Radiology report generation is a critical task for radiologists, and automating the process can significantly simplify their workload. However, creating accurate and reliable radiology reports requires radiologists to have sufficient experience and time to review medical images. Unfortunately, many radiology reports end with ambiguous conclusions, resulting in additional testing and diagnostic procedures for patients. To address this, we proposed an encoder-decoder-based deep learning framework that utilizes chest X-ray images to produce diagnostic radiology reports. In our study, we have introduced a novel text modelling and visual feature extraction strategy as part of our proposed encoder-decoder-based deep learning framework. Our approach aims to extract essential visual and textual information from chest X-ray images to generate more accurate and reliable radiology reports. Additionally, we have developed a dynamic web portal that accepts chest X-rays as input and generates a radiology report as output. We conducted an extensive analysis of our model and compared its performance with other state-of-the-art deep learning approaches. Our findings indicate significant improvement achieved by our proposed model compared to existing models, as evidenced by the higher BLEU scores (BLEU1 = 0.588, BLEU2 = 0.4325, BLEU3 = 0.4017, BLEU4 = 0.3860) attained on the Indiana University Dataset. These results underscore the potential of our deep learning framework to enhance the accuracy and reliability of radiology reports, leading to more efficient and effective medical treatment.doi: 10.5829/ije.2023.36.08b.16

Background.To determine the proportion of postpartum depression in women attending a Tertiary Hospital and to determine and study the risk factors associated with postpartum depression.Methods.The present study was a Hospital based Cross-sectional study in which 561 women were assessed on the 3 rd postnatal day and at 6 weeks postpartum for depression and Results.Total number of 600 postnatal women participated in the study.39 women were lost to follow up at 6 weeks.Final sample size for analysis 561.Out of the total 561 postnatal women, 135 of them had a score of > 13 on the EPDS on the 3 rd postpartum day, indicating 24.1% of the postnatal women with "Postpartum Blues".The proportion of postpartum depression was 7.7%.Conclusions.The present study found factors like Age of the woman, low level of education, low socio-economic status, age at marriage, primiparity, obstetric complications, previous miscarriage, preference for a male child, neonatal complications, psychiatric disorder, living in joint families, marital con-

Aim. Estimation of gestational age on basis of Last Menstrual period is reliable and universally followed. Ultrasound gives an objective evidence and dates pregnancy based on crown rump length, biparietal diameter, head circumference, abdominal circumference and femur length. Patients with uncertain dating in third trimester require a simple easy reproducible method when parameters are lagging behind and fetal kidney length can be used as an indicator for gestational age. Materials and methods. A total of 100 well dated normal pregnant patients were studied in third trimester using ultrasound and 3.5 mHz probe and purposive sampling technique. The fetal kidney size was measured and compared with other standard parameters used in pregnancy dating by Ultrasound. Statistical analysis was done using Karl Pearson coefficient and significance was found by student "t" test. Analysis was computed using statistical package SPSS version 11.5.P value is expressed in correlation coefficient. The third trimester was divided into two groups 28-34 weeks and 34-41 weeks. Results. The mean Kidney length was measured and was in the range of 28-38 mm in the first group A and 31-41 mm in second group B. Linear coefficient of individual parameters BPD, HC, AC, FL with gestational age showed strong correlation. Kidney length also showed strong correlation as compared to these parameters. Conclusion. Measurement of Kidney length is of value when other parameters do not accurately predict gestational age and is not affected by growth aberrations and artifacts associated with other standard parameters. What is new in this paper. This paper studies the possibility of using fetal kidney as a biometric indicator for fetal growth when BPD HC AC and FL are inconclusive due to any cause.

The solid pseudopapillary tumour (SPT) of the pancreas is an uncommon cystic pancreatic neoplasm mostly seen in young females. We present a large SPT in a 16-year-old female who presented with acute onset upper- and mid-quadrant abdominal pain associated with nausea and vomiting for 4 days. The lesion was demonstrated by abdominal ultrasound and by computed tomography, which was successfully removed surgically.

Pancreatic injury occurs in less than 5% of major abdominal injuries [1]. Two thirds of pancreatic injuries are associated with penetrating abdominal trauma and one third associated with blunt abdominal trauma [2]. An early diagnosis of pancreatic trauma can be challenging and difficult because of the lack of correlation between the initial presenting features, radiological and laboratory findings, and the severity of the trauma. Caused by compression of the pancreas between the vertebral column and exteral compression, these injuries were extremely difficult to detect in the yesterdyears, but have now become easier to pick up with the advent of cross sectional imaging especially the computed tomography(CT) scan [3]. Morbidity and mortality increases with associated injury to other abdominal organs and vascular structures as well as with delay in diagnosis. We present a rare case of isolated pancreatic injury in a six- year old female.

© 2006. Indian Radiological Association. This is an open access article published by Thieme under the terms of the Creative Commons Attribution-NonDerivative-NonCommercial-License, permitting copying and reproduction so long as the original work is given appropriate credit. Contents may not be used for commercial purposes, or adapted, remixed, transformed or built upon. (https://creativecommons.org/licenses/by-nc-nd/4.0/).