1. Towards Ophthalmologist Level Accurate Deep Learning System for OCT Screening and Diagnosis

   Authors: Mrinal Haloi

   Abstract: In this work, we propose an advanced AI based grading system for OCT images. The proposed system is a very deep fully convolutional attentive classification network trained with end to end advanced transfer learning with online random augmentation. It uses quasi random augmentation that outputs confidence values for diseases prevalence during inference. Its a fully automated retinal OCT analysis A… ▽ More In this work, we propose an advanced AI based grading system for OCT images. The proposed system is a very deep fully convolutional attentive classification network trained with end to end advanced transfer learning with online random augmentation. It uses quasi random augmentation that outputs confidence values for diseases prevalence during inference. Its a fully automated retinal OCT analysis AI system capable of pathological lesions understanding without any offline preprocessing/postprocessing step or manual feature extraction. We present a state of the art performance on the publicly available Mendeley OCT dataset. △ Less

   Download

2. Towards Radiologist-Level Accurate Deep Learning System for Pulmonary Screening

   Authors: Mrinal Haloi, K. Raja Rajalakshmi, Pradeep Walia

   Abstract: In this work, we propose advanced pneumonia and Tuberculosis grading system for X-ray images. The proposed system is a very deep fully convolutional classification network with online augmentation that outputs confidence values for diseases prevalence. Its a fully automated system capable of disease feature understanding without any offline preprocessing step or manual feature extraction. We have… ▽ More In this work, we propose advanced pneumonia and Tuberculosis grading system for X-ray images. The proposed system is a very deep fully convolutional classification network with online augmentation that outputs confidence values for diseases prevalence. Its a fully automated system capable of disease feature understanding without any offline preprocessing step or manual feature extraction. We have achieved state- of-the- art performance on the public databases such as ChestXray-14, Mendeley, Shenzhen Hospital X-ray and Belarus X-ray set. △ Less

   Download

3. Rethinking Convolutional Semantic Segmentation Learning

   Authors: Mrinal Haloi

   Abstract: Deep convolutional semantic segmentation (DCSS) learning doesn't converge to an optimal local minimum with random parameters initializations; a pre-trained model on the same domain becomes necessary to achieve convergence.In this work, we propose a joint cooperative end-to-end learning method for DCSS. It addresses many drawbacks with existing deep semantic segmentation learning; the proposed appr… ▽ More Deep convolutional semantic segmentation (DCSS) learning doesn't converge to an optimal local minimum with random parameters initializations; a pre-trained model on the same domain becomes necessary to achieve convergence.In this work, we propose a joint cooperative end-to-end learning method for DCSS. It addresses many drawbacks with existing deep semantic segmentation learning; the proposed approach simultaneously learn both segmentation and classification; taking away the essential need of the pre-trained model for learning convergence. We present an improved inception based architecture with partial attention gating (PAG) over encoder information. The PAG also adds to achieve faster convergence and better accuracy for segmentation task. We will show the effectiveness of this learning on a diabetic retinopathy classification and segmentation dataset. △ Less

   Download

4. Deep Learning: Generalization Requires Deep Compositional Feature Space Design

   Authors: Mrinal Haloi

   Abstract: Generalization error defines the discriminability and the representation power of a deep model. In this work, we claim that feature space design using deep compositional function plays a significant role in generalization along with explicit and implicit regularizations. Our claims are being established with several image classification experiments. We show that the information loss due to convolu… ▽ More Generalization error defines the discriminability and the representation power of a deep model. In this work, we claim that feature space design using deep compositional function plays a significant role in generalization along with explicit and implicit regularizations. Our claims are being established with several image classification experiments. We show that the information loss due to convolution and max pooling can be marginalized with the compositional design, improving generalization performance. Also, we will show that learning rate decay acts as an implicit regularizer in deep model training. △ Less

   Download

5. Diabetic Retinopathy Screening using Deep Learning Technology

   Authors: Pradeep K Walia, RajaRajalakshmi, Mrinal Haloi, Mohammad Fazal Kamal

   Download

6. The Deep Learning Computer model in reading Diabetic Retinopathy & Normal Images

   Authors: Pradeep K Walia, RajaRajalakshmi, Mohammad Fazal Kamal

   Download

7. Towards Human Level Accurate Deep Learning System for Diabetic Reinopathy Screening

   Authors: Mrinal Haloi, Lalit Pant, Anurag Sahay, Pradeep Walia

   Download

Social