Malaria Parasite Detection using Efficient Neural Ensembles

Caused by the bite of the Anopheles mosquito infected with the parasite of genus Plasmodium, malaria has remained a major burden towards healthcare for years with an approximate 400,000 deaths reported globally every year. The traditional diagnosis process for malaria involves an examination of the blood smear slide under the microscope. This process is not only time consuming but also requires pathologists to be highly skilled in their work. Timely diagnosis and availability of robust diagnostic facilities and skilled laboratory technicians are very much vital to reduce the mortality rate. This study aims to build a robust system by applying deep learning techniques such as transfer learning and snapshot ensembling to automate the detection of the parasite in the thin blood smear images. All the models were evaluated against the following metrics - F1 score, Accuracy, Precision, Recall, Mathews Correlation Coefficient (MCC), Area Under the Receiver Operating Characteristics (AUC-ROC) and the Area under the Precision Recall curve (AUC-PR). The snapshot ensembling model created by combining the snapshots of the EfficientNet-B0 pre-trained model outperformed every other model achieving a f1 score - 99.37%, precision - 99.52% and recall - 99.23%. The results show the potential of model ensembles which combine the predictive power of multiple weal models to create a single efficient model that is better equipped to handle the real world data. The GradCAM experiment displayed the gradient activation maps of the last convolution layer to visually explicate where and what a model sees in an image to classify them into a particular class. The models in this study correctly activate the stained parasitic region of interest in the thin blood smear images. Such visuals make the model more transparent, explainable, and trustworthy which are very much essential for deploying AI based models in the healthcare network.

Malaria Parasite Detection using Efficient Neural Ensembles

Caused by the bite of the Anopheles mosquito infected with the parasite of genus Plasmodium, malaria has remained a major burden towards healthcare for years with an approximate 400,000 deaths reported globally every year. The traditional diagnosis process for malaria involves an examination of the blood smear slide under the microscope. This process is not only time consuming but also requires pathologists to be highly skilled in their work. Timely diagnosis and availability of robust diagnostic facilities and skilled laboratory technicians are very much vital to reduce the mortality rate. This study aims to build a robust system by applying deep learning techniques such as transfer learning and snapshot ensembling to automate the detection of the parasite in the thin blood smear images. All the models were evaluated against the following metrics - F1 score, Accuracy, Precision, Recall, Mathews Correlation Coefficient (MCC), Area Under the Receiver Operating Characteristics (AUC-ROC) and the Area under the Precision Recall curve (AUC-PR). The snapshot ensembling model created by combining the snapshots of the EfficientNet-B0 pre-trained model outperformed every other model achieving a f1 score - 99.37%, precision - 99.52% and recall - 99.23%. The results show the potential of model ensembles which combine the predictive power of multiple weal models to create a single efficient model that is better equipped to handle the real world data. The GradCAM experiment displayed the gradient activation maps of the last convolution layer to visually explicate where and what a model sees in an image to classify them into a particular class. The models in this study correctly activate the stained parasitic region of interest in the thin blood smear images. Such visuals make the model more transparent, explainable, and trustworthy which are very much essential for deploying AI based models in the healthcare network.

Bovine Cerebral Theileriosis: First Molecular Confirmed Report in Cross Bred Cattle Calf in India

Bovine tropical theileriosis caused by Theileria annulata, is a serious constraint to Indian dairy industry with more fatal infections in exotic cattle and substantial losses to cross-bred and indigenous zebu cattle. The present communication is to place on record the first report of molecular based confirmed case of cerebral theileriosis caused by T. annulata coupled with its morphological detection, clinical manifestations, haematological alterations and therapeutic management in a cross bred cattle calf from India. After preparation of peripheral thin blood smear from cross bred cattle calf at the site of collection and fixation with methanol, blood sample brought to Department of Veterinary Parasitology, College of Veterinary Science and A.H, Jabalpur and stained by standard protocol for Giemsa staining. Genomic DNA was isolated from the collected blood sample using QIAamp® DNA blood mini kit following the manufacturer’s recommendations and PCR was performed. The cross bred cow calf revealed high rise in temperature (105.5°F), increased heart rate, labored breathing with seromucous nasal discharge, enlargement of prescapular lymph node and animal exhibited tonic clonic convulsions in response to any sudden noise. Giemsa stained thin blood smear revealed intraerythrocytic piroplasm and Koch blue bodies of T. annulata within the cytoplasm of lymphocytes. The species of Theileria was confirmed by molecular amplification of genomic DNA as T. annulata.

High incidence of asymptomatic cases during an outbreak of Plasmodium malariae in a remote village of Malaysian Borneo

An outbreak of Plasmodium malariae occurred in Sonsogon Paliu village in the remote area of Ulu Bengkoka sub-district of Kota Marudu, Northern Sabah, Malaysian Borneo from July through August 2019. This was the first outbreak of malaria in this village since 2014. On 11th July 2019 the Kota Kinabalu Public Health Laboratory notified the Kota Marudu District Health Office of a Polymerase Chain Reaction (PCR) positive case of P. malariae. This index case was a male from Sulawesi, Indonesia working for a logging company operating in Sonsogon Paliu. During the resulting outbreak, a total of 14 symptomatic cases were detected. All of these cases were positive by thick and thin blood smear examination, and also by PCR. During the outbreak, a mass blood survey screening was performed by light-microscopy and PCR. A total of 94 asymptomatic villagers 31 (33.0%) were PCR positive but thick and thin blood smear negative for P. malariae. Both symptomatic and asymptomatic cases received treatment at the district hospital. When symptomatic and asymptomatic cases were considered together, males (29/45. 64.5%) were infected more than females (16/45, 35.6%), the male:female ratio being 1.8:1. Adults were the predominant age group infected (22/45, 48.9%) followed by adolescents (19/45, 42.2%) and children under five years of age (4/45, 8.9%). This report illustrates that symptomatic and submicroscopic cases pose a challenge during P. malariae outbreaks and that PCR is a valuable tool for their identification. The rapid identification and control of imported malaria is crucial for the continued control of malaria in Malaysia.

First Report on Molecular Identification of Babesia bigemina in a Nervous Signs Evident Naturally Infected Holstein-Friesian Cattle from Central India

Background: Bovine babesiosis caused by an intraerythrocytic apicomplexan protozoon responsible for the most prevalent and costly tick borne diseases (TBD’s) of cattle throughout the globe. Cerebral babesiosis of bovine is fatal and mainly caused by Babesia bovis. To the knowledge of author, there is no confirm molecular report of Babeisa bigemina caused cerebral babesiosis in cattle. Therefore, authors want to report Babesia bigemina caused cerebral babesiosis on record. Methods: In the year 2015, a Holstein-Friesian cow aged 3 years and weighing approximately 300 kg, was attended at Jabalpur, (M.P.) with the clinical signs of high rise in temperature (104°F), recumbency, severe dysponea, peculiar sound during open mouth breathing, pale color of eye conjunctiva and mucous membrane of vagina, convulsions, sever anaemia, paddling of legs at frequent interval. After preparation of peripheral thin blood smear from animal at the site of collection and fixation with methanol, blood sample brought to Department of Veterinary Parasitology, College of Veterinary Science and A.H, Jabalpur and stained by standard protocol for Giemsa staining. Genomic DNA was isolated from the collected blood sample using QIAamp® DNA blood mini kit following the manufacturer’s recommendations and PCR was performed. Conclusion: The thin blood smear examination revealed the presence of Babesia parasite. The species of Babesia was confirmed by molecular amplification of genomic DNA as B. bigemina. This might be the first confirmed report of cerebral babesiosis caused by B. bigemina from Central India.