Basal Cell Carcinoma Diagnosis with Fusion of Deep Learning and Telangiectasia Features.

In recent years, deep learning (DL) has been used extensively and successfully to diagnose different cancers in dermoscopic images. However, most approaches lack clinical inputs supported by dermatologists that could aid in higher accuracy and explainability. To dermatologists, the presence of telangiectasia, or narrow blood vessels that typically appear serpiginous or arborizing, is a critical indicator of basal cell carcinoma (BCC). Exploiting the feature information present in telangiectasia through a combination of DL-based techniques could create a pathway for both, improving DL results as well as aiding dermatologists in BCC diagnosis. This study demonstrates a novel "fusion" technique for BCC vs non-BCC classification using ensemble learning on a combination of (a) handcrafted features from semantically segmented telangiectasia (U-Net-based) and (b) deep learning features generated from whole lesion images (EfficientNet-B5-based). This fusion method achieves a binary classification accuracy of 97.2%, with a 1.3% improvement over the corresponding DL-only model, on a holdout test set of 395 images. An increase of 3.7% in sensitivity, 1.5% in specificity, and 1.5% in precision along with an AUC of 0.99 was also achieved. Metric improvements were demonstrated in three stages: (1) the addition of handcrafted telangiectasia features to deep learning features, (2) including areas near telangiectasia (surround areas), (3) discarding the noisy lower-importance features through feature importance. Another novel approach to feature finding with weak annotations through the examination of the surrounding areas of telangiectasia is offered in this study. The experimental results show state-of-the-art accuracy and precision in the diagnosis of BCC, compared to three benchmark techniques. Further exploration of deep learning techniques for individual dermoscopy feature detection is warranted.

Hybrid Topological Data Analysis and Deep Learning for Basal Cell Carcinoma Diagnosis.

A critical clinical indicator for basal cell carcinoma (BCC) is the presence of telangiectasia (narrow, arborizing blood vessels) within the skin lesions. Many skin cancer imaging processes today exploit deep learning (DL) models for diagnosis, segmentation of features, and feature analysis. To extend automated diagnosis, recent computational intelligence research has also explored the field of Topological Data Analysis (TDA), a branch of mathematics that uses topology to extract meaningful information from highly complex data. This study combines TDA and DL with ensemble learning to create a hybrid TDA-DL BCC diagnostic model. Persistence homology (a TDA technique) is implemented to extract topological features from automatically segmented telangiectasia as well as skin lesions, and DL features are generated by fine-tuning a pre-trained EfficientNet-B5 model. The final hybrid TDA-DL model achieves state-of-the-art accuracy of 97.4% and an AUC of 0.995 on a holdout test of 395 skin lesions for BCC diagnosis. This study demonstrates that telangiectasia features improve BCC diagnosis, and TDA techniques hold the potential to improve DL performance.

Effectiveness of 225Ac-Labeled Anti-EGFR Radioimmunoconjugate in EGFR-Positive Kirsten Rat Sarcoma Viral Oncogene and BRAF Mutant Colorectal Cancer Models.

Eighty percent of colorectal cancers (CRCs) overexpress epidermal growth factor receptor (EGFR). Kirsten rat sarcoma viral oncogene (KRAS) mutations are present in 40% of CRCs and drive de novo resistance to anti-EGFR drugs. BRAF oncogene is mutated in 7%-10% of CRCs, with even worse prognosis. We have evaluated the effectiveness of [225Ac]Ac-macropa-nimotuzumab in KRAS mutant and in KRAS wild-type and BRAFV600E mutant EGFR-positive CRC cells in vitro and in vivo. Anti-CD20 [225Ac]Ac-macropa-rituximab was developed and used as a nonspecific radioimmunoconjugate. Methods: Anti-EGFR antibody nimotuzumab was radiolabeled with 225Ac via an 18-membered macrocyclic chelator p-SCN-macropa. The immunoconjugate was characterized using flow cytometry, radioligand binding assay, and high-performance liquid chromatography, and internalization was studied using live-cell imaging. In vitro cytotoxicity was evaluated in 2-dimensional monolayer EGFR-positive KRAS mutant DLD-1, SW620, and SNU-C2B; in KRAS wild-type and BRAFV600E mutant HT-29 CRC cell lines; and in 3-dimensional spheroids. Dosimetry was studied in healthy mice. The in vivo efficacy of [225Ac]Ac-macropa-nimotuzumab was evaluated in mice bearing DLD-1, SW620, and HT-29 xenografts after treatment with 3 doses of 13 kBq/dose administered 10 d apart. Results: In all cell lines, in vitro studies showed enhanced cytotoxicity of [225Ac]Ac-macropa-nimotuzumab compared with nimotuzumab and controls. The inhibitory concentration of 50% in the DLD-1 cell line was 1.8 nM for [225Ac]Ac-macropa-nimotuzumab versus 84.1 nM for nimotuzumab. Similarly, the inhibitory concentration of 50% was up to 79-fold lower for [225Ac]Ac-macropa-nimotuzumab than for nimotuzumab in KRAS mutant SNU-C2B and SW620 and in KRAS wild-type and BRAFV600E mutant HT-29 CRC cell lines. A similar trend was observed for 3-dimensional spheroids. Internalization peaked 24-48 h after incubation and depended on EGFR expression. In the [225Ac]Ac-macropa-nimotuzumab group, 3 of 7 mice bearing DLD-1 tumors had complete remission. Median survival was 40 and 34 d for mice treated with phosphate-buffered saline and [225Ac]Ac-macropa-rituximab (control), respectively, whereas it was not reached for the [225Ac]Ac-macropa-nimotuzumab group (>90 d). Similarly, median survival of mice bearing HT-29 xenografts was 16 and 12.5 d for those treated with [225Ac]Ac-macropa-rituximab and phosphate-buffered saline, respectively, and was not reached for those treated with [225Ac]Ac-macropa-nimotuzumab (>90 d). One of 7 mice bearing HT-29 xenografts and treated using [225Ac]Ac-macropa-nimotuzumab had complete remission. Compared with untreated mice, [225Ac]Ac-macropa-nimotuzumab more than doubled (16 vs. 41 d) the median survival of mice bearing SW620 xenografts. Conclusion: [225Ac]Ac-macropa-nimotuzumab is effective against KRAS mutant and BRAFV600E mutant CRC models.

Improving Automatic Melanoma Diagnosis Using Deep Learning-Based Segmentation of Irregular Networks.

Deep learning has achieved significant success in malignant melanoma diagnosis. These diagnostic models are undergoing a transition into clinical use. However, with melanoma diagnostic accuracy in the range of ninety percent, a significant minority of melanomas are missed by deep learning. Many of the melanomas missed have irregular pigment networks visible using dermoscopy. This research presents an annotated irregular network database and develops a classification pipeline that fuses deep learning image-level results with conventional hand-crafted features from irregular pigment networks. We identified and annotated 487 unique dermoscopic melanoma lesions from images in the ISIC 2019 dermoscopic dataset to create a ground-truth irregular pigment network dataset. We trained multiple transfer learned segmentation models to detect irregular networks in this training set. A separate, mutually exclusive subset of the International Skin Imaging Collaboration (ISIC) 2019 dataset with 500 melanomas and 500 benign lesions was used for training and testing deep learning models for the binary classification of melanoma versus benign. The best segmentation model, U-Net++, generated irregular network masks on the 1000-image dataset. Other classical color, texture, and shape features were calculated for the irregular network areas. We achieved an increase in the recall of melanoma versus benign of 11% and in accuracy of 2% over DL-only models using conventional classifiers in a sequential pipeline based on the cascade generalization framework, with the highest increase in recall accompanying the use of the random forest algorithm. The proposed approach facilitates leveraging the strengths of both deep learning and conventional image processing techniques to improve the accuracy of melanoma diagnosis. Further research combining deep learning with conventional image processing on automatically detected dermoscopic features is warranted.

Identification of Volatile Organic Liquids by Combining an Array of Fiber-Optic Sensors and Machine Learning.

In this paper, we report an array of fiber-optic sensors based on the Fabry-Perot interference principle and machine learning-based analyses for identifying volatile organic liquids (VOLs). Three optical fiber tip sensors with different surfaces were included in the array of sensors to improve the accuracy for identifying liquids: an intrinsic (unmodified) flat cleaved endface, a hydrophobic-coated endface, and a hydrophilic-coated endface. The time-transient responses of evaporating droplets from the optical fiber tip sensors were monitored and collected following the controlled immersion tests of 11 different organic liquids. A continuous wavelet transform was used to convert the time-transient response signal into images. These images were then utilized to train convolution neural networks for classification (identification of VOLs). We show that diversity in the information collected using the array of three sensors helps machine learning-based methods perform significantly better. We explore different pipelines for combining the information from the array of sensors within a machine learning framework and their effect on the robustness of models. The results showed that the machine learning-based methods achieved high accuracy in their classification of different liquids based on their droplet evaporation time-transient events.

Machine learning identifies liquids employing a simple fiber-optic tip sensor.

We proposed an extremely simple fiber-optic tip sensor system to identify liquids by combining their corresponding droplet evaporation events with analyses using machine learning techniques. Pendant liquid droplets were suspended from the cleaved endface of a single-mode fiber during the experiment. The optical fiber-droplet interface and the droplet-air interface served as two partial reflectors of an extrinsic Fabry-Perot interferometer (EFPI) with a liquid droplet cavity. As the liquid pendant droplet evaporated, its length diminished. A light source can be used to observe the effective change in the net reflectivity of the optical fiber sensor system by observing the resulting optical interference phenomenon of the reflected waves. Using a single-wavelength probing light source, the entire evaporation event of the liquid droplet was precisely captured. The measured time transient response from the fiber-optic tip sensor to an evaporation event of a liquid droplet of interest was then transformed into image data using a continuous wavelet transform. The obtained image data was used to fine-tune pre-trained convolution neural networks (CNNs) for the given task. The results demonstrated that machine learning-based classification methods achieved greater than 98% accuracy in classifying different liquids based on their corresponding droplet evaporation processes, measured by the fiber-optic tip sensor.