Trustworthy Medical Image Segmentation with improved performance for in-distribution samples.

Despite the enormous achievements of Deep Learning (DL) based models, their non-transparent nature led to restricted applicability and distrusted predictions. Such predictions emerge from erroneous In-Distribution (ID) and Out-Of-Distribution (OOD) samples, which results in disastrous effects in the medical domain, specifically in Medical Image Segmentation (MIS). To mitigate such effects, several existing works accomplish OOD sample detection; however, the trustworthiness issues from ID samples still require thorough investigation. To this end, a novel method TrustMIS (Trustworthy Medical Image Segmentation) is proposed in this paper, which provides the trustworthiness and improved performance of ID samples for DL-based MIS models. TrustMIS works in three folds: IT (Investigating Trustworthiness), INT (Improving Non-Trustworthy prediction) and CSO (Classifier Switching Operation). Initially, the IT method investigates the trustworthiness of MIS by leveraging similar characteristics and consistency analysis of input and its variants. Subsequently, the INT method employs the IT method to improve the performance of the MIS model. It leverages the observation that an input providing erroneous segmentation can provide correct segmentation with rotated input. Eventually, the CSO method employs the INT method to scrutinise several MIS models and selects the model that delivers the most trustworthy prediction. The experiments conducted on publicly available datasets using well-known MIS models reveal that TrustMIS has successfully provided a trustworthiness measure, outperformed the existing methods, and improved the performance of state-of-the-art MIS models. Our implementation is available at https://github.com/SnehaShukla937/TrustMIS.

Eosinophilic mastitis mimicking a developing asymmetry.

Eosinophilic mastitis is a very rare form of mastitis with few reported cases in the literature. This is a case of eosinophilic mastitis in a 48-year-old woman which presented as a screen detected right breast developing asymmetry. No sonographic abnormalities were visualized on diagnostic workup, and subsequent tomosynthesis-guided biopsy was performed. Knowledge of this rare entity is helpful in the radiologic-pathologic correlation, diagnosis, and clinical management of future cases.

From Scylla to Charybdis: Fixed drug combinations for tuberculosis and increased ethambutol-induced optic neuropathy in India.

Purpose: To describe the increase in prevalence of ethambutol-induced optic neuropathy (EON) in patients presenting to a single tertiary referral eye care center in India after introduction of weight-based fixed dose combinations and an increase in duration of ethambutol use from 2016 in the Revised National Tuberculosis Control Program. Methods: This was a retrospective, observational, referral hospital-based study of 156 patients with a diagnosis of EON presenting to a single tertiary referral eye care center between January 2016 and December 2019. The main outcome measure was to assess the increase in prevalence of EON cases presenting to our tertiary care institute. Results: During the 4-year study period, 156 new patients were diagnosed with EON. A total of 101 patients (64.7%) were males and 55 (35.3%) were females. The most common age group affected was 41-60 years. The significant complaint at presentation was decreased vision in all the patients. A rising trend in the number of patients diagnosed as EON was seen, with the prevalence increasing from 16 cases in 2016, 13 cases in 2017, and 31 cases in 2018 to 96 cases in 2019. Conclusion: The results of this study indicated an alarming increase in the trend of EON cases presenting to our tertiary care institute.

Local Recurrence of Invasive Secretory Breast Carcinoma in a Gravid Patient Post-Mastectomy.

This is a case of locally recurrent invasive secretory carcinoma of the breast during pregnancy, detected as a palpable mass in the reconstructed right breast of a 32-year-old female at 24 weeks gestation. The patient was initially diagnosed with secretory carcinoma 8 years prior, for which she underwent nipple sparing mastectomy followed by adjuvant chemotherapy and endocrine therapy. Due to pregnancy, the recurrence was treated initially with conservative excision alone, followed by definitive management postpartum which included wide local excision, sentinel lymph node biopsy and adjuvant chest wall radiation. Secretory carcinoma of the breast is a rare cancer with a predilection for young age and indolent course. This case report describes an unusual case of recurrent secretory carcinoma, of interest due to both its diagnosis during pregnancy, and its recurrence after nipple sparing mastectomy.

Applying Auto-Regressive Model's Yule-Walker Approach to Amyotrophic Lateral Sclerosis (ALS) patients' Data.

OBJECTIVE: The purpose of this study is to identifying time series analysis and mathematical model fitting on electroencephalography channels that are placed on Amyotrophic Lateral Sclerosis (ALS) patients with P300 based brain-computer interface (BCI). METHODS: Amyotrophic Lateral Sclerosis (ALS) or motor neuron diseases are a rapidly progressing neurological disease that attacks and kills neurons responsible for controlling voluntary muscles. There is no cure and treatment effective to reverse, to halt the disease progression. A Brain- Computer Interface enables disable person to communicate & interact with each other and with the environment. To bypass the important motor difficulties present in ALS patient, BCI is useful. An input for BCI system is patient's brain signals and these signals are converted into external operations, for brain signals detection, Electroencephalography (EEG) is normally used. P300 based BCI is used to record the reading of EEG brain signals with the help of non-invasive placement of channels. In EEG, channel analysis Autoregressive (AR) model is a widely used. In the present study, Yule-Walker approach of AR model has been used for channel data fitting. Model fitting as a form of digitization is majorly required for good understanding of the dataset, and also for data prediction. RESULTS: Fourth order of the mathematical curve for this dataset is selected. The reason is the high accuracy obtained in the 4th order of Autoregressive model (97.51±0.64). CONCLUSION: In proposed Auto Regressive (AR) model has been used for Amyotrophic Lateral Sclerosis (ALS) patient data analysis. The 4th order of Yule Walker auto-regressive model is giving best fitting on this problem.