A promising deep learning-assistive algorithm for histopathological screening of colorectal cancer.

Colorectal cancer is one of the most common cancers worldwide, accounting for an annual estimated 1.8 million incident cases. With the increasing number of colonoscopies being performed, colorectal biopsies make up a large proportion of any histopathology laboratory workload. We trained and validated a unique artificial intelligence (AI) deep learning model as an assistive tool to screen for colonic malignancies in colorectal specimens, in order to improve cancer detection and classification; enabling busy pathologists to focus on higher order decision-making tasks. The study cohort consists of Whole Slide Images (WSI) obtained from 294 colorectal specimens. Qritive's unique composite algorithm comprises both a deep learning model based on a Faster Region Based Convolutional Neural Network (Faster-RCNN) architecture for instance segmentation with a ResNet-101 feature extraction backbone that provides glandular segmentation, and a classical machine learning classifier. The initial training used pathologists' annotations on a cohort of 66,191 image tiles extracted from 39 WSIs. A subsequent application of a classical machine learning-based slide classifier sorted the WSIs into 'low risk' (benign, inflammation) and 'high risk' (dysplasia, malignancy) categories. We further trained the composite AI-model's performance on a larger cohort of 105 resections WSIs and then validated our findings on a cohort of 150 biopsies WSIs against the classifications of two independently blinded pathologists. We evaluated the area under the receiver-operator characteristic curve (AUC) and other performance metrics. The AI model achieved an AUC of 0.917 in the validation cohort, with excellent sensitivity (97.4%) in detection of high risk features of dysplasia and malignancy. We demonstrate an unique composite AI-model incorporating both a glandular segmentation deep learning model and a classical machine learning classifier, with excellent sensitivity in picking up high risk colorectal features. As such, AI plays a role as a potential screening tool in assisting busy pathologists by outlining the dysplastic and malignant glands.

A case report of COVID-19 in a patient with non-Hodgkin's lymphoma.

BACKGROUND: The current literature is scarce as to the outcomes of COVID-19 infection in non-Hodgkin's lymphoma patients and whether immunosuppressive or chemotherapeutic agents can cause worsening of the patients' condition during COVID-19 infection. CASE PRESENTATION: Our case is a 59-year-old gentleman who presented to the Emergency Department of the Cancer Institute of Hospital das Clínicas da Universidade de São Paulo, São Paulo, Brazil on 10th May 2020 with a worsening dyspnea and chest pain which had started 3 days prior to presentation to the Emergency Department. He had a past history of non-Hodgkin's lymphoma for which he was receiving chemotherapy. Subsequent PCR testing demonstrated that our patient was SARS-CoV-2 positive. CONCLUSION: In this report, we show a patient with non-Hodgkin lymphoma in the middle of chemotherapy, presented a mild clinical course of COVID-19 infection.

Amyloidosis cutis dyschromica: report of 3 cases.

Amyloidosis cutis dyschromica (ACD) is a rare pigmentary disorder with about 50 cases having been reported in the English literature. Only one case of ACD has been reported from Iran. We present three patients who presented with generalized hyper- and hypopigmented patches, sparing face, hands, and feet in all three cases. The presence of amorphous eosinophilic deposits in the papillary dermis confirmed the diagnosis of ACD; the deposits were stained by crystal violet in the histopathological examination of the lesions. In all three cases, similar lesions were present in some of the family members. ACD should be considered in the differential diagnosis of diffuse hyperpigmentation studded with hypopigmentation, especially when beginning in childhood.