Transformer-based framework for multi-class segmentation of skin cancer from histopathology images

Introduction

Non-melanoma skin cancer comprising Basal cell carcinoma (BCC), Squamous cell carcinoma (SCC), and Intraepidermal carcinoma (IEC) has the highest incidence rate among skin cancers. Intelligent decision support systems may address the issue of the limited number of subject experts and help in mitigating the parity of health services between urban centers and remote areas.

Method

In this research, we propose a transformer-based model for the segmentation of histopathology images not only into inflammation and cancers such as BCC, SCC, and IEC but also to identify skin tissues and boundaries that are important in decision-making. Accurate segmentation of these tissue types will eventually lead to accurate detection and classification of non-melanoma skin cancer. The segmentation according to tissue types and their visual representation before classification enhances the trust of pathologists and doctors being relatable to how most pathologists approach this problem. The visualization of the confidence of the model in its prediction through uncertainty maps is also what distinguishes this study from most deep learning methods.

Results

The evaluation of proposed system is carried out using publicly available dataset. The application of our proposed segmentation system demonstrated good performance with an F1 score of 0.908, mean intersection over union (mIoU) of 0.653, and average accuracy of 83.1%, advocating that the system can be used as a decision support system successfully and has the potential of subsequently maturing into a fully automated system.

Discussion

This study is an attempt to automate the segmentation of the most occurring non-melanoma skin cancer using a transformer-based deep learning technique applied to histopathology skin images. Highly accurate segmentation and visual representation of histopathology images according to tissue types by the proposed system implies that the system can be used for skin-related routine pathology tasks including cancer and other anomaly detection, their classification, and measurement of surgical margins in the case of cancer cases.

Towards sweetness classification of orange cultivars using short-wave NIR spectroscopy

The global orange industry constantly faces new technical challenges to meet consumer demands for quality fruits. Instead of traditional subjective fruit quality assessment methods, the interest in the horticulture industry has increased in objective, quantitative, and non-destructive assessment methods. Oranges have a thick peel which makes their non-destructive quality assessment challenging. This paper evaluates the potential of short-wave NIR spectroscopy and direct sweetness classification approach for Pakistani cultivars of orange, i.e., Red-Blood, Mosambi, and Succari. The correlation between quality indices, i.e., Brix, titratable acidity (TA), Brix: TA and BrimA (Brix minus acids), sensory assessment of the fruit, and short-wave NIR spectra, is analysed. Mix cultivar oranges are classified as sweet, mixed, and acidic based on short-wave NIR spectra. Short-wave NIR spectral data were obtained using the industry standard F-750 fruit quality meter (310-1100 nm). Reference Brix and TA measurements were taken using standard destructive testing methods. Reference taste labels i.e., sweet, mix, and acidic, were acquired through sensory evaluation of samples. For indirect fruit classification, partial least squares regression models were developed for Brix, TA, Brix: TA, and BrimA estimation with a correlation coefficient of 0.57, 0.73, 0.66, and 0.55, respectively, on independent test data. The ensemble classifier achieved 81.03% accuracy for three classes (sweet, mixed, and acidic) classification on independent test data for direct fruit classification. A good correlation between NIR spectra and sensory assessment is observed as compared to quality indices. A direct classification approach is more suitable for a machine-learning-based orange sweetness classification using NIR spectroscopy than the estimation of quality indices.

3D Printable Thermoplastic Polyurethane Energy Efficient Passive Foot

Passive energy storing prosthetics are redesigned to improve the stored and recovered energy during different phases of the gait cycle. Furthermore, the demand of the low-cost passive prosthesis that are capable of energy storing is increasing day by day especially in underdeveloping countries. This article proposes a new passive foot design that is more energy efficient if 3D printed using thermoplastic polyurethane (TPU) material. The model is built in SOLIDWORKS®, and then the finite element analysis is conducted on ANSYS®. Two models of the foot are designed with and without Steps on the toe and heel, where the difference of Steps showed difference in the energy stored in the foot during stimulation. TPU being a flexible material with high strength and durability is chosen as the material for the 3D printed foot. The analysis performed on the foot is for an 80 kg person at different angles during the gait cycle for the K2 human activity level. The results obtained indicate high energy storage ability of TPU that is 0.044 J/Kg, comparative to other materials Hytrel, Delrin, and Carbon Fiber DA that are commonly used in passive foots.

A Soft Multi-Axis High Force Range Magnetic Tactile Sensor for Force Feedback in Robotic Surgical Systems

This paper presents a multi-axis low-cost soft magnetic tactile sensor with a high force range for force feedback in robotic surgical systems. The proposed sensor is designed to fully decouple the output response for normal, shear and angular forces. The proposed sensor is fabricated using rapid prototyping techniques and utilizes Neodymium magnets embedded in an elastomer over Hall sensors such that their displacement produces a voltage change that can be used to calculate the applied force. The initial spacing between the magnets and the Hall sensors is optimized to achieve a large displacement range using finite element method (FEM) simulations. The experimental characterization of the proposed sensor is performed for applied force in normal, shear and 45° angular direction. The force sensitivity of the proposed sensor in normal, shear and angular directions is 16 mV/N, 30 mV/N and 81 mV/N, respectively, with minimum mechanical crosstalk. The force range for the normal, shear and angular direction is obtained as 0–20 N, 0–3.5 N and 0–1.5 N, respectively. The proposed sensor shows a perfectly linear behavior and a low hysteresis error of 8.3%, making it suitable for tactile sensing and biomedical applications. The effect of the material properties of the elastomer on force ranges and sensitivity values of the proposed sensor is also discussed.

A novel approach of overtaking maneuvering using modified RG method

Intelligent and safe overtaking maneuvering is always a challenging task for autonomous vehicles. This paper proposes and experimentally implements a novel approach of overtaking maneuvering using modified form of Rendezvous Guidance (RG) algorithm for trajectory planning and obstacle avoidance, considering driver safety and comfort during autonomous overtaking. The simulations for all possible scenarios are conducted to ensure the effectiveness of proposed modified RG algorithm. These scenarios involved presence and absence of obstacle vehicle in overtaking lane alongside leading vehicle in driving lane. In addition, the enhanced performance of modified RG algorithm is established over conventional RG algorithm by comparative analysis. The results indicate that overtaking maneuvering period could be decreased by 10% using a modified RG algorithm and vehicle will cover less distance to complete overtaking. The efficacy of proposed method is justified by performing experiments using mobile robots. The experimental results and simulation results of modified RG algorithm are compared, and their plots are almost identical.