Tofacitinib in pyoderma gangrenosum - A case series.

Pyoderma gangrenosum (PG) is a rare autoinflammatory disorder falling under the spectrum of neutrophilic dermatosis, characterized by distinctive skin ulceration which is non-infective, non-neoplastic and usually with no primary vasculitis. PG lesions are notorious for relapse and hence require multiple trials of medications often with prolonged and concomitant use of steroids. Due to lack of evidence-based studies on effective treatment options for PG, we have presented three isolated biopsy-proven PG cases who were successfully treated with Tofacitinib, a Janus kinase/signal transducers and activators of transcription (JAK/STAT) pathway inhibitor, without relapse in follow up.

Uncommon presentation of granulomatosis with polyangiitis: Prostate involvement.

Granulomatosis with polyangiitis (GPA) is an autoimmune granulomatous disease of unknown etiology; frequently associated with anti-proteinase 3 antineutrophil cytoplasmic antibody (PR3-ANCA). Although any organ can be involved, prostatic involvement in GPA is very rare. We present a male patient with GPA, 26 years old, with pulmonary manifestations and prostatic involvement who underwent exhaustive evaluation. The patient's laboratory tests and imaging scans showed evidence of lesions in multiple areas, including the prostate. Histopathological testing confirmed that the lesions were consistent with granulomatosis with polyangiitis. The patient was treated with oral steroids and rituximab and showed significant improvement. He was later maintained on azathioprine without any relapse.

Tofacitinib as monotherapy in cutaneous polyarteritis nodosa: a case series.

Objective: Cutaneous polyarteritis nodosa (CPAN) is a distinct clinical entity represented by a chronic, relapsing, benign course, with rare systemic involvement. Treatment is with CSs, CYC or other conventional synthetic DMARDs (csDMARDs). In this case series, we aimed to share our varied clinical experience of successfully treating patients with CPAN, with tofacitinib in a refractory/relapsing course or as upfront monotherapy without CSs/csDMARDs. Methods: We report this retrospective case series managed at our rheumatology centre in Bangalore from 2019 to 2022. Four patients identified as CPAN on biopsy were able to achieve disease-free remission with tofacitinib as part of their treatment, with no relapse on further follow-up. Our patients presented with subcutaneous nodules and cutaneous ulcers. After systemic evaluation, all the patients underwent skin biopsy, which showed fibrinoid necrosis in the vessel walls of the dermis, with a histopathological impression of CPAN. They were initially treated with a conventional approach of CSs with/without csDMARDs. On experiencing a refractory/relapsing course, tofacitinib was tried in all the patients as either CS sparing or upfront monotherapy without concomitant csDMARDs. Results: Use of tofacitinib resulted in improvement of ulcers and paraesthesia and in gradual healing of skin lesions, albeit with scarring, with no further recurrence or relapse over a follow-up period of 6 months for all the patients. The therapeutic effect of tofacitinib was consistent when used either as CS sparing or as upfront monotherapy, thereby proving the drug to be a promising option that warrants larger trials in future to treat the subset of patients with established CPAN. Conclusion: Tofacitinib could be used for disease-free remission as monotherapy for CPAN either upfront or as CS sparing, even without concomitant csDMARDs, in those patients who are dependent on CSs or multiple DMARDs.

Reactive arthritis following treatment with intravesical Bacillus Calmette-Guerin for papillary carcinoma of bladder.

A man in his 60s developed reactive arthritis following treatment with intravesical Bacillus Calmette-Guerin (iBCG) for papillary carcinoma of bladder. Evaluation revealed leucocytosis and raised inflammatory markers. HLA B27 was positive. Based on the temporal relationship, it was attributed to BCG-related reactive arthritis. iBCG was stopped. Treatment with non-steroidal anti-inflammatory drugs (NSAIDS) and glucocorticoids were ineffective. Prolonged course of disease-modifying antirheumatic drugs (DMARDS) was required which aided in alleviation of symptoms and sustained remission. Intravesical BCG therapy is a treatment for bladder cancer. It is rarely associated with reactive arthritis, which responds to discontinuation of iBCG and treatment with NSAIDS and/or short-term glucocorticoids. iBCG-related reactive arthritis commonly has an acute/subacute course. Chronic arthritis as observed in our case requiring prolonged treatment with DMARDS is rare.

Confidence-Calibrated Human Activity Recognition.

Wearable sensors are widely used in activity recognition (AR) tasks with broad applicability in health and well-being, sports, geriatric care, etc. Deep learning (DL) has been at the forefront of progress in activity classification with wearable sensors. However, most state-of-the-art DL models used for AR are trained to discriminate different activity classes at high accuracy, not considering the confidence calibration of predictive output of those models. This results in probabilistic estimates that might not capture the true likelihood and is thus unreliable. In practice, it tends to produce overconfident estimates. In this paper, the problem is addressed by proposing deep time ensembles, a novel ensembling method capable of producing calibrated confidence estimates from neural network architectures. In particular, the method trains an ensemble of network models with temporal sequences extracted by varying the window size over the input time series and averaging the predictive output. The method is evaluated on four different benchmark HAR datasets and three different neural network architectures. Across all the datasets and architectures, our method shows an improvement in calibration by reducing the expected calibration error (ECE)by at least 40%, thereby providing superior likelihood estimates. In addition to providing reliable predictions our method also outperforms the state-of-the-art classification results in the WISDM, UCI HAR, and PAMAP2 datasets and performs as good as the state-of-the-art in the Skoda dataset.

Action Anticipation Using Pairwise Human-Object Interactions and Transformers.

The ability to anticipate future actions of humans is useful in application areas such as automated driving, robot-assisted manufacturing, and smart homes. These applications require representing and anticipating human actions involving the use of objects. Existing methods that use human-object interactions for anticipation require object affordance labels for every relevant object in the scene that match the ongoing action. Hence, we propose to represent every pairwise human-object (HO) interaction using only their visual features. Next, we use cross-correlation to capture the second-order statistics across human-object pairs in a frame. Cross-correlation produces a holistic representation of the frame that can also handle a variable number of human-object pairs in every frame of the observation period. We show that cross-correlation based frame representation is more suited for action anticipation than attention-based and other second-order approaches. Furthermore, we observe that using a transformer model for temporal aggregation of frame-wise HO representations results in better action anticipation than other temporal networks. So, we propose two approaches for constructing an end-to-end trainable multi-modal transformer (MM-Transformer; code at https://github.com/debadityaroy/MM-Transformer_ActAnt) model that combines the evidence across spatio-temporal, motion, and HO representations. We show the performance of MM-Transformer on procedural datasets like 50 Salads and Breakfast, and an unscripted dataset like EPIC-KITCHENS55. Finally, we demonstrate that the combination of human-object representation and MM-Transformers is effective even for long-term anticipation.

Decoding enigma: Turner syndrome with ring chromosome.

Ring chromosome X is one of the rarest with some unique phenotypical features in Turner syndrome. A young female presented to us with anasarca developed over the past 2 months due to congestive cardiac failure along with jaundice and orthopnea. She had growth retardation, intellectual disability, primary amenorrhea, lack of secondary sexual character development and dysmorphic features like low posterior hairline, shield chest and cubitus valgus. She had dilated cardiomyopathy (DCM) with intracardiac thrombus on echocardiography. Skeletal survey revealed short fourth metacarpal/tarsal on limbs. Karyotyping showed a mosaic pattern, with 45, X/46, X,r(X)(p22.3q28), i.e. Turner syndrome karyotype with ring chromosome. Her heart failure with reduced ejection fraction was managed with vasopressor along with anticoagulant and given oral contraceptive pills for hormone replacement therapy. The ring chromosomal pattern of karyotype in this patient and DCM is a rare cardiological phenomenon that can be associated with Turner syndrome, making this case a unique one.

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.

Echocardiogram Analysis Using Motion Profile Modeling.

Echocardiography is a widely used and cost-effective medical imaging procedure that is used to diagnose cardiac irregularities. To capture the various chambers of the heart, echocardiography videos are captured from different angles called views to generate standard images/videos. Automatic classification of these views allows for faster diagnosis and analysis. In this work, we propose a representation for echo videos which encapsulates the motion profile of various chambers and valves that helps effective view classification. This variety of motion profiles is captured in a large Gaussian mixture model called universal motion profile model (UMPM). In order to extract only the relevant motion profiles for each view, a factor analysis based decomposition is applied to the means of the UMPM. This results in a low-dimensional representation called motion profile vector (MPV) which captures the distinctive motion signature for a particular view. To evaluate MPVs, a dataset called ECHO 1.0 is introduced which contains around 637 video clips of the four major views: a) parasternal long-axis view (PLAX), b) parasternal short-axis (PSAX), c) apical four-chamber view (A4C), and d) apical two-chamber view (A2C). We demonstrate the efficacy of motion profile-vectors over other spatio-temporal representations. Further, motion profile-vectors can classify even poorly captured videos with high accuracy which shows the robustness of the proposed representation.

Rheumatoid Arthritis Complicated by Myositis and Vasculitic Neuropathy: A Rare Association.

Rheumatoid arthritis (RA) is a multisystem disease with a variety of manifestations. Vasculitis and myositis are two very rare complications of RA. However, the coexistence of both of these complications in the same patient is extremely rare in medical literature. We here present such a rare association of clinical features in a 36 year old male patient with RA. He had RA for around four years before development of these complications almost simultaneously. The patient was treated with rituximab and oral steroids. The myositis component responded promptly but the vasculitic neuropathy was very slow to respond.

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.

Multiple Cerebral Venous Sinus Thrombosis as Fist Manifestation of Primary Anti-Phospholipid Antibody Syndrome.

Antiphospholipid antibody syndrome (APS) is an autoimmune disorder, mainly found in young females, presenting with vascular thrombosis and/or obstetric complications. Thrombosis at anatomically significant sites may lead to considerable morbidity and/or mortality. We here present a case of primary APS presenting with sudden onset bilateral multiple cerebral venous sinus thrombosis. The patient, a 17 year old female with no prior rheumatological history, presented with sudden onset bilateral painful blindness and massive proptosis. MRI venography was instrumental in diagnosis. She also had significant thrombocytopenia. Except for the visual dimness, the other symptoms responded to therapy. Such massive cerebral venous thrombosis is extremely rare in primary APS.