Deep neural network for automated simultaneous intervertebral disc (IVDs) identification and segmentation of multi-modal MR images.

BACKGROUND AND OBJECTIVE: Lower back pain in humans has become a major risk. Classical approaches follow a non-invasive imaging technique for the assessment of spinal intervertebral disc (IVDs) abnormalities, where identification and segmentation of discs are done separately, making it a time-consuming phenomenon. This necessitates designing a robust automated and simultaneous IVDs identification and segmentation of multi-modality MRI images. METHODS: We introduced a novel deep neural network architecture coined as 'RIMNet', a Region-to-Image Matching Network model, capable of performing an automated and simultaneous IVDs identification and segmentation of MRI images. The multi-modal input data is being fed to the network with a dropout strategy, by randomly disabling modalities in mini-batches. The performance accuracy as a function of the testing dataset was determined. The execution of the deep neural network model was evaluated by computing the IVDs Identification Accuracy, Dice coefficient, MDOC, Average Symmetric Surface Distance, Jaccard Coefficient, Hausdorff Distance and F1 Score. RESULTS: Proposed model has attained 94% identification accuracy, dice coefficient value of 91.7±1% in segmentation and MDOC 90.2±1%. Our model also achieved 0.87±0.02 for Jaccard Coefficient, 0.54±0.04 for ASD and 0.62±0.02 mm Hausdorff Distance. The results have been validated and compared with other methodologies on dataset of MICCAI IVD 2018 challenge. CONCLUSIONS: Our proposed deep-learning methodology is capable of performing simultaneous identification and segmentation on IVDs MRI images of the human spine with high accuracy.

Nanomagnetic logic based runtime Reconfigurable area efficient and high speed adder design methodology.

In this study, we present a runtime reconfigurable nanomagnetic (RRN) adder design offering significant area efficiency and high speed operations. Subsequently, it is implemented using a micromagnetic simulation tool, by exploiting the reversal magnetization and energy minimization nature of the nanomagnets. We compute the carry and sum of the 1-bit full adder using only two majority gates comprising a total of 7 nanomagnets and single design layout. Consequently, the on-chip clocking schematic for the proposed RRN adder implementation for both horizontal and vertical layouts are introduced. The quantitative analysis of the required resources for higher bit adder architecture using the proposed design is performed and compared with state-of-the art. The proposed design methodology leads to ∼86%, ∼83% and ∼93% reduction in the number of nanomagnets, majority gates and clock cycles respectively resulting in an area efficient and high speed RRN adder architecture.

Dipole coupled magnetic quantum-dot cellular automata-based efficient approximate nanomagnetic subtractor and adder design approach.

In this paper, we propose a dipole coupled magnetic quantum-dot cellular automata-based approximate nanomagnetic (APN) architectural design approach for subtractor and adder. In addition, we also introduce an APN architecture which offers runtime reconfigurability using a single design layout comprising only four nanomagnets. Subsequently, we propose the APN add/sub architecture by exploiting shape anisotropy and ferromagnetically coupled fixed input majority gate. The proposed APN architecture designs have been implemented using a micromagnetic simulation tool and performance has been compared with the state-of-the-art approach resulting in a ∼50%-80% reduction in the number of nanomagnets and clock cycles without degradation in the accuracy leading to area and energy efficiency.

Nanomagnetic logic design approach for area and speed efficient adder using ferromagnetically coupled fixed input majority gate.

In this letter, we introduce the magnetic quantum-dot cellular automata (MQCA) based area and speed efficient design approach for nanomagnetic full adder implementation. We exploited the physical properties of three input MQCA majority gate (MG), where the fixed input of the MG is coupled ferromagnetically to one of the primary input operands. Subsequently we propose a design methodology, mapping logic and micromagnetic software implementation, validation of the binary full adder architecture built using two-three inputs MQCA MGs. In addition, we also analyzed our proposed design for switching errors to ensure bit stability and reliability. Our proposed design leads to ∼36%-69% reduction in the number of nanomagnets, ∼50%-75% reduction in the number of clock cycles and ∼33%-50% reduction in the number of MG operations required for the binary full adder implementation compared to the state of art designs.