Medical image analysis tasks like segmentation and detection of injury involving manual interventions usually suffers from high inter-observer variabilities. To carry them out efficiently, various deep neural networks have been proposed recently as they provide much higher and reliable performance than the traditional image processing and manual segmentation methods. Non-invasive and robust quantification of salvageable tissue in acute ischemic stroke i.e., the ischemic penumbra, is critical for interventional stroke therapy. This paper proposes a Multi- Sequence Network (MSNet) architecture for this task. In this architecture, the information from multiple sequences are combined for identification and segmentation of core and penumbra (salvageable tissue) regions of ischemic stroke lesions and was tested on multisequence MRI ischemic lesion dataset of ISLES15. Performance of the proposed architecture, in terms of dice similarity coefficient, sensitivity and specificity are found to be 0.68, 0.805 and 0.99 respectively for the core of the lesion and 0.69, 0.949 and 0.964 respectively for the penumbra region.