Automatic diagnosis and biopsy classification with dynamic Full-Field OCT and machine learning

Abstract The adoption of emerging imaging technologies in the medical community is often hampered if they provide a new unfamiliar contrast that requires experience to be interpreted. Here, in order to facilitate such integration, we developed two complementary machine learning approaches, respectively based on feature engineering and on convolutional neural networks (CNN), to perform automatic diagnosis of breast biopsies using dynamic full field optical coherence tomography (D-FF-OCT) microscopy. This new technique provides fast, high resolution images of biopsies with a contrast similar to H&E histology, but without any tissue preparation and alteration. We conducted a pilot study on 51 breast biopsies, and more than 1,000 individual images, and performed standard histology to obtain each biopsy diagnosis. Using our automatic diagnosis algorithms, we obtained an accuracy above 88% at the image level, and above 96% at the biopsy level. Finally, we proposed different strategies to narrow down the spatial scale of the automatic segmentation in order to be able to draw the tumor margins by drawing attention maps with the CNN approach, or by performing high resolution precise annotation of the datasets. Altogether, these results demonstrate the high potential of D-FF-OCT coupled to machine learning to provide a rapid, automatic, and accurate histopathology diagnosis.

Download Full-text

Land Cover Classification using Machine Learning Approaches from High Resolution Images

Journal of Applied and Emerging Sciences ◽

10.36785/2021111501 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Akhtar Jamil ◽

Aftab Ahmed Khan ◽

Alaa Ali Hameed ◽

Sibghat Sibghat Ullah Bazai

Keyword(s):

Machine Learning ◽

High Resolution ◽

Land Cover ◽

Land Cover Classification ◽

Learning Approaches ◽

High Resolution Images

Download Full-text

Land Cover Classification using Machine Learning Approaches from High Resolution Images

Journal of Applied and Emerging Sciences ◽

10.36785/jaes.111501 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Akhtar Jamil ◽

Aftab Ahmed Khan ◽

Alaa Ali Hameed ◽

Sibghat Sibghat Ullah Bazai

Keyword(s):

Machine Learning ◽

High Resolution ◽

Land Cover ◽

Land Cover Classification ◽

Learning Approaches ◽

High Resolution Images

Download Full-text

Identifying Urban Poverty Using High-Resolution Satellite Imagery and Machine Learning Approaches: Implications for Housing Inequality

Land ◽

10.3390/land10060648 ◽

2021 ◽

Vol 10 (6) ◽

pp. 648

Author(s):

Guie Li ◽

Zhongliang Cai ◽

Yun Qian ◽

Fei Chen

Keyword(s):

Machine Learning ◽

High Resolution ◽

Satellite Imagery ◽

Low Income ◽

Urban Poverty ◽

Image Features ◽

Housing Affordability ◽

Learning Approaches ◽

Housing Inequality ◽

High Resolution Satellite Imagery

Enriching Asian perspectives on the rapid identification of urban poverty and its implications for housing inequality, this paper contributes empirical evidence about the utility of image features derived from high-resolution satellite imagery and machine learning approaches for identifying urban poverty in China at the community level. For the case of the Jiangxia District and Huangpi District of Wuhan, image features, including perimeter, line segment detector (LSD), Hough transform, gray-level cooccurrence matrix (GLCM), histogram of oriented gradients (HoG), and local binary patterns (LBP), are calculated, and four machine learning approaches and 25 variables are applied to identify urban poverty and relatively important variables. The results show that image features and machine learning approaches can be used to identify urban poverty with the best model performance with a coefficient of determination, R2, of 0.5341 and 0.5324 for Jiangxia and Huangpi, respectively, although some differences exist among the approaches and study areas. The importance of each variable differs for each approach and study area; however, the relatively important variables are similar. In particular, four variables achieved relatively satisfactory prediction results for all models and presented obvious differences in varying communities with different poverty levels. Housing inequality within low-income neighborhoods, which is a response to gaps in wealth, income, and housing affordability among social groups, is an important manifestation of urban poverty. Policy makers can implement these findings to rapidly identify urban poverty, and the findings have potential applications for addressing housing inequality and proving the rationality of urban planning for building a sustainable society.

Download Full-text

Using U-Net-Like Deep Convolutional Neural Networks for Precise Tree Recognition in Very High Resolution RGB (Red, Green, Blue) Satellite Images

Forests ◽

10.3390/f12010066 ◽

2021 ◽

Vol 12 (1) ◽

pp. 66

Author(s):

Kirill A. Korznikov ◽

Dmitry E. Kislov ◽

Jan Altman ◽

Jiří Doležal ◽

Anna S. Vozmishcheva ◽

...

Keyword(s):

Machine Learning ◽

High Resolution ◽

Satellite Images ◽

Russian Far East ◽

Pinus Koraiensis ◽

Accuracy Score ◽

Learning Approaches ◽

Individual Tree ◽

Populus Suaveolens ◽

Very High

Very high resolution satellite imageries provide an excellent foundation for precise mapping of plant communities and even single plants. We aim to perform individual tree recognition on the basis of very high resolution RGB (red, green, blue) satellite images using deep learning approaches for northern temperate mixed forests in the Primorsky Region of the Russian Far East. We used a pansharpened satellite RGB image by GeoEye-1 with a spatial resolution of 0.46 m/pixel, obtained in late April 2019. We parametrized the standard U-Net convolutional neural network (CNN) and trained it in manually delineated satellite images to solve the satellite image segmentation problem. For comparison purposes, we also applied standard pixel-based classification algorithms, such as random forest, k-nearest neighbor classifier, naive Bayes classifier, and quadratic discrimination. Pattern-specific features based on grey level co-occurrence matrices (GLCM) were computed to improve the recognition ability of standard machine learning methods. The U-Net-like CNN allowed us to obtain precise recognition of Mongolian poplar (Populus suaveolens Fisch. ex Loudon s.l.) and evergreen coniferous trees (Abies holophylla Maxim., Pinus koraiensis Siebold & Zucc.). We were able to distinguish species belonging to either poplar or coniferous groups but were unable to separate species within the same group (i.e. A. holophylla and P. koraiensis were not distinguishable). The accuracy of recognition was estimated by several metrics and exceeded values obtained for standard machine learning approaches. In contrast to pixel-based recognition algorithms, the U-Net-like CNN does not lead to an increase in false-positive decisions when facing green-colored objects that are similar to trees. By means of U-Net-like CNN, we obtained a mean accuracy score of up to 0.96 in our computational experiments. The U-Net-like CNN recognizes tree crowns not as a set of pixels with known RGB intensities but as spatial objects with a specific geometry and pattern. This CNN’s specific feature excludes misclassifications related to objects of similar colors as objects of interest. We highlight that utilization of satellite images obtained within the suitable phenological season is of high importance for successful tree recognition. The suitability of the phenological season is conceptualized as a group of conditions providing highlighting objects of interest over other components of vegetation cover. In our case, the use of satellite images captured in mid-spring allowed us to recognize evergreen fir and pine trees as the first class of objects (“conifers”) and poplars as the second class, which were in a leafless state among other deciduous tree species.

Download Full-text

Comparison of Machine Learning Approaches to Improve Diagnosis of Optic Neuropathy Using Photopic Negative Response Measured Using a Handheld Device

Frontiers in Medicine ◽

10.3389/fmed.2021.771713 ◽

2021 ◽

Vol 8 ◽

Author(s):

Tina Diao ◽

Fareshta Kushzad ◽

Megh D. Patel ◽

Megha P. Bindiganavale ◽

Munam Wasi ◽

...

Keyword(s):

Machine Learning ◽

Time Series ◽

Optic Neuropathy ◽

Negative Response ◽

Photopic Negative Response ◽

Learning Approaches ◽

Data Set ◽

Full Field ◽

Handheld Device ◽

Technical Requirements

The photopic negative response of the full-field electroretinogram (ERG) is reduced in optic neuropathies. However, technical requirements for measurement and poor classification performance have limited widespread clinical application. Recent advances in hardware facilitate efficient clinic-based recording of the full-field ERG. Time series classification, a machine learning approach, may improve classification by using the entire ERG waveform as the input. In this study, full-field ERGs were recorded in 217 eyes (109 optic neuropathy and 108 controls) of 155 subjects. User-defined ERG features including photopic negative response were reduced in optic neuropathy eyes (p < 0.0005, generalized estimating equation models accounting for age). However, classification of optic neuropathy based on user-defined features was only fair with receiver operating characteristic area under the curve ranging between 0.62 and 0.68 and F1 score at the optimal cutoff ranging between 0.30 and 0.33. In comparison, machine learning classifiers using a variety of time series analysis approaches had F1 scores of 0.58–0.76 on a test data set. Time series classifications are promising for improving optic neuropathy diagnosis using ERG waveforms. Larger sample sizes will be important to refine the models.

Download Full-text

Soil moisture estimation from high-resolution UASs imagery based on machine learning approaches for land cover classification

10.5194/egusphere-egu21-15586 ◽

2021 ◽

Author(s):

Teresa Pizzolla ◽

Silvano Fortunato Dal Sasso ◽

Ruodan Zhuang ◽

Alonso Pizarro ◽

Salvatore Manfreda

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Soil Moisture ◽

High Resolution ◽

Thermal Inertia ◽

Bare Soil ◽

Unmanned Aerial Systems ◽

Learning Approaches ◽

Land Use Classification ◽

Aerial Systems

Soil moisture (SM) is an essential variable in the earth system as it influences water, energy and, carbon fluxes between the land surface and the atmosphere. The SM spatio-temporal variability requires detailed analyses, high-definition optics and fast computing approaches for near real-time SM estimation at different spatial scales. Remote Sensing-based Unmanned Aerial Systems (UASs) represents the actual solution providing low-cost approaches to meet the requirements of spatial, spectral and temporal resolutions [1; 3; 4]. In this context, a proper land use classification is crucial in order to discriminate the behaviors of vegetation and bare soil in such high-resolution imagery. Therefore, high-resolution UASs-based imagery requires a specific images classification approach also considering the illumination conditions. In this work, the land use classification was carried out using a methodology based on a combined machine learning approaches: k-means clustering algorithm for removing shadow pixels from UASs images and, binary classifier for vegetation filtering. This approach led to identifying the bare soil on which SM estimation was computed using the Apparent Thermal Inertia (ATI) method [2]. The estimated SM values were compared with field measurements obtaining a good correlation (R2 = 0.80). The accuracy of the results shows good reliability of the procedure and allows extending the use of UASs also in unclassified areas and ungauged basins, where the monitoring of the SM is very complex.References[1] Manfreda, S., McCabe, M.F., Miller, P.E., Lucas, R., Pajuelo Madrigal, V., Mallinis, G., Ben Dor, E., Helman, D., Estes, L., Ciraolo, G., et al. On the Use of Unmanned Aerial Systems for Environmental Monitoring, Remote Sensing, 2018, 10, 641.[2] Minacapilli, M., Cammalleri, C., Ciraolo, G., D&#8217;Asaro, F., Iovino, M., and Maltese, A. Thermal Inertia Modeling for Soil Surface Water Content Estimation: A Laboratory Experiment. Soil. Sci. Soc. Amer. J. 2012, vol.76, n.1, pp. 92&#8211;100[3] Paruta, A., P. Nasta, G. Ciraolo, F. Capodici, S. Manfreda, N. Romano, E. Bendor, Y. Zeng, A. Maltese, S. F. Dal Sasso and R. Zhuang, A geostatistical approach to map near-surface soil moisture through hyper-spatial resolution thermal inertia, IEEE Transactions on Geoscience and Remote Sensing, 2020.[4] Petropoulos, G.P., A. Maltese, T. N. Carlson, G. Provenzano, A. Pavlides, G. Ciraolo, D. Hristopulos, F. Capodici, C. Chalkias, G. Dardanelli, S. Manfreda, Exploring the use of UAVs with the simplified &#8220;triangle&#8221; technique for Soil Water Content and Evaporative Fraction retrievals in a Mediterranean setting, International Journal of Remote Sensing, 2020.

Download Full-text