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.

Detection of Human PapillomaVirus and its Association with Potentially Malignant Disorders and Oral Squamous Cell Carcinoma: A Retrospective Study.

Aim: This study was carried out with the objective of recognizing the involvement of human papillomavirus (HPV) in conditions of oral squamous cell carcinoma (OSCC) and oral potentially malignant conditions and lesions. Materials and Methods: OSCC samples from thirty patients were collected and thirty paraffin-embedded, oral premalignant specimens were collected. It was decided to use as a negative control samples gingiva from healthy individuals who had no prior history of oral proliferative leukoplakia or OSCC. The samples were then processed using a paraffin-embedded tissue block method. Deoxyribonucleic acid will be extracted from the paraffin-embedded tumor sample of sixty case subjects and tested for the presence of HPV DNA using polymerase chain reaction. Results: In study Group 1, 24 samples were taken from males and 6 from females. In study Group 2, 26 cases were males and 4 were females. In Group 1, 16 cases of moderately differentiated and 14 cases of well differentiated each were present. No case of poorly differentiated were found. There was statistically no significant difference present between male and female when Group 1 and Group 2 was considered. In study Group 1, 0 samples had positive HPV DNA detection, whereas 30 samples had negative HPV DNA detection. In study Group 2, 0 samples had positive HPV DNA detection, whereas 30 samples had negative HPV expression. Conclusion: According to our findings, certain incidences of OSCC may be linked to HPV, however, this was not the case for all of the cancers.

Pleomorphic adenoma of the upper lip.

This case report describes a rare and unusual lesion found in a 33-year-old male, which was diagnosed as pleomorphic adenoma of the minor salivary glands in the upper lip. The tumor was a circumscribed, large firm mass, about 3 cm in diameter, almost obstructing the nares and characterized by slow growth. Complete excision was performed and the histopathologic analysis showed pleomorphic adenoma. The tumor did not recur. A brief review of the relevant literature is also presented.

Efficacy of Iliac Crest vs. Medpor in Orbital Floor Reconstruction.

AIM: The present study is to compare the effectiveness of iliac crest graft and medpor implant, for repairing traumatic orbital floor defects. MATERIALS AND METHODS: A total of 20 patients were included in the study. Autogenous iliac crest graft and medpor implant was used in 10 patients of the each group. Patients were evaluated for the presence or absence of diplopia, enophthalmos, infraorbital nerve paresthesia, and ocular motility disorders. Surgical indications for orbital exploration included entrapment of orbital tissues, large orbital defect (greater than 50% of the orbital floor or more than 8 mm), or orbital floor defects with involvement of other zygomaticofrontal complex fractures. RESULTS: All patients were successfully treated by restoration of the orbital wall continuity. Follow-up was done at 1-12 weeks. One patient had postoperative infection. There was no graft extrusion. CONCLUSIONS: Both the groups showed satisfactory results, but group II was better than group I, as there was no donor site morbidity. Porous polyethylene (Medpor) is a biocompatible and high-density polyethylene implant. It is well tolerated by surrounding tissue, and its porous structure is rapidly infiltrated by host tissue. It is a highly stable and somewhat flexible porous alloplast that has rapid tissue in growth into its pores.

Laparoscopic nephroplication and nephropexy as an adjunct to pyeloplasty in UPJO with giant hydronephrosis.

Giant hydronephrosis due to uretero-pelvic junction obstruction (UPJO) is rare and usually the treatment is nephrectomy. When renal salvage is required, reconstruction of the UPJ alone is usually inadequate to improve drainage from the pelvicalyceal system. Various open surgical techniques have been described to improve gravity-assisted drainage from the giant hydronephrotic kidney. We describe, for the first time, a complete laparoscopic approach for pyeloplasty combined with nephroplication and nephropexy.