jpg\")
\n\nSource : https://viso.ai/deep-learning/mask-r-cnn/ \n\n#### Backbone: \n\nSimilar to the ConvNet that we use in Faster R-CNN to extract feature maps from the image, we use the ResNet 101 architecture to extract features from the images in Mask R-CNN. So, the first step is to take an image and extract features using the ResNet 101 architecture. These features act as an input for the next layer.\n\n#### Region Proposal Network (RPN):\n\nNow, we take the feature maps obtained in the previous step and apply a region proposal network (RPM). This basically predicts if an object is present in that region (or not). In this step, we get those regions or feature maps which the model predicts contain some object.\n\n#### Region of Interest (RoI):\n\nThe regions obtained from the RPN might be of different shapes, right? Hence, we apply a pooling layer and convert all the regions to the same shape. Next, these regions are passed through a fully connected network so that the class label and bounding boxes are predicted.\n\nTill this point, the steps are almost similar to how Faster R-CNN works. Now comes the difference between the two frameworks. In addition to this, Mask R-CNN also generates the segmentation mask.\n\nFor that, we first compute the region of interest so that the computation time can be reduced. For all the predicted regions, we compute the Intersection over Union (IoU) with the ground truth boxes. We can computer IoU like this:\n\nIoU = Area of the intersection / Area of the union\n\nNow, only if the IoU is greater than or equal to 0.5, we consider that as a region of interest. Otherwise, we neglect that particular region. We do this for all the regions and then select only a set of regions for which the IoU is greater than 0.5.\n\n#### Segmentation Mask:\n\nOnce we have the RoIs based on the IoU values, we can add a mask branch to the existing architecture. This returns the segmentation mask for each region that contains an object. It returns a mask of size 28 X 28 for each region which is then scaled up for inference.\n\n