Automated breast tumor ultrasound image segmentation with hybrid UNet and classification using fine-tuned CNN model.

Introduction: Breast cancer stands as the second most deadly form of cancer among women worldwide. Early diagnosis and treatment can significantly mitigate mortality rates. Purpose: The study aims to classify breast ultrasound images into benign and malignant tumors. This approach involves segmenting the breast's region of interest (ROI) employing an optimized UNet architecture and classifying the ROIs through an optimized shallow CNN model utilizing an ablation study. Method: Several image processing techniques are utilized to improve image quality by removing text, artifacts, and speckle noise, and statistical analysis is done to check the enhanced image quality is satisfactory. With the processed dataset, the segmentation of breast tumor ROI is carried out, optimizing the UNet model through an ablation study where the architectural configuration and hyperparameters are altered. After obtaining the tumor ROIs from the fine-tuned UNet model (RKO-UNet), an optimized CNN model is employed to classify the tumor into benign and malignant classes. To enhance the CNN model's performance, an ablation study is conducted, coupled with the integration of an attention unit. The model's performance is further assessed by classifying breast cancer with mammogram images. Result: The proposed classification model (RKONet-13) results in an accuracy of 98.41 %. The performance of the proposed model is further compared with five transfer learning models for both pre-segmented and post-segmented datasets. K-fold cross-validation is done to assess the proposed RKONet-13 model's performance stability. Furthermore, the performance of the proposed model is compared with previous literature, where the proposed model outperforms existing methods, demonstrating its effectiveness in breast cancer diagnosis. Lastly, the model demonstrates its robustness for breast cancer classification, delivering an exceptional performance of 96.21 % on a mammogram dataset. Conclusion: The efficacy of this study relies on image pre-processing, segmentation with hybrid attention UNet, and classification with fine-tuned robust CNN model. This comprehensive approach aims to determine an effective technique for detecting breast cancer within ultrasound images.

Occurrence of shigellosis in pediatric diarrheal patients in Chattogram, Bangladesh: A molecular based approach.

Shigellaa Gram-negative, non-motile bacillus, is the primary causative agent of the infectious disease shigellosis, which kills 1.1 million people worldwideevery year. The children under the age of five are primarily the victims of this disease. This study has been conducted to assess the prevalence of shigellosis through selective plating, biochemical test and conventional PCR assays, where the samples were collected from suspected diarrheoal patients. Invasive plasmid antigen H (ipaH) and O-antigenic rfc gene were used to identify Shigella spp. and S. flexneri respectively. For validation of these identification, PCR product of ipaH gene of a sample (Shigella flexneri MZS 191) has been sequenced and submitted to NCBI database (GenBank accession no- MW774908.1). Further this strain has been used as positive control. Out of 204, around 14.2% (n = 29)(P> 0.01) pediatric diarrheoal cases were screened as shigellosis. Another interesting finding was that most of shigellosis affected children were 7 months to 1 year (P> 0.01).The significance of this study lies in the analyses of the occurrenceand the molecular identification of Shigellaspp. and S. flexneri that can be utilized in improving the accurate identification and the treatment of the most severe and alarming shigellosis.

Resistance of SARS-CoV-2 variants to neutralization by antibodies induced in convalescent patients with COVID-19.

Administration of convalescent plasma or neutralizing monoclonal antibodies (mAbs) is a potent therapeutic option for coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. However, SARS-CoV-2 variants with mutations in the spike protein have emerged in many countries. To evaluate the efficacy of neutralizing antibodies induced in convalescent patients against emerging variants, we isolate anti-spike mAbs from two convalescent COVID-19 patients infected with prototypic SARS-CoV-2 by single-cell sorting of immunoglobulin-G-positive (IgG+) memory B cells. Anti-spike antibody induction is robust in these patients, and five mAbs have potent neutralizing activities. The efficacy of most neutralizing mAbs and convalescent plasma samples is maintained against B.1.1.7 and mink cluster 5 variants but is significantly decreased against variants B.1.351 from South Africa and P.1 from Brazil. However, mAbs with a high affinity for the receptor-binding domain remain effective against these neutralization-resistant variants. Rapid spread of these variants significantly impacts antibody-based therapies and vaccine strategies against SARS-CoV-2.

Focal Ischemic Injury with Complex Middle Cerebral Artery in Stroke-Prone Spontaneously Hypertensive Rats with Loss-Of-Function in NADPH Oxidases.

By means of introgressing a loss-of-function mutation in the p22phox gene from the Matsumoto Eosinophilia Shinshu (MES) rat to stroke-prone spontaneously hypertensive rats (SHRSP), we constructed the SHRSP-based congenic strain lacking the P22PHOX expression (i.e., lacking NADPH oxidases [NOX] activities) (SHRSP.MES-Cyba(mes)/Izm; hereafter referred to as SP.MES). To examine the effects of Nox activities on the focal ischemic injury or stroke, we performed middle cerebral artery (MCA) occlusion in this new congenic strain; the distal MCA was occluded by 561-nm laser-driven photothrombosis. Resting mean arterial blood pressure was significantly lower in SP.MES when compared with the control PM0/SHRSP (150±11 mmHg vs. 166±11 mmHg). Cerebral blood flow decreased to 37±13% in SP.MES and 35±17% in PM0/SHRSP at 10 min after MCA occlusion (not significant). Infarct volume determined at 24 h after MCA occlusion in SP.MES was 89±39 mm3, which was not significantly different from 83±35 mm3 in PM0/SHRSP. The distal MCA pattern was more complex in SP.MES (median 3, IQR 3-5) than PM0/SHRSP (median 2, IQR 1-3) (p = 0.001). Because more complex distal MCA is known to produce larger infarction after distal MCA occlusion in SHR, we adjusted for the branching pattern in an ANCOVA. The adjusted mean of infarct volume was significantly smaller in SP.MES compared with that in PM0/SHRSP (67 [95% CI 46 to 87] mm3 vs. 100 [95% CI 82 to 118] mm3, p = 0.032). Elimination of the P22PHOX expression induced complex distal MCA, which would suggest the presence of 'loss of complexity' induced by enhanced oxidative stress in SHRSP; infarct size in SP.MES--when adjusted for distal MCA complexity--was significantly attenuated compared with that in PM0/SHRSP. Therefore, the present results suggest that Nox is harmful for ischemic brain tissue.