Deep learning training typically starts with a random sampling initialization approach to set the weights of trainable layers. Therefore, different and/or uncontrolled weight initialization prevents learning the same model multiple times. Consequently, such models yield different results during testing. However, even with the exact same initialization for the weights, a lack of repeatability, replicability, and reproducibility may still be observed during deep learning for many reasons such as software versions, implementation variations, and hardware differences. In this paper, we study repeatability when training deep learning models for segmentation and classification tasks using U-Net and LeNet-5 architectures in two development environments Pytorch and Keras (with TensorFlow backend). We show that even with the available control of randomization in Keras and TensorFlow, there are uncontrolled randomizations. We also show repeatable results for the same deep learning architectures using the Pytorch deep learning library. Finally, we discuss variations in the implementation of the weight initialization algorithm across deep learning libraries as a source of uncontrolled error in deep learning results.

Low-dose computed tomography (LDCT) plays a critical role in the early detection of lung cancer. Despite the life-saving benefit of early detection by LDCT, there are many limitations of this imaging modality including high rates of detection of indeterminate pulmonary nodules. Radiomics is the process of extracting and analyzing image-based, quantitative features from a region-of-interest which then can be analyzed to develop decision support tools that can improve lung cancer screening. Although prior published research has shown that delta radiomics (i.e., changes in features over time) have utility in predicting treatment response, limited work has been conducted using delta radiomics in lung cancer screening. As such, we conducted analyses to assess the performance of incorporating delta with conventional (non delta) features using machine learning to predict lung nodule malignancy. We found the best improved area under the receiver operating characteristic curve (AUC) was 0.822 when delta features were combined with conventional features versus an AUC 0.773 for conventional features only. Overall, this paper demonstrates the important utility of combining delta radiomics features with conventional radiomics features to improve performance of models in the lung cancer screening setting.

Automated food detection and recognition methods have been studied to enhance an end-user life. However, most of the existing research focused on food ingredient type recognition with little work has been done for food ingredient state recognition. Successful recognition of food ingredient state plays a significant role in handling the food ingredient by an intelligent system. In this work, we propose a new novel cascaded multi-head approach based on deep learning for simultaneously recognizing the state and type of food ingredients. We trained and evaluated the proposed approach on a benchmark dataset of food ingredients images with 9 different food states and 18 food types. We compared the proposed approach with a non-cascaded deep learning approach. The cascaded deep learning approach shows improvement in food ingredient state recognition with an accuracy of 87% compared to 81% using a non-cascaded deep learning method. Our proposed method broadly applies to various tasks where food ingredient state recognition is important, such as feeding elderly and disabled person, and for automation of food recognition and preparation.

The novel coronavirus disease 2019 (COVID-19) added tremendous pressure on healthcare services worldwide. COVID-19 early detection is of the utmost importance to control the spread of the coronavirus pandemic and to reduce pressure on health services. There have been many approaches to detect COVID-19; the most commonly used one is the nasal swab technique. Before that was available chest X-ray radiographs were used. X-ray radiographs are a primary care method to reveal lung infections, which allows physicians to assess and plan a course of treatment. X-ray machines are prevalent, which makes this method a preferable first approach for the detection of new diseases. However, this method requires a radiologist to assess each chest X-ray image. Therefore, different automated methods using machine learning techniques have been proposed to assist in speeding up diagnoses and improving the decision-making process. In this paper, we review deep learning approaches for COVID-19 detection using chest X-ray images. We found that the majority of deep learning approaches for COVID-19 detection use transfer learning. A discussion of the limitations and challenges of deep learning in radiography images is presented. Finally, we provide potential improvements for higher accuracy and generalisability when using deep learning models for COVID-19 detection.

The detection and segmentation of stained cells and nuclei are essential prerequisites for subsequent quantitative research for many diseases. Recently, deep learning has shown strong performance in many computer vision problems, including solutions for medical image analysis. Furthermore, accurate stereological quantification of microscopic structures in stained tissue sections plays a critical role in understanding human diseases and developing safe and effective treatments. In this article, we review the most recent deep learning approaches for cell (nuclei) detection and segmentation in cancer and Alzheimer’s disease with an emphasis on deep learning approaches combined with unbiased stereology. Major challenges include accurate and reproducible cell detection and segmentation of microscopic images from stained sections. Finally, we discuss potential improvements and future trends in deep learning applied to cell detection and segmentation.