Search

Skin lesion segmentation plays a crucial role in the computer-aided diagnosis of melanoma. Deep Learning models have shown promise in accurately segmenting skin lesions, but their widespread adoption in real-life clinical settings is hindered by their inherent black-box nature. In domains as critical as healthcare, interpretability is not merely a feature but a fundamental requirement for model adoption. This paper proposes IARS SegNet an advanced segmentation framework built upon the SegNet baseline model. Our approach incorporates three critical components: Skip connections, residual convolutions, and a global attention mechanism onto the baseline Segnet architecture. These elements play a pivotal role in accentuating the significance of clinically relevant regions, particularly the contours of skin lesions. The inclusion of skip connections enhances the model's capacity to learn intricate contour details, while the use of residual convolutions allows for the construction of a deeper model while preserving essential image features. The global attention mechanism further contributes by extracting refined feature maps from each convolutional and deconvolutional block, thereby elevating the model's interpretability. This enhancement highlights critical regions, fosters better understanding, and leads to more accurate skin lesion segmentation for melanoma diagnosis., Comment: Submitted to the journal: Computers in Biology and Medicine

The mouth, often regarded as a window to the internal state of the body, plays an important role in reflecting one's overall health. Poor oral hygiene has far-reaching consequences, contributing to severe conditions like heart disease, cancer, and diabetes, while inadequate care leads to discomfort, pain, and costly treatments. Federated Learning (FL) for object detection can be utilized for this use case due to the sensitivity of the oral image data of the patients. FL ensures data privacy by storing the images used for object detection on the local device and trains the model on the edge. The updated weights are federated to a central server where all the collected weights are updated via The Federated Averaging algorithm. Finally, we have developed a mobile app named OralH which provides user-friendly solutions, allowing people to conduct self-assessments through mouth scans and providing quick oral health insights. Upon detection of the issues, the application alerts the user about potential oral health concerns or diseases and provides details about dental clinics in the user's locality. Designed as a Progressive Web Application (PWA), the platform ensures ubiquitous access, catering to users across devices for a seamless experience. The application aims to provide state-of-the-art segmentation and detection techniques, leveraging the YOLOv8 object detection model to identify oral hygiene issues and diseases. This study deals with the benefits of leveraging FL in healthcare with promising real-world results.

We employ a method involving an array detector to measure the transverse spatial variation of the von Neumann Entropy (VNE) associated with the polarization state of light for different light sources including the coherent light from a diode laser, the chaotic light from an LED, the fluorescent emission from a dye widely used as a contrast agent and also the downconverted output from the process of Spontaneous Parametric Down Conversion which has widespread applications in Quantum Optics as a source of entangled photon pairs. Additionally, we studied the variation of the Stokes parameters as well as von Neumann entropy with pixel binning in the array detector output.

Table-top Rearrangement and Planning is a challenging problem that relies heavily on an excellent perception stack. The perception stack involves observing and registering the 3D scene on the table, detecting what objects are on the table, and how to manipulate them. Consequently, it greatly influences the system's task-planning and motion-planning stacks that follow. We present a comprehensive overview and discuss the different challenges associated with the perception module. This work is a result of our extensive involvement in the ICRA 2022 Open Cloud Robot Table Organization Challenge, in which we stood third in the final rankings., Comment: 5 pages including references, 3 figures

Various nonclassical and quantum phase properties of photon added then subtracted displaced Fock state have been examined systematically and rigorously. Higher-order moments of the relevant bosonic operators are computed to test the nonclassicality of the state of interest, which reduces to various quantum states (having applications in quantum optics, metrology and information processing) in different limits ranging from the coherent (classical) state to the Fock (most nonclassical) states. The nonclassical features are discussed using Klyshko's, Vogel's, and Agarwal-Tara's criteria as well as the criteria of lower- and higher-order antibunching, sub-Poissonian photon statistics and squeezing. In addition, phase distribution function and quantum phase fluctuation have been studied. These properties are examined for various combinations of number of photon addition and/or subtraction and Fock parameter. The examination has revealed that photon addition generally improves nonclassicality, and this advantage enhances for the large (small) values of displacement parameter using photon subtraction (Fock parameter). The higher-order sub-Poissonian photon statistics is only observed for the odd orders. In general, higher-order nonclassicality criteria are found to detect nonclassicality even in the cases when corresponding lower-order criteria failed to do so. Photon subtraction is observed to induce squeezing, but only large number of photon addition can be used to probe squeezing for large values of displacement parameter. Further, photon subtraction is found to alter the phase properties more than photon addition, while Fock parameter has an opposite effect of the photon addition/subtraction. Finally, nonclassicality and non-Gaussianity is also established using $Q$ function., Comment: Nonclassical and quantum phase properties of photon added then subtracted displaced Fock state are studied in detail

The effect of two quantum state engineering processes that can be used to burn hole at vacuum in the photon number distribution of quantum states of radiation field are compared using various witnesses of lower- and higher-order nonclassicality as well as a measure of nonclassicality. Specifically, the witnesses of nonclassical properties due to the effect of vacuum state filtration and a single photon addition on an even coherent state, binomial state and Kerr state are investigated using the criteria of lower- and higher-order antibunching, squeezing and sub-Poissonian photon statistics. Further, the amount of nonclassicality present in these engineered quantum states is quantified and analyzed by using an entanglement potential based on linear entropy. It is observed that all the quantum states studied here are highly nonclassical, and on many occasions the hole burning processes are found to introduce/enhance nonclassical features. However, it is not true in general. The investigation has further revealed that despite the fact that a hole at vacuum implies a maximally nonclassical state (as far as Lee's nonclassical depth is used as the quantitative measure of nonclassicality). However, any particular process of hole burning at vacuum does not ensure the existence of a particular nonclassical feature. Specifically,lower- and higher-order squeezing are not observed for photon added even coherent state and vacuum filtered even coherent state., Comment: Effect of holeburning is studied for various engineered quantum states

Quantum phase properties of photon added and subtracted displaced Fock states (and a set of quantum states which can be obtained as the limiting cases of these states) are investigated from a number of perspectives, and it is shown that the quantum phase properties are dependent on the quantum state engineering operations performed. Specifically, the analytic expressions for quantum phase distributions and angular $Q$ distribution as well as measures of quantum phase fluctuation and phase dispersion are obtained. The uniform phase distribution of the initial Fock states is observed to be transformed by the unitary operation (i.e., displacement operator) into non-Gaussian shape, except for the initial vacuum state. It is observed that the phase distribution is symmetric with respect to the phase of the displacement parameter and becomes progressively narrower as its amplitude increases. The non-unitary (photon addition/subtraction) operations make it even narrower in contrast to the Fock parameter, which leads to broadness. The photon subtraction is observed to be a more powerful quantum state engineering tool in comparison to the photon addition. Further, one of the quantum phase fluctuation parameters is found to reveal the existence of antibunching in both the engineered quantum states under consideration. Finally, the relevance of the engineered quantum states in the quantum phase estimation is also discussed, and photon added displaced Fock state is shown to be preferable for the task., Comment: Quantum phase properties of an engineered quantum state has been studied from various perspectives