Search

This research paper presents an innovative solution for offline handwritten word recognition in Bengali, a prominent Indic language. The complexities of this script, particularly in cursive writing, often lead to overlapping characters and segmentation challenges. Conventional methodologies, reliant on individual character recognition and aggregation, are error-prone. To overcome these limitations, we propose a novel method treating the entire document as a coherent entity and utilizing the efficient you only look once (YOLO) model for word extraction. In our approach, we view individual words as distinct objects and employ the YOLO model for supervised learning, transforming object detection into a regression problematic to predict spatially detached bounding boxes and class possibilities. Rigorous training results in outstanding performance, with remarkable box_loss of 0.014, obj_loss of 0.14, and class_loss of 0.009. Furthermore, the achieved mAP_0.5 score of 0.95 and map_0.5:0.95 score of 0.97 demonstrates the model's exceptional accuracy in detecting and recognizing handwritten words. To evaluate our method comprehensively, we introduce the Omor-Ekush dataset, a meticulously curated collection of 21,300 handwritten words from 150 participants, featuring 141 words per document. Our pioneering YOLO-based approach, combined with the curated Omor-Ekush dataset, represents a significant advancement in handwritten word recognition in Bengali. [ABSTRACT FROM AUTHOR]

Expanding urban impervious surface area (ISA) mapping is crucial to sustainable development, urban planning, and environmental studies. Multispectral ISA mapping is challenging because of the mixed-pixel problems with bare soil. This study presents a novel approach using spectral and temporal information to develop a Soil-Suppressed Impervious Surface Area Index (SISAI) using the Landsat Operational Land Imager (OLI) data set, which reduces the soil but enhances the ISA signature. This study mapped the top 12 populated megacities using SISAI and achieved an overall accuracy of 0.87 with an F1-score of 0.85. It also achieved a higher Spatial Dissimilarity Index between the ISA and bare soil. However, it is limited by bare gray soil and shadows of clouds and hills. SISAI encourages urban dynamics and inter-urban comparison studies owing to its automatic and unsupervised methodology. [ABSTRACT FROM AUTHOR]

BACKGROUND & OBJECTIVE: Tibial shaft fracture treatment with intermedullary nailing is very common these days. In the current study, our objective was to determine the percentage of patients with anterior knee pain following tibial shaft fracture treatment with interlocking intermedullary nailing. METHODOLOGY: Our research design was a Descriptive cross-sectional study. The study duration was approximately one year (03-3-2020 to 3-3-2021). The study was conducted at the orthopedics department of CMH Muzafarrabad. A sample of 125 participants was calculated. All patients underwent interlocking intermedullary nailing. We analyzed data using SPSS version 24. p-value less than 0.05 was considered statistically significant for result authenticity. RESULTS: In the present study 125 patients were included.Mean age of patients was 42.4±8.6SD years.Among all the patients, 82(65.6%) reported no pain while 43(34.4%) reported pain. Visual analogue scale showed mean pain scores 3.22±2.5SD and lysholm scores were 80.74±3.28SD (p≤0.000 and p≤0.000, respectively). CONCLUSION: Tibial shaft fractures are common these days. A relatively high incidence of anterior knee pain following intermedually nailing after tibial shaft fracture was found in our study. [ABSTRACT FROM AUTHOR]

Background: Because juvenile brain tumors may have a variable presentation and comparable imaging appearances, noninvasive diagnosis can be difficult. The MRS measures certain metabolites and their ratios. When paired with conventional magnetic resonance imaging's high spatial resolution anatomical images (MRI), magnetic resonance spectroscopy (MRS) gives metabolic information from the surrounding tissue and the lesion itself. Making the distinction between malignant and noncancerous, as well as between low-grade and high-grade neoplasms. Its use is crucial for selecting the best course of treatment. We used MRS to measure certain metabolic ratios and examine the metabolic profiles of various lesions in order to make a more precise diagnosis. Method: 30 individuals were prospectively included in this study, ranging in age from 1 to 16 years old and with a mean age (SD) of 11.56 (months) to 2.48 years (14 male and 16 female). They visited the pediatric cancer clinic between May 2021 and May 2022 with brain mass lesions that had been detected by CT. The patient's guardians provided written informed consent in conformity with the National Ethics Committee. All patients had complete clinical assessments, routine MRS, and MRI exams utilizing a 1.5T scanner outfitted with the typical head coil. Due to anomalies that were too near to the middle ear or nasal cavity, several patients were excluded from the investigation, which resulted in a poor diagnostic spectrum. Results: 28 of the 30 individuals who had MRI and MRS scans exhibited intracranial mass lesions, according to the data. The remaining two patients were found to have multiple sclerosis in one case and acute disseminated encephalomyelitis (ADEM) in the other after radiological and clinical follow-ups. After receiving an orthogonal biopsy, 26 of the 28 patients with mass lesions were histologically shown to be malignant. Two cases of brainstem gliomas underwent clinical and radiological monitoring but did not undergo surgery or a biopsy. Conclusions: For the non-invasive diagnosis of adolescent brain tumors, the use of important metabolites with high specificity and sensitivity to differentiate between malignant from benign tumor lesions and minimal to fast growing neoplasms is helpful. MRS may address sampling issues with inaccessible and different lesions as well as an unneeded sampling by evaluating tumor spatial extent and projecting tumor activity. [ABSTRACT FROM AUTHOR]

Objective: To compare the efficacy of topical Adapalene plus oral Azithromycin versus topical Adapalene plus oral Doxycycline in treating mild to moderate acne vulgaris. Study Design: Quasi-experimental study. Place and Duration of Study: Dermatology Department, Pak Emirates Military Hospital Rawalpindi, from Jun to Dec 2017. Methodology: A total of 60 patients were enrolled in the study and were grouped into two groups, A and B, comprising 30 patients in each group. Random tables were used to allocate patients to each group. In this study, Group A was prescribed topical Adapalene be applied as a thin layer over affected areas at night plus oral Azithromycin 250 mg capsule once daily for 03 months, while Group B was given the same instructions for topical Adapalene plus oral Doxycycline100 mg twice daily for 03 months. Fifty percent reduction of lesions from the baseline was considered an effective therapeutic response. Results: In our patient sample mean age in Group A was 18 years (± 4.77), while the mean age in Group B was 19 years (± 5.12). In Group A, 13 (43%) patients were male, and 17 (57%) patients were female, while in Group B, 12 (40%) patients were male, and 18 (60%) patients were female. Treatment in Group A was effective in 90% of patients, while 73% of patients in Group B showed effective response. Conclusion: This study concluded that a combination of topical Adapalene plus oral Azithromycin was equally efficacious to topical Adapalene plus oral Doxycycline in treating mild and moderate acne vulgaris. [ABSTRACT FROM AUTHOR]