An automated malaria cells detection from thin blood smear images using deep learning.

Timely and rapid diagnosis is crucial for faster and proper malaria treatment planning. Microscopic examination is the gold standard for malaria diagnosis, where hundreds of millions of blood films are examined annually. However, this method's effectiveness depends on the trained microscopist's skills. With the increasing interest in applying deep learning in malaria diagnosis, this study aims to determine the most suitable deep-learning object detection architecture and their applicability to detect and distinguish red blood cells as either malaria-infected or non-infected cells. The object detectors Yolov4, Faster R-CNN, and SSD 300 are trained with images infected by all five malaria parasites and from four stages of infection with 80/20 train and test data partition. The performance of object detectors is evaluated, and hyperparameters are optimized to select the best-performing model. The best-performing model was also assessed with an independent dataset to verify the models' ability to generalize in different domains. The results show that upon training, the Yolov4 model achieves a precision of 83%, recall of 95%, F1-score of 89%, and mean average precision of 93.87% at a threshold of 0.5. Conclusively, Yolov4 can act as an alternative in detecting the infected cells from whole thin blood smear images. Object detectors can complement a deep learning classification model in detecting infected cells since they eliminate the need to train on single-cell images and have been demonstrated to be more feasible for a different target domain.

An automated malaria cells detection from thin blood smear images using deep learning

@#Timely and rapid diagnosis is crucial for faster and proper malaria treatment planning. Microscopic examination is the gold standard for malaria diagnosis, where hundreds of millions of blood films are examined annually. However, this method’s effectiveness depends on the trained microscopist’s skills. With the increasing interest in applying deep learning in malaria diagnosis, this study aims to determine the most suitable deep-learning object detection architecture and their applicability to detect and distinguish red blood cells as either malaria-infected or non-infected cells. The object detectors Yolov4, Faster R-CNN, and SSD 300 are trained with images infected by all five malaria parasites and from four stages of infection with 80/20 train and test data partition. The performance of object detectors is evaluated, and hyperparameters are optimized to select the best-performing model. The best-performing model was also assessed with an independent dataset to verify the models’ ability to generalize in different domains. The results show that upon training, the Yolov4 model achieves a precision of 83%, recall of 95%, F1-score of 89%, and mean average precision of 93.87% at a threshold of 0.5. Conclusively, Yolov4 can act as an alternative in detecting the infected cells from whole thin blood smear images. Object detectors can complement a deep learning classification model in detecting infected cells since they eliminate the need to train on single-cell images and have been demonstrated to be more feasible for a different target domain.

Spontaneous Omental Infarction: An Unusual Etiology of Abdominal Pain.

A 49-year-old lady with previous scars complained of acute abdominal pain for two days. Her right hypochondrium was tender and guarding upon assessment. The laboratory investigations were unremarkable. Due to a diagnostic incongruity, computed tomography of the abdomen was performed showing a suspicious lesion at anterolateral aspect of the ascending colon. Surgical intervention was decided and intraoperative finding was consistent with spontaneous omental infarction. Omentectomy was undertaken and final histology was compatible with the intraoperative diagnosis. Although it is exceptional, omental infarction should be considered as part of the differential diagnoses of right-sided acute abdominal pain with normal laboratory investigations. This case highlights its unexpected discovery and we describe its literature reviews.

Evaluation of irradiated salivary gland function in patients with head and neck tumours treated with radiotherapy.

INTRODUCTION: Radiotherapy is an important treatment modality for head and neck tumours. One of its major drawbacks is post-treatment salivary gland hypofunction. This study was performed to objectively evaluate the salivary gland function in post-irradiated head and neck tumour patients. METHODS: We performed a cross-sectional study of 30 patients with head and neck tumours who had received radiotherapy. Unstimulated and stimulated whole salivary flow rates were assessed in these 30 patients, and compared with those of 30 normal subjects. Unstimulated whole saliva was measured by the draining method, while the spitting method was used to collect stimulated whole saliva. RESULTS: Both unstimulated and stimulated whole salivary flow rates were significantly reduced in the irradiated patients, compared with the normal subjects. This difference was statistically significant (p = 0.0001). CONCLUSION: Salivary function in post-irradiated head and neck tumour patients (assessed as salivary flow rates) was significantly reduced compared with normal controls, suggesting marked salivary gland hypofunction.

Non-cytotoxic polymer vesicles for rapid and efficient intracellular delivery.

We have recently achieved efficient cytosolic delivery by using pH-sensitive poly(2-(methacryloyloxy)ethylphosphorylcholine)-co-poly(2-(diisopropylamino)ethylmethacrylate) (PMPC-PDPA) diblock copolymers that self-assemble to form vesicles, known as polymersomes, in aqueous solution. It is particularly noteworthy that these diblock copolymers form stable polymersomes at physiological pH but rapidly dissociate below pH 6 to give molecularly-dissolved copolymer chains (unimers). These PMPC-PDPA polymersomes are used to encapsulate nucleic acids for efficient intracellular delivery. Confocal laser scanning microscopy and fluorescence flow cytometry are used to quantify cellular uptake and to study the kinetics of this process. Finally, we examine how PMPC-PDPA polymersomes affect the viability of primary human cells (human dermal fibroblasts (HDF)), paying particular regard to whether inflammatory responses are triggered.