CT Image Synthesis Using Weakly Supervised Segmentation and Geometric Inter-Label Relations For COVID Image Analysis

Abstract

While medical image segmentation is an important task for computer aided diagnosis, the high expertise requirement for pixelwise manual annotations makes it a challenging and time consuming task. Since conventional data augmentations do not fully represent the underlying distribution of the training set, the trained models have varying performance when tested on images captured from different sources. Most prior work on image synthesis for data augmentation ignore the interleaved geometric relationship between different anatomical labels. We propose improvements over previous GAN-based medical image synthesis methods by learning the relationship between different anatomical labels. We use a weakly supervised segmentation method to obtain pixel level semantic label map of images which is used learn the intrinsic relationship of geometry and shape across semantic labels. Latent space variable sampling results in diverse generated images from a base image and improves robustness. We use the synthetic images from our method to train networks for segmenting COVID-19 infected areas from lung CT images. The proposed method outperforms state-of-theart segmentation methods on a public dataset. Ablation studies also demonstrate benefits of integrating geometry and diversity.

Improved Super Resolution of MR Images Using CNNs and Vision Transformers

“…Also, CNN methods capture mostly local context information and do not explore the global aspects. Zhang et al in [191,153,152,155,157,24], [22,130,151], [79,51,78,49], [42,43,11], [90,77,88], [168,8,75,76] propose a squeeze and excitation network to capture the global characteristics thus leading to improved super resolution output. However, squeeze and excitation relies on CNN features to capture global context which is not optimal.…”

Multimodal Generalized Zero Shot Learning for Gleason Grading using Self-Supervised Learning

“…One major reason being the availability of class attribute vectors for natural images that describe characteristics of seen and unseen classes, but are challenging to obtain for medical images. Self-supervised learning (SSL) also addresses labeled data shortage and has found wide use in medical image analysis by using innovative pre-text tasks for active learning [33,35,62,63,104,107,110,[114][115][116][117]119,120,122,132,135], anomaly detection [8, 10, 11, 20, 26, 27, 36, 59-61, 67, 72, 74, 92, 112, 146], and data augmentation [3-5, 57, 64, 66, 71, 84, 85, 87-91]. SSL has been applied to histopathology images using domain specific pretext tasks [1,18,23,32,86,95,108,113,144], semisupervised histology classification [42], stain normalization [73], registration [157] and cancer subtyping using visual dictionaries.…”