Development and evaluation of deep learning algorithms for assessment of acute burns and the need for surgery.

Assessment of burn extent and depth are critical and require very specialized diagnosis. Automated image-based algorithms could assist in performing wound detection and classification. We aimed to develop two deep-learning algorithms that respectively identify burns, and classify whether they require surgery. An additional aim assessed the performances in different Fitzpatrick skin types. Annotated burn (n = 1105) and background (n = 536) images were collected. Using a commercially available platform for deep learning algorithms, two models were trained and validated on 70% of the images and tested on the remaining 30%. Accuracy was measured for each image using the percentage of wound area correctly identified and F1 scores for the wound identifier; and area under the receiver operating characteristic (AUC) curve, sensitivity, and specificity for the wound classifier. The wound identifier algorithm detected an average of 87.2% of the wound areas accurately in the test set. For the wound classifier algorithm, the AUC was 0.885. The wound identifier algorithm was more accurate in patients with darker skin types; the wound classifier was more accurate in patients with lighter skin types. To conclude, image-based algorithms can support the assessment of acute burns with relatively good accuracy although larger and different datasets are needed.

Detection of breast cancer lymph node metastases in frozen sections with a point-of-care low-cost microscope scanner.

BACKGROUND: Detection of lymph node metastases is essential in breast cancer diagnostics and staging, affecting treatment and prognosis. Intraoperative microscopy analysis of sentinel lymph node frozen sections is standard for detection of axillary metastases but requires access to a pathologist for sample analysis. Remote analysis of digitized samples is an alternative solution but is limited by the requirement for high-end slide scanning equipment. OBJECTIVE: To determine whether the image quality achievable with a low-cost, miniature digital microscope scanner is sufficient for detection of metastases in breast cancer lymph node frozen sections. METHODS: Lymph node frozen sections from 79 breast cancer patients were digitized using a prototype miniature microscope scanner and a high-end slide scanner. Images were independently reviewed by two pathologists and results compared between devices with conventional light microscopy analysis as ground truth. RESULTS: Detection of metastases in the images acquired with the miniature scanner yielded an overall sensitivity of 91% and specificity of 99% and showed strong agreement when compared to light microscopy (k = 0.91). Strong agreement was also observed when results were compared to results from the high-end slide scanner (k = 0.94). A majority of discrepant cases were micrometastases and sections of which no anticytokeratin staining was available. CONCLUSION: Accuracy of detection of metastatic cells in breast cancer sentinel lymph node frozen sections by visual analysis of samples digitized using low-cost, point-of-care microscopy is comparable to analysis of digital samples scanned using a high-end, whole slide scanner. This technique could potentially provide a workflow for digital diagnostics in resource-limited settings, facilitate sample analysis at the point-of-care and reduce the need for trained experts on-site during surgical procedures.

Quantification of Estrogen Receptor-Alpha Expression in Human Breast Carcinomas With a Miniaturized, Low-Cost Digital Microscope: A Comparison with a High-End Whole Slide-Scanner.

INTRODUCTION: A significant barrier to medical diagnostics in low-resource environments is the lack of medical care and equipment. Here we present a low-cost, cloud-connected digital microscope for applications at the point-of-care. We evaluate the performance of the device in the digital assessment of estrogen receptor-alpha (ER) expression in breast cancer samples. Studies suggest computer-assisted analysis of tumor samples digitized with whole slide-scanners may be comparable to manual scoring, here we study whether similar results can be obtained with the device presented. MATERIALS AND METHODS: A total of 170 samples of human breast carcinoma, immunostained for ER expression, were digitized with a high-end slide-scanner and the point-of-care microscope. Corresponding regions from the samples were extracted, and ER status was determined visually and digitally. Samples were classified as ER negative (<1% ER positivity) or positive, and further into weakly (1-10% positivity) and strongly positive. Interobserver agreement (Cohen's kappa) was measured and correlation coefficients (Pearson's product-momentum) were calculated for comparison of the methods. RESULTS: Correlation and interobserver agreement (r = 0.98, p < 0.001, kappa = 0.84, CI95% = 0.75-0.94) were strong in the results from both devices. Concordance of the point-of-care microscope and the manual scoring was good (r = 0.94, p < 0.001, kappa = 0.71, CI95% = 0.61-0.80), and comparable to the concordance between the slide scanner and manual scoring (r = 0.93, p < 0.001, kappa = 0.69, CI95% = 0.60-0.78). Fourteen (8%) discrepant cases between manual and device-based scoring were present with the slide scanner, and 16 (9%) with the point-of-care microscope, all representing samples of low ER expression. CONCLUSIONS: Tumor ER status can be accurately quantified with a low-cost imaging device and digital image-analysis, with results comparable to conventional computer-assisted or manual scoring. This technology could potentially be expanded for other histopathological applications at the point-of-care.

Assessment of tumour viability in human lung cancer xenografts with texture-based image analysis.

AIMS: To build and evaluate an automated method for assessing tumour viability in histological tissue samples using texture features and supervised learning. METHODS: H&E-stained sections (n=56) of human non-small cell lung adenocarcinoma xenografts were digitised with a whole-slide scanner. A novel image analysis method based on local binary patterns and a support vector machine classifier was trained with a set of sample regions (n=177) extracted from the whole-slide images and tested with another set of images (n=494). The extracted regions, or single-tissue entity images, were chosen to represent as pure as possible examples of three morphological tissue entities: viable tumour tissue, non-viable tumour tissue and mouse host tissue. RESULTS: An agreement of 94.5% (area under the curve=0.995, kappa=0.90) was achieved to classify the single-tissue entity images in the test set (n=494) into the viable tumour and non-viable tumour tissue categories. The algorithm assigned 250 of the 252 non-viable and 219 of the 242 of viable sample regions to the correct categories, respectively. This corresponds to a sensitivity of 90.5% and specificity of 99.2%. CONCLUSIONS: The proposed image analysis-based tumour viability assessment resulted in a high agreement with expert annotations. By providing extraction of detailed information of the tumour microenvironment, the automated method can be used in preclinical research settings. The method could also have implications in cancer diagnostics, cancer outcome prognostics and prediction.

Development and evaluation of a virtual microscopy application for automated assessment of Ki-67 expression in breast cancer.

BACKGROUND: The aim of the study was to develop a virtual microscopy enabled method for assessment of Ki-67 expression and to study the prognostic value of the automated analysis in a comprehensive series of patients with breast cancer. METHODS: Using a previously reported virtual microscopy platform and an open source image processing tool, ImageJ, a method for assessment of immunohistochemically (IHC) stained area and intensity was created. A tissue microarray (TMA) series of breast cancer specimens from 1931 patients was immunostained for Ki-67, digitized with a whole slide scanner and uploaded to an image web server. The extent of Ki-67 staining in the tumour specimens was assessed both visually and with the image analysis algorithm. The prognostic value of the computer vision assessment of Ki-67 was evaluated by comparison of distant disease-free survival in patients with low, moderate or high expression of the protein. RESULTS: 1648 evaluable image files from 1334 patients were analysed in less than two hours. Visual and automated Ki-67 extent of staining assessments showed a percentage agreement of 87% and weighted kappa value of 0.57. The hazard ratio for distant recurrence for patients with a computer determined moderate Ki-67 extent of staining was 1.77 (95% CI 1.31-2.37) and for high extent 2.34 (95% CI 1.76-3.10), compared to patients with a low extent. In multivariate survival analyses, automated assessment of Ki-67 extent of staining was retained as a significant prognostic factor. CONCLUSIONS: Running high-throughput automated IHC algorithms on a virtual microscopy platform is feasible. Comparison of visual and automated assessments of Ki-67 expression shows moderate agreement. In multivariate survival analysis, the automated assessment of Ki-67 extent of staining is a significant and independent predictor of outcome in breast cancer.