Memory Guided Transformer With Spatio-Semantic Visual Extractor for Medical Report Generation.

Medicalimaging-based report writing for effective diagnosis in radiology is time-consuming and can be error-prone by inexperienced radiologists. Automatic reporting helps radiologists avoid missed diagnoses and saves valuable time. Recently, transformer-based medical report generation has become prominent in capturing long-term dependencies of sequential data with its attention mechanism. Nevertheless, input features obtained from traditional visual extractor of conventional transformers do not capture spatial and semantic information of an image. So, the transformer is unable to capture fine-grained details and may not produce detailed descriptive reports of radiology images. Therefore, we propose a spatio-semantic visual extractor (SSVE) to capture multi-scale spatial and semantic information from radiology images. Here, we incorporate two types of networks in ResNet 101 backbone architecture, i.e. (i) deformable network at the intermediate layer of ResNet 101 that utilizes deformable convolutions in order to obtain spatially invariant features, and (ii) semantic network at the final layer of backbone architecture which uses dilated convolutions to extract rich multi-scale semantic information. Further, these network representations are fused to encode fine-grained details of radiology images. The performance of our proposed model outperforms existing works on two radiology report datasets, i.e., IU X-ray and MIMIC-CXR.

Facial Expression Recognition in Videos using Dynamic Kernels.

Recognition of facial expressions across various actors, contexts, and recording conditions in real-world videos involves identifying local facial movements. Hence, it is important to discover the formation of expressions from local representations captured from different parts of the face. So in this paper, we propose a dynamic kernel-based representation for facial expressions that assimilates facial movements captured using local spatio-temporal representations in a large universal Gaussian mixture model (uGMM). These dynamic kernels are used to preserve local similarities while handling global context changes for the same expression by utilizing the statistics of uGMM. We demonstrate the efficacy of dynamic kernel representation using three different dynamic kernels, namely, explicit mapping based, probability-based, and matching-based, on three standard facial expression datasets, namely, MMI, AFEW, and BP4D. Our evaluations show that probability-based kernels are the most discriminative among the dynamic kernels. However, in terms of computational complexity, intermediate matching kernels are more efficient as compared to the other two representations.

Spontaneous Expression Recognition using Universal Attribute Model.

Spontaneous expression recognition refers to recognizing non-posed human expressions. In literature, most of the existing approaches for expression recognition mainly rely on manual annotations by experts, which is both time-consuming and difficult to obtain. Hence, we propose an unsupervised framework for spontaneous expression recognition that preserves discriminative information for the videos of each expression without using annotations. Initially, a large Gaussian mixture model called universal attribute model (UAM) is trained to learn the attributes of various expressions implicitly. Attributes are the movements of various facial muscles that are combined to form a particular facial expression. Then a concatenated mean vector called the super expression-vector (SEV) is formed by using a maximum a posteriori adaptation of the UAM means for each expression clip. This SEV contains attributes from all the expressions resulting in a high dimensional representation. To retain only the attributes of that particular expression clip, the SEV is decomposed using factor analysis to produce a low-dimensional expression-vector. This procedure does not require any class labels and produces expression-vectors that are distinct for each expression irrespective of high inter-actor variability present in spontaneous expressions. On spontaneous expression datasets like BP4D and AFEW, we demonstrate that expression-vector achieves better performance than state-of-the-art techniques. Further, we also show that UAM trained on a constrained dataset can be effectively used to recognize expressions in unconstrained expression videos.

An algorithmic approach for clinical management of low back pain.

BACKGROUND: Low back pain is caused by a variety of conditions. When conventional imaging failed, single-photon emission computed tomography (SPECT) was superior to scintigraphy in identifying the pathology. Injection therapies are often helpful in treating the pathology. AIM: To determine the cause of chronic low backache in individuals with normal conventional imaging (radiographs, computed tomography and magnetic resonance imaging), to determine the specific pathology using scintigraphic studies and diagnostic blocks; and, to treat the individuals with various spinal injection techniques and determine their efficacy. MATERIAL AND METHODS: All the patients having chronic back pain on presentation in the outpatient clinic from April 2013 to October 2014 were prospectively evaluated. RESULTS: The 40 patients included in the study were followed up pre- and post operatively with various pain scales (visual analogue scale [VAS], Oswestry disability index [ODI] and short form health survery 36 [SF36]). The mean age at presentation was 41.3 years. Female patients formed the predominant subgroup in the study (57.5% female and 42.5% male patients). Pain indices like VAS and ODI were helpful in assessing the efficacy of spinal injections. Preoperative and postoperative pain scale assessment, supplemented by a SPECT evaluation of the sacroiliac and facet joints, showed a statistically significant difference, which correlated with clinically significant pain relief. CONCLUSIONS: SPECT imaging is helpful in diagnosing sacroiliac joint syndrome and facetal syndrome. Epidural injections were a better choice in cases of low backache, where clinically, the patient had no signs of sacroiliac joint syndrome and facetal syndrome. Spinal injections with steroid and local anaesthetic had better relief. Radiotracer uptake at the pain generating area is a good predictor of outcome. Image guided spinal injection improves the accuracy of the injection.

Adaptive learning based heartbeat classification.

Cardiovascular diseases (CVD) are a leading cause of unnecessary hospital admissions as well as fatalities placing an immense burden on the healthcare industry. A process to provide timely intervention can reduce the morbidity rate as well as control rising costs. Patients with cardiovascular diseases require quick intervention. Towards that end, automated detection of abnormal heartbeats captured by electronic cardiogram (ECG) signals is vital. While cardiologists can identify different heartbeat morphologies quite accurately among different patients, the manual evaluation is tedious and time consuming. In this chapter, we propose new features from the time and frequency domains and furthermore, feature normalization techniques to reduce inter-patient and intra-patient variations in heartbeat cycles. Our results using the adaptive learning based classifier emulate those reported in existing literature and in most cases deliver improved performance, while eliminating the need for labeling of signals by domain experts.

Development and evaluation of a chloramphenicol hypertonic ophthalmic solution.

Hypertonic ophthalmic solutions are used to treat ocular diseases associated with edema. In this study, we developed a chloramphenicol hypertonic ophthalmic solution. These drops were developed based on the cosolvency and additional dielectric constant concepts. Two different solvents: PEG 300 and glycerol were used as cosolvents. Solubility curves were plotted. Based on the solubility curves, two different solutions were selected. These solutions were evaluated for physical parameters and accelerated stability. The results indicated that chloramphenicol was stable in these formulations. The selected blend of solutions was hypertonic. Thus, the solubility and stability of chloramphenicol was enhanced using a cosolvency technique so as to develop a chloramphenicol hypertonic ophthalmic solution.